To see the other types of publications on this topic, follow the link: AlexNet CNN.
Journal articles on the topic 'AlexNet CNN'
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 'AlexNet CNN.'
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
Aditya, Kakde Nitin Arora Durgansh Sharma. "A COMPARATIVE STUDY OF DIFFERENT TYPES OF CNN AND HIGHWAY CNN TECHNIQUES." Global Journal of Engineering Science and Research Management 6, no. 4 (2019): 18–31. https://doi.org/10.5281/zenodo.2639265.
Full textAbstract:
In recent years, convolutional networks have shown breakthrough performance in image classification and detection. The main reason behind the performance of convnets is that they are inspired from the mammal’s visual cortex. In this paper, we have investigated the performance of four models that are Alexnet, Highway Convolutional Neural Network, Convolutional Neural Network and an evolutionary approach on highway convolutional neural network on the basis of train loss, test loss, train accuracy and test accuracy. These models are tested on two datasets that are WANG dataset and Simpsons dataset. In WANG dataset, Alexnet model achieved the highest test accuracy of 0.2625 and the highest train accuracy of 0.2193. Evolutionary Highway CNN has the least train loss of 0.1599 and CNN has the least test loss of 0.1604. In Simpsons dataset, Evolutionary Highway CNN has the Highest test accuracy of 0.5780. Highway CNN has the highest train accuracy of 0.5662 and for loss domain; Evolutionary Highway CNN has the least train and test loss
2
Sachin, B. Jadhav, R. Udupi Vishwanath, and B. Patil Sanjay. "Convolutional neural networks for leaf image-based plant disease classification." International Journal of Artificial Intelligence (IJ-AI) 8, no. 4 (2019): 328–41. https://doi.org/10.11591/ijai.v8.i4.pp328-341.
Full textAbstract:
Plant pathologists desire soft computing technology for accurate and reliable diagnosis of plant diseases. In this study, we propose an efficient soybean disease identification method based on a transfer learning approach by using a pre-trained convolutional neural network (CNN’s) such as AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201. The proposed convolutional neural networks were trained using 1200 plant village image dataset of diseased and healthy soybean leaves, to identify three soybean diseases out of healthy leaves. Pre-trained CNN used to enable a fast and easy system implementation in practice. We used the five-fold cross-validation strategy to analyze the performance of networks. In this study, we used a pre-trained convolutional neural network as feature extractors and classifiers. The experimental results based on the proposed approach using pre-trained AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201 networks achieve an accuracy of 95%, 96.4%, 96.4%, 92.1%, 93.6% respectively. The experimental results for the identification of soybean diseases indicated that the proposed networks model achieves the highest accuracy.
3
Nur, Azida Muhammad, Ab Nasir Amelina, Ibrahim Zaidah, and Sabri Nurbaity. "Evaluation of CNN, Alexnet and GoogleNet for Fruit Recognition." Indonesian Journal of Electrical Engineering and Computer Science 12, no. 2 (2018): 468–75. https://doi.org/10.11591/ijeecs.v12.i2.pp468-475.
Full textAbstract:
Fruit recognition is useful for automatic fruit harvesting. Fruit recognition application can reduce or minimize human intervention during fruit harvesting operation. However, in computer vision, fruit recognition is very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also lead to a challenging task for fruit recognition. Thus, this paper tends to investigate the performance of basic Convolutional Neural Network (CNN), Alexnet and Googlenet in recognizing nine different types of fruits from a publicly available dataset. The experimental results indicate that all these techniques produce excellent recognition accuracy, but basic CNN achieves the fastest recognition result compared with Alexnet and Googlenet.
4
Akbar, Fauzan, Achmad Hidayatno, and Aris Triwiyatno. "PERANCANGAN PROGRAM PENGENALAN ISYARAT TANGAN DENGAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)." Transient: Jurnal Ilmiah Teknik Elektro 9, no. 1 (2020): 26–36. http://dx.doi.org/10.14710/transient.v9i1.26-36.
Full textAbstract:
Convolutional Neural Network is one of the Deep Learning Algorithms. CNN itself is developed from Multilayer Peceptron (MLP) method. CNN and MLP are algorithms that focused on processing data in two dimensions form, such as pictures or sounds. CNN is made with the principle of translation invariance. That means CNN is able to recognize objects at various possible positions. There are 150 sign language images that are classified using Alexnet in this system. Alexnet is Krizhevsky's work at developing CNN method as a clessifier. CNN architecture developed by Alex has eight feature extraction layers. The layer consists of five convolution layers and three pooling layers. In its classification layer, Alexnet has two fully connected layers, each of them has 4096 neurons. At the end of the layer, there are classifications into 5 categories using softmax activation. The average accuracy of the classification results even reaches 100%.
5
Denis, Eka Cahyani, Dwi Hariadi Anjar, Farris Setyawan Faisal, Gumilar Langlang, and Setumin Samsul. "COVID-19 classification using CNN-BiLSTM based on chest X-ray images." Bulletin of Electrical Engineering and Informatics 12, no. 3 (2023): 1773~1782. https://doi.org/10.11591/eei.v12i3.4848.
Full textAbstract:
Cases of the COVID-19 virus continue to spread still needs to be considered even though we have entered the post-pandemic era. Rapid identification of COVID-19 cases is necessary to prevent the virus from spreading further. This study developed a chest X-ray-based (CXR) COVID-19 classification for COVID-19 detection using the convolutional neural networkbidirectional long short-term memory (CNN-BiLSTM) combination model and compared the CNN-BiLSTM combination model with CNN models. The CNN models used in this study are the transfer learning models, namely Resnet50, VGG19, InceptionV3, Xception, and AlexNet. This research classifies CXR into three groups: COVID-19, normal, and viral pneumonia. In comparison to other models, the Resnet50-BiLSTM model is the most accurate and hence the best. The accuracy of the Resnet50-BiLSTM model was 98.48%. The model that obtains the next highest accuracy i.e Resnet50, VGG19-BiLSTM, VGG19, InceptionV3-BiLSTM, InceptionV3, XceptionBiLSTM, Xception, AlexNet-BiLSTM, and AlexNet. In this study, precision, recall, and F1-measure are also employed to demonstrate that Resnet50-BiLSTM achieves the highest value compared to other approaches. When compared to previous studies, this study enhances classification performance results.
6
Dyah Irawati, Indrarini, Gelar Budiman, Sofia Saidah, Suci Rahmadiani, and Rohaya Latip. "Block-based compressive sensing in deep learning using AlexNet for vegetable classification." PeerJ Computer Science 9 (November 16, 2023): e1551. http://dx.doi.org/10.7717/peerj-cs.1551.
Full textAbstract:
Vegetables can be distinguished according to differences in color, shape, and texture. The deep learning convolutional neural network (CNN) method is a technique that can be used to classify types of vegetables for various applications in agriculture. This study proposes a vegetable classification technique that uses the CNN AlexNet model and applies compressive sensing (CS) to reduce computing time and save storage space. In CS, discrete cosine transform (DCT) is applied for the sparsing process, Gaussian distribution for sampling, and orthogonal matching pursuit (OMP) for reconstruction. Simulation results on 600 images for four types of vegetables showed a maximum test accuracy of 98% for the AlexNet method, while the combined block-based CS using the AlexNet method produced a maximum accuracy of 96.66% with a compression ratio of 2×. Our results indicated that AlexNet CNN architecture and block-based CS in AlexNet can classify vegetable images better than previous methods.
7
C, Sridevi, and Kannan M. "Convolutional Neural Network Architecture-Inception (GoogLeNet) For Deep Architected Learning-Assisted Lung Cancer Classification in Computed Tomography Images." Indian Journal of Science and Technology 18, no. 7 (2025): 504–16. https://doi.org/10.17485/IJST/v18i7.3086.
