Relevant bibliographies by topics / F1-score and accuracy

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Book chapters
  4. Conference papers
  5. Reports

Academic literature on the topic 'F1-score and accuracy'

Author: Grafiati
Published: 5 June 2025
Last updated: 15 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'F1-score and accuracy.'

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.

Journal articles on the topic "F1-score and accuracy"

1

Rahmawan, Fachrudin Okta, Hanafi, and Windha Mega Pradnya Dhuita. "Comparison of The Accuracy of K-Nearest Neighbor and Roberta Algorithm in Analysis of Sentiment on Miawaug Youtube Channel Comments." Teknika 14, no. 1 (2025): 26–33. https://doi.org/10.34148/teknika.v14i1.1117.

Full text
Abstract:
This study aims to evaluate the accuracy of two algorithms, K-Nearest Neighbor (KNN) and Robustly Optimized BERT Approach (RoBERTa), in analyzing sentiment within comments on MiawAug’s YouTube channel. Sentiment analysis was conducted on two sentiment categories: binary classification (positive and negative) and multi-class classification (positive, neutral, and negative). Using KNN, the binary classification yielded an accuracy of 86.12%, F1-score of 87.44%, recall of 96.64%, and precision of 79.89%. In contrast, the multi-class classification achieved 98.21% accuracy, F1-score, and recall wi
APA, Harvard, Vancouver, ISO, and other styles
2

Soni, Ekta, Arpita Nagpal, and Sujata Bhutani. "Automatic ECG Arrhythmia Recognition using ANN and CNN." International Journal of Experimental Research and Review 45, Spl Vol (2024): 01–14. https://doi.org/10.52756/ijerr.2024.v45spl.001.

Full text
Abstract:
Present research highlights the need for more patient-oriented monitoring systems for cardiac health, especially in the aftermath of COVID-19. The study introduces a contactless and affordable ECG device capable of recording heart arrhythmias for remote monitoring, which is vital in managing the rising incidence of untimely heart attacks. Two deep learning algorithms have been developed to design the system: RCANN (Real-time Compressed Artificial Neural Network) and RCCNN (Real-time Compressed Convolutional Neural Network), respectively, based on ANN and CNN. These methods are designed to clas
APA, Harvard, Vancouver, ISO, and other styles
3

A.Harshavardhan. "Optimal Routing in Wireless Sensor Networks for Advancing IoT Efficiency and Sustainability using Enhanced Ant Colony Algorithm with machine learning approaches." Journal of Electrical Systems 20, no. 2s (2024): 922–30. http://dx.doi.org/10.52783/jes.1689.

Full text
Abstract:
This research study aims to investigate the incorporation of machine learning tools, such as Q-learning, Genetic Algorithms, Unsupervised Learning, and Ensemble Learning, into Enhanced Ant Colony Algorithm to assess the impacts of such incorporation on the WSN’s performance. Ten experimental trials were conducted on each to analyze the accuracy, precision, and F1 score results. It was observed that Q-learning achieves an average accuracy of 0.867; precision of 0.842; and F1 score of 0.854, making it highly adaptable and efficient in making routing decisions. The GA presented average accuracy o
APA, Harvard, Vancouver, ISO, and other styles
4

Ramadan, Muhamad Firly, Martanto, Arif Rinaldi Dikananda, and Ahmad Rifa'i. "Comparison of Sentiment Analysis Models Enhanced by Naïve Bayes and Support Vector Machine Algorithms on Mobile Banking BRImo Reviews." Journal of Artificial Intelligence and Engineering Applications (JAIEA) 4, no. 2 (2025): 677–86. https://doi.org/10.59934/jaiea.v4i2.732.

Full text
Abstract:
This study compares the effectiveness of the Support Vector Machine (SVM) and Naïve Bayes algorithms in classifying user sentiment regarding the BRImo application. User reviews were obtained from the Google Play Store platform and underwent a text preprocessing stage to clean and prepare the data. Subsequently, the SVM and Naïve Bayes algorithms were applied for sentiment analysis, using evaluation metrics such as accuracy, precision, recall, and F1-score. The results show that SVM achieved a training accuracy of 95.67% and a testing accuracy of 83.11%, with its best performance on positive se
APA, Harvard, Vancouver, ISO, and other styles
5

Adhitya, Rahmat Ryan, Wina Witanti, and Rezki Yuniarti. "PERBANDINGAN METODE CART DAN NAÏVE BAYES UNTUK KLASIFIKASI CUSTOMER CHURN." INFOTECH journal 9, no. 2 (2023): 307–18. http://dx.doi.org/10.31949/infotech.v9i2.5641.

