To see the other types of publications on this topic, follow the link: SLR; CNN; Artificial Neural Network.
Journal articles on the topic 'SLR; CNN; Artificial Neural Network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'SLR; CNN; Artificial Neural Network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Himanshu, Rai Goyal Savita. "Crop Yield Prediction Using Adam Optimizer and Machine Learning." Scandinavian Journal of Information Systems 34, no. 1 (2023): 138–43. https://doi.org/10.5281/zenodo.7885144.
Full textAbstract:
The data in its form generated from variable sensors incredibly impacts the structure of the functional structure utilizing Machine Learning (ML) calculations. Many of its components are utilized to work on all areas of the rice harvesting process in horticulture, which change customary rice cultivating tests into another period of smart rice horticulture or accuracy in rice farming. Here played out a study of the most recent examination on keen information handling innovation applied in farming, especially in crop yield forecast. Artificial Intelligence (AI) is a rule based unbiased calculation model for significant prediction on paddy and crop horticulture. This played out a Systematic Literature Review (SLR) to extricate and blend the calculations and elements that have been utilized in crop yield expectation studies. In view of pursuit standards, recovered 567 important examinations from six electronic information bases, of which have been chosen 50 investigations for additional investigation utilizing incorporation and avoidance measures. Examined these chose concentrates cautiously, investigated the techniques and elements utilized, and gave ideas to additional exploration. As indicated by examinations, the most utilized highlights are temperature, precipitation, and soil type, and the most applied calculation is Artificial Neural Networks in these models. As indicated by this extra examination, Convolutional Neural Networks (CNN) is the deep learning architecture that involves the immense layers of calculations on the investigation results and improving the forecast results.
2
Ferreira, Pedro M., Diogo Pernes, Ana Rebelo, and Jaime S. Cardoso. "Signer-Independent Sign Language Recognition with Adversarial Neural Networks." International Journal of Machine Learning and Computing 11, no. 2 (2021): 121–29. http://dx.doi.org/10.18178/ijmlc.2021.11.2.1024.
Full textAbstract:
Sign Language Recognition (SLR) has become an appealing topic in modern societies because such technology can ideally be used to bridge the gap between deaf and hearing people. Although important steps have been made towards the development of real-world SLR systems, signer-independent SLR is still one of the bottleneck problems of this research field. In this regard, we propose a deep neural network along with an adversarial training objective, specifically designed to address the signer-independent problem. Specifically, the proposed model consists of an encoder, mapping from input images to latent representations, and two classifiers operating on these underlying representations: (i) the sign-classifier, for predicting the class/sign labels, and (ii) the signer-classifier, for predicting their signer identities. During the learning stage, the encoder is simultaneously trained to help the sign-classifier as much as possible while trying to fool the signer-classifier. This adversarial training procedure allows learning signer-invariant latent representations that are in fact highly discriminative for sign recognition. Experimental results demonstrate the effectiveness of the proposed model and its capability of dealing with the large inter-signer variations.
3
Zhang, Yong. "Seedlings Supplement Device and Seedling Recognition Based on Convolution Neural Network." Traitement du Signal 39, no. 5 (2022): 1567–75. http://dx.doi.org/10.18280/ts.390513.
Full textAbstract:
A fully automatic plug seedling device is designed, its structure and working principle are introduced, and a plug seedling hole identification method based on CNN is proposed to address the issue of adjacent holes in order to increase the automation and intelligence of the vegetable transplanting machine. The issue of low recognition accuracy of plug seedlings is brought on by intertwined stems and leaves. This study first grows tomato seedlings in an artificial greenhouse and then utilizes an SLR camera to take pictures of those plants. The photos are then subjected to the appropriate preprocessing, such as separating the complete hole plate image into several hole images in accordance with the hole plate standards to facilitate recognition. The CNN model is then finished being trained after receiving the processed image. Relu, which has a better ability for classification, is chosen as the activation function of the convolutional layer after the network is enlarged on the basis of LeNet-5CNN. In addition, the over-fitting issue of the model is resolved using data augmentation technology, resulting in a recognition accuracy of the test set of the model that is as high as 0.985. The automatic vegetable transplanting machine can greatly increase the automation and intelligence level of the plug seedling recognition model based on CNN, which has high recognition accuracy and generalization ability. This model also solves the main technical problems of the plug seedling device and improves the machine's ability to transplant.
4
Nugroho, Erwin Setyo, Igi Ardiyanto, and Hanung Adi Nugroho. "Systematic literature review of dermoscopic pigmented skin lesions classification using convolutional neural network (CNN)." International Journal of Advances in Intelligent Informatics 9, no. 3 (2023): 363. http://dx.doi.org/10.26555/ijain.v9i3.961.
Full textAbstract:
The occurrence of pigmented skin lesions (PSL), including melanoma, are rising, and early detection is crucial for reducing mortality. To assist Pigmented skin lesions, including melanoma, are rising, and early detection is crucial in reducing mortality. To aid dermatologists in early detection, computational techniques have been developed. This research conducted a systematic literature review (SLR) to identify research goals, datasets, methodologies, and performance evaluation methods used in categorizing dermoscopic lesions. This review focuses on using convolutional neural networks (CNNs) in analyzing PSL. Based on specific inclusion and exclusion criteria, the review included 54 primary studies published on Scopus and PubMed between 2018 and 2022. The results showed that ResNet and self-developed CNN were used in 22% of the studies, followed by Ensemble at 20% and DenseNet at 9%. Public datasets such as ISIC 2019 were predominantly used, and 85% of the classifiers used were softmax. The findings suggest that the input, architecture, and output/feature modifications can enhance the model's performance, although improving sensitivity in multiclass classification remains a challenge. While there is no specific model approach to solve the problem in this area, we recommend simultaneously modifying the three clusters to improve the model's performance.
5
Colantonio, Lorenzo, Lucas Equeter, Pierre Dehombreux, and François Ducobu. "A Systematic Literature Review of Cutting Tool Wear Monitoring in Turning by Using Artificial Intelligence Techniques." Machines 9, no. 12 (2021): 351. http://dx.doi.org/10.3390/machines9120351.
Full textAbstract:
In turning operations, the wear of cutting tools is inevitable. As workpieces produced with worn tools may fail to meet specifications, the machining industries focus on replacement policies that mitigate the risk of losses due to scrap. Several strategies, from empiric laws to more advanced statistical models, have been proposed in the literature. More recently, many monitoring systems based on Artificial Intelligence (AI) techniques have been developed. Due to the scope of different artificial intelligence approaches, having a holistic view of the state of the art on this subject is complex, in part due to a lack of recent comprehensive reviews. This literature review therefore presents 20 years of literature on this subject obtained following a Systematic Literature Review (SLR) methodology. This SLR aims to answer the following research question: “How is the AI used in the framework of monitoring/predicting the condition of tools in stable turning condition?” To answer this research question, the “Scopus” database was consulted in order to gather relevant publications published between 1 January 2000 and 1 January 2021. The systematic approach yielded 8426 articles among which 102 correspond to the inclusion and exclusion criteria which limit the application of AI to stable turning operation and online prediction. A bibliometric analysis performed on these articles highlighted the growing interest of this subject in the recent years. A more in-depth analysis of the articles is also presented, mainly focusing on six AI techniques that are highly represented in the literature: Artificial Neural Network (ANN), fuzzy logic, Support Vector Machine (SVM), Self-Organizing Map (SOM), Hidden Markov Model (HMM), and Convolutional Neural Network (CNN). For each technique, the trends in the inputs, pre-processing techniques, and outputs of the AI are presented. The trends highlight the early and continuous importance of ANN, and the emerging interest of CNN for tool condition monitoring. The lack of common benchmark database for evaluating models performance does not allow clear comparisons of technique performance.
6
Mustaqim, Adi Zaenul, Nurdana Ahmad Fadil, and Dyah Aruming Tyas. "Artificial Neural Network for Classification Task in Tabular Datasets and Image Processing: A Systematic Literature Review." Jurnal Online Informatika 8, no. 2 (2023): 158–68. http://dx.doi.org/10.15575/join.v8i2.1002.
Full textAbstract:
Artificial Neural Network (ANN) is one of the machine learning algorithms that is widely used for classification cases. Some examples of classification cases that can be handled with ANN include classifications in the health sector, banking, and classification in image processing. This study presents a systematic literature review (SLR) of the ANN algorithm to find a research gap that can be used in future research. There are 3 phases used in preparing the SLR. Those are planning, conducting, and reporting. Formulation of research questions and establishing a review protocol is carried out in the planning phase. The second phase is conducted. In this phase, searching for relevant articles is carried out, determining the quality of the literature found and selecting particles according to what has been formulated in the planning phase. The selected literature is then carried out by the process of extracting data and information and then synthesizing the data. Writing SLR articles based on existing findings is carried out in the last phase, namely reporting. The results of data and information extraction from the 13 reviewed articles show that the ANN algorithm is powerful enough with satisfactory results to handle classification cases that use tabular datasets or image datasets. The challenges faced are the need for extensive training data so that ANN performance can be better, the use of appropriate evaluation measures based on the cases studied does not only rely on accuracy scores, and the determination of the correct hyperparameters to get better performance in the case of image processing.
7
Alluhaidan, Ala Saleh, Oumaima Saidani, Rashid Jahangir, Muhammad Asif Nauman, and Omnia Saidani Neffati. "Speech Emotion Recognition through Hybrid Features and Convolutional Neural Network." Applied Sciences 13, no. 8 (2023): 4750. http://dx.doi.org/10.3390/app13084750.
Full textAbstract:
Speech emotion recognition (SER) is the process of predicting human emotions from audio signals using artificial intelligence (AI) techniques. SER technologies have a wide range of applications in areas such as psychology, medicine, education, and entertainment. Extracting relevant features from audio signals is a crucial task in the SER process to correctly identify emotions. Several studies on SER have employed short-time features such as Mel frequency cepstral coefficients (MFCCs), due to their efficiency in capturing the periodic nature of audio signals. However, these features are limited in their ability to correctly identify emotion representations. To solve this issue, this research combined MFCCs and time-domain features (MFCCT) to enhance the performance of SER systems. The proposed hybrid features were given to a convolutional neural network (CNN) to build the SER model. The hybrid MFCCT features together with CNN outperformed both MFCCs and time-domain (t-domain) features on the Emo-DB, SAVEE, and RAVDESS datasets by achieving an accuracy of 97%, 93%, and 92% respectively. Additionally, CNN achieved better performance compared to the machine learning (ML) classifiers that were recently used in SER. The proposed features have the potential to be widely utilized to several types of SER datasets for identifying emotions.