Full textAbstract:
<strong>Objectives:</strong> The primary objective of this study is to investigate the performance of AlexNet and GoogLeNet architectures in classifying lung cancer images from the LIDC-IDRI dataset. Additionally, the AlexNet architecture is modified to generate three classes (benign, malignant, and non-nodules) using a new dataset. <strong>Methods:</strong> This study utilizes the LIDC-IDRI dataset, consisting of 1018 thoracic CT scans from 1010 patient cases, with annotations from four radiologists. The AlexNet and GoogLeNet architectures are employed for image classification, with the following Hyperparameters: AlexNet uses a learning rate of 0.01 and a dropout of 0.5, while GoogLeNet uses a learning rate of 0.03 and a dropout of 0.4. Both architectures are trained and tested using the LIDC-IDRI dataset. The training accuracy achieved for VGG 16 and GoogLeNet is 0.952 and 0.963 respectively with low log loss. <strong>Findings:</strong> The findings of this study indicate that GoogLeNet outperforms VGG 16 in terms of accuracy, with a classification accuracy of 0.963 compared to 0.952 for VGG 16. Additionally, GoogLeNet demonstrates a higher F1-score (0.946) compared to AlexNet (0.714) and VGG 16 (0.825). The receiver operating characteristic (ROC) curve analysis reveals that GoogLeNet has a higher area under the curve (AUC) value (0.973) compared to AlexNet (0.923) and VGG 16 (0.968). This study demonstrates the effectiveness of deep learning architectures in classifying lung cancer images, with GoogLeNet outperforming AlexNet in terms of accuracy and F1-score. The proposed methodology can be extended to develop a hybrid convolutional neural network for identifying cancer cells in image datasets with improved performance and reduced computational time. <strong>Novelty/application:</strong> Future studies can focus on developing a hybrid convolutional neural network that combines the strengths of AlexNet and GoogLeNet for improved performance and reduced computational time. Additionally, investigating the application of transfer learning and fine-tuning techniques can improve the performance of deep learning architectures in lung cancer image classification. <strong>Keywords:</strong> Lung Cancer, CNN Architecture, GoogLeNet, AlexNet, Performance Analysis
8
Pratama, Aan Rachmatullah, and Adi Fajaryanto Cobantoro. "KLASIFIKASI CITRA PNEUMONIA MENGGUNAKAN ARSITEKTUR CONVOLUTIONAL NEURAL NETWORK (CNN)." Networking Engineering Research Operation 8, no. 2 (2023): 133–44. https://doi.org/10.21107/nero.v8i2.18992.
Full textAbstract:
Pneumonia adalah infeksi atau peradangan akut pada bagian jaringan paru yang disebabkan oleh berbagai mikroorganisme seperti bakteri, virus, parasit, jamur, kerusakan fisik paru ataupun bahan kimia. Pneumonia dapat menyerang orang dewasa maupun anak-anak, banyak kasus yang terjadi, terutama pada Negara berkembang dimana kebanyakan mengandalkan energi yang berpontensi menyebabkan polusi udara yang akan berdampak pada pernafasan manusia. Klasifikasi citra Pneumonia dari hasil rontgen dengan algoritma Convolutional Neural Network yang memiliki metode alur pemecahan masalah yang menyerupai pola pikir manusia. Pada program ini melakukan penelitian tentang membandingkan performa dari kedua model arsitektur Convolutional Neural Network arsitektur AlexNet dengan GoogleNet. Pada hasil confusion matrix mendapatkan hasil tingkat akurasi 0,79 untuk arsitektur Alexnet dan untuk arsitektur GoogLeNet mendapatkan hasil akurasi 0,78. Umumnya akurasi dari GoogLeNet lebih tinggi namun pada penelitian ini AlexNet mendapatkan akurasi yang lebih tinggi, namun GoogLeNet memiliki loss yang lebih rendah, loss dan Accuracy diperngaruhi callback yang didalamanya terdapat epoch. Pada hasil implementasi kedua model dari web app menggunakan flask dan Google colab, dari jumlah masukan 16 citra 15 prediksi dilakukan benar dan 1 salah mendapatkan hasil akurasi 0,94.Kata kunci : AlexNet, CNN, GoogLeNet, Pneumonia
9
Ong, Jia Heng, Pauline Ong, and Kiow Lee Woon. "IMAGE-BASED OIL PALM LEAVES DISEASE DETECTION USING CONVOLUTIONAL NEURAL NETWORK." Journal of Information and Communication Technology 21, No.3 (2022): 383–410. http://dx.doi.org/10.32890/jict2022.21.3.4.
Full textAbstract:
Over the years, numerous studies have been conducted on the integration of computer vision and machine learning in plant disease detection. However, these conventional machine learning methods often require the contour segmentation of the infected region from the entire leaf region and the manual extraction of different discriminative features before the classification models can be developed. In this study, deep learning models, specifically, the AlexNet convolutional neural network (CNN) and the combination of AlexNet and support vector machine (AlexNet-SVM), which overcome the limitation of handcrafting of feature representation were implemented for oil palm leaf disease identification. The images of healthy and infected leaf samples were collected, resized, and renamed before the model training. These images were directly used to fit the classification models, without the need for segmentation and feature extraction as in models, without the need for segmentation and feature extraction as in the conventional machine learning methods. The optimal architecture of AlexNet CNN and AlexNet-SVM models were then determined and subsequently applied for the oil palm leaf disease identification.Comparative studies showed that the overall performance of the AlexNet CNN model outperformed AlexNet-SVM-based classifier.
10
Damatraseta, Febri, Rani Novariany, and Muhammad Adlan Ridhani. "Real-time BISINDO Hand Gesture Detection and Recognition with Deep Learning CNN." Jurnal Informatika Kesatuan 1, no. 1 (2021): 71–80. http://dx.doi.org/10.37641/jikes.v1i1.774.
Full textAbstract:
BISINDO is one of Indonesian sign language, which do not have many facilities to implement. Because it can cause deaf people have difficulty to live their daily life. Therefore, this research tries to offer an recognition or translation system of the BISINDO alphabet into a text. The system is expected to help deaf people to communicate in two directions. In this study the problems encountered is small datasets. Therefore this research will do the testing of hand gesture recognition, by comparing two model CNN algorithms, that is LeNet-5 and Alexnet. This test will look for which classification technique is better if the dataset conditions in an amount that does not reach 1000 images in each class. After testing, the results found that the CNN technique on the Alexnet architectural model is better to used, this is because when doing the testing process by using still-image and Alexnet model data which has been released in training process, Alexnet model data gives greater prediction results that is equal to 76%. While the LeNet model is only able to predict with the percentage of 19%. When that Alexnet data model used on the system offered, only able to predict correcly by 60%.
 
 Keywords: Sign language, BISINDO, Computer Vision, Hand Gesture Recognition, Skin Segmentation, CIELab, Deep Learning, CNN.
11
Swarup, Chetan, Kamred Udham Singh, Ankit Kumar, Saroj Kumar Pandey, Neeraj varshney, and Teekam Singh. "Brain tumor detection using CNN, AlexNet & GoogLeNet ensembling learning approaches." Electronic Research Archive 31, no. 5 (2023): 2900–2924. http://dx.doi.org/10.3934/era.2023146.
Full textAbstract:
<abstract> <p>The detection of neurological disorders and diseases is aided by automatically identifying brain tumors from brain magnetic resonance imaging (MRI) images. A brain tumor is a potentially fatal disease that affects humans. Convolutional neural networks (CNNs) are the most common and widely used deep learning techniques for brain tumor analysis and classification. In this study, we proposed a deep CNN model for automatically detecting brain tumor cells in MRI brain images. First, we preprocess the 2D brain image MRI image to generate convolutional features. The CNN network is trained on the training dataset using the GoogleNet and AlexNet architecture, and the data model's performance is evaluated on the test data set. The model's performance is measured in terms of accuracy, sensitivity, specificity, and AUC. The algorithm performance matrices of both AlexNet and GoogLeNet are compared, the accuracy of AlexNet is 98.95, GoogLeNet is 99.45 sensitivity of AlexNet is 98.4, and GoogLeNet is 99.75, so from these values, we can infer that the GooGleNet is highly accurate and parameters that GoogLeNet consumes is significantly less; that is, the depth of AlexNet is 8, and it takes 60 million parameters, and the image input size is 227 × 227. Because of its high specificity and speed, the proposed CNN model can be a competent alternative support tool for radiologists in clinical diagnosis.</p> </abstract>
12
Komariyah, Aprilia Nur, Bagas Rohmatulloh, Yusuf Hendrawan, Sandra Malin Sutan, Dimas Firmanda Al Riza, and Mochamad Bagus Hermanto. "Klasifikasi Kualitas Teh Hitam Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Citra Digital." Jurnal Ilmiah Rekayasa Pertanian dan Biosistem 11, no. 2 (2023): 221–31. http://dx.doi.org/10.29303/jrpb.v11i2.542.