Full text
Abstract:
Classification is the process of identifying and grouping an object into the same group or category Classification can be used to group a large-sized dataset, and some commonly used classification methods are CART (Classification And Regression Tree) and Naïve Bayes. This study discusses the comparison of CART and Naïve Bayes methods by measuring accuracy, precision, recall, and f1-score values with 3 scenarios of training and testing dataset distribution. Accuracy, precision, recall, and f1-score measurements are performed using a confusion matrix. The scenarios for training and testing datas
APA, Harvard, Vancouver, ISO, and other styles
6

Mahmud, Fuad, Badruddowza Badruddowza, Md Shohail Uddin Sarker, et al. "ADVANCEMENTS IN AIRLINE SECURITY: EVALUATING MACHINE LEARNING MODELS FOR THREAT DETECTION." American Journal of Engineering and Technology 06, no. 10 (2024): 86–99. http://dx.doi.org/10.37547/tajet/volume06issue10-10.

Full text
Abstract:
This study assessed the performance of four machine learning algorithms—Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN)—for predicting airline security threats using a dataset of 100,000 entries with 30 features. The models were evaluated based on accuracy, precision, recall, F1-Score, and AUC-ROC. The Neural Network achieved the highest performance, with an accuracy of 88%, precision of 86%, recall of 85%, F1-Score of 85.5%, and AUC-ROC of 0.90, demonstrating superior capability in capturing complex, non-linear patterns. The Random Forest model fo
APA, Harvard, Vancouver, ISO, and other styles
7

Kim, Seong-Jin, Xue-Cheng Jin, Rajaraman Bharanidharan, and Na-Yeon Kim. "Monitoring Multiple Behaviors in Beef Calves Raised in Cow–Calf Contact Systems Using a Machine Learning Approach." Animals 14, no. 22 (2024): 3278. http://dx.doi.org/10.3390/ani14223278.

Full text
Abstract:
The monitoring of pre-weaned calf behavior is crucial for ensuring health, welfare, and optimal growth. This study aimed to develop and validate a machine learning-based technique for the simultaneous monitoring of multiple behaviors in pre-weaned beef calves within a cow–calf contact (CCC) system using collar-mounted sensors integrating accelerometers and gyroscopes. Three complementary models were developed to classify feeding-related behaviors (natural suckling, feeding, rumination, and others), postural states (lying and standing), and coughing events. Sensor data, including tri-axial acce
APA, Harvard, Vancouver, ISO, and other styles
8

Inda, Nur. "Analisis Perbandingan Kinerja Model Yolov7 dalam Deteksi Kuku Diabetes." Journal of System and Computer Engineering (JSCE) 5, no. 2 (2024): 226–36. http://dx.doi.org/10.61628/jsce.v5i2.1334.

Full text
Abstract:
abstrak Diabetes mellitus (DM) penyakit degenerative dan tidak menular yang dapat dilihat dari warna kuku jari tangan. Dalam menganalisis warna mata manusia memiliki keterbatasan dalam pengenalan warna dan analisis tekstur sedangkan komputer mampu mengklasifikasi jutaan warna dan sedikit perubahan tekstur untuk mengenali perubahan warna kuku individu untuk mencega gejala awal diabetes menggunakan metode YOLOv7 untuk mewakili model satu tahap untuk mendeteksi objek menggunakan Convolutional Neural Network (CNN). Penelitian ini dilaksanakan di Puskesmas Polewali. Pengambilan sampel dilakukan den
APA, Harvard, Vancouver, ISO, and other styles
9

Wirawan, Bima Mahardika, Mahendra Dwifebri Purbolaksono, and Fhira Nhita. "Handling Unbalanced Data Sets Using DBMUTE and NearMiss Methods to Improve Classification Performance of Yeast Data Sets." JURNAL MEDIA INFORMATIKA BUDIDARMA 7, no. 3 (2023): 1062. http://dx.doi.org/10.30865/mib.v7i3.6306.