8
Frieyadie, Frieyadie. "SYSTEMATIC LITERATURE REVIEW (SLR): DISEASE DETECTION IN MELONS USING DIGITAL IMAGE PROCESSING." Jurnal Riset Informatika 3, no. 1 (2021): 75–80. http://dx.doi.org/10.34288/jri.v3i1.178.
Full textAbstract:
Systematic Literature Review (SLR) is a technique used in this study which is used to study techniques for identifying leaf diseases using digital images as a basis for obtaining an understanding of disease identification techniques in melon leaves with digital images. Based on data from the Central Statistics Agency for the last 3 years from 2017-2019, melon production has increased considerably. Melon production data in 2017 was 92.43 tons, in 2018 was 118,708 and in 2019, overall melon production was 122,105 tons collected from 34 provinces in Indonesia. The problem that is often encountered in melon cultivation is the presence of plant pests that can harm and not maximize the yields of farmers. Several viruses cause mosaic disease that infects Cucurbitaceae plants, namely Cucumber aphid borne yellows virus (CABYV), Cucumber green mottle mosaic virus (CGMMV), Cucumber mosaic virus (CMV), Papaya ringspot virus (PRSV), Squash mosaic virus (SqMV), Squash leaf curl virus (SLCV), Watermelon mosaic virus (WMV). Information technology has now developed to be able to manage digital image data to identify problems faced by farmers. Several classification methods that can be used to answer problems include SVM, Artificial Neural Network, Decision Tree, Convolutional Neural Network.
9
Jayavardhana, Arya, and Samuel Ady Sanjaya. "A Systematic Literature Review: A Comparison Of Available Approaches In Chatbot And Dialogue Manager Development." International Journal of Science, Technology & Management 4, no. 6 (2023): 1441–50. http://dx.doi.org/10.46729/ijstm.v4i6.983.
Full textAbstract:
The present study reviewed a number of articles chosen from a screening and selecting process on the various different methods that can be used in the context of chatbot development and dialogue managers. Since chatbots have seen a significant rise in popularity and have played an important role in helping humans complete daily tasks, this systematic literature review (SLR) aims to act as a guidance for future research. During the process of analyzing and extracting data from the 13 articles chosen, it has been identified that Artificial Neural Network (ANN), Ensemble Learning, Recurrent Neural Network (RNN), and Long-Short Term Memory (LSTM) is among some of the most popular algorithms used for developing a chatbot. Where all of these algorithms are suitable for each unique use case where it offers different advantages when implemented. Other than that, dialogue managers lean more towards the field of Deep Reinforcement Learning (DRL), where Deep Q-Networks (DQN) and its variants such as Double Deep-Q Networks (DDQN) and DDQN with Personalized Experience Replay (DDQN-PER) is commonly used. All these variants have different averages on episodic reward and dialogue length, along with different training time needed which indicates the computational power needed. This SLR aims to identify the methods that can be used and identify the best proven method to be applied in future research.
10
Kamara, Alhassan A. "SARSNet—A Novel CNN Approach for SARWater Body Segmentation." International Journal of Electrical and Electronic Engineering & Telecommunications 13, no. 5 (2024): 323–30. http://dx.doi.org/10.18178/ijeetc.13.4.323-330.
Full textAbstract:
This paper presents the SARSNet architecture, developed to address the growing challenges in Synthetic Aperture Radar (SAR) deep learning-based automatic water body extraction. Such a task is riddled with significant challenges, encompassing issues like cloud interference, scarcity of annotated dataset, and the intricacies associated with varied topography. Recent strides in Convolutional Neural Networks (CNNs) and multispectral segmentation techniques offer a promising avenue to address these predicaments. In our research, we propose a series of solutions to elevate the process of water body segmentation. Our proposed solutions span several domains, including image resolution enhancement, refined extraction techniques tailored for narrow water bodies, self-balancing of the class pixel level, and minority class-influenced loss function, all aimed at amplifying prediction precision and streamlining computational complexity inherent in deep neural networks. The framework of our approach includes the introduction of a multichannel Data-Fusion Register, the incorporation of a CNN-based Patch Adaptive Network augmentation method, and the integration of class pixel level balancing and the Tversky loss function. We evaluated the performance of the model using the Sentinel-1 SAR electromagnetic signal dataset from the Earth flood water body extraction competition organized by the artificial intelligence department of Microsoft. In our analysis, our suggested SARSNet was compared to well-known semantic segmentation models, and a comprehensive assessment demonstrates that SARSNet consistently outperforms these models in all data subsets, including training, validation, and testing sets.
11
Kamara, Alhassan A. "SARSNet—A Novel CNN Approach for SARWater Body Segmentation." International Journal of Electrical and Electronic Engineering & Telecommunications 13, no. 4 (2024): 323–31. http://dx.doi.org/10.18178/ijeetc.13.4.323-331.
Full textAbstract:
This paper presents the SARSNet architecture, developed to address the growing challenges in Synthetic Aperture Radar (SAR) deep learning-based automatic water body extraction. Such a task is riddled with significant challenges, encompassing issues like cloud interference, scarcity of annotated dataset, and the intricacies associated with varied topography. Recent strides in Convolutional Neural Networks (CNNs) and multispectral segmentation techniques offer a promising avenue to address these predicaments. In our research, we propose a series of solutions to elevate the process of water body segmentation. Our proposed solutions span several domains, including image resolution enhancement, refined extraction techniques tailored for narrow water bodies, self-balancing of the class pixel level, and minority class-influenced loss function, all aimed at amplifying prediction precision and streamlining computational complexity inherent in deep neural networks. The framework of our approach includes the introduction of a multichannel Data-Fusion Register, the incorporation of a CNN-based Patch Adaptive Network augmentation method, and the integration of class pixel level balancing and the Tversky loss function. We evaluated the performance of the model using the Sentinel-1 SAR electromagnetic signal dataset from the Earth flood water body extraction competition organized by the artificial intelligence department of Microsoft. In our analysis, our suggested SARSNet was compared to well-known semantic segmentation models, and a comprehensive assessment demonstrates that SARSNet consistently outperforms these models in all data subsets, including training, validation, and testing sets.
12
Solikin, Solikin. "Deteksi Penyakit Pada Tanaman Mangga Dengan Citra Digital : Tinjauan Literatur Sistematis (SLR)." BINA INSANI ICT JOURNAL 7, no. 1 (2020): 63. http://dx.doi.org/10.51211/biict.v7i1.1336.
Full textAbstract:
Abstrak: Penelitian dengan melakukan tinjauan literatur sistematis (Sistematic Literatur Review-SLR) dilakukan untuk mempelajari berbagai teknik identifikasi penyakit pada daun dengan citra digital sebagai tahapan untuk mendapatkan pemahaman mengenai teknik identifikasi penyakit pada daun mangga dengan citra digital. Produksi Mangga di Indonesia dari tahun 2014 – 2018 secara fluktuatif selalu mengalami peningkatan dan di tahun 2018 produksi mangga di Indonesia mencapai 2.624.783 ton, proses budidaya tanaman mangga tidak selamanya dapat terlepas dari serangan penyakit. Penyakit pada tanaman mangga disebabkan oleh jamur atau bakteri yang biasanya menyerang pada bagian akar, batang, kulit batang, ranting atau buah mangga. Jenis penyakit pada tanaman mangga adalah : Penyakit mangga (Jamur Gloesoporium), Penyakit Diplodia, Cendawan jelaga, Bercak karat merah, Kudis buah, Penyakit Blendok. Penyakit pada mangga memiliki berbagai gejala dan kadang sulit didiagnosis oleh petani dan untuk itu diperlukan keahlian untuk mendiagnosis penyakit pada tanaman mangga dan bagaimana cara penanggulangannya yang biasanya keahlian tersebut terdapat pada ahli patologi tanaman professional. Sehingga dibutuhkan suatu Teknologi IT dengan Sistem Cerdas yang dirancang untuk dapat mengidentifikasi secara otomatis penyakit tanaman mangga dan cara penanggulangannya berdasarkan gejala visual dengan menggunakan metode citra digital. Metode literatur review yang digunakan yaitu Compare, Contrast, Criticize, Synthesize dan Summarize. Metode Citra Digital yang dapat digunakan dalam identifikasi penyakit pada daun mangga adalah tahapan Image Acquisition, Preprocessing , Segmentation, Ekstraksi Fitur, Seleksi Fitur. Metode Klasifikasi yang dapat digunakan adalah SVM, Artificial Neural Network, Decision Tree, Convolutional Neural Network.
 
 Kata kunci: citra digital, daun, penyakit mangga, tinjauan literatur sistematis
 
 
 Abstract: Research by conducting a systematic literature review (Systematic Literature Review-SLR) was conducted to study various techniques of disease identification in leaves with digital images as a stage to gain an understanding of the techniques for disease identification on mango leaves with digital images. Mango production in Indonesia from 2014 - 2018 fluctuations has always increased and in 2018 mango production in Indonesia reached 2,624,783 tons, the process of mango cultivation is not always free from disease. Diseases of mango plants are caused by fungi or bacteria that usually attack the roots, stems, bark, twigs or mangoes. Types of diseases in mango plants are: Mango disease (Gloesoporium Fungus), Diplodia disease, sooty fungus, red rust spots, fruit scabies, Blendok disease. Diseases of mangoes have a variety of symptoms and are sometimes difficult to diagnose by farmers and expertise is needed to diagnose diseases on mango plants and how to overcome them which are usually found in professional plant pathologists. So that we need an IT Technology with an Intelligent System that is designed to be able to automatically identify mango plant diseases and how to overcome them based on visual symptoms using digital image methods. The literature review method used is Compare, Contrast, Criticize, Synthesize and Summarize. Digital image methods that can be used in the identification of diseases on mango leaves are the stages of Image Acquisition, Preprocessing, Segmentation, Feature Extraction, Feature Selection. Classification methods that can be used are SVM, Artificial Neural Network, Decision Tree, Convolutional Neural Network.
13
Sofi'an Eka Putra, Ahnaf, Chotibul Umam Hanif, and Moch Azriel Maulana Racmadhani. "PENERAPAN ARTIFICIAL INTELLIGENCE UNTUK MENINGKATKAN PRODUKTIVITAS DAN KEBERLANJUTAN PERTANIAN DI INDONESIA." JATI (Jurnal Mahasiswa Teknik Informatika) 9, no. 1 (2024): 407–13. https://doi.org/10.36040/jati.v9i1.12339.