Full textAbstract:
Sebagai negara tropis, produksi teh hitam di Indonesia sangat besar. Berdasarkan kualitasnya, teh hitam di Indonesia telah diekspor ke beberapa negara. Dalam rangka memenuhi permintaan standar kualitas yang dibutuhkan di tiap negara, teh hitam diklasifikasikan menjadi tiga jenis, diantaranya grade A, grade B, dan grade C. tetapi, pada kenyataannya industri memiliki permasalahan pada pemenuhan standar quality control karena kebanyakan industri masih menggunakan metode manual. Maka dari itu tujuan dari penelitian ini adalah untuk mengklasifikan tiga jenis mutu teh secara otomatis dengan menggunakan convolutional neural network (CNN). Dua tipe pre-trained network digunakan yakni arsitektur AlexNet dan ResNet50. Berdasarkan analisis sensitivitas didapatkan nilai akurasi yang tinggi pada proses training dan validasi. Tiga model terbaik dari CNN didapatkan diantaranya AlexNet dengan solver Adam dan learning rate 0.00005; AlexNet dengan solver RMSProp dan learning rate 0.0001; ResNet50 dengan solver SGDm dan learning rate 0.00005 yang mana mendapatkan nilai akurasi training dan validasi hingga 100%. Selanjutnya didapatkan nilai akurasi klasifikasi dengan arsitektur AlexNet dengan solver Adam dan learning rate 0.00005 mampu mengklasifikasikan grade B dan grade C tepat 100% tanpa adanya error. Tetapi untuk grade A terdapat kesalahan sehingga nilai akurasi menjadi 99.7%. Sedangkan untuk arsitektur AlexNet dengan solver RMSProp dan learning rate 0.0001 dan arsitektur ResNet50 dengan solver SGDm dan learning rate 0.00005 dapat mengklasifikasikan teh hitam tepat sesuai dengan kelasnya. Berdasarkan hasil tersebut dapat disimpulkan bahwa CNN mampu mengklasifikasikan teh hitam secara efektif.
13
Muhaafidz, Md Saufi, Afiq Zamanhuri Mohd, Mohammad Norasiah, and Ibrahim Zaidah. "Deep Learning for Roman Handwritten Character Recognition." Indonesian Journal of Electrical Engineering and Computer Science 12, no. 2 (2018): 455–60. https://doi.org/10.11591/ijeecs.v12.i2.pp455-460.
Full textAbstract:
The advantage of deep learning is that the analysis and learning of massive amounts of unsupervised data make it a beneficial tool for Big Data analysis. Convolution Neural Network (CNN) is a deep learning method that can be used to classify image, cluster them by similarity, and perform image recognition in the scene. This paper conducts a comparative study between three deep learning models, which are simple-CNN, AlexNet and GoogLeNet for Roman handwritten character recognition using Chars74K dataset. The produced results indicate that GooleNet achieves the best accuracy but it requires a longer time to achieve such result while AlexNet produces less accurate result but at a faster rate.
14
Ramesh Naidu, P., S. Pruthvi Sagar, K. Praveen, K. Kiran, and K. Khalandar. "Stress Recognition Using Facial Landmarks and Cnn (Alexnet)." Journal of Physics: Conference Series 2089, no. 1 (2021): 012039. http://dx.doi.org/10.1088/1742-6596/2089/1/012039.
Full textAbstract:
Abstract Stress is a psychological disorder that affects every aspect of life and diminishes the quality of sleep. The strategy presented in this paper for detecting cognitive stress levels using facial landmarks is successful. The major goal of this system was to employ visual technology to detect stress using a machine learning methodology. The novelty of this work lies in the fact that a stress detection system should be as non-invasive as possible for the user. The user tension and these evidences are modelled using machine learning. The computer vision techniques we utilized to extract visual evidences, the machine learning model we used to forecast stress and related parameters, and the active sensing strategy we used to collect the most valuable evidences for efficient stress inference are all discussed. Our findings show that the stress level identified by our method is accurate is consistent with what psychological theories predict. This presents a stress recognition approach based on facial photos and landmarks utilizing AlexNet architecture in this research. It is vital to have a gadget that can collect the appropriate data. The use of a biological signal or a thermal image to identify stress is currently being investigated. To address this limitation, we devised an algorithm that can detect stress in photos taken with a standard camera. We have created DNN that uses facial positions points as input to take advantage of the fact that when a person is worried their eye, mouth, and head movements differ from what they are used to. The suggested algorithm senses stress more efficiently, according to experimental data.
15
A, Shikha Rai. "Melanoma Skin Cancer Detection using CNN AlexNet Architecture." International Journal for Research in Applied Science and Engineering Technology 8, no. 5 (2020): 301–5. http://dx.doi.org/10.22214/ijraset.2020.5049.
Full text
16
Abdul Hamid, Nik Noor Akmal, Rabiatul Adawiya Razali, and Zaidah Ibrahim. "Comparing bags of features, conventional convolutional neural network and AlexNet for fruit recognition." Indonesian Journal of Electrical Engineering and Computer Science 14, no. 1 (2019): 333. http://dx.doi.org/10.11591/ijeecs.v14.i1.pp333-339.
Full textAbstract:
This paper presents a comparative study between Bag of Features (BoF), Conventional Convolutional Neural Network (CNN) and Alexnet for fruit recognition. Automatic fruit recognition can minimize human intervention in their fruit harvesting operations, operation time and harvesting cost. On the other hand, this task is very challenging because of the similarities in shapes, colours and textures among various types of fruits. Thus, a robust technique that can produce good result is necessary. Due to the outstanding performance of deep learning like CNN and its pre-trained models like AlexNet in image recognition, this paper investigates the accuracy of conventional CNN, and Alexnet in recognizing thirty different types of fruits from a publicly available dataset. Besides that, the recognition performance of BoF is also examined since it is one of the machine learning techniques that achieves good result in object recognition. The experimental results indicate that all of these three techniques produce excellent recognition accuracy. Furthermore, conventional CNN achieves the fastest recognition result compared to BoF, and Alexnet.
17
Karungaru, Stephen, Lyu Dongyang, and Kenji Terada. "Vehicle Detection and Type Classification Based on CNN-SVM." International Journal of Machine Learning and Computing 11, no. 4 (2021): 304–10. http://dx.doi.org/10.18178/ijmlc.2021.11.4.1052.
Full textAbstract:
In this paper, we propose vehicle detection and classification in a real road environment using a modified and improved AlexNet. Among the various challenges faced, the problem of poor robustness in extracting vehicle candidate regions through a single feature is solved using the YOLO deep learning series algorithm used to propose potential regions and to further improve the speed of detection. For this, the lightweight network Yolov2-tiny is chosen as the location network. In the training process, anchor box clustering is performed based on the ground truth of the training set, which improves its performance on the specific dataset. The low classification accuracy problem after template-based feature extraction is solved using the optimal feature description extracted through convolution neural network learning. Moreover, based on AlexNet, through adjusting parameters, an improved algorithm was proposed whose model size is smaller and classification speed is faster than the original AlexNet. Spatial Pyramid Pooling (SPP) is added to the vehicle classification network which solves the problem of low accuracy due to image distortion caused by image resizing. By combining CNN with SVM and normalizing features in SVM, the generalization ability of the model was improved. Experiments show that our method has a better performance in vehicle detection and type classification.
18
Sarkar, Alok, Md Maniruzzaman, Mohammad Ashik Alahe, and Mohiuddin Ahmad. "An Effective and Novel Approach for Brain Tumor Classification Using AlexNet CNN Feature Extractor and Multiple Eminent Machine Learning Classifiers in MRIs." Journal of Sensors 2023 (March 8, 2023): 1–19. http://dx.doi.org/10.1155/2023/1224619.
Full textAbstract:
A brain tumor is an uncontrolled malignant cell growth in the brain, which is denoted as one of the deadliest types of cancer in people of all ages. Early detection of brain tumors is needed to get proper and accurate treatment. Recently, deep learning technology has attained much attraction to the physicians for the diagnosis and treatment of brain tumors. This research presents a novel and effective brain tumor classification approach from MRIs utilizing AlexNet CNN for separating the dataset into training and test data along with extracting the features. The extracted features are then fed to BayesNet, sequential minimal optimization (SMO), Naïve Bayes (NB), and random forest (RF) classifiers for classifying brain tumors as no-tumor, glioma, meningioma, and pituitary tumors. To evaluate our model’s performance, we have utilized a publicly available Kaggle dataset. This paper demonstrates ROC, PRC, and cost curves for realizing classification performance of the models; also, performance evaluating parameters, such as accuracy, sensitivity, specificity, false positive rate, false negative rate, precision, f-measure, kappa statistics, MCC, ROC area, and PRC area, have been calculated for four testing options: the test data itself, cross-validation fold (CVF) 4, CVF 10, and percentage split (PS) 34% of the test data. We have achieved 88.75%, 98.15%, 86.25% and 100% of accuracy using the AlexNet CNN+BayesNet, AlexNet CNN+SMO, AlexNet CNN+NB, and AlexNet CNN+RF models, respectively, for the test data itself. The results imply that our approach is outstanding and very effective.
19
Azida Muhammad, Nur, Amelina Ab Nasir, Zaidah Ibrahim, and Nurbaity Sabri. "Evaluation of CNN, Alexnet and GoogleNet for Fruit Recognition." Indonesian Journal of Electrical Engineering and Computer Science 12, no. 2 (2018): 468. http://dx.doi.org/10.11591/ijeecs.v12.i2.pp468-475.