Full text
Abstract:
Yeast vacuole biogenesis was chosen as a model system for organelle assembly because most vacuole functions can be used for vegetative cell growth. Therefore it is possible to generate an extensive collection of mutants with defects in unbalanced vacuole assembly. With this in mind, we must find the structural balance of data in yeast. Imbalanced data is when there is an unbalanced distribution of data classes and the number of data classes is either more or lower than the number of other data classes. Our method uses the f1score performance matrix method and the balanced accuracy on DBMUTE an
APA, Harvard, Vancouver, ISO, and other styles
10

Chetry, Mandika, Ruiling Feng, Samra Babar, et al. "Early detection and analysis of accurate breast cancer for improved diagnosis using deep supervised learning for enhanced patient outcomes." PeerJ Computer Science 11 (April 24, 2025): e2784. https://doi.org/10.7717/peerj-cs.2784.

Full text
Abstract:
Early detection of breast cancer (BC) is essential for effective treatment and improved prognosis. This study compares the performance of various machine learning (ML) algorithms, including convolutional neural networks (CNNs), logistic regression (LR), support vector machines (SVMs), and Gaussian naive Bayes (GNB), on two key datasets, Wisconsin Diagnostic Breast Cancer (WDBC) and Breast Cancer Histopathological Image Classification (BreaKHis). For the BreaKHis dataset, the CNN achieved an impressive accuracy of 92%, with precision, recall, and F1 score values of 91%, 93%, and 91%, respective
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "F1-score and accuracy"

1

Wahab, Nor-Ul. "Evaluation of Supervised Machine LearningAlgorithms for Detecting Anomalies in Vehicle’s Off-Board Sensor Data." Thesis, Högskolan Dalarna, Mikrodataanalys, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:du-28962.

Full text
Abstract:
A diesel particulate filter (DPF) is designed to physically remove diesel particulate matter or soot from the exhaust gas of a diesel engine. Frequently replacing DPF is a waste of resource and waiting for full utilization is risky and very costly, so, what is the optimal time/milage to change DPF? Answering this question is very difficult without knowing when the DPF is changed in a vehicle. We are finding the answer with supervised machine learning algorithms for detecting anomalies in vehicles off-board sensor data (operational data of vehicles). Filter change is considered an anomaly becau
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "F1-score and accuracy"

1

Rostovski, Jakob, Mohammad Hasan Ahmadilivani, Andrei Krivošei, Alar Kuusik, and Muhammad Mahtab Alam. "Real-Time Gait Anomaly Detection Using 1D-CNN and LSTM." In Communications in Computer and Information Science. Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-59091-7_17.

Full text
Abstract:
AbstractAnomaly detection and fall prevention represent one of the key research areas within gait analysis for patients suffering from neurological disorders. Deep Learning has penetrated into healthcare applications, encompassing disease diagnosis and anomaly prediction. Connected wearable medical sensors are emerging due to computationally expensive machine learning tasks, which traditionally require use of remote PC or cloud computing. However, to reduce needs for wireless communication channel throughput, for data processing latency, and increase service reliability and safety, on device machine learning is gaining attention. This paper presents an innovative approach that leverages one dimensional convolutional neural network (1D-CNN) and long-short term memory (LSTM) neural network for the real-time detection of abnormal gait patterns during the step. Real-time anomaly detection pertains to the algorithm’s ability to promptly detect true gait abnormality occurrence during the swing phase of an ongoing step.For the experiments, we have collected eight different common gait anomalies, simulated by 22 persons, using motion sensors containing multidimensional inertial measurement units (IMUs).Results have demonstrated that the proposed 1D-CNN-AD algorithm achieves an average accuracy of 95% and an average F1-score of 88% for all gait types and can run in true real-time. Average earliness for 1D-CNN-AD algorithm was 0.6 s, which is mid-swing phase of the step. Proposed LSTM-AD algorithm achieved average accuracy of 87% and average F1-score of 70% for all gait types.
APA, Harvard, Vancouver, ISO, and other styles
2

Montassar, Imen, Belkacem Chikhaoui, and Shengrui Wang. "Agitated Behaviors Detection in Children with ASD Using Wearable Data." In Digital Health Transformation, Smart Ageing, and Managing Disability. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-43950-6_8.

Full text
Abstract:
AbstractChildren diagnosed with Autism Spectrum Disorder (ASD) often exhibit agitated behaviors that can isolate them from their peers. This study aims to examine if wearable data, collected during everyday activities, could effectively detect such behaviors. First, we used the Empatica E4 device to collect real data including Blood Volume Pulse (BVP), Electrodermal Activity (EDA), and Acceleration (ACC), from a 9-years-old male child with autism over 6 months. Second, we analyzed and extracted numerous features from each signal, and employed different classifiers including Support Vector Machine (SVM), Random Forest (FR), eXtreme Gradient Boosting (XGBoost), and TabNet. Our preliminary findings showed good performance in comparison with the state of the art. Notably, XGBoost demonstrated the highest performance in terms of accuracy, precision, recall, and F1-score. The accuracy achieved in this paper using XGBoost is equal to $$80\%$$ 80 % which exceeds previous research.
APA, Harvard, Vancouver, ISO, and other styles
3

Rajendram Bashyam, Lakshmi, and Ralf Krestel. "Advancing Automatic Subject Indexing: Combining Weak Supervision with Extreme Multi-label Classification." In Lecture Notes in Computer Science. Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-65794-8_14.