Full textAbstract:
Pertanian di Indonesia menghadapi tantangan seperti peningkatan kebutuhan pangan, keterbatasan sumber daya, dan perubahan iklim. Artificial Intelligence (AI) muncul sebagai solusi potensial untuk meningkatkan efisiensi dan keberlanjutan sektor pertanian. Penelitian ini menggunakan metode Systematic Literature Review (SLR) untuk mengkaji implementasi AI dalam sektor pertanian, dengan fokus pada algoritma dan teknologi yang efektif. Algoritma seperti Support Vector Machine (SVM), Convolutional Neural Networks (CNN), dan Long Short-Term Memory (LSTM) menunjukkan hasil yang baik dalam deteksi penyakit tanaman, prediksi hasil panen, dan pengelolaan sumber daya. Hasil penelitian menunjukkan bahwa integrasi AI dengan Internet of Things (IoT) dan remote sensing dapat meningkatkan produktivitas pertanian dan mengurangi dampak lingkungan. Namun, penerapan AI di sektor pertanian Indonesia masih menghadapi tantangan dalam aksesibilitas teknologi dan infrastruktur. Penelitian lebih lanjut diperlukan untuk mengoptimalkan penerapan AI dalam praktik pertanian di Indonesia.
14
Rozi, Fahrur. "Systematic Literature Review pada Analisis Prediktif dengan IoT: Tren Riset, Metode, dan Arsitektur." Jurnal Sistem Cerdas 3, no. 1 (2020): 43–53. http://dx.doi.org/10.37396/jsc.v3i1.53.
Full textAbstract:
Nowadays IoT researches on intelligent service systems is becoming a trend. IoT produces a variety of data from sensors or smart phones. Data generated from IoT can be more useful and can be followed up if data analysis is carried out. Predictive analytic with IoT is part of data analysis that aims to predict something solution. This analysis utilization produces innovative applications in various fields with diverse predictive analytic methods or techniques. This study uses Systematic Literature Review (SLR) to understand about research trends, methods and architecture used in predictive analytic with IoT. So the first step is to determine the research question (RQ) and then search is carried out on several literature published in popular journal databases namely IEEE Xplore, Scopus and ACM from 2015 - 2019. As a result of a review of thirty (30) selected articles, there are several research fields which are trends, namely Transportation, Agriculture, Health, Industry, Smart Home, and Environment. The most studied fields are agriculture. Predictive analytic with IoT use varied method according to the conditions of data used. There are five most widely used methods, namely Bayesian Network (BN), Artificial Neural Network (ANN), Recurrent Neural Networks (RNN), Neural Network (NN), and Support Vector Machines (SVM). Some studies also propose architectures that use predictive analytic with IoT.
15
Hazra, Sumon Kumar, Romana Rahman Ema, Syed Md Galib, Shalauddin Kabir, and Nasim Adnan. "Emotion recognition of human speech using deep learning method and MFCC features." Radioelectronic and Computer Systems, no. 4 (November 29, 2022): 161–72. http://dx.doi.org/10.32620/reks.2022.4.13.
Full textAbstract:
Subject matter: Speech emotion recognition (SER) is an ongoing interesting research topic. Its purpose is to establish interactions between humans and computers through speech and emotion. To recognize speech emotions, five deep learning models: Convolution Neural Network, Long-Short Term Memory, Artificial Neural Network, Multi-Layer Perceptron, Merged CNN, and LSTM Network (CNN-LSTM) are used in this paper. The Toronto Emotional Speech Set (TESS), Surrey Audio-Visual Expressed Emotion (SAVEE) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) datasets were used for this system. They were trained by merging 3 ways TESS+SAVEE, TESS+RAVDESS, and TESS+SAVEE+RAVDESS. These datasets are numerous audios spoken by both male and female speakers of the English language. This paper classifies seven emotions (sadness, happiness, anger, fear, disgust, neutral, and surprise) that is a challenge to identify seven emotions for both male and female data. Whereas most have worked with male-only or female-only speech and both male-female datasets have found low accuracy in emotion detection tasks. Features need to be extracted by a feature extraction technique to train a deep-learning model on audio data. Mel Frequency Cepstral Coefficients (MFCCs) extract all the necessary features from the audio data for speech emotion classification. After training five models with three datasets, the best accuracy of 84.35 % is achieved by CNN-LSTM with the TESS+SAVEE dataset.
16
Hegazi, Ehab H., Lingbo Yang, and Jingfeng Huang. "A Convolutional Neural Network Algorithm for Soil Moisture Prediction from Sentinel-1 SAR Images." Remote Sensing 13, no. 24 (2021): 4964. http://dx.doi.org/10.3390/rs13244964.
Full textAbstract:
Achieving the rational, optimal, and sustainable use of resources (water and soil) is vital to drink and feed 9.725 billion by 2050. Agriculture is the first source of food production, the biggest consumer of freshwater, and the natural filter of air purification. Hence, smart agriculture is a “ray of hope” in regard to food, water, and environmental security. Satellites and artificial intelligence have the potential to help agriculture flourish. This research is an essential step towards achieving smart agriculture. Prediction of soil moisture is important for determining when to irrigate and how much water to apply, to avoid problems associated with over- and under-watering. This also contributes to an increase in the number of areas being cultivated and, hence, agricultural productivity and air purification. Soil moisture measurement techniques, in situ, are point measurements, tedious, time-consuming, expensive, and labor-intensive. Therefore, we aim to provide a new approach to detect moisture content in soil without actually being in contact with it. In this paper, we propose a convolutional neural network (CNN) architecture that can predict soil moisture content over agricultural areas from Sentinel-1 images. The dual-pol (VV–VH) Sentinel-1 SAR data have being utilized (V = vertical, H = horizontal). The CNN model is composed of six convolutional layers, one max-pooling layer, one flatten layer, and one fully connected layer. The total number of Sentinel-1 images used for running CNN is 17,325 images. The best values of the performance metrics (coefficient of determination (R2=0.8664), mean absolute error (MAE=0.0144), and root mean square error (RMSE=0.0274)) have been achieved due to the use of Sigma naught VH and Sigma naught VV as input data to the CNN architecture (C). Results show that VV polarization is better than VH polarization for soil moisture retrieval, and that Sigma naught, Gamma naught, and Beta naught have the same influence on soil moisture estimation.
17
Raj, Nawin, Jaishukh Murali, Lila Singh-Peterson, and Nathan Downs. "Prediction of Sea Level Using Double Data Decomposition and Hybrid Deep Learning Model for Northern Territory, Australia." Mathematics 12, no. 15 (2024): 2376. http://dx.doi.org/10.3390/math12152376.
Full textAbstract:
Sea level rise (SLR) attributed to the melting of ice caps and thermal expansion of seawater is of great global significance to vast populations of people residing along the world’s coastlines. The extent of SLR’s impact on physical coastal areas is determined by multiple factors such as geographical location, coastal structure, wetland vegetation and related oceanic changes. For coastal communities at risk of inundation and coastal erosion due to SLR, the modelling and projection of future sea levels can provide the information necessary to prepare and adapt to gradual sea level rise over several years. In the following study, a new model for predicting future sea levels is presented, which focusses on two tide gauge locations (Darwin and Milner Bay) in the Northern Territory (NT), Australia. Historical data from the Australian Bureau of Meteorology (BOM) from 1990 to 2022 are used for data training and prediction using artificial intelligence models and computation of mean sea level (MSL) linear projection. The study employs a new double data decomposition approach using Multivariate Variational Mode Decomposition (MVMD) and Successive Variational Mode Decomposition (SVMD) with dimensionality reduction techniques of Principal Component Analysis (PCA) for data modelling using four artificial intelligence models (Support Vector Regression (SVR), Adaptive Boosting Regressor (AdaBoost), Multilayer Perceptron (MLP), and Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN-BiGRU). It proposes a deep learning hybrid CNN-BiGRU model for sea level prediction, which is benchmarked by SVR, AdaBoost, and MLP. MVMD-SVMD-CNN-BiGRU hybrid models achieved the highest performance values of 0.9979 (d), 0.996 (NS), 0.9409 (L); and 0.998 (d), 0.9959 (NS), 0.9413 (L) for Milner Bay and Darwin, respectively. It also attained the lowest error values of 0.1016 (RMSE), 0.0782 (MABE), 2.3699 (RRMSE), and 2.4123 (MAPE) for Darwin and 0.0248 (RMSE), 0.0189 (MABE), 1.9901 (RRMSE), and 1.7486 (MAPE) for Milner Bay. The mean sea level (MSL) trend analysis showed a rise of 6.1 ± 1.1 mm and 5.6 ± 1.5 mm for Darwin and Milner Bay, respectively, from 1990 to 2022.
18
S.Hanuman Shabarish, B.Sasi Priya, A.P.Sooriakand, and D.Sujitha. "AI ASSISTED FARMING FOR CROP RECOMMENDATION AND FARM YIELD PREDICTION." international journal of engineering technology and management sciences 6, no. 6 (2022): 628–35. http://dx.doi.org/10.46647/ijetms.2022.v06i06.106.
Full textAbstract:
Machine learning is a crucial decision-support tool for forecasting agricultural yields, enabling judgments about which crops to cultivate and what to do when in the growing seasonFor this study,we performed a Systematic Literature Review(SLR) to find and combine the methods and components that are employed in agricultural prediction research. Using inclusion and exclusion criteria from six internet databases, we chose 50 publications out of a total of 567 that met our search criteria for relevancy.We thoroughly examined the chosen publications, applied, and offeredrecommendations for additional studies. Our data show that temperature, rainfall, and soil type are the most often used characteristics in these models, and artificial neural networks are the most frequently used methodology. This observation was based on an examination of 50 publications, and we next looked for studies employing deep learning in additional electronic databases. We gathered the deep learning algorithms from 30 of these publications that we discovered. Convolution Neural Networks(CNN),Long-Short Term Memory(LSTM), and Deep Neural Networks are the three deep learning algorithms that are used in these investigations, according to this additional analysis(DNN).
19
Cayhualla Amaro, Liset, Sebastian Rau Reyes, María Acuña Meléndez, and Christian Ovalle. "Systematic review of artificial intelligence with near-infrared in blueberries." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 4 (2024): 3761. http://dx.doi.org/10.11591/ijai.v13.i4.pp3761-3771.