Full textAbstract:
Fruit recognition is useful for automatic fruit harvesting. Fruit recognition application can reduce or minimize human intervention during fruit harvesting operation. However, in computer vision, fruit recognition is very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also leads to a challenging task for fruit recognition. Thus, this paper tends to investigate the performance of basic Convolutional Neural Network (CNN), Alexnet and Googlenet in recognizing nine different types of fruits from a publicly available dataset. The experimental results indicate that all these techniques produce excellent recognition accuracy, but basic CNN achieves the fastest recognition result compared with Alexnet and Googlenet.
20
Kurniawan, Rudi, Samsuryadi Samsuryadi, Fatma Susilawati Mohamad, Harma Oktafia Lingga Wijaya, and Budi Santoso. "Classification of palm oil fruit ripeness based on AlexNet deep Convolutional Neural Network." SINERGI 29, no. 1 (2025): 207. https://doi.org/10.22441/sinergi.2025.1.019.
Full textAbstract:
The palm oil industry faces significant challenges in accurately classifying fruit ripeness, which is crucial for optimizing yield, quality, and profitability. Manual methods are slow and prone to errors, leading to inefficiencies and increased costs. Deep Learning, particularly the AlexNet architecture, has succeeded in image classification tasks and offers a promising solution. This study explores the implementation of AlexNet to improve the efficiency and accuracy of palm oil fruit maturity classification, thereby reducing costs and production time. We employed a dataset of 1500 images of palm oil fruits, meticulously categorized into three classes: raw, ripe, and rotten. The experimental setup involved training AlexNet and comparing its performance with a conventional Convolutional Neural Network (CNN). The results demonstrated that AlexNet significantly outperforms the traditional CNN, achieving a validation loss of 0.0261 and an accuracy of 0.9962, compared to the CNN's validation loss of 0.0377 and accuracy of 0.9925. Furthermore, AlexNet achieved superior precision, recall, and F-1 scores, each reaching 0.99, while the CNN scores were 0.98. These findings suggest that adopting AlexNet can enhance the palm oil industry's operational efficiency and product quality. The improved classification accuracy ensures that fruits are harvested at optimal ripeness, leading to better oil yield and quality. Reducing classification errors and manual labor can also lead to substantial cost savings and increased profitability. This study underscores the potential of advanced deep learning models like AlexNet in revolutionizing agricultural practices and improving industrial outcomes.
21
Safie, Sairul Izwan, and Puteri Zarina Megat Khalid. "Practical Consideration in using Pre-trained Convolutional Neural Network (CNN) for Finger Vein Biometric." International Journal of Online and Biomedical Engineering (iJOE) 19, no. 02 (2023): 163–75. http://dx.doi.org/10.3991/ijoe.v19i02.35273.
Full textAbstract:
Using a pre-trained Convolutional Neural Network (CNN) model for a practical biometric authentication system requires specific procedures for training and performance evaluation. There are two criteria for a practical biometric system studied in this paper. First, the system’s ability to handle identity theft or impersonation attacks. Second, the ability of the system to generate high authentication performance with minimal enrollment period. We propose the use of the Multiple Clip Contrast Limited Adaptive Histogram Equalization (MC-CLAHE) technique to process finger images before being trained by CNN. A pre-trained CNN model called AlexNet is used to extract features as well as classify the MC-CLAHE images. The authentication performance of the pre-trained AlexNet model has increased by a maximum of 30% when using this technique. To ensure that the pre-trained AlexNet model is evaluated based on its ability to prevent impersonation attacks, a procedure to generate the Receiver Operating Characteristics (ROC) curve is proposed. An offline procedure for training the pre-trained AlexNet model is also proposed in this paper. The purpose is to minimize the user enrollment period without compromising the authentication performance. In this paper, this procedure successfully reduces the enrollment time by up to 95% compared to using on-line training.
22
Tjoa, Elbert Alfredo, I. Putu Yowan Nugraha Suparta, Rita Magdalena, and Nor Kumalasari CP. "The use of CLAHE for improving an accuracy of CNN architecture for detecting pneumonia." SHS Web of Conferences 139 (2022): 03026. http://dx.doi.org/10.1051/shsconf/202213903026.
Full textAbstract:
Artificial intelligence (AI) has now grown rapidly for helping many aspects of human life, one of them is for medical image processing. Currently, the world is still suffering from COVID-19 pandemic outbreak which affects more than 36 million people and it is estimated that more than 1 million death occurred as a result of this outbreak. Early detection for COVID-19 suffers is needed to assist doctors and medical experts to determine the next medication for patients for avoiding the worsening condition which leads to death. AI-based model is can be used for assisting medical experts for detecting and classify the lung condition based on chest x-ray (CXR) patient‗s image accurately by using deep learning. On this paper, authors proposed the use on contrast limited adaptive histogram equalization (CLAHE) for pre-processing the medical images combined with CNN AlexNet architecture. The result of this method then compared with non-CLAHE CNN AlexNet also self-made CNN architecture. The result shows a promising result by the accuracy of CNN AlexNet architecture is 91.11%.
23
FUADAH, YUNENDAH NUR, IBNU DAWAN UBAIDULLAH, NUR IBRAHIM, FAUZI FRAHMA TALININGSING, NIDAAN KHOFIYA SY, and MUHAMMAD ADNAN PRAMUDITHO. "Optimasi Convolutional Neural Network dan K-Fold Cross Validation pada Sistem Klasifikasi Glaukoma." ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika 10, no. 3 (2022): 728. http://dx.doi.org/10.26760/elkomika.v10i3.728.
Full textAbstract:
ABSTRAKPada penelitian ini dilakukan perancangan arsitektur Convolutional Neural Network (CNN) yang terdiri dari 5 layer konvolusi dan 1-fully connected layer untuk mengklasifikasikan citra fundus kedalam kondisi normal, early, moderate, deep, dan ocular hypertension (OHT). Selanjutnya, model yang diusulkan dibandingkan dengan arsitektur AlexNet yang memiliki 5 layer konvolusi dan 3- fully connected layer. Data yang digunakan berupa citra fundus yang terdiri dari 3200 data latih, 800 data validasi, dan 1000 data uji. Optimasi model CNN dilakukan dengan melakukan pengujian hyperparameter yang terdiri dari learning rate, batch-size, epoch, dan optimizer. Selain itu, pada tahap training diimplementasikan 5-fold cross validation untuk seleksi model terbaik. Dengan model yang lebih sederhana dari AlexNet, model CNN usulan dapat memberikan performansi yang sama dengan arsitektur AlexNet yaitu akurasi 100%, presisi, recall, f1-score dan AUC score bernilai 1.Kata kunci: glaukoma, citra fundus, convolutional neural network (CNN), AlexNet ABSTRACTThis study proposes a Convolutional Neural Network with 5 convolutional layer and 1-fully connected layer to classify fundus images into normal, early, moderate, deep, and ocular hypertension (OHT) conditions. Furthermore, the proposed model is compared with the AlexNet architecture which has 5 convolution layers and 3- fully connected layers. The data used is a fundus image consisting of 3200 training data, 800 validation data, and 1000 test data. The optimization of the CNN model is performed by testing the hyperparameters consisting of learning rate, batch size, epoch, and optimizer. In addition, at the training stage, 5-fold cross validation is implemented to select the best model to be used in the test stage. With a simpler model from AlexNet, the proposed model provides 100% accuracy performance with precision values, recall, f1-score, and AUC score of 1.Keywords: glaucoma, fundus images, convolutional neural network (CNN), AlexNet
24
Patil, Pragati, Priyanka Jadhav, Nandini Chaudhari, Nitesh Sureja, and Umesh Pawar. "Deep learning for grape leaf disease detection." International Journal of Informatics and Communication Technology (IJ-ICT) 14, no. 2 (2025): 653. https://doi.org/10.11591/ijict.v14i2.pp653-662.
Full textAbstract:
Agriculture is crucial to India's economy. Agriculture supports almost 75% of the world's population and much of its gross domestic product (GDP). Climate and environmental changes pose a threat to agriculture. India is recognized for its grapes, a commercially important fruit. Diseases reduce grape yields by 10-30%. If not recognized and treated early, grape diseases can cost farmers a lot. The main grape diseases include downy and powdery mildew, leaf blight, esca, and black rot. This work creates an Android grape disease detection app which uses machine learning. When a farmer submits a snapshot of a diseased grape leaf, the smartphone app identifies the ailment and offers grape plant disease prevention tips. In this research, an android app that detects grape plant illnesses use convolutional neural network (CNN) and AlexNet machine learning architectures. We investigated and compared CNN and AlexNet architecture's efficacy for grape disease detection using accuracy and other metrics. The dataset used comes from Kaggle. CNN and AlexNet architectures yielded 98.04% and 99.03% accuracy. AlexNet was more accurate than CNN in the final result.
25
Dasari Akash. "Deep Learning for Plant Species Classification." Power System Technology 49, no. 1 (2025): 352–64. https://doi.org/10.52783/pst.1541.