Full text
Abstract:
AbstractThe multi-label automatic classification of scientific publications based on a pre-defined taxonomy, also called automatic subject indexing is a continuing research endeavor with significant cross-domain applicability. In this paper, we assess the performance of X-transformer and its variants with other extreme multi-label classification models for the above task. Our model Weak X-transformer achieves a micro F1-score of 0.65 and 64% accuracy on the task outperforming all other methods. We also investigate the impact of incorporating additional unlabelled data and hierarchical structure into the models. Our findings demonstrate that the transformer-based model with weak supervision outperforms other approaches, providing insights into effective strategies for extreme multi-label classification in scholarly publications.
APA, Harvard, Vancouver, ISO, and other styles
4

Kant, Vishnu, Kanwarpartap Singh Gill, Mukesh Kumar, and Ruchira Rawat. "Safeguarding Finances: State-of-the-Art Fraud Detection Methods for Credit Cards." In Applied Intelligence and Computing. Soft Computing Research Society, 2024. http://dx.doi.org/10.56155/978-81-955020-9-7-12.

Full text
Abstract:
This research primarily aims to shed light on the serious issue of credit card fraud, which has become much worse with the advent of internet shopping and, more specifically, the present COVID-19 epidemic. Developing a machine learning system capable of distinguishing between legitimate and fraudulent credit card transactions is the primary objective of this project, which aims to decrease an annual loss of $24 billion. Using data such as transformed numerical characteristics after PCA analyses, transaction time and amount, and Logistic Regression, Decision Tree Classifier, and K-Nearest Neighbours approaches are employed in the research study. The accuracy rates of these algorithms are demonstrated by the cross-validation score, ROC AUC score, and F1 score within the context of fraud detection. Improving the models' accuracy and resilience is as simple as using statistical tests like ANOVA when selecting features. To improve the detection of fraudulent behaviour and to accurately compare the results of various algorithms, balanced datasets are essential, as this shows. There was a 91% F1 score, 92.35% ROC AUC, and 98.01% cross-validation accuracy rate for fraud detection in the logistic regression model. Alternatively, a decision tree classifier's fraud detection cross-validation score was 96.67%, ROC AUC was 91.36%, and F1 was 90%. When it came to detecting fraud, K-Nearest Neighbours performed exceptionally well with scores of 97.63% for ROC AUC, 99.34% for cross-validation, and 97% for F1.
APA, Harvard, Vancouver, ISO, and other styles
5

Varna, Chinthapatla Pranay, Mannipudi Prabhu Das, Gurram Sunitha, A. V. Sriharsha, and Mohammad Gouse Galety. "Predictive Modeling in Finance." In Advances in Computational Intelligence and Robotics. IGI Global, 2024. http://dx.doi.org/10.4018/979-8-3693-6215-0.ch003.

Full text
Abstract:
Predicting financial stability is crucial for assessing risk and making informed decisions in the financial sector. Accurate predictions can help prevent financial crises and guide strategic planning for companies and investors. Various machine learning algorithms have been employed to enhance prediction accuracy for economic distress, including XGB, LGBM, Linear Discriminant Analysis, and Logistic Regression. These models were assessed based on key performance metrics: Accuracy, ROC AUC, and F1 Score. The result revealed that LDA excels with an ROC AUC of 0.90 and an F1 Score of 0.98, demonstrating its superior ability to balance precision and recall and effectively differentiate between distressed and non-distressed entities. While the XGB Classifier and LGBM Classifier also show strong performance, they do not exceed LDA in overall effectiveness. These results highlight the importance of leveraging multiple evaluation metrics to select the most suitable model, with LDA emerging as the most reliable choice for accurate financial distress predictions.
APA, Harvard, Vancouver, ISO, and other styles
6

Alozie, Chisom Elizabeth. "Strategic recommendations for enhancing DDoS defense mechanisms in cloud environments." In Deep Science Publishing. Deep Science Publishing, 2025. https://doi.org/10.70593/978-93-49307-78-0_5.