Full textAbstract:
The fruit quality has a direct impact on how the fruit looks and how tasty the fruit is. The correct use of tools to determine fruit quality is essential to offer the best product for the final consumer. This study has used the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology. The study objective was elaborate a systematic literature review (SLR) about research of the application of techniques based on artificial intelligence to analyze indicators obtained by near infrared spectroscopy (NIRS) and chemometrics to determine the quality of fruits, including blueberries. The most frequently addressed indicator is the soluble solids concentration (SSC) which was used in several studies with techniques such as support vector machines (SVM) and convolutional neural networks (CNN). According to the results obtained, it is possible to use these techniques to predict blueberry quality indicators. There was an acceptable performance and high accuracy of these models. However, future research could cover other techniques and help to provide better quality control of products in food industries.
20
Liset, Cayhualla Amaro, Rau Reyes Sebastian, Acuña Meléndez María, and Ovalle Christian. "Systematic review of artificial intelligence with near-infrared in blueberries." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 4 (2024): 3761–71. https://doi.org/10.11591/ijai.v13.i4.pp3761-3771.
Full textAbstract:
The fruit quality has a direct impact on how the fruit looks and how tasty the fruit is. The correct use of tools to determine fruit quality is essential to offer the best product for the final consumer. This study has used the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology. The study objective was elaborate a systematic literature review (SLR) about research of the application of techniques based on artificial intelligence to analyze indicators obtained by near infrared spectroscopy (NIRS) and chemometrics to determine the quality of fruits, including blueberries. The most frequently addressed indicator is the soluble solids concentration (SSC) which was used in several studies with techniques such as support vector machines (SVM) and convolutional neural networks (CNN). According to the results obtained, it is possible to use these techniques to predict blueberry quality indicators. There was an acceptable performance and high accuracy of these models. However, future research could cover other techniques and help to provide better quality control of products in food industries.
21
Bandi, Sudheer Reddy, M. Anbarasan, and D. Sheela. "Fusion of SAR and optical images using pixel-based CNN." Neural Network World 32, no. 4 (2022): 197–213. http://dx.doi.org/10.14311/nnw.2022.27.012.
Full textAbstract:
Sensors of different wavelengths in remote sensing field capture data. Each and every sensor has its own capabilities and limitations. Synthetic aperture radar (SAR) collects data that has a high spatial and radiometric resolution. The optical remote sensors capture images with good spectral information. Fused images from these sensors will have high information when implemented with a better algorithm resulting in the proper collection of data to predict weather forecasting, soil exploration, and crop classification. This work encompasses a fusion of optical and radar data of Sentinel series satellites using a deep learning-based convolutional neural network (CNN). The three-fold work of the image fusion approach is performed in CNN as layered architecture covering the image transform in the convolutional layer, followed by the activity level measurement in the max pooling layer. Finally, the decision-making is performed in the fully connected layer. The objective of the work is to show that the proposed deep learning-based CNN fusion approach overcomes some of the difficulties in the traditional image fusion approaches. To show the performance of the CNN-based image fusion, a good number of image quality assessment metrics are analyzed. The consequences demonstrate that the integration of spatial and spectral information is numerically evident in the output image and has high robustness. Finally, the objective assessment results outperform the state-of-the-art fusion methodologies.
22
Bandi, Sudheer Reddy, M. Anbarasan, and D. Sheela. "Fusion of SAR and optical images using pixel-based CNN." Neural Network World 32, no. 4 (2022): 197–213. http://dx.doi.org/10.14311/nnw.2022.32.012.
Full textAbstract:
Sensors of different wavelengths in remote sensing field capture data. Each and every sensor has its own capabilities and limitations. Synthetic aperture radar (SAR) collects data that has a high spatial and radiometric resolution. The optical remote sensors capture images with good spectral information. Fused images from these sensors will have high information when implemented with a better algorithm resulting in the proper collection of data to predict weather forecasting, soil exploration, and crop classification. This work encompasses a fusion of optical and radar data of Sentinel series satellites using a deep learning-based convolutional neural network (CNN). The three-fold work of the image fusion approach is performed in CNN as layered architecture covering the image transform in the convolutional layer, followed by the activity level measurement in the max pooling layer. Finally, the decision-making is performed in the fully connected layer. The objective of the work is to show that the proposed deep learning-based CNN fusion approach overcomes some of the difficulties in the traditional image fusion approaches. To show the performance of the CNN-based image fusion, a good number of image quality assessment metrics are analyzed. The consequences demonstrate that the integration of spatial and spectral information is numerically evident in the output image and has high robustness. Finally, the objective assessment results outperform the state-of-the-art fusion methodologies.
23
Mundlamuri, Rahul, Devasena Inupakutika, and David Akopian. "SDR-Fi-Z: A Wireless Local Area Network-Fingerprinting-Based Indoor Positioning Method for E911 Vertical Accuracy Mandate." Sensors 25, no. 3 (2025): 823. https://doi.org/10.3390/s25030823.
Full textAbstract:
The Enhanced 911 (E911) mandate of the Federal Communications Commission (FCC) drives the evolution of indoor three-dimensional (3D) location/positioning services for emergency calls. Many indoor localization systems exploit location-dependent wireless signaling signatures, often called fingerprints, and machine learning techniques for position estimation. In particular, received signal strength indicators (RSSIs) and Channel State Information (CSI) in Wireless Local Area Networks (WLANs or Wi-Fi) have gained popularity and have been addressed in the literature. While RSSI signatures are easy to collect, the fluctuation of wireless signals resulting from environmental uncertainties leads to considerable variations in RSSIs, which poses a challenge to accurate localization on a single floor, not to mention multi-floor or even three-dimensional (3D) indoor localization. Considering recent E911 mandate attention to vertical location accuracy, this study aimed to investigate CSI from Wi-Fi signals to produce baseline Z-axis location data, which has not been thoroughly addressed. To that end, we utilized CSI measurements and two representative machine learning methods, an artificial neural network (ANN) and convolutional neural network (CNN), to estimate both 3D and vertical-axis positioning feasibility to achieve E911 accuracy compliance.
24
N. Venkateswara Rao, Dr. "Sign-Prac : Real - Time Language and Practice System." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 06 (2025): 1–9. https://doi.org/10.55041/ijsrem50581.
Full textAbstract:
Abstract: In today’s technologically advanced world, bridging the communication gap between hearing-impaired individuals and the rest of society is a critical challenge. Sign language serves as a primary mode of communication for the deaf and hard of-hearing community. However, due to the limited number of people proficient in sign language, there exists a significant communication barrier. This project aims to address this gap by developing an intelligent, real-time sign language recognition system using deep learning techniques. The proposed system utilizes a combination of computer vision and deep learning algorithms to accurately recognize hand gestures representing sign language. Leveraging tools such as MediaPipe for hand tracking and a Convolutional Neural Network (CNN) or keypoint-based classifier for gesture classification, the system processes live video input or uploaded images to identify signs and convert them into readable text. The model is trained on a custom or publicly available sign language dataset, ensuring accuracy and robustness across various lighting conditions and hand orientations. Key modules of the system include data preprocessing, feature extraction, model training using gesture sequences, and real-time inference. The model demonstrates high classification accuracy and low latency, making it suitable for real-world applications such as education, customer service, and accessibility platforms. This project not only highlights the potential of artificial intelligence in assistive technologies but also contributes to fostering inclusivity and equal communication opportunities for all individuals, regardless of physical ability. Keywords: Sign Language Recognition (SLR), Real-Time Gesture Recognition, Deaf and Hard-of-Hearing Communication, MediaPipe, Deep Learning, Computer Vision, DualNet-SLR, Point History Network, Keypoint History Network, Streamlit Interface.
25
Li, Shu-Hua, Feng-Long Yan, and Ying-Qiu Li. "An Improved Multi Target Ship Recognition Model Based on Deep Convolutional Neural Network." Journal of Advanced Computational Intelligence and Intelligent Informatics 28, no. 1 (2024): 216–23. http://dx.doi.org/10.20965/jaciii.2024.p0216.
Full textAbstract:
Deep learning is the major technique used to identify objects in images captured by the synthetic aperture radar (SAR). While SAR images can be used to identify ships in general, detecting multiple ships or small vessels in these images in complex contexts remains an outstanding challenge. This study proposes a model of detection based on the improved PP-YOLO deep convolutional neural network that can identify multiple ships as well as small vessels in complex scenarios from SAR images. The histogram equalization algorithm is first used to preprocess the SAR images, and then the initial anchor box is optimized by using the shape similarity distance-based K-means clustering algorithm. Following this, the accuracy of the training network is improved based on the feature pyramid network and an attention mechanism. The experimental results show that the average accuracy (average precision) of the model was 94.25% at 41.63 frames per second on the GF-3 and the Sentinel-1 SAR datasets, superior to those of YOLOv3 (Darknet), YOLOv7, FPN (VGG), SSD, Faster R-CNN, and PP-YOLO (RestNet50-vd). The model also satisfies the demands of real-time detection.
26
Zielonka, Marta, Artur Piastowski, Andrzej Czyżewski, Paweł Nadachowski, Maksymilian Operlejn, and Kamil Kaczor. "Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets." Electronics 11, no. 22 (2022): 3831. http://dx.doi.org/10.3390/electronics11223831.
Full textAbstract:
Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire.
27
Geng, Xiaomeng, Lei Shi, Jie Yang, et al. "Ship Detection and Feature Visualization Analysis Based on Lightweight CNN in VH and VV Polarization Images." Remote Sensing 13, no. 6 (2021): 1184. http://dx.doi.org/10.3390/rs13061184.
Full textAbstract:
Synthetic aperture radar (SAR) is a significant application in maritime monitoring, which can provide SAR data throughout the day and in all weather conditions. With the development of artificial intelligence and big data technologies, the data-driven convolutional neural network (CNN) has become widely used in ship detection. However, the accuracy, feature visualization, and analysis of ship detection need to be improved further, when the CNN method is used. In this letter, we propose a two-stage ship detection for land-contained sea area without a traditional sea-land segmentation process. First, to decrease the possibly existing false alarms from the island, an island filter is used as the first step, and then threshold segmentation is used to quickly perform candidate detection. Second, a two-layer lightweight CNN model-based classifier is built to separate false alarms from the ship object. Finally, we discuss the CNN interpretation and visualize in detail when the ship is predicted in vertical–horizontal (VH) and vertical–vertical (VV) polarization. Experiments demonstrate that the proposed method can reach an accuracy of 99.4% and an F1 score of 0.99 based on the Sentinel-1 images for a ship with a size of less than 32 × 32.