Full textAbstract:
Neither the ecology of the world nor the existence of humans can exist without plants. It is necessary to have an automated technique that makes use of deep learning in order to safeguard endangered species. In order to pre-process leaf images and extract important features, a new CNN-based technique known as D-Leaf was introduced. Specifically, this approach takes use of three distinct CNN models: D-Leaf, pre-trained AlexNet, and fine-tuned AlexNet. The support vector machine (SVM), artificial neural network (ANN), k-nearest neighbour (k-NN), naive bayes, and convolutional neural network (CNN) were the five various machine learning approaches that were used in order to establish the classification of these qualities. The D-Leaf model surpassed both the raw AlexNet model (93.26% accuracy) and the fine-tuned AlexNet model (95.54% accuracy) in the testing process. Additionally, the ANN classifier was an excellent choice for the CNN that was emphasised. According to the findings of the empirical research, D-Leaf has the potential to serve as an effective automated method for the classification of plant species.
26
Naseer, Iftikhar, Sheeraz Akram, Tehreem Masood, Arfan Jaffar, Muhammad Adnan Khan, and Amir Mosavi. "Performance Analysis of State-of-the-Art CNN Architectures for LUNA16." Sensors 22, no. 12 (2022): 4426. http://dx.doi.org/10.3390/s22124426.
Full textAbstract:
The convolutional neural network (CNN) has become a powerful tool in machine learning (ML) that is used to solve complex problems such as image recognition, natural language processing, and video analysis. Notably, the idea of exploring convolutional neural network architecture has gained substantial attention as well as popularity. This study focuses on the intrinsic various CNN architectures: LeNet, AlexNet, VGG16, ResNet-50, and Inception-V1, which have been scrutinized and compared with each other for the detection of lung cancer using publicly available LUNA16 datasets. Furthermore, multiple performance optimizers: root mean square propagation (RMSProp), adaptive moment estimation (Adam), and stochastic gradient descent (SGD), were applied for this comparative study. The performances of the three CNN architectures were measured for accuracy, specificity, sensitivity, positive predictive value, false omission rate, negative predictive value, and F1 score. The experimental results showed that the CNN AlexNet architecture with the SGD optimizer achieved the highest validation accuracy for CT lung cancer with an accuracy of 97.42%, misclassification rate of 2.58%, 97.58% sensitivity, 97.25% specificity, 97.58% positive predictive value, 97.25% negative predictive value, false omission rate of 2.75%, and F1 score of 97.58%. AlexNet with the SGD optimizer was the best and outperformed compared to the other state-of-the-art CNN architectures.
27
Cahyani, Denis Eka, Anjar Dwi Hariadi, Faisal Farris Setyawan, Langlang Gumila, and Samsul Setumin. "COVID-19 classification using CNN-BiLSTM based on chest X-ray images." Bulletin of Electrical Engineering and Informatics 12, no. 3 (2023): 1773–82. http://dx.doi.org/10.11591/eei.v12i3.4848.
Full textAbstract:
Cases of the COVID-19 virus continue to spread still needs to be considered even though we have entered the post-pandemic era. Rapid identification of COVID-19 cases is necessary to prevent the virus from spreading further. This study developed a chest X-ray-based (CXR) COVID-19 classification for COVID-19 detection using the convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) combination model and compared the CNN-BiLSTM combination model with CNN models. The CNN models used in this study are the transfer learning models, namely Resnet50, VGG19, InceptionV3, Xception, and AlexNet. This research classifies CXR into three groups: COVID-19, normal, and viral pneumonia. In comparison to other models, the Resnet50-BiLSTM model is the most accurate and hence the best. The accuracy of the Resnet50-BiLSTM model was 98.48%. The model that obtains the next highest accuracy i.e Resnet50, VGG19-BiLSTM, VGG19, InceptionV3-BiLSTM, InceptionV3, Xception-BiLSTM, Xception, AlexNet-BiLSTM, and AlexNet. In this study, precision, recall, and F1-measure are also employed to demonstrate that Resnet50-BiLSTM achieves the highest value compared to other approaches. When compared to previous studies, this study enhances classification performance results.
28
Kumar Patnala, Satish, Umme Najma, Savitha S. Savitha S, Hridaynath Pandurang Khandagale, Tirumalasetti Lakshmi Narayana, and Jyothi N M. "Advanced Deep Neural Architectures for Parkinson’s Disease Prediction and Classification Systems." Journal of Neonatal Surgery 14, no. 6 (2025): 148–55. https://doi.org/10.63682/jns.v14i6.3049.
Full textAbstract:
Introduction: Parkinson’s disease (PD) greatly decreases motor function in a progressive disease of the nervous system. Beginning accurate diagnoses establishes both on time action and more effective treatment of diseases. The traditional techniques for diagnosis depend upon individual examinations that could result in complications. The aim of this research is to examine potential of deep learning models—especially Convolutional Neural Networks (CNNs)—for PD identification and prediction integrating waveform and swirling drawing datasets as biomarkers. Methods: AlexNet, an already-trained deep neural system renowned for its excellent feature acquiring abilities, and a custom-made CNN model were evaluated. Augmentation approaches were employed in preliminary processing to boost picture variance and endurance. Standard performance indicators including preciseness, specificity, and sensitivity steered both models' training and evaluation. Results: AlexNet managed to retrieve convoluted spatial details and surpassed the modified CNN with preciseness by 100%. Although effectively functioning, the tailored CNN model accomplished a much less precise prediction of 93.2%. Superior accuracy and recall of AlexNet demonstrated the effectiveness in PD classifying more thoroughly. Conclusion: This research illustrates the significance of deep learning in the diagnosis of PD through exhibiting AlexNet's superior performance. These findings affirm the prospects for machine-driven, non-intrusive effectual PD examinations. Additional data sets and blended architectures should be examined in subsequent investigations to enhance model versatility
29
Zayd, Muhammad H., Muhammad W. Oktavian, Dewa G. T. Meranggi, Javier A. Figo, and Novanto Yudistira. "Improvement of garbage classification using pretrained Convolutional Neural Network." Teknologi 12, no. 1 (2022): 1–8. http://dx.doi.org/10.26594/teknologi.v0i0.2403.
Full textAbstract:
Recycling waste is necessary for the sustainability of a good social life. The recycling process for waste is generally carried out manually and with many types of waste categories. For the waste sorting process to run more effectively and efficiently, automatic waste sorting is required. One example is by using an image-based waste type classification system using deep learning or machine learning algorithms. In previous research, AlexNet and SVM were used as classification algorithms for waste types in 6 different waste categories. The results of this study show that SVM performance is better with an accuracy of 63% compared to AlexNet's performance with an accuracy of 20%. Whereas in general, the CNN algorithm's performance should produce better accuracy than SVM. Based on this, we propose to re-examine the classification of waste types in the same dataset as previous research using the latest CNN algorithm architecture, namely ResNet. More completely, the architectures used are AlexNet, ResNet-18, and ResNet-50, respectively with and without pretrained, so that a total of 6 types of CNN algorithm architecture are used in the training. In this study, the AlexNet architecture is used with a different configuration from previous studies. The test parameter is the number of epochs of 50 epochs with attention to how many epochs the training results have shown convergent. From the training results, the highest accuracy obtained by the ResNet-50 architecture with pretrained is 91.16% and shows convergent results since the 14th epoch. Then for the lowest accuracy obtained by the AlexNet architecture without pretrained, which is 58% and shows convergent results since the 21st epoch.
30
Zayd, Muhammad H., Muhammad W. Oktavian, Dewa G. T. Meranggi, Javier A. Figo, and Novanto Yudistira. "Improvement of garbage classification using pretrained Convolutional Neural Network." Teknologi 12, no. 1 (2022): 1–8. http://dx.doi.org/10.26594/teknologi.v12i1.2403.
Full textAbstract:
Recycling waste is necessary for the sustainability of a good social life. The recycling process for waste is generally carried out manually and with many types of waste categories. For the waste sorting process to run more effectively and efficiently, automatic waste sorting is required. One example is by using an image-based waste type classification system using deep learning or machine learning algorithms. In previous research, AlexNet and SVM were used as classification algorithms for waste types in 6 different waste categories. The results of this study show that SVM performance is better with an accuracy of 63% compared to AlexNet's performance with an accuracy of 20%. Whereas in general, the CNN algorithm's performance should produce better accuracy than SVM. Based on this, we propose to re-examine the classification of waste types in the same dataset as previous research using the latest CNN algorithm architecture, namely ResNet. More completely, the architectures used are AlexNet, ResNet-18, and ResNet-50, respectively with and without pretrained, so that a total of 6 types of CNN algorithm architecture are used in the training. In this study, the AlexNet architecture is used with a different configuration from previous studies. The test parameter is the number of epochs of 50 epochs with attention to how many epochs the training results have shown convergent. From the training results, the highest accuracy obtained by the ResNet-50 architecture with pretrained is 91.16% and shows convergent results since the 14th epoch. Then for the lowest accuracy obtained by the AlexNet architecture without pretrained, which is 58% and shows convergent results since the 21st epoch.