Full text
Abstract:
As presented and motivated in the introduction of this project study, a DDoS detection system for a cloud environment aided by a machine learning modem technique was implemented and a comparative analysis modem was conducted. The CICFlowMeter was used to extract the new dataset to CSV format which includes obtaining the proper flow features for the model building. Furthermore, feature selection using person correlation coefficient improved the accuracy performance of the ML models training with Random Forest, Support Vector Machine, Decision Tree, and K-Nearest Neighbors achieving a rate of 100% accuracy, precision, recall and F1 score except for Naive Bayes with a 98% accuracy, 97% precision, 99% recall and 98% F1 score. Also, the open-source dataset performs very well with RF, DT and KNN achieving an accuracy of 100%, SVM 95% and NB 99%. Overall, the new dataset outperforms the open-source dataset with an accuracy score of 99.6% while the benchmark achieved 98.8%. Based on the results achieved, all the models selected, the new datasets and the open-source dataset used for this study are ideal models and datasets for intrusion detection.
APA, Harvard, Vancouver, ISO, and other styles
7

Kumar, Sunil, Tamanna M. Prajapati, Mamata Mayee Panda, Prachi Chhabra, Shilpi Dubey, and Amar Pal Yadav. "Improving the Resilience of Supply Chains in a Post-COVID-19 Era." In Advances in Logistics, Operations, and Management Science. IGI Global, 2024. http://dx.doi.org/10.4018/979-8-3693-1347-3.ch008.

Full text
Abstract:
The COVID-19 pandemic has highlighted the critical need for supply chain resilience in the face of unforeseen disruptions. This research investigates the application of machine learning (ML) algorithms to enhance supply chain resilience during the COVID-19 crisis. The authors evaluated several ML algorithms, including decision trees, random forests, naïve bayes, and LSTM. They explored using the SPIN COVID-19 RMRIO dataset to develop a proactive and data-driven approach to mitigate disruptions and improve supply chain performance. The ML model worked with and without feature selection. With chi-square feature selection, the long short-term memory (LSTM) performed well and achieved the highest accuracy, 96.74%, with an F1 score of 91.01%. Without feature selection, random forest outperformed, which provided an accuracy of 96.21% with an F1 score of 81.25%.
APA, Harvard, Vancouver, ISO, and other styles
8

Yadav, Ayush, and Bhuvaneswari Amma N. G. "A Smart Healthcare Diabetes Prediction System Using Ensemble of Classifiers." In Advances in Media, Entertainment, and the Arts. IGI Global, 2024. http://dx.doi.org/10.4018/979-8-3693-0639-0.ch005.

Full text
Abstract:
Throughout the world, diabetes is a life-threatening disease. This research study aims to develop a smart healthcare machine-learning model for diabetes prediction. The dataset is pre-processed to handle missing data and outliers, and feature selection techniques are used to identify the most relevant variables for the model. An ensemble of classifiers is built by combining logistic regression, XGBoost, random forest, and support vector machine. The performance of the proposed model is assessed using metrics such as accuracy, precision, recall, and F1-score. The results show that the random forest algorithm outperforms other models in terms of accuracy, precision, recall, and F1 score. The model achieves an accuracy of 85%, indicating that it can correctly predict diabetes in 85% of cases. In conclusion, this study demonstrates the feasibility of using machine learning models for diabetes prediction based on patient data. The model can be further improved by incorporating more extensive and diverse datasets and exploring more advanced machine-learning techniques.
APA, Harvard, Vancouver, ISO, and other styles
9

El Yanboiy, Naima, Mohamed Khala, Ismail Elabbassi, et al. "Enhanced Fault Detection in Photovoltaic Systems Through Hybrid SVM Evolutionary Optimization Techniques." In Advances in Computational Intelligence and Robotics. IGI Global, 2025. https://doi.org/10.4018/979-8-3373-1220-0.ch006.