28
Deepika, Chandupatla, and Swarna Kuchibhotla. "Enhanced Speech Emotion RecognitionUsing AudioSignal Processing with CNN Assistance." Data and Metadata 4 (April 9, 2025): 715. https://doi.org/10.56294/dm2025715.
Full textAbstract:
Abstract: The important form human communicating is speech, which can also be used as a potential means of human-computer interaction (HCI) with the use of a microphone sensor. An emerging field of HCI research uses these sensors to detect quantifiable emotions from speech signals. This study has implications for human-reboot interaction, the experience of virtual reality, actions assessment, Health services, and Customer service centres for emergencies, among other areas, to ascertain the speaker's emotional state as shown by their speech. We present significant contributions for; in this work. (i) improving Speech Emotion Recognition (SER) accuracy in comparison in the most advanced; and (ii) lowering computationally complicated nature of the model SER that is being given. We present a plain nets strategy convolutional neural network (CNN) architecture with artificial intelligence support to train prominent and distinguishing characteristics from speech signal spectrograms were improved in previous rounds to get better performance. Rather than using a pooling layer, convolutional layers are used to learn local hidden patterns, whereas Layers with complete connectivity are utilized to understand global discriminative features and Speech emotion categorization is done using a soft-max classifier. The suggested method reduces the size of the model by 34.5 MB while improving the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and Interactive Emotional Dyadic Motion Capture (IEMDMC) datasets, respectively, increasing accuracy by 4.5% and 7.85%. It shows how the proposed SER technique can be applied in real-world scenarios and proves its applicability and efficacy.
29
Rahmawati, Fennyka. "DETEKSI CACAT DAN PENGUKURAN JARUM JAHIT MENGGUNAKAN COMPUTER VISION DAN MACHINE LEARNING: TINJAUAN PUSTAKA SISTEMATIS (SLR)." J@ti Undip: Jurnal Teknik Industri 20, no. 2 (2025): 125–37. https://doi.org/10.14710/jati.20.2.125-137.
Full textAbstract:
Masih ditemukan kerusakan jahitan akibat interaksi antara jarum dan kain mempengaruhi optimalisasi operasi. Mesin jahit industri memiliki kecepatan tinggi dapat menyebabkan jarum jahit patah selama proses penjahitan. Patahan jarum jahit yang masih tertinggal akan memperburuk kerusakan pada serat kain. Deteksi cacat mendapat perhatian lebih bertujuan untuk menjaga kualitas produk. Pemanfaatan teknologi seperti computer vision dan machine learning mempermudah proses deteksi lebih cepat dan akurat. Basis data Scopus digunakan untuk mengekstrak artikel, yang mana hasil informasi akan divisualisasi perangkat lunak VOSViewer. Penelitian ini memberi gambaran umum yang komprehensif dan analisis bibliometrik dari studi publikasi terkait deteksi cacat dan pengukuran di bidang tekstil dalam kurun waktu 10 tahun terakhir yang didapatkan 131 artikel pada pencarian 23 Desember 2024. Walaupun terdapat peningkatan yang signifikan, namun tidak ditemukan pada deteksi cacat khusus jarum jahit dalam tren melainkan banyak ditemukan deteksi cacat pada jahitan dan kain. Metode yang paling sering digunakan adalah transformasi hough, GLCM, morphology sebagai fitur ekstraksi. Sementara dalam klasifikasi kecacatan yang paling banyak digunakan adalah support vector machine (SVM) dan Artificial Neural Network (ANN). Tiongkok memimpin jumlah publikasi terbanyak. Textile Research journal merupakan jurnal paling produktif dalam bidang penelitian ini. Abstract[Defect Detection and Sewing Needle Measurement Using Computer Vision and Machine Learning: Systematic Literature Review (SLR)] Sewing damage is still found due to the interaction between the needle and the fabric affecting the optimization of operations. Industrial sewing machines have high speeds that can cause sewing needles to break during the sewing process. Broken sewing needles that are still left will worsen the damage to the fabric fibers. More focus has been placed on defect identification in order to preserve product quality. The detection procedure is facilitated more quickly and precisely by the use of technologies like computer vision and machine learning. After articles are extracted from the Scopus database, the information is shown using VOSViewer software. The 131 papers that the search on December 23, 2024, turned up for this study's thorough examination and bibliometric analysis of published works regarding flaw detection and measurement in the textile sector during the past ten years. There was a noticeable rise in sewing and fabric fault detections, even if the trend did not find any particular issues with sewing needles. Artificial neural networks (ANN) and support vector machines (SVM) are the most used methods for classifying faults. The country with the most publications is China. The most fruitful journal in this area of study is Textile Research.Keywords: bibliometric analysis; defect detection; broken needle; extraction method; classification method
30
Mustaqeem and Soonil Kwon. "A CNN-Assisted Enhanced Audio Signal Processing for Speech Emotion Recognition." Sensors 20, no. 1 (2019): 183. http://dx.doi.org/10.3390/s20010183.
Full textAbstract:
Speech is the most significant mode of communication among human beings and a potential method for human-computer interaction (HCI) by using a microphone sensor. Quantifiable emotion recognition using these sensors from speech signals is an emerging area of research in HCI, which applies to multiple applications such as human-reboot interaction, virtual reality, behavior assessment, healthcare, and emergency call centers to determine the speaker’s emotional state from an individual’s speech. In this paper, we present major contributions for; (i) increasing the accuracy of speech emotion recognition (SER) compared to state of the art and (ii) reducing the computational complexity of the presented SER model. We propose an artificial intelligence-assisted deep stride convolutional neural network (DSCNN) architecture using the plain nets strategy to learn salient and discriminative features from spectrogram of speech signals that are enhanced in prior steps to perform better. Local hidden patterns are learned in convolutional layers with special strides to down-sample the feature maps rather than pooling layer and global discriminative features are learned in fully connected layers. A SoftMax classifier is used for the classification of emotions in speech. The proposed technique is evaluated on Interactive Emotional Dyadic Motion Capture (IEMOCAP) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) datasets to improve accuracy by 7.85% and 4.5%, respectively, with the model size reduced by 34.5 MB. It proves the effectiveness and significance of the proposed SER technique and reveals its applicability in real-world applications.
31
Anvarjon, Tursunov, Mustaqeem, and Soonil Kwon. "Deep-Net: A Lightweight CNN-Based Speech Emotion Recognition System Using Deep Frequency Features." Sensors 20, no. 18 (2020): 5212. http://dx.doi.org/10.3390/s20185212.
Full textAbstract:
Artificial intelligence (AI) and machine learning (ML) are employed to make systems smarter. Today, the speech emotion recognition (SER) system evaluates the emotional state of the speaker by investigating his/her speech signal. Emotion recognition is a challenging task for a machine. In addition, making it smarter so that the emotions are efficiently recognized by AI is equally challenging. The speech signal is quite hard to examine using signal processing methods because it consists of different frequencies and features that vary according to emotions, such as anger, fear, sadness, happiness, boredom, disgust, and surprise. Even though different algorithms are being developed for the SER, the success rates are very low according to the languages, the emotions, and the databases. In this paper, we propose a new lightweight effective SER model that has a low computational complexity and a high recognition accuracy. The suggested method uses the convolutional neural network (CNN) approach to learn the deep frequency features by using a plain rectangular filter with a modified pooling strategy that have more discriminative power for the SER. The proposed CNN model was trained on the extracted frequency features from the speech data and was then tested to predict the emotions. The proposed SER model was evaluated over two benchmarks, which included the interactive emotional dyadic motion capture (IEMOCAP) and the berlin emotional speech database (EMO-DB) speech datasets, and it obtained 77.01% and 92.02% recognition results. The experimental results demonstrated that the proposed CNN-based SER system can achieve a better recognition performance than the state-of-the-art SER systems.
32
Teran-Quezada, Alvaro A., Victor Lopez-Cabrera, Jose Carlos Rangel, and Javier E. Sanchez-Galan. "Sign-to-Text Translation from Panamanian Sign Language to Spanish in Continuous Capture Mode with Deep Neural Networks." Big Data and Cognitive Computing 8, no. 3 (2024): 25. http://dx.doi.org/10.3390/bdcc8030025.
Full textAbstract:
Convolutional neural networks (CNN) have provided great advances for the task of sign language recognition (SLR). However, recurrent neural networks (RNN) in the form of long–short-term memory (LSTM) have become a means for providing solutions to problems involving sequential data. This research proposes the development of a sign language translation system that converts Panamanian Sign Language (PSL) signs into text in Spanish using an LSTM model that, among many things, makes it possible to work with non-static signs (as sequential data). The deep learning model presented focuses on action detection, in this case, the execution of the signs. This involves processing in a precise manner the frames in which a sign language gesture is made. The proposal is a holistic solution that considers, in addition to the seeking of the hands of the speaker, the face and pose determinants. These were added due to the fact that when communicating through sign languages, other visual characteristics matter beyond hand gestures. For the training of this system, a data set of 330 videos (of 30 frames each) for five possible classes (different signs considered) was created. The model was tested having an accuracy of 98.8%, making this a valuable base system for effective communication between PSL users and Spanish speakers. In conclusion, this work provides an improvement of the state of the art for PSL–Spanish translation by using the possibilities of translatable signs via deep learning.
33
Karraz, George. "A Convolutional Neural Network Framework to Detect COVID-19 Disease in Computerized Tomography Images." Damascus University Journal for Basic Sciences, no. 11163-201 (April 29, 2024): 1–15. https://doi.org/10.5281/zenodo.11087588.
Full textAbstract:
COVID-19 is an RNA virus that causes infectious diseases that are transmitted between animals and have evolved among humans. This class of pathogens is responsible for respiratory diseases. Coronavirus refers to the crown-like protrusions on the outside surface of the virus. Commonly, coronavirus is an infection that causes breathing difficulties in humans. In recent years, there has been an expansion in employing symptom investigation techniques based on advanced tools in the field of digital image processing and analysis DIPA, which are essential for deeply examining disease symptoms, and lead to better results obtained from medical imaging devices for identifying and diagnosing a lot of diseases. From this standpoint, the urgent need to employ artificial intelligence as a supporter of DIPA in disease detection arose. In this research, we propose an efficient approach to manipulate the lung’s CT-scan images adaptively, and then detect the probability of coronavirus infection based on a sophisticated classifier based on the convolutional neural network CNN as a deep learning tool. We chose the well-known severe acute respiratory syndrome coronavirus 2 SARS-COV-2 dataset as an efficient dataset proposed in the relevant literature to train and validate the artificial intelligence models that could proposed by researchers related to detecting automatically the presence of coronavirus in the lung's CT-scan image. On the other hand, the SARS-COV-2 dataset contains sufficient study cases from a statistical point of view, that makes any developed AI model able to be trained and validated. We used 70% of the total images presented in SAR-CoV-2 in the classifier's training phase, and the other 30% in its testing stage as unseen data that was not involved during the training phase. The obtained results proved the successful performance of our approach in both the training and testing phases without any famous encountered problems, such as over-fitting, early stooping, or unstable performance. So we confirm the performance quality and stability of our approach with achieved accuracy over unseen data of up to 99% in detecting and distinguishing the infection cases.