31
Khan, Izhar Dad, Omar Farooq, and Yusuf Uzzaman Khan. "Automatic Seizure Detection Using Modified CNN Architecture and Activation Layer." Journal of Physics: Conference Series 2318, no. 1 (2022): 012013. http://dx.doi.org/10.1088/1742-6596/2318/1/012013.
Full textAbstract:
Abstract An epileptology expert must visually inspect the EEG to identify abnormal neural activity, which is time-consuming and subject to human errors. The capability of convolution neural networks (CNN) to extract visuospatial features and learn from these discriminative features makes them useful for this task. This paper presents seizure classification based on long-term EEGs using CNN. After filtering, the scalogram is plotted using a 1-second window each. A recently published dataset (TUSZ v1.5.2) was used for the performance evaluation of various CNN-based deep neural networks. The best accuracy obtained for GoogLeNet and AlexNet is 95.88%, and 95.79% respectively with 50 epochs and 32 mini-batch sizes by using the SWISH activation function. The proposed hybrid architecture (AG86) for epoch 50 with mini-batch size 32 has shown the best testing results in terms of accuracy (94.98%) as compared to the SqueezeNet (93.19%), GoogLeNet (92.65%), and AlexNet (94.44%). Similar performance was observed using metrics specificity, sensitivity, Mathew correlation coefficient (MCC), and F1 score. A general inference based on evaluation can be drawn as the proposed hybrid architecture (AG86) showed better test results compared to pre-trained CNN models. Moreover, by replacing ReLU with the SWISH activation function, the performance of AlexNet and GoogLeNet improved.
32
Marshal, Aldo Leviko, and Ahmad Nurul Fajar Ahmad Nurul Fajar. "Image Classification of Mangoes Using CNN VGG16 and AlexNet." Journal of Social Science (JoSS) 2, no. 8 (2023): 694–703. http://dx.doi.org/10.57185/joss.v2i8.103.
Full textAbstract:
Mango is one of the fruits that is often consumed by Indonesian people and is the fruit with the third largest amount of production in Indonesia, but currently, there are obstacles in the export of mangoes in Indonesia where fruit conditions and regulations weaken the mango export process in Indonesia. This study focuses on comparisons and classifications in the use of the CNN VGG16 and AlexNet architectures for classifying arum manis mango images. In this research, 4 images of Arum Manis mangoes will be used with a dataset of 400. With the results of the classification carried out with the two architectural models, CNN VGG16 provides a high accuracy of 92.50% with the use of epoch 50 while the use of AlexNet gets an accuracy of 79.64%. This research was conducted to provide a solution to overcome the quality of mangoes that are not in accordance with the production standards of mangoes to be exported.
33
Putra, Adya Zizwan, Amir Mahmud Husein, Nicholas Nicholas, Frederico Wijaya, and Aribel Aribel. "Comparison of Tubercolosis Detection Using CNN Models (AlexNet and ResNet)." sinkron 8, no. 4 (2024): 2309–17. http://dx.doi.org/10.33395/sinkron.v8i4.13979.
Full textAbstract:
The bacterial infection caused by Mycobacterium tubercolosis, leading to tubercolosis is a prevalent contagious disease. This bacterium commonly targets the primary respiratory organs, particularly the lungs. Tuberculosis poses a significant global health challenge and necessitates early detection for effective management. In this context, to facilitate healthcare professionals in the early detection of patients, a technology capable of accurately identifying lung conditions is required. Therefore, CNN (Convolutional Neural Network) will be employed as the algorithm for detecting lung images. The research will utilize Convolutional Neural Network models, namely AlexNet and ResNet. The study aims to compare the performance of these two models in detecting TB through the analysis of chest X-ray images. The dataset comprises X-rays from both normal patients and TB patients, totaling 4.200 data points. The training process involves dividing the data into training and validation sets, with an 80% allocation for training and 20% for validation. The evaluation results indicate that the AlexNet model demonstrates higher detection accuracy, reaching 88.33% on the validation data, while ResNet achieves 83.10%. These findings suggest that the use of CNN models, especially AlexNet, can be an effective approach to enhancing early tuberculosis detection through the interpretation of chest X-ray images, with potential implications for improving global TB management and prevention efforts.
34
G, Shanmugapriya, Pavithra G, Anandkumar M.K., and Pavankumar D. "VIDEO SEGMENTATION AND OBJECT TRACKING USING IMPROVISED DEEP LEARNING ALGORITHMS." ICTACT Journal on Image and Video Processing 15, no. 2 (2024): 3441–47. https://doi.org/10.21917/ijivp.2024.0487.
Full textAbstract:
Video segmentation and object tracking are critical tasks in computer vision, with applications ranging from autonomous driving to surveillance and video analytics. Traditional approaches often struggle with challenges like occlusion, background clutter, and high computational costs, limiting their accuracy and efficiency in real-world scenarios. This research addresses these issues by employing improvised deep learning algorithms, specifically Convolutional Neural Networks (CNN), VGG, and AlexNet, to enhance the precision and speed of video segmentation and object tracking. The proposed method integrates feature extraction capabilities of CNN with the deeper architecture of VGG for improved feature representation and AlexNet's computational efficiency to ensure scalability. A novel multi-stage training process is implemented, where CNN provides initial object localization, VGG refines segmentation boundaries, and AlexNet accelerates tracking in real-time. The framework was trained and evaluated on benchmark datasets such as DAVIS and MOT17, covering diverse scenarios with varying complexities. The results show significant improvements in accuracy and speed compared to existing methods. On the DAVIS dataset, the approach achieved a segmentation accuracy of 89.7% and an Intersection over Union (IoU) score of 86.5%. For object tracking on MOT17, the system attained a Multi-Object Tracking Accuracy (MOTA) of 82.3% and an average frame processing rate of 35 frames per second (FPS), outperforming baseline methods by 8.5% in accuracy and 15% in computational efficiency. The CNN, VGG, and AlexNet in a unified framework offers a robust solution for video segmentation and object tracking, demonstrating enhanced accuracy, adaptability, and real-time performance. These findings hold promise for applications in areas requiring reliable and efficient visual analysis.
35
Nour, Nahla, Mohammed Elhebir, and Serestina Viriri. "Face Expression Recognition using Convolution Neural Network (CNN) Models." International Journal of Grid Computing & Applications 11, no. 4 (2020): 1–11. http://dx.doi.org/10.5121/ijgca.2020.11401.
Full textAbstract:
This paper proposes the design of a Facial Expression Recognition (FER) system based on deep convolutional neural network by using three model. In this work, a simple solution for facial expression recognition that uses a combination of algorithms for face detection, feature extraction and classification is discussed. The proposed method uses CNN models with SVM classifier and evaluates them, these models are Alex-net model, VGG-16 model and Res-Net model. Experiments are carried out on the Extended Cohn-Kanada (CK+) datasets to determine the recognition accuracy for the proposed FER system. In this study the accuracy of AlexNet model compared with Vgg16 model and ResNet model. The result show that AlexNet model achieved the best accuracy (88.2%) compared to other models.
36
Banaszewska, Krystyna, and Małgorzata Plechawska-Wójcik. "Comparative analysis of CNN models for handwritten digit recognition." Journal of Computer Sciences Institute 32 (September 30, 2024): 179–85. http://dx.doi.org/10.35784/jcsi.6239.
Full textAbstract:
The paper discusses the subject of convolutional neural networks used for handwritten digit classification. The purpose of the research is to evaluate the accuracy, performance, training, and classification time of three OCR networks (VGG-16, VGG-19 and AlexNet) and compare them with each other while selecting the most optimal one. The popular MNIST dataset of 70,000 images was used for the study. For each model, a preliminary study was conducted to determine the optimal parameters in the form of the number of input data and number of training epochs. The result of the work indicates that, despite the longer training and classification time, the AlexNet model achieved the highest precision, recall, and F1-score, indicating its ability to effectively classify images.
37
Susanto, Luban Abdi. "PEMILIHAN HYPERPARAMETER PADA ALEXNET CNN UNTUK KLASIFIKASI CITRA PENYAKIT KEDELAI." INDEXIA 5, no. 02 (2023): 113. http://dx.doi.org/10.30587/indexia.v5i02.5508.