Full text
Abstract:
Fault detection in photovoltaic (PV) systems is vital for maintaining optimal performance. Early detection of faults can prevent downtime and minimize energy loss. In this study, An approach for fault detection in PV systems is proposed. The method integrates a hybrid support vector machine (SVM) with optimization algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), Bayesian optimization (BO), and Randomized Search CV (RS). Experimental results demonstrate the effectiveness of the approach, notably the SVM-PSO variant achieving a significant precision in fault detection accuracy. Specifically, employing the RBF kernel, the SVM-PSO model exhibits an accuracy of 98.24%, precision of 98.29%, recall of 98.25%, and an F1 score of 98.08%. In contrast, utilizing the linear kernel yields slightly lower performance, with an accuracy of 89.47%, precision of 89.82%, recall of 89.47%, and an F1 score of 89.51%. The proposed system enhances performance and reliability, ultimately leading to increased energy generation and reduced maintenance costs.
APA, Harvard, Vancouver, ISO, and other styles
10

Bhardwaj, Akashdeep. "Comparison of IoT Communication Protocols Using Anomaly Detection with Security Assessments of Smart Devices." In Smart Home and Industrial IoT Devices: Critical Perspectives on Cyberthreats, Frameworks and Protocols. BENTHAM SCIENCE PUBLISHERS, 2024. http://dx.doi.org/10.2174/9789815256710124010009.

Full text
Abstract:
The authors implemented an attack scenario simulating attacks to compromise node and sensor data. This research proposes a framework with algorithms that generate automated malicious commands, which conform to device protocol standards and bypass compromise detection. The authors performed attack detection testing with three different home setup simulations and referred to accuracy of detection, ease of precision, and attack recall, with F1-score as the parameters. The results obtained for anomaly detection of IoT logs and messages used K-nearest neighbor, multi-layer perceptron, logistic regression, random forest, and linear support vector classifier models. The attack results presented false-positive responses with and without the proposed framework and false-negative responses for different models. This research calculated precision, accuracy, F1-score, and recall as attack detection performance models. Finally, the authors evaluated the performance of the proposed IoT communication protocol attack framework by evaluating a range of anomalies and compared them with the maliciously generated log messages. IoT Home #1 in which the model involved IP Camera and NAS device traffic displayed 97.7% Accuracy, 96.54% Precision, 97.29% Recall, and 96.88% F-1 Score. This demonstrated the model classified the Home #1 dataset consistently.
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "F1-score and accuracy"

1

PS, Anu Rakhi, and Rajesh RS. "Comparative Study of Various Deep Learning Models For Medical Image Segmentation." In 7th International Conference on Recent Innovations in Computer and Communication (ICRICC 23). International Journal of Advanced Trends in Engineering and Management, 2023. http://dx.doi.org/10.59544/wobh4884/icricc23p26.

Full text
Abstract:
Image processing plays a vital role in the detection of medical images segmentation. Accurate detection will help the radiologilist to predict the images masses. Using Deep Learning methods the segmentation of medical images can be possible with best results when compared with state o art methods. In this paper we have compared the deep learning methods like a) U net, b) U net attention, c) Dense net, d) Attention Dense U net for the segmentation of mammography images. Performance metrics like Accuracy, Sensitivity, Specificity, F1 Score, and AUC are measure for the above mentioned models. Att
APA, Harvard, Vancouver, ISO, and other styles
2

Souza, Daniel Abella C. M. de, Danyllo Albuquerque, Emanuel Dantas Filho, Mirko Perkusich, and Angelo Perkusich. "Using Machine Learning for Non-Functional Requirements Classification: A Practical Study." In Workshop Brasileiro de Engenharia de Software Inteligente. Sociedade Brasileira de Computação, 2023. http://dx.doi.org/10.5753/ise.2023.235829.

Full text
Abstract:
Non-Functional Requirements (NFR) are used to describe a set of software quality attributes such as reliability, maintainability, and performance. Since the functional and non-functional requirements are mixed together in software documentation, it requires a lot of effort to distinguish them. This study proposed automatic NFR classification by using machine learning classification techniques. An empirical study with three machine learning algorithms was applied to classify NFR automatically. Precision, recall, F1-score, and accuracy were calculated for the classification results through all t
APA, Harvard, Vancouver, ISO, and other styles
3

Yajnik, Archit, and Sabu Lama Tamang. "Chunker Based Sentiment Analysis for Nepali Text." In 4th International Conference on NLP Trends & Technologies. Academy & Industry Research Collaboration, 2023. http://dx.doi.org/10.5121/csit.2023.131406.