34
Tziolas, Nikolaos, Nikolaos Tsakiridis, Eyal Ben-Dor, John Theocharis, and George Zalidis. "Employing a Multi-Input Deep Convolutional Neural Network to Derive Soil Clay Content from a Synergy of Multi-Temporal Optical and Radar Imagery Data." Remote Sensing 12, no. 9 (2020): 1389. http://dx.doi.org/10.3390/rs12091389.
Full textAbstract:
Earth observation (EO) has an immense potential as being an enabling tool for mapping spatial characteristics of the topsoil layer. Recently, deep learning based algorithms and cloud computing infrastructure have become available with a great potential to revolutionize the processing of EO data. This paper aims to present a novel EO-based soil monitoring approach leveraging open-access Copernicus Sentinel data and Google Earth Engine platform. Building on key results from existing data mining approaches to extract bare soil reflectance values the current study delivers valuable insights on the synergistic use of open access optical and radar images. The proposed framework is driven by the need to eliminate the influence of ambient factors and evaluate the efficiency of a convolutional neural network (CNN) to effectively combine the complimentary information contained in the pool of both optical and radar spectral information and those form auxiliary geographical coordinates mainly for soil. We developed and calibrated our multi-input CNN model based on soil samples (calibration = 80% and validation 20%) of the LUCAS database and then applied this approach to predict soil clay content. A promising prediction performance (R2 = 0.60, ratio of performance to the interquartile range (RPIQ) = 2.02, n = 6136) was achieved by the inclusion of both types (synthetic aperture radar (SAR) and laboratory visible near infrared–short wave infrared (VNIR-SWIR) multispectral) of observations using the CNN model, demonstrating an improvement of more than 5.5% in RMSE using the multi-year median optical composite and current state-of-the-art non linear machine learning methods such as random forest (RF; R2 = 0.55, RPIQ = 1.91, n = 6136) and artificial neural network (ANN; R2 = 0.44, RPIQ = 1.71, n = 6136). Moreover, we examined post-hoc techniques to interpret the CNN model and thus acquire an understanding of the relationships between spectral information and the soil target identified by the model. Looking to the future, the proposed approach can be adopted on the forthcoming hyperspectral orbital sensors to expand the current capabilities of the EO component by estimating more soil attributes with higher predictive performance.
35
Song, Juyoung, Duk-jin Kim, and Ki-mook Kang. "Automated Procurement of Training Data for Machine Learning Algorithm on Ship Detection Using AIS Information." Remote Sensing 12, no. 9 (2020): 1443. http://dx.doi.org/10.3390/rs12091443.
Full textAbstract:
Development of convolutional neural network (CNN) optimized for object detection, led to significant developments in ship detection. Although training data critically affect the performance of the CNN-based training model, previous studies focused mostly on enhancing the architecture of the training model. This study developed a sophisticated and automatic methodology to generate verified and robust training data by employing synthetic aperture radar (SAR) images and automatic identification system (AIS) data. The extraction of training data initiated from interpolating the discretely received AIS positions to the exact position of the ship at the time of image acquisition. The interpolation was conducted by applying a Kalman filter, followed by compensating the Doppler frequency shift. The bounding box for the ship was constructed tightly considering the installation of the AIS equipment and the exact size of the ship. From 18 Sentinel-1 SAR images using a completely automated procedure, 7489 training data were obtained, compared with a different set of training data from visual interpretation. The ship detection model trained using the automatic training data obtained 0.7713 of overall detection performance from 3 Sentinel-1 SAR images, which exceeded that of manual training data, evading the artificial structures of harbors and azimuth ambiguity ghost signals from detection.
36
Ali, Abdulalem, Shukor Abd Razak, Siti Hajar Othman, et al. "Financial Fraud Detection Based on Machine Learning: A Systematic Literature Review." Applied Sciences 12, no. 19 (2022): 9637. http://dx.doi.org/10.3390/app12199637.
Full textAbstract:
Financial fraud, considered as deceptive tactics for gaining financial benefits, has recently become a widespread menace in companies and organizations. Conventional techniques such as manual verifications and inspections are imprecise, costly, and time consuming for identifying such fraudulent activities. With the advent of artificial intelligence, machine-learning-based approaches can be used intelligently to detect fraudulent transactions by analyzing a large number of financial data. Therefore, this paper attempts to present a systematic literature review (SLR) that systematically reviews and synthesizes the existing literature on machine learning (ML)-based fraud detection. Particularly, the review employed the Kitchenham approach, which uses well-defined protocols to extract and synthesize the relevant articles; it then report the obtained results. Based on the specified search strategies from popular electronic database libraries, several studies have been gathered. After inclusion/exclusion criteria, 93 articles were chosen, synthesized, and analyzed. The review summarizes popular ML techniques used for fraud detection, the most popular fraud type, and evaluation metrics. The reviewed articles showed that support vector machine (SVM) and artificial neural network (ANN) are popular ML algorithms used for fraud detection, and credit card fraud is the most popular fraud type addressed using ML techniques. The paper finally presents main issues, gaps, and limitations in financial fraud detection areas and suggests possible areas for future research.
37
Geng, Xiaomeng, Lingli Zhao, Lei Shi, Jie Yang, Pingxiang Li, and Weidong Sun. "Small-Sized Ship Detection Nearshore Based on Lightweight Active Learning Model with a Small Number of Labeled Data for SAR Imagery." Remote Sensing 13, no. 17 (2021): 3400. http://dx.doi.org/10.3390/rs13173400.
Full textAbstract:
Marine ship detection by synthetic aperture radar (SAR) is an important remote sensing technology. The rapid development of big data and artificial intelligence technology has facilitated the wide use of deep learning methods in SAR imagery for ship detection. Although deep learning can achieve a much better detection performance than traditional methods, it is difficult to achieve satisfying performance for small-sized ships nearshore due to the weak scattering caused by their material and simple structure. Another difficulty is that a huge amount of data needs to be manually labeled to obtain a reliable CNN model. Manual labeling each datum not only takes too much time but also requires a high degree of professional knowledge. In addition, the land and island with high backscattering often cause high false alarms for ship detection in the nearshore area. In this study, a novel method based on candidate target detection, boundary box optimization, and convolutional neural network (CNN) embedded with active learning strategy is proposed to improve the accuracy and efficiency of ship detection in nearshore areas. The candidate target detection results are obtained by global threshold segmentation. Then, the strategy of boundary box optimization is defined and applied to reduce the noise and false alarms caused by island and land targets as well as by sidelobe interference. Finally, a lightweight CNN embedded with active learning scheme is used to classify the ships using only a small labeled training set. Experimental results show that the performance of the proposed method for small-sized ship detection can achieve 97.78% accuracy and 0.96 F1-score with Sentinel-1 images in complex nearshore areas.
38
Chandrasekara, P. G. I. M., L. L. Gihan Chathuranga, K. A. A. Chathurangi, D. M. K. N. Seneviratna, and R. M. K. T. Rathnayaka. "Intelligent Video Surveillance Mechanisms for Abnormal Activity Recognition in Real-Time: A Systematic Literature Review." KDU Journal of Multidisciplinary Studies 5, no. 1 (2023): 26–40. http://dx.doi.org/10.4038/kjms.v5i1.60.
Full textAbstract:
Video surveillance plays a crucial role in securing indoor and outdoor locations in today's unreliable world, particularly in real-time applications for behaviour detection, comprehension, and labelling activities as normal or suspicious. For example, in the development of automated video surveillance systems, smart video reconnaissance systems based on picture recognition and activity recognition that detect violent behaviours is basic to forestalling wrongdoings and giving public security. According to the literature, Artificial Intelligent, Machine Learning, and deep portrayal-based approaches have been effectively utilized in image recognition and human activity observation tasks. In this literature review, a 3D convolution neural network based on deep learning is used as the proposed methodology. Thus, this article completed a Systematic Literature Review (SLR) in light of intelligent video surveillance to real-time identify abnormal activities from 2016 to 2021. In this current study, 50 research papers were considered and based on the screen filtering, the most suitable 16 papers were filtered based on intelligent video surveillance and real-time abnormal activities. Furthermore, this study identifies potential areas for improvement in intelligent video surveillance systems that can enhance public safety and security, underscoring the importance of ongoing research in this field.
39
Demertzis, Konstantinos, Lazaros Iliadis, and Elias Pimenidis. "Geo-AI to aid disaster response by memory-augmented deep reservoir computing." Integrated Computer-Aided Engineering 28, no. 4 (2021): 383–98. http://dx.doi.org/10.3233/ica-210657.
Full textAbstract:
It is a fact that natural disasters often cause severe damage both to ecosystems and humans. Moreover, man-made disasters can have enormous moral and economic consequences for people. A typical example is the large deadly and catastrophic explosion in Beirut on 4 August 2020, which destroyed a very large area of the city. This research paper introduces a Geo-AI disaster response computer vision system, capable to map an area using material from Synthetic Aperture Radar (SAR). SAR is a unique form of radar that can penetrate the clouds and collect data day and night under any weather conditions. Specifically, the Memory-Augmented Deep Convolutional Echo State Network (MA/DCESN) is introduced for the first time in the literature, as an advanced Machine Vision (MAV) architecture. It uses a meta-learning technique, which is based on a memory-augmented approach. The target is the employment of Deep Reservoir Computing (DRC) for domain adaptation. The developed Deep Convolutional Echo State Network (DCESN) combines a classic Convolutional Neural Network (CNN), with a Deep Echo State Network (DESN), and analog neurons with sparse random connections. Its training is performed following the Recursive Least Square (RLS) method. In addition, the integration of external memory allows the storage of useful data from past processes, while facilitating the rapid integration of new information, without the need for retraining. The proposed DCESN implements a set of original modifications regarding training setting, memory retrieval mechanisms, addressing techniques, and ways of assigning attention weights to memory vectors. As it is experimentally shown, the whole approach produces remarkable stability, high generalization efficiency and significant classification accuracy, significantly extending the state-of-the-art Machine Vision methods.
40
Naseer, Mehwish, Wu Zhang, and Wenhao Zhu. "Early Prediction of a Team Performance in the Initial Assessment Phases of a Software Project for Sustainable Software Engineering Education." Sustainability 12, no. 11 (2020): 4663. http://dx.doi.org/10.3390/su12114663.
Full textAbstract:
Software engineering is a competitive field in education and practice. Software projects are key elements of software engineering courses. Software projects feature a fusion of process and product. The process reflects the methodology of performing the overall software engineering practice. The software product is the final product produced by applying the process. Like any other academic domain, an early evaluation of the software product being developed is vital to identify the at-risk teams for sustainable education in software engineering. Guidance and instructor attention can help overcome the confusion and difficulties of low performing teams. This study proposed a hybrid approach of information gain feature selection with a J48 decision tree to predict the earliest possible phase for final performance prediction. The proposed technique was compared with the state-of-the-art machine learning (ML) classifiers, naïve Bayes (NB), artificial neural network (ANN), logistic regression (LR), simple logistic regression (SLR), repeated incremental pruning to produce error reduction (RIPPER), and sequential minimal optimization (SMO). The goal of this process is to predict the teams expected to obtain a below-average grade in software product development. The proposed technique outperforms others in the prediction of low performing teams at an early assessment stage. The proposed J48-based technique outperforms others by making 89% correct predictions.
41
SANTOS, IWLDSON GUILHERME DA SILVA. "Previsão de Focos de Calor na Região Metropolitana de Maceió Utilizando Rede Neural Artificial." Revista Brasileira de Geografia Física 15, no. 5 (2022): 2313. http://dx.doi.org/10.26848/rbgf.v15.5.p2313-2326.
Full textAbstract:
O objetivo deste estudo é o de analisar a previsão de focos de calor (FC) na Região Metropolitana de Maceió (RMM) utilizando Rede Neural Artificial (RNA). Foram usados neste estudo os dados de focos de calor no período de 1999 a 2019, disponíveis no Banco de Dados de Queimadas (BDQueimadas). A previsão foi feita com base na RNA não linear autorregressiva (NAR) com os FC sendo dados de entrada e alvo. As previsões se basearam na função de ativação Tangente Hiperbólica e Sigmoide, para averiguar qual função se adaptaria melhor ao modelo de previsão de FC na RMM. O desempenho do modelo foi verificado pelo diagrama de espalhamento (1:1), com destaque para Regressão Linear Simples (RLS), os coeficientes de determinação (R2) e de Pearson (r), seguido dos indicadores de erros (EM - Erro Médio, REQM – Raiz do Erro Quadrático Médio, EPAM – Erro Percentual Absoluto Médio). O EM variou entre -0,47 a 1,49 focos, o REQM (1,16 a 7,02 focos) e o EPAM (14,45 a 24,66%). Os coeficientes r (0,08 a 0,52) e R2 (1 a 58%). Os modelos com base nas funções de ativação foram similares entre observado e previsto, sendo satisfatória na maioria dos municípios. Os modelos não tiveram sucesso na previsão de FC elevados, principalmente nos anos 2008, 2012, 2015 e 2016, período de seca extrema. Os resultados obtidos indicam que a aplicação de RNA na previsão de FC pode auxiliar nas tomadas de decisões dos gestores públicos e no monitoramento de queimadas e incêndios em áreas urbanas.Palavras-chave: incêndios, inteligência artificial, monitoramento ambiental. Forecast of Fire Foci in the Metropolitan Region of Maceió Using Artificial Neural NetworkABSTRACTThe aim of this study is to analyze the forecast of fire foci (FF) in the Maceió Metropolitan Region (MMR) using Artificial Neural Network (ANN). It was used in the study fire foci data available in the Burning Database (BDQueimadas) in the period from 1999 to 2019. The forecast was made based on the ANN non-linear autoregressive (NAR) with the FF, being input and target data. The forecast was based Hyperbolic Tangent and Sigmoid activation function, to find out which function would best adapt to the forecast model of FF in the MMR. The model performance was based on the Scatter Diagram (1:1), with emphasis on Simple Linear Regression (SLR), the coefficients of determination (R2) and Pearson’s (r), followed by the error indicators (ME – Mean Error, RMSE – Root Mean Square Error, MAPE – Mean Absolute Percentage Error). The ME ranged from -0.47 to 1.49 foci, RMSE (1.16 to 7.02 foci), MAPE (14.45 to 24.66%). The coefficients r (0.08 to 0.52) and R2 (1 to 58%). The models based on activation function were similar between observed and predicted, being satisfactory in most municipalities. The models were not successful in forecast high FF, especially in the years 2008, 2012, 2015 and 2016, a period of extreme drought. These results obtained in the study indicate that the application of ANN in the forecast of FF can help in the decision-making of public managers and in the monitoring of burnings and fires in urban areas.Keywords: Fire foci, Artificial Intelligence, Environmental Monitoring.
42
Alonso, Jesús, and Tatiana Silva. "Leveraging Copernicus for Ice Block Detection: A Step Towards Safer Arctic Navigation." Open Research Europe 4 (July 30, 2024): 159. http://dx.doi.org/10.12688/openreseurope.18090.1.
Full textAbstract:
Background The Arctic is becoming more accessible due to ice melting, posing challenges for navigation due to floating ice blocks. Detecting these ice blocks is crucial for ensuring the safety of vessels navigating these waters. Methods This study introduces a novel method for detecting ice blocks in the Arctic using Artificial Intelligence (AI) and Synthetic Aperture Radar (SAR) satellite images from the Sentinel-1 mission of the Copernicus program. Our approach combines state-of-the-art image segmentation and deep learning techniques. We utilize a Convolutional Neural Network (CNN) classifier to accurately locate ice blocks within the images and retrieve their geographic coordinates. The method's performance is validated using precision, recall, and F1-score metrics. Results Our CNN classifier demonstrates robust performance in detecting ice blocks, validated through precision, recall, and F1-score metrics. The practical application of our technology was showcased in the AI-ARC project’s Arctic demo, receiving positive feedback from coast guards across various European countries. The system provides near-real-time alerts about detected ice blocks, allowing for timely route adjustments and reducing collision risks. Conclusions The developed system significantly contributes to Arctic navigation safety by providing accurate and timely detection of ice blocks. This work underscores the transformative potential of AI in environmental monitoring and maritime safety. Future refinements will be based on user feedback and advancements in AI technology, enhancing the system's effectiveness and reliability.
43
Favorskaya, Margarita, and Nishchhal Nishchhal. "Verification of Marine Oil Spills Using Aerial Images Based on Deep Learning Methods." Informatics and Automation 21, no. 5 (2022): 937–62. http://dx.doi.org/10.15622/ia.21.5.4.
Full textAbstract:
The article solves the problem of verifying oil spills on the water surfaces of rivers, seas and oceans using optical aerial photographs, which are obtained from cameras of unmanned aerial vehicles, based on deep learning methods. The specificity of this problem is the presence of areas visually similar to oil spills on water surfaces caused by blooms of specific algae, substances that do not cause environmental damage (for example, palm oil), or glare when shooting (so-called look-alikes). Many studies in this area are based on the analysis of synthetic aperture radars (SAR) images, which do not provide accurate classification and segmentation. Follow-up verification contributes to reducing environmental and property damage, and oil spill size monitoring is used to make further response decisions. A new approach to the verification of optical images as a binary classification problem based on the Siamese network is proposed, when a fragment of the original image is repeatedly compared with representative examples from the class of marine oil slicks. The Siamese network is based on the lightweight VGG16 network. When the threshold value of the output function is exceeded, a decision is made about the presence of an oil spill. To train the networks, we collected and labeled our own dataset from open Internet resources. A significant problem is an imbalance of classes in the dataset, which required the use of augmentation methods based not only on geometric and color manipulations, but also on the application of a Generative Adversarial Network (GAN). Experiments have shown that the classification accuracy of oil spills and look-alikes on the test set reaches values of 0.91 and 0.834, respectively. Further, an additional problem of accurate semantic segmentation of an oil spill is solved using convolutional neural networks (CNN) of the encoder-decoder type. Three deep network architectures U-Net, SegNet, and Poly-YOLOv3 have been explored for segmentation. The Poly-YOLOv3 network demonstrated the best results, reaching an accuracy of 0.97 and an average image processing time of 385 s with the Google Colab web service. A database was also designed to store both original and verified images with problem areas.
44
Portal Díaz, Jorge, Irina Siles Siles, Eduardo Puig Contreras, and Ania Sánchez. "Aplicación de técnicas de inteligencia artificial para reconocimiento facial en sistemas de seguridad en ambientes de intranet." Mare Ingenii 4, no. 1 (2022): 20–32. http://dx.doi.org/10.52948/mare.v4i1.682.
Full textAbstract:
El vertiginoso crecimiento y la precisión de las técnicas de Inteligencia Artificial (AI, del inglés Artificial Intelligence) permiten analizar grandes volúmenes de datos de forma rápida y eficiente. En ese sentido, la aplicación de técnicas de reconocimiento facial en sistemas de seguridad (video-vigilancia) no quedan exentas y resultan convenientes pues asistirían al desempeño humano en las labores de observación, interpretación y etiquetado de imágenes en tiempo real, a la vez que funcionarían como un sistema de alerta o alarma ante la presencia de intrusos. La implementación de estos sistemas puede llevarse a cabo con hardware relativamente barato y aprovechando la capacidad de procesamiento del clúster big data de la Universidad Central “Marta Abreu” de Las Villas (UCLV). Con la puesta en práctica del proyecto se ofrecen soluciones a las problemáticas identificadas en la dirección de informatización asociadas a la gestión de cuentas por parte de los usuarios y aplicaciones futuras relacionadas con la detección de personal en áreas de interés. Con la implementación se pretenden dos posibles contribuciones: en primer lugar, se ha de diseñar un procedimiento capaz de ensamblar un conjunto de datos a gran escala, minimizando al mismo tiempo la cantidad de anotaciones manuales involucradas. Este procedimiento se ha de desarrollar para caras, pero evidentemente es adecuado para otras clases de objetos, así como para tareas específicas. La segunda contribución ha de ser mostrar que una Red Neuronal Convolucional (CNN, del inglés Convolutional Neural Network), profunda con la formación adecuada, puede lograr resultados comparables a los del estado de la técnica.
45
Islam, MD Samiul, Xinyao Sun, Zheng Wang, and Irene Cheng. "FAPNET: Feature Fusion with Adaptive Patch for Flood-Water Detection and Monitoring." Sensors 22, no. 21 (2022): 8245. http://dx.doi.org/10.3390/s22218245.
Full textAbstract:
In satellite remote sensing applications, waterbody segmentation plays an essential role in mapping and monitoring the dynamics of surface water. Satellite image segmentation—examining a relevant sensor data spectrum and identifying the regions of interests to obtain improved performance—is a fundamental step in satellite data analytics. Satellite image segmentation is challenging for a number of reasons, which include cloud interference, inadequate label data, low lighting and the presence of terrain. In recent years, Convolutional Neural Networks (CNNs), combined with (satellite captured) multispectral image segmentation techniques, have led to promising advances in related research. However, ensuring sufficient image resolution, maintaining class balance to achieve prediction quality and reducing the computational overhead of the deep neural architecture are still open to research due to the sophisticated CNN hierarchical architectures. To address these issues, we propose a number of methods: a multi-channel Data-Fusion Module (DFM), Neural Adaptive Patch (NAP) augmentation algorithm and re-weight class balancing (implemented in our PHR-CB experimental setup). We integrated these techniques into our novel Fusion Adaptive Patch Network (FAPNET). Our dataset is the Sentinel-1 SAR microwave signal, used in the Microsoft Artificial Intelligence for Earth competition, so that we can compare our results with the top scores in the competition. In order to validate our approach, we designed four experimental setups and in each setup, we compared our results with the popular image segmentation models UNET, VNET, DNCNN, UNET++, U2NET, ATTUNET, FPN and LINKNET. The comparisons demonstrate that our PHR-CB setup, with class balance, generates the best performance for all models in general and our FAPNET approach outperforms relative works. FAPNET successfully detected the salient features from the satellite images. FAPNET with a MeanIoU score of 87.06% outperforms the state-of-the-art UNET, which has a score of 79.54%. In addition, FAPNET has a shorter training time than other models, comparable to that of UNET (6.77 minutes for 5 epochs). Qualitative analysis also reveals that our FAPNET model successfully distinguishes micro waterbodies better than existing models. FAPNET is more robust to low lighting, cloud and weather fluctuations and can also be used in RGB images. Our proposed method is lightweight, computationally inexpensive, robust and simple to deploy in industrial applications. Our research findings show that flood-water mapping is more accurate when using SAR signals than RGB images. Our FAPNET architecture, having less parameters than UNET, can distinguish micro waterbodies accurately with shorter training time.
46
Valade, Sébastien, Andreas Ley, Francesco Massimetti, et al. "Towards Global Volcano Monitoring Using Multisensor Sentinel Missions and Artificial Intelligence: The MOUNTS Monitoring System." Remote Sensing 11, no. 13 (2019): 1528. http://dx.doi.org/10.3390/rs11131528.
Full textAbstract:
Most of the world’s 1500 active volcanoes are not instrumentally monitored, resulting in deadly eruptions which can occur without observation of precursory activity. The new Sentinel missions are now providing freely available imagery with unprecedented spatial and temporal resolutions, with payloads allowing for a comprehensive monitoring of volcanic hazards. We here present the volcano monitoring platform MOUNTS (Monitoring Unrest from Space), which aims for global monitoring, using multisensor satellite-based imagery (Sentinel-1 Synthetic Aperture Radar SAR, Sentinel-2 Short-Wave InfraRed SWIR, Sentinel-5P TROPOMI), ground-based seismic data (GEOFON and USGS global earthquake catalogues), and artificial intelligence (AI) to assist monitoring tasks. It provides near-real-time access to surface deformation, heat anomalies, SO2 gas emissions, and local seismicity at a number of volcanoes around the globe, providing support to both scientific and operational communities for volcanic risk assessment. Results are visualized on an open-access website where both geocoded images and time series of relevant parameters are provided, allowing for a comprehensive understanding of the temporal evolution of volcanic activity and eruptive products. We further demonstrate that AI can play a key role in such monitoring frameworks. Here we design and train a Convolutional Neural Network (CNN) on synthetically generated interferograms, to operationally detect strong deformation (e.g., related to dyke intrusions), in the real interferograms produced by MOUNTS. The utility of this interdisciplinary approach is illustrated through a number of recent eruptions (Erta Ale 2017, Fuego 2018, Kilauea 2018, Anak Krakatau 2018, Ambrym 2018, and Piton de la Fournaise 2018–2019). We show how exploiting multiple sensors allows for assessment of a variety of volcanic processes in various climatic settings, ranging from subsurface magma intrusion, to surface eruptive deposit emplacement, pre/syn-eruptive morphological changes, and gas propagation into the atmosphere. The data processed by MOUNTS is providing insights into eruptive precursors and eruptive dynamics of these volcanoes, and is sharpening our understanding of how the integration of multiparametric datasets can help better monitor volcanic hazards.
47
Reddy, Mr G. Sekhar, A. Sahithi, P. Harsha Vardhan, and P. Ushasri. "Conversion of Sign Language Video to Text and Speech." International Journal for Research in Applied Science and Engineering Technology 10, no. 5 (2022): 159–64. http://dx.doi.org/10.22214/ijraset.2022.42078.
Full textAbstract:
Abstract: Sign Language recognition (SLR) is a significant and promising technique to facilitate communication for hearingimpaired people. Here, we are dedicated to finding an efficient solution to the gesture recognition problem. This work develops a sign language (SL) recognition framework with deep neural networks, which directly transcribes videos of SL sign to word. We propose a novel approach, by using Video sequences that contain both the temporal as well as the spatial features. So, we have used two different models to train both the temporal as well as spatial features. To train the model on the spatial features of the video sequences we use the (Convolutional Neural Networks) CNN model. CNN was trained on the frames obtained from the video sequences of train data. We have used RNN(recurrent neural network) to train the model on the temporal features. A trained CNN model was used to make predictions for individual frames to obtain a sequence of predictions or pool layer outputs for each video. Now this sequence of prediction or pool layer outputs was given to RNN to train on the temporal features. Thus, we perform sign language translation where input video will be given, and by using CNN and RNN, the sign shown in the video is recognized and converted to text and speech. Keywords: CNN (Convolutional Neural Network), RNN(Recurrent Neural Network), SLR(Sign Language Recognition), SL(Sign Language).
48
Luo, Qun, and Jiliang Yang. "The Artificial Intelligence and Neural Network in Teaching." Computational Intelligence and Neuroscience 2022 (June 10, 2022): 1–11. http://dx.doi.org/10.1155/2022/1778562.
Full textAbstract:
This study aims to explore the application of artificial intelligence (AI) and network technology in teaching. By studying the AI-based smart classroom teaching mode and the advantages and disadvantages of network teaching using network technology and taking the mathematics classroom as an example, this study makes an intelligent analysis of the questioning link of classroom teachers in the teaching process. For the questions raised by teachers, the network classification models of convolutional neural network (CNN) and long short-term memory (LSTM) are used to classify the questions according to the content and types of questions and carry out experimental verification. The results show that the overall performance of the CNN model is better than that of the LSTM model in the classification results of the teacher’s question content dimension. CNN has higher accuracy, and the classification accuracy of essential knowledge points reaches 86.3%. LSTM is only 79.2%, and CNN improves by 8.96%. In the classification results of teacher question types, CNN has higher accuracy. The classification accuracy of the prompt question is the highest, reaching 87.82%. LSTM is only 83.2%, and CNN improves by 4.95%. CNN performs better in teacher question classification results.
49
Mucomole, Fernando Venâncio, Carlos Augusto Santos Silva, and Lourenço Lázaro Magaia. "Parametric Forecast of Solar Energy over Time by Applying Machine Learning Techniques: Systematic Review." Energies 18, no. 6 (2025): 1460. https://doi.org/10.3390/en18061460.
Full textAbstract:
To maximize photovoltaic (PV) production, it is necessary to estimate the amount of solar radiation that is available on Earth’s surface, as it can occasionally vary. This study aimed to systematize the parametric forecast (PF) of solar energy over time, adopting the validation of estimates by machine learning models (MLMs), with highly complex analyses as inclusion criteria and studies not validated in the short or long term as exclusion criteria. A total of 145 scholarly sources were examined, with a value of 0.17 for bias risk. Four components were analyzed: atmospheric, temporal, geographic, and spatial components. These quantify dispersed, absorbed, and reflected solar energy, causing energy to fluctuate when it arrives at the surface of a PV plant. The results revealed strong trends towards the adoption of artificial neural network (ANN), random forest (RF), and simple linear regression (SLR) models for a sample taken from the Nipepe station in Niassa, validated by a PF model with errors of 0.10, 0.11, and 0.15. The included studies’ statistically measured parameters showed high trends of dependence on the variability in transmittances. The synthesis of the results, hence, improved the accuracy of the estimations produced by MLMs, making the model applicable to any reality, with a very low margin of error for the calculated energy. Most studies adopted large time intervals of atmospheric parameters. Applying interpolation models can help extrapolate short scales, as their inference and treatment still require a high investment cost. Due to the need to access the forecasted energy over land, this study was funded by CS–OGET.
50
Galety, Mohammad, Firas Hussam Al Mukthar, Rebaz Jamal Maaroof, and Fanar Rofoo. "Deep Neural Network Concepts for Classification using Convolutional Neural Network: A Systematic Review and Evaluation." Technium Romanian Journal of Applied Sciences and Technology 3, no. 8 (2021): 58–70. http://dx.doi.org/10.47577/technium.v3i8.4554.
Full textAbstract:
In recent years, artificial intelligence (AI) has piqued the curiosity of researchers. Convolutional Neural Networks (CNN) is a deep learning (DL) approach commonly utilized to solve problems. In standard machine learning tasks, biologically inspired computational models surpass prior types of artificial intelligence by a considerable margin. The Convolutional Neural Network (CNN) is one of the most stunning types of ANN architecture. The goal of this research is to provide information and expertise on many areas of CNN. Understanding the concepts, benefits, and limitations of CNN is critical for maximizing its potential to improve image categorization performance. This article has integrated the usage of a mathematical object called covering arrays to construct the set of ideal parameters for neural network design due to the complexity of the tuning process for the correct selection of the parameters used for this form of neural network.