Full textAbstract:
Kedelai merupakan makanan yang populer. Estimasi hasil di Indonesia berkisar antara 1,2 dan 1,5 ton per hektar, masih jauh di bawah potensi hasil sebesar 2 hingga 2,5 ton per hektar. Gangguan penyakit pada tanaman kedelai merupakan salah satu penyebab rendahnya hasil, sehingga petani harus mengenal penyakit yang menyerang kedelai agar dapat memilih jenis penyakit dan tindakan pengobatan yang tepat. Proses laboratorium pendampingan penyakit masih belum efisien sehingga membutuhkan waktu yang lama. Computer vision dan pembelajaran mendalam sekarang dapat digunakan untuk mengenali informasi prediktif pada objek, meskipun objek diposisikan di mana pun objek tersebut dimasukkan. Convolutional Neural Network (CNN) adalah teknik pembelajaran mendalam yang paling sering digunakan saat ini. Penelitian ini menggunakan arsitektur CNN yakni AlexNet dengan hyperparameter tuning untuk mengklasifikasikan citra penyakit kedelai. Hyperparameter tuning sangat berpengaruh terhadap performa model. Dataset yang digunakan berjumlah 1.500 citra penyakit pada daun kedelai, terdiri dari 3 kelas yakni caterpillar, diabrotica speciosa, dan healthy. Hyperparameter tuning pada AlexNet CNN dengan ukuran bacth size 12, dropout 0.2, optimizer Adam menghasilkan hasil terbaik dari segi nilai akurasi 84%, presisi 81,95%, recall 80,66%, serta f1-score 80,96%.
38
Lin, Cheng-Jian, Yu-Chi Li, and Hsueh-Yi Lin. "Using Convolutional Neural Networks Based on a Taguchi Method for Face Gender Recognition." Electronics 9, no. 8 (2020): 1227. http://dx.doi.org/10.3390/electronics9081227.
Full textAbstract:
In general, a convolutional neural network (CNN) consists of one or more convolutional layers, pooling layers, and fully connected layers. Most designers adopt a trial-and-error method to select CNN parameters. In this study, an AlexNet network with optimized parameters is proposed for face image recognition. A Taguchi method is used for selecting preliminary factors and experiments are performed through orthogonal table design. The proposed method filters out factors that are significantly affected. Finally, experimental results show that the proposed Taguchi-based AlexNet network obtains 87.056% and 98.72% average accuracy of image gender recognition in the CIA and MORPH databases, respectively. In addition, the average accuracy of the proposed Taguchi-based AlexNet network is 1.576% and 3.47% higher than that of the original AlexNet network in CIA and MORPH databases, respectively.
39
Barile, Claudia, Caterina Casavola, Giovanni Pappalettera, Vimalathithan Paramsamy Kannan, and Dany Katamba Mpoyi. "Acoustic Emission and Deep Learning for the Classification of the Mechanical Behavior of AlSi10Mg AM-SLM Specimens." Applied Sciences 13, no. 1 (2022): 189. http://dx.doi.org/10.3390/app13010189.
Full textAbstract:
In this research paper, the acoustic emission technique and a deep learning framework based on two types of pre-trained CNN models (alexNet and squeezeNet) and a new model are proposed to characterize and classify the mechanical behavior of AlSi10Mg components. Specimens are built in a Selective Laser Melting machine with different bed orientations along X, Y, Z, and 45 degrees. Tensile tests are performed, and AE signals are recorded from these tests. To characterize the elastic and plastic deformation stages, a time-frequency domain analysis was performed using CWT-based spectrograms. Three different categories of damage classification strategies were implemented, and CNN models were trained for each strategy. CNN models including AlexNet, SqueezeNet, and the new model were used. Several training modes were performed to determine the CNN model that can accurately classify AE data. Understanding the minimum set of AE signals needed to train the CNN while having 100% accuracy and understanding the parameters affecting the accuracy of a CNN and the training time for the efficient classification of AE signals are the main objectives of this work. The results obtained demonstrated that the new simplified CNN model proposed can accurately classify the AE signals in a short time compared to AlexNet and SqueezeNet.
40
Altaee, Mustafa, Talib A., M. A. Jalil, Ali J., and Thamer A. Alalwani. "Intelligent Multi-Level Feature Fusion Using Remote Sensing and CNN Image Classification Algorithm." Journal of Intelligent Systems and Internet of Things 9, no. 1 (2023): 53–70. http://dx.doi.org/10.54216/jisiot.090103.
Full textAbstract:
The collection of fetures in both multispectral and hyperspectral domains is possible with Hyperspectral Image (HSI). It comprises a vast array of multispectral bands with functional relationships. However, they become more complex when dealing with small samples. To tackle this issue, researchers employed a deep learning convolutionary neural network system (DL-CNN) and implemented a temporal abstraction strategy to grade HSI. This approach is an intelligent multi-level feature fusion that combines the temporal abstraction strategy and DL-CNN for HSI grading. Researchers have introduced the impact of seven separate classifiers in implementing the Location estimation on our broad CNN framework, which plays the shallow CNN model's main training phase. PSO, Adagrad, Plans to implement, Alexnet, Adam, Environmental benefits, and Nadam are the seven distinct remained significantly included in this analysis. A detailed study of the four multispectral remote sensing techniques sets showed the deep CNN system's supremacy followed with the HSI identification AlexNet Optimizer.
41
Zabir, M., N. Fazira, Zaidah Ibrahim, and Nurbaity Sabri. "Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition." International Journal of Engineering & Technology 7, no. 3.15 (2018): 95. http://dx.doi.org/10.14419/ijet.v7i3.15.17509.
Full textAbstract:
This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models.
42
Sabri, Nurbaity, Zalilah Abdul Aziz, Zaidah Ibrahim, Muhammad Akmal Rasydan Bin Mohd Rosni, and Abdul Hafiz bin Abd Ghapul. "Comparing Convolution Neural Network Models for Leaf Recognition." International Journal of Engineering & Technology 7, no. 3.15 (2018): 141. http://dx.doi.org/10.14419/ijet.v7i3.15.17518.
Full textAbstract:
This research compares the recognition performance between pre-trained models, GoogLeNet and AlexNet, with basic Convolution Neural Network (CNN) for leaf recognition. Lately, CNN has gained a lot of interest in image processing applications. Numerous pre-trained models have been introduced and the most popular pre-trained models are GoogLeNet and AlexNet. Each model has its own layers of convolution and computational complexity. A great success has been achieved using these classification models in computer vision and this research investigates their performances for leaf recognition using MalayaKew (MK), an open access leaf dataset. GoogLeNet achieves a perfect 100% accuracy, outperforms both AlexNet and basic CNN. On the other hand, the processing time for GoogLeNet is longer compared to the other models due to the high number of layers in its architecture.
43
Dawud, Awwal Muhammad, Kamil Yurtkan, and Huseyin Oztoprak. "Application of Deep Learning in Neuroradiology: Brain Haemorrhage Classification Using Transfer Learning." Computational Intelligence and Neuroscience 2019 (June 3, 2019): 1–12. http://dx.doi.org/10.1155/2019/4629859.
Full textAbstract:
In this paper, we address the problem of identifying brain haemorrhage which is considered as a tedious task for radiologists, especially in the early stages of the haemorrhage. The problem is solved using a deep learning approach where a convolutional neural network (CNN), the well-known AlexNet neural network, and also a modified novel version of AlexNet with support vector machine (AlexNet-SVM) classifier are trained to classify the brain computer tomography (CT) images into haemorrhage or nonhaemorrhage images. The aim of employing the deep learning model is to address the primary question in medical image analysis and classification: can a sufficient fine-tuning of a pretrained model (transfer learning) eliminate the need of building a CNN from scratch? Moreover, this study also aims to investigate the advantages of using SVM as a classifier instead of a three-layer neural network. We apply the same classification task to three deep networks; one is created from scratch, another is a pretrained model that was fine-tuned to the brain CT haemorrhage classification task, and our modified novel AlexNet model which uses the SVM classifier. The three networks were trained using the same number of brain CT images available. The experiments show that the transfer of knowledge from natural images to medical images classification is possible. In addition, our results proved that the proposed modified pretrained model “AlexNet-SVM” can outperform a convolutional neural network created from scratch and the original AlexNet in identifying the brain haemorrhage.
44
Patil, Pragati, and Priyanka Jadhav. "A NOVEL APPROACH FOR DETECTION OF GRAPE LEAF DISEASE USING CNN AND ALEXNET." ICTACT Journal on Data Science and Machine Learning 5, no. 2 (2024): 598–603. https://doi.org/10.21917/ijdsml.2024.0128.
Full textAbstract:
Agriculture plays a key role in India’s economic sector. More than 75% of the world’s population is dependent on agriculture, with most of its GDP coming from agriculture. Climatic and other environmental changes have become a major threat to agriculture. Grapes are a well-known fruit crop in India and are considered very important from a commercial point of view. However, there is a loss of 10-30% in grapes due to diseases. Grape diseases can cause significant losses to farmers and their grape production if not detected and treated early. Downy mildew, powdery mildew, leaf blight, Esca and black rot are the major grape diseases. Machine learning is a very effective solution to solve this problem. According to our research, convolutional neural network (CNN) is the most popular deep learning algorithm widely used in plant disease detection. In this paper, we did comparative analysis between CNN and AlexNet architecture to detect the diseases in grape plant and compared the accuracy and efficiency between these architectures. We used CNN algorithm and achieved an accuracy of 95.84% and AlexNet is a kind of CNN architecture used and achieved an excellent accuracy of 98.03%. The final result shows that the AlexNet architecture obtained higher accuracy than the CNN algorithm. In this work, an Android application has been designed to detect grape disease. When a farmer captures or uploads a photo of a diseased grape leaf, the mobile app predicts the disease and offers solutions to reduce the risk of the disease.
45
Suwirmayanti, Ni Luh Gede Pivin, I. Wayan Budi Sentana, I. Ketut Gede Darma Putra, Made Sudarma, I. Made Sukarsa, and Komang Budiarta. "Deep Learning Implementation Using CNN to Classify Bali God Sculpture Pictures." Lontar Komputer : Jurnal Ilmiah Teknologi Informasi 15, no. 02 (2024): 87. https://doi.org/10.24843/lkjiti.2024.v15.i02.p02.
Full textAbstract:
Efforts to preserve Balinese culture can be carried out by integrating art and technology as new steps that need to be developed. This research is motivated by the existence of various forms of God statues which have a central role in Balinese culture. The Deep Learning method is proposed because it has unique features that can be extracted automatically. The technique used in Deep Learning is Convolutional Neural Network (CNN). The training process is first performed to perform the classification process, and then the testing process is performed. We compared our CNN model with two other models, AlexNet and ResNet, based on the experimental results. Using a data split of 70%- 30%, our CNN model has the highest accuracy in managing statue image data. Specifically, our model achieves 97.14% accuracy, while Alexnet and Resnet achieve 24.44% and 33.33%, respectively. Apart from contributing to introducing the Balinese God Statue, this research can also be a basis for developing more comprehensive applications in culture and tourism.
46
Hardi, Nila, and Jenie Sundari. "Pengenalan Telapak Tangan Menggunakan Convolutionall Neural Network (CNN)." Reputasi: Jurnal Rekayasa Perangkat Lunak 4, no. 1 (2023): 10–15. http://dx.doi.org/10.31294/reputasi.v4i1.1951.
Full textAbstract:
Berbeda dengan atribut perilaku biometrik yang lainnya, telapak tangan (Palmprint) merupakan atribut yang cukup baru dalam biometrics. Pada mode sekarang, personal recognition system atau bahasa lainnya yaitu sistem pengenalan diri secara semakin hari semakin hari semakin menarik banyak peminat, sehingga kebutuhannyapun ikut meningkat khususnya dalam penerapan di sektor keamanan. Sistem pengenalan guna dijadikan sistem keamanan sudah banyak dikembangkan dengan menggunakan berbagai jenis atribut biometrik salah satunya dengan menggunakan pengenalan telapak tangan (Palmprint). Penelitian yang dilakukan memiliki tujuan guna melakukan Pengenalan Palmprint menggunakan Convolutionall Neural Network (CNN). CNN yang diterapakan pada penelitian ini yaitu metode Alexnet. Pada metode Alexnet diterapkan 3 tahapan yaitu tahap pertama diawali dengan pengumpulan dataset yang kemudian dilakukan proses Pre-processing sehingga citra yang dihasilkan ukurannya menjadi 64x64px. Tahap selanjutnya adalah Ekstraksi Fitur dengan 3 layer yaitu Convolutionall Layer, Pooling Layer, Fully Connected Layer, Pada implementasi implementasi Convolutionall Neural Network menggunakan 10 epoch. Hasil akurasi dari penelitian pengenalan Palmprint menggunakan metode Convolutionall Neural Network paling tinggi ditemukan pada epoch ke-9 yaitu 0,9701 atau jika diubah kedalam bentuk proporsi yaitu 97,01%.
47
Zhang, Qingtao. "Optimization of Nonlinear Convolutional Neural Networks based on Improved Chameleon Group Algorithm." Scalable Computing: Practice and Experience 25, no. 2 (2024): 840–47. http://dx.doi.org/10.12694/scpe.v25i2.2486.
Full textAbstract:
In order to solve the most difficult problem of the architectural model established by CNN in solving specific problems, which results in parameter overflow and inefficient training, an optimization algorithm for nonlinear convolutional neural networks based on improved chameleon swarm algorithm is proposed. This article mainly introduces the use of Chameleon Swarm Optimization (PSO) algorithm to research the parameters of CNN architecture, solve them, and achieve the optimization of the optimization model.Although the number of parameters that need to be set up in CNN is very large, this method can find better testing space for Alexnet samples with 5 different images. In order to improve the performance of the improved pruning algorithms, two candidate pruning algorithms are also proposed. The experimental results show that compared with the traditional Alexnet model, the improved pruning method improves the image recognition ability of the Caffe primary parameter set from 1.3% to 5.7%. This method has wide applicability and can be applied to most neural networks which do not require any special functional modules of the Alexnet network model.
48
Alrahhal, Maher, and Supreethi K.P. "Multimedia Image Retrieval System by Combining CNN With Handcraft Features in Three Different Similarity Measures." International Journal of Computer Vision and Image Processing 10, no. 1 (2020): 1–23. http://dx.doi.org/10.4018/ijcvip.2020010101.
Full textAbstract:
The authors propose WNAHVF, a combined weighted and normalized AlexNet with handcrafted visual features for extracting features from images and using those vectors for image retrieval and classification. The authors test the WNAHVF method on two general datasets, Corel-1k and Corel-10k, and one medical dataset. The outcomes demonstrate combining Bag of Features and Local Neighbor patterns with AlexNet enhances the accuracy and gives better results in general and medical image datasets in retrieval and classification problems. This algorithm gives results that are superior to existing strategies.
49
Sivalingam, Saravanan Madderi, and Lakshmi Devi Badabagni. "Tomato plant disease prediction system with a new framework SSMAN using advanced deep learning techniques." International Journal of Electrical and Computer Engineering (IJECE) 15, no. 1 (2025): 940. http://dx.doi.org/10.11591/ijece.v15i1.pp940-948.
Full textAbstract:
Agriculture plays a pivotal role in India's economy, and the timely detection of plant infections is essential to safeguard crops and prevent further spread of diseases. The conventional approach involves manual inspection of plant leaves to identify the specific type of disease, a task typically carried out by farmers or plant pathologists. In previous studies, you only look once (YOLO) and faster region-based convolutional neural network (R-CNN), machine learning algorithms were applied to datasets for detecting objects on tomato leaves which includes a total of images 2403 and got accuracies of 86 and 82 percent. In this paper, a deep convolutional neural network (DCNN) model proposed with a new framework separate, shift, and merge based AlexNet50 algorithm (SSMAN) is used to predict the disease at an earlier stage with higher accuracy. Among various pre-trained deep models, AlexNet emerges as the top performer, achieving the highest accuracy in disease classification. SSMAN can address anomalies in images by employing a class decomposition approach to scrutinize class boundaries. AlexNet exhibits a notable accuracy of 98.30% in successfully identifying tomato leaf diseases from images, with pre-trained new framework, superior to the original AlexNet architecture as well as traditional classification methods with other algorithms.
50
Tuncer, Seda Arslan, Ahmet Çınar, and Murat Fırat. "Hybrid CNN Based Computer-Aided Diagnosis System for Choroidal Neovascularization, Diabetic Macular Edema, Drusen Disease Detection from OCT Images." Traitement du Signal 38, no. 3 (2021): 673–79. http://dx.doi.org/10.18280/ts.380314.
Full textAbstract:
In the treatment of eye diseases, optical coherence tomography (OCT) is a medical imaging method that displays biological tissue layers by taking high resolution tomographic sections at the micron level. It has an important role in the diagnosis and follow-up of many diseases such as Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), age-related macular degeneration (AMD), Diabetic Retinopathy, Central Serous Retinopathy, Epiretinal Membrane, and Macular Hole. Computer-Aided Diagnostic (CAD) tools are needed in early detection and treatment monitoring of such eye diseases. In this paper, a hybrid Convolutional Neural Networks-based CAD system, which can classify Diabetic Macular Edema (DME), Drusen Choroidal Neovascularization (CNV), and normal OCT images, is proposed. The proposed system is CNN-SVM (Convolutional Neural Networks – Support Vector Machine) model and doesn’t require any additional extraction of feature or noise filtering on OCT images. A total of 968 OCT images is classified in pre-trained CNN methods with Alexnet, Resnet18 and Googlenet. Accuracy is achieved with highest Googlenet 97.4%. To examine the performance of the proposed CAD system, the CNN-SVM method achieves 98.96% with the highest accuracy hybrid Alexnet-SVM model, which is implemented with Alexnet-SVM, Resnet18-SVM and Googlenet-SVM models.