Full text
Abstract:
The article represents the Sentiment Analysis (SA) of a Nepali sentence. Skip-gram model is used for the word to vector encoding. In the first experiment the vector representation of each sentence is generated by using Skip-gram model followed by the Multi-Layer Perceptron (MLP) classification and it is observed that the F1 score of 0.6486 is achieved for positive-negative classification with overall accuracy of 68%. Whereas in the second experiment the verb chunks are extracted using Nepali parser and carried out the similar experiment on the verb chunks. F1 score of 0.6779 is observedfor pos
APA, Harvard, Vancouver, ISO, and other styles
4

Menezes, Richardson Santiago Teles, Angelo Marcelino Cordeiro, Rafael Magalhães, and Helton Maia. "Classification of Paintings Authorship Using Convolutional Neural Network." In Congresso Brasileiro de Inteligência Computacional. SBIC, 2021. http://dx.doi.org/10.21528/cbic2021-116.

Full text
Abstract:
In this paper, state-of-the-art architectures of Convolutional Neural Networks (CNNs) are explained and compared concerning authorship classification of famous paintings. The chosen CNNs architectures were VGG-16, VGG-19, Residual Neural Networks (ResNet), and Xception. The used dataset is available on the website Kaggle, under the title “Best Artworks of All Time”. Weighted classes for each artist with more than 200 paintings present in the dataset were created to represent and classify each artist’s style. The performed experiments resulted in an accuracy of up to 95% for the Xception archit
APA, Harvard, Vancouver, ISO, and other styles
5

Narayan, Umesh, and Devendra Kumar. "SENTIMENT ANALYSIS USING TRANSFORMER BASED MODEL." In Computing for Sustainable Innovation: Shaping Tomorrow’s World. Innovative Research Publication, 2024. http://dx.doi.org/10.55524/csistw.2024.12.1.46.

Full text
Abstract:
This paper delves into the realm of sentiment analysis, focusing on the state-of-the-art method of employing transformers for classification. Specifically, the study explores the efficient classification techniques utilizing transformers, with a primary focus on fine-tuning tasks. We have used Distil BERT for fine-tuned using a fine-grained emotion dataset and their performances are evaluated in terms of F1-score and processing time. Using data from the Hugging Face dataset, the study evaluates and benchmarks the performance of various transformer models. We have obtained a test loss of 0.2205
APA, Harvard, Vancouver, ISO, and other styles
6

Reynolds, Robert, and Tyler Ivie. "Japanese readability assessment using machine learning." In EuroCALL 2023: CALL for all Languages. Editorial Universitat Politécnica de Valéncia, 2023. http://dx.doi.org/10.4995/eurocall2023.2023.16989.

Full text
Abstract:
We present a new corpus of Japanese texts, labeled according to six second-language readability levels. We also show the results of experiments training machine-learning classifiers to automatically label new texts according to reading level. The resulting models can be used in language-learning websites and applications to enhance Japanese language learning. The best-performing model, Random Forest, achieved an F1 score of 0.86, with an adjacent accuracy of 0.97. Of the 114 features used, we identify a small subset of five features that are sufficient to achieve an F1 score of 0.74. The corpu
APA, Harvard, Vancouver, ISO, and other styles
7

Henz, Douglas, André Luís Del Mestre Martins, Juliano Costa Machado, and Fábio Pires Itturriet. "Detecção de Hipertensão Arterial usando Fotopletismografia e Aprendizado de Máquina." In Computer on the Beach. Universidade do Vale do Itajaí, 2024. http://dx.doi.org/10.14210/cotb.v15.p110-117.

Full text
Abstract:
ABSTRACTHypertension is the leading cause of death worldwide, consideringcardiovascular diseases. In its initial phase, it presents no symptomsand is usually diagnosed when it has already affected other organs.Continuous blood pressure monitoring allows the discovery of thefirst temporary and sporadic events of hypertension. This workproposes using the non-invasive photoplethysmography (PPG)signal in conjunction with machine learning techniques to detecthypertension events. Morphological information is extracted fromsignals acquired from a database fed to models trained with thek-Nearest Neigh
APA, Harvard, Vancouver, ISO, and other styles
8

Althabiti, Saud, Mohammad Ammar Alsalka, and Eric Atwell. "TA’KEED the First Generative Fact-Checking System for Arabic Claims." In 11th International Conference on Artificial Intelligence and Applications. Academy & Industry Research Collaboration Center, 2024. http://dx.doi.org/10.5121/csit.2024.140103.

Full text
Abstract:
This paper introduces Ta’keed, an explainable Arabic automatic fact-checking system. While existing research often focuses on classifying claims as "True" or "False," there is a limited exploration of generating explanations for claim credibility, particularly in Arabic. Ta’keed addresses this gap by assessing claim truthfulness based on retrieved snippets, utilizing two main components: information retrieval and LLM-based claim verification. We compiled the ArFactEx, a testing gold-labelled dataset with manually justified references, to evaluate the system. The initial model achieved a promis
APA, Harvard, Vancouver, ISO, and other styles
9

Zupanič, Matjaž, Dejan Georgiev, and Jure Žabkar. "Automatic Assessment of Bradykinesia in Parkinson’s Disease Using Tapping Videos." In 10th Student Computing Research Symposium. University of Maribor Press, 2024. https://doi.org/10.18690/um.feri.6.2024.15.

Full text
Abstract:
Parkinson’s disease is a chronic neurodegenerative illness that se-verely affects the everyday life of a patient. The severity of Parkin-son’s disease is assessed using the MDS-UPDRS scale. In this study, we explore the feasibility of automatically evaluating bradykinesia, a key symptom of Parkinson’s disease, from tapping videos recorded on smartphones in everyday settings. We collected a dataset of 183 tapping videos, from 91 individuals. Videos were assessed by neu-rologist into 5 classes of the MDS-UPDRS scale. For data extraction, we employed MediaPipe Hand, which provides a time series o
APA, Harvard, Vancouver, ISO, and other styles
10

Ayub, Mohammed, and SanLinn Kaka. "First-Break Picking Classification Models Using Recurrent Neural Network." In SPE Middle East Oil & Gas Show and Conference. SPE, 2021. http://dx.doi.org/10.2118/204862-ms.

Full text
Abstract:
Abstract Manual first-break picking from a large volume of seismic data is extremely tedious and costly. Deployment of machine learning models makes the process fast and cost effective. However, these machine learning models require high representative and effective features for accurate automatic picking. Therefore, First- Break (FB) picking classification model that uses effective minimum number of features and promises performance efficiency is proposed. The variants of Recurrent Neural Networks (RNNs) such as Long ShortTerm Memory (LSTM) and Gated Recurrent Unit (GRU) can retain contextual
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "F1-score and accuracy"

1

Panta, Manisha, Md Tamjidul Hoque, Kendall Niles, Joe Tom, Mahdi Abdelguerfi, and Maik Flanagin. Deep learning approach for accurate segmentation of sand boils in levee systems. Engineer Research and Development Center (U.S.), 2024. http://dx.doi.org/10.21079/11681/49460.

Full text
Abstract:
Sand boils can contribute to the liquefaction of a portion of the levee, leading to levee failure. Accurately detecting and segmenting sand boils is crucial for effectively monitoring and maintaining levee systems. This paper presents SandBoilNet, a fully convolutional neural network with skip connections designed for accurate pixel-level classification or semantic segmentation of sand boils from images in levee systems. In this study, we explore the use of transfer learning for fast training and detecting sand boils through semantic segmentation. By utilizing a pretrained CNN model with ResNe
APA, Harvard, Vancouver, ISO, and other styles
2

Maloney, Megan, Sarah Becker, Andrew Griffin, Susan Lyon, and Kristofer Lasko. Automated built-up infrastructure land cover extraction using index ensembles with machine learning, automated training data, and red band texture layers. Engineer Research and Development Center (U.S.), 2024. http://dx.doi.org/10.21079/11681/49370.

Full text
Abstract:
Automated built-up infrastructure classification is a global need for planning. However, individual indices have weaknesses, including spectral confusion with bare ground, and computational requirements for deep learning are intensive. We present a computationally lightweight method to classify built-up infrastructure. We use an ensemble of spectral indices and a novel red-band texture layer with global thresholds determined from 12 diverse sites (two seasonally varied images per site). Multiple spectral indexes were evaluated using Sentinel-2 imagery. Our texture metric uses the red band to s
APA, Harvard, Vancouver, ISO, and other styles
3

Griffin, Andrew, Sean Griffin, Kristofer Lasko, et al. Evaluation of automated feature extraction algorithms using high-resolution satellite imagery across a rural-urban gradient in two unique cities in developing countries. Engineer Research and Development Center (U.S.), 2021. http://dx.doi.org/10.21079/11681/40182.

Full text
Abstract:
Feature extraction algorithms are routinely leveraged to extract building footprints and road networks into vector format. When used in conjunction with high resolution remotely sensed imagery, machine learning enables the automation of such feature extraction workflows. However, many of the feature extraction algorithms currently available have not been thoroughly evaluated in a scientific manner within complex terrain such as the cities of developing countries. This report details the performance of three automated feature extraction (AFE) datasets: Ecopia, Tier 1, and Tier 2, at extracting
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'F1-score and accuracy' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography