Convolutional Neural Networks: A Survey
Open accessThe DOI matches its Crossref record; 199 of the 199 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of AI that have emerged as a powerful tool for various tasks including image recognition, speech recognition, natural language processing (NLP), and even in the field of genomics, where they have been utilized to classify DNA sequences. This paper provides a comprehensive overview of CNNs and their applications in image recognition tasks. It first introduces the fundamentals of CNNs, including the layers of CNNs, convolution operation (Conv_Op), Feat_Maps, activation functions (Activ_Func), and training methods. It then discusses several popular CNN architectures such as LeNet, AlexNet, VGG, ResNet, and InceptionNet, and compares their performance. It also examines when to use CNNs, their advantages and limitations, and provides recommendations for developers and data scientists, including preprocessing the data, choosing appropriate hyperparameters (Hyper_Param), and evaluating model performance. It further explores the existing platforms and libraries for CNNs such as TensorFlow, Keras, PyTorch, Caffe, and MXNet, and compares their features and functionalities. Moreover, it estimates the cost of using CNNs and discusses potential cost-saving strategies. Finally, it reviews recent developments in CNNs, including attention mechanisms, capsule networks, transfer learning, adversarial training, quantization and compression, and enhancing the reliability and efficiency of CNNs through formal methods. The paper is concluded by summarizing the key takeaways and discussing the future directions of CNN research and development.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Finally, RobotReviewer/RobotSearch employs an ensemble classifier, combining multiple CNN models (Krichen 2023) and soft-margin Support Vector Machines (Boser et al. 1992) in order to categorise articles based on their risk of bias assessment (either low or high/unclear) and concurrently extract sentences that substantiate these judgements.”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Krichen 2023
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Understanding of a convolutional neural network
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017) · 2017 International Conference on Engineering and Technology (ICET) · doi:10.1109/icengtechnol.2017.8308186 · Cited by 3,986 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2584107 · Cited by 2,984
Artificial intelligence and the future of work: Human-AI symbiosis in organizational decision making
Jarrahi, M. H. (2018) · Business Horizons · doi:10.1016/j.bushor.2018.03.007 · Cited by 2,772
Duan, Y., Edwards, J. S., & Dwivedi, Y. K. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.01.021 · Cited by 2,628
Attention mechanisms in computer vision: A survey
Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0271-y · Cited by 2,566 · cited 1×
“Attention mechanisms are a powerful tool for improving the performance of CNNs [178–182].”
Research works printed but not linked: 9
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
- Bengio, Y., Goodfellow, I., and Courville, A. (2017). Deep Learning, MIT Press.
- Gan, 2019, Research of facial beauty prediction based on deep convolutional features using double activation layer, Acta Electonica Sin., 47, 636
- Simon, 2019, Shallow cnn with lstm layer for tuberculosis detection in microscopic images, Int. J. Recent Technol. Eng., 7, 56
- Ndong, P.S.B., Adoni, W.Y.H., Nahhal, T., Kimpolo, C., Krichen, M., Byed, A.E., Assayad, I., and Mutombo, F.K. (2021). Advances on Smart and Soft Computing: Proceedings of ICACIn 2021, Springer.
- Mehdi, C.A., Nour-Eddine, J., and Mohamed, E. (2022, January 22–27). Regularization in CNN: A Mathematical Study for L 1, L 2 and Dropout Regularizers. Proceedings of the International Conference on Advanced Intelligent Systems for Sustainable Development, Rabat, Morocco. · DOI
- Moolayil, J., Moolayil, J., and John, S. (2019). Learn Keras for Deep Neural Networks, Springer. · DOI
- Wu, P. (2021-, January 27). PyTorch 2.0: The Journey to Bringing Compiler Technologies to the Core of PyTorch (Keynote). Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization, Virtual.
- Rundong, 2022, Multidimensional Linear Data Processing Based on OpenCL Kernel Function in MXNet Framework, Front. Data Domputing, 4, 29
Cited by
A Comprehensive Overview and Comparative Analysis on Deep Learning Models
Perumal, T., Mustapha, N., Mohamed, R., & Shiri, F. M. (2024) · Journal on artificial intelligence · doi:10.32604/jai.2024.054314 · Cited by 664
Artificial intelligence for literature reviews: opportunities and challenges
Bolaños, F., Salatino, A., Osborne, F., & Motta, E. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10902-3 · Cited by 246
“Finally, RobotReviewer/RobotSearch employs an ensemble classifier, combining multiple CNN models [101] and soft-margin Support Vector Machines [102] in order to categorise articles based on their risk of bias assessment (either low or high/unclear) and concurrently extract sentences that…”
Deep Convolutional Neural Networks in Medical Image Analysis: A Review
Mienye, I. D., Swart, T. G., Obaido, G., Jordan, M., & Ilono, P. (2025) · Information · doi:10.3390/info16030195 · Cited by 242
“Medical image analysis requires robust algorithms capable of extracting subtle patterns from high-dimensional and often noisy datasets, a challenge that CNNs are uniquely equipped to address [11–13].”
Khanam, R., Hussain, M., Hill, R., & Allen, P. (2024) · IEEE Access · doi:10.1109/access.2024.3425166 · Cited by 237
Generative Artificial Intelligence in Education: Advancing Adaptive and Personalized Learning
Guettala, M., Bourekkache, S., Kazar, O., & Harous, S. (2024) · Acta Informatica Pragensia · doi:10.18267/j.aip.235 · Cited by 218
Breast Cancer Detection and Prevention Using Machine Learning
Khalid, A., Mehmood, A., Alabrah, A. A., Alkhamees, B. F., Amin, F., AlSalman, H., & Choi, G. S. (2023) · Diagnostics · doi:10.3390/diagnostics13193113 · Cited by 207
“Artificial intelligence (AI) [10] and machine learning (ML) may be found in the field of study that focuses on developing better technological systems to handle complicated tasks with less reliance on human intellect [11].”
BackgroundThe Challenges of Machine Learning: A Critical Review
Barbierato, E., & Gatti, A. (2024) · Electronics · doi:10.3390/electronics13020416 · Cited by 199
A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3376441 · Cited by 197
Deep Learning for Credit Card Fraud Detection: A Review of Algorithms, Challenges, and Solutions
Mienye, I. D., & Jere, N. (2024) · IEEE Access · doi:10.1109/access.2024.3426955 · Cited by 179
“The pooling layer is utilized to reduce the feature maps’ spatial dimensions [69].”
MethodA Review of CNN Applications in Smart Agriculture Using Multimodal Data
El Sakka, M., Ivanovici, M., Chaari, L., & Mothe, J. (2025) · Sensors · doi:10.3390/s25020472 · Cited by 176
“Originally developed for feature extraction from images for tasks such as image classification or segmentation, CNNs became widely used across domains requiring high accuracy in computer vision [31,32].”
Akkaş, T., Reshadsedghi, M., Şen, M., Kılıç, V., & Horzum, N. (2025) · Advanced Materials · doi:10.1002/adma.202504796 · Cited by 174
Managing natural disasters: An analysis of technological advancements, opportunities, and challenges
Krichen, M., Abdalzaher, M. S., Elwekeil, M., & Fouda, M. M. (2024) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.09.002 · Cited by 171
Self-citationIn-Depth Review of YOLOv1 to YOLOv10 Variants for Enhanced Photovoltaic Defect Detection
Hussain, M., & Khanam, R. (2024) · Solar · doi:10.3390/solar4030016 · Cited by 165
“As an example, the max-pooling function applied to a one-dimensional input can be expressed as follows (Equation (2)): The ReLU activation function, defined in Equation (3), has emerged as the dominant choice within CNN blocks [82].”
Exploring Convolutional Neural Network Architectures for EEG Feature Extraction
Rakhmatulin, I., Dao, M.-S., Nassibi, A., & Mandic, D. P. (2024) · Sensors · doi:10.3390/s24030877 · Cited by 159
“Pooling in convolutional neural networks [166,167] can also be used to reduce dimensionality.”
MethodDevelopments in Image Processing Using Deep Learning and Reinforcement Learning
Valente, J., António, J., Mora, C., & Jardim, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9100207 · Cited by 124
Systematic Review of Emotion Detection with Computer Vision and Deep Learning
Pereira, R., Mendes, C., Ribeiro, J., Ribeiro, R., Miragaia, R., Rodrigues, N. M. M., Costa, N., & Pereira, A. M. D. J. (2024) · Sensors · doi:10.3390/s24113484 · Cited by 111
“CNNs are designed to automatically learn and extract features from images, which can then be used to make predictions about the emotional state of a person in an image [48,49].”
BackgroundRangel, G., Cuevas-Tello, J. C., Nunez-Varela, J. I., Puente, C., & Trujillo, A. G. S. (2024) · Journal of Sensors · doi:10.1155/2024/2797320 · Cited by 111
Elhanashi, A., Dini, P., Saponara, S., & Zheng, Q. (2023) · Electronics · doi:10.3390/electronics12244925 · Cited by 106
Alpha-EIOU-YOLOv8: An Improved Algorithm for Rice Leaf Disease Detection
Cong, D. T., Mac, A., Dang, K. G., Nguyen, T. H., Nguyen, H., & Bui, T. D. (2024) · AgriEngineering · doi:10.3390/agriengineering6010018 · Cited by 105
Shamim, D. M. M. I., Hamid, A. B. A., Nyamasvisva, T. E., & Rafi, N. S. B. (2025) · Modelling—International Open Access Journal of Modelling in Engineering Science · doi:10.3390/modelling6020035 · Cited by 105
“CNNs, combined with NLP, can assist with textual data such as project specifications to extract cost-related knowledge [26,30].”
Zhang, H., Li, S., Miao, Q., Fang, R., Song, X., Hu, Q., Hu, J., & Chan, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-57990-3 · Cited by 104
A Deep Learning Methodology for Predicting Cybersecurity Attacks on the Internet of Things
Alkhudaydi, O. A., Krichen, M., & Alghamdi, A. D. (2023) · Information · doi:10.3390/info14100550 · Cited by 98
“Three subcomponents contributed to the extraction of characteristics: simulated IoT services, networking structure, and investigative analyses.”
BackgroundSelf-citationCardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets
Sattar, S., Mumtaz, R., Qadir, M., Mumtaz, S., Khan, M. A., Waele, T. D., Poorter, E. D., Moerman, I., & Shahid, A. (2024) · Sensors · doi:10.3390/s24082484 · Cited by 98
“CNNs have the capacity for hierarchical representation learning, capturing complex patterns from the input data [32].”
BackgroundAshbaugh, L., & Yan, Z. (2024) · Computers · doi:10.3390/computers13120340 · Cited by 98
Ali, M. U., Benfante, V., Basirinia, G., Alongi, P., Sperandeo, A., Quattrocchi, A., Giannone, A. G., Cabibi, D., Yezzi, A. J., Raimondo, D. D., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11020059 · Cited by 95
“Convolutional Neural Networks (CNNs) are a specialized type of ANN designed to process structural grid data, e.g., images [92] CNNs are particularly effective in image recognition and classification tasks because they can automatically and adaptively learn the spatial hierarchies of features [93].”
Ravi Raj, K. G., & Kos, A. (2025) · Sensors · doi:10.3390/s25041033 · Cited by 91
“During During convolution, the kernel traverses the height and breadth of the picture, computing the dot product between each component of the kernel and the data provided at each spatial location [15].”
Ahmad, M., Irfan, M. A., Sadique, U., Haq, I. U., Jan, A., Khattak, M. I., Ghadi, Y. Y., & Aljuaid, H. (2023) · Cancers · doi:10.3390/cancers15215247 · Cited by 87
“To address this issue, pooling layers were introduced into the CNN [39,40].”
MethodTlili, F., Ayed, S., & Fourati, L. C. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101281 · Cited by 86
Artificial Intelligence in Endodontics: A Scoping Review.
Asgary, S. (2024) · Iranian endodontic Journal/Iranian endodontic journal. · doi:10.22037/iej.v19i2.44842 · Cited by 84
“These networks comprise convolutional and pooling layers, which relevant features from input images, enabling accurate predictions [7].”
BackgroundMultimodal Detection of Fake Reviews using BERT and ResNet-50
Veluru, S. R., Erukude, S. T., & Marella, V. C. (2025) · International Conference on Innovative Mechanisms for Industry Applications · doi:10.1109/icimia67127.2025.11200892 · Cited by 80
“This embedding was subsequently passed to the fusion module. c) Image Encoding with ResNet-50: The visual modality was processed using ResNet-50, a 50-layer deep residual network pre-trained on the ImageNet dataset [4].”
Bilal, A., Liu, X., Baig, T. I., Long, H., & Shafiq, M. (2023) · Electronics · doi:10.3390/electronics12194094 · Cited by 78
Synergy between Artificial Intelligence and Hyperspectral Imagining—A Review
Khonina, S. N., Kazanskiy, N. L., Oseledets, I. V., Nikonorov, A. V., & Butt, M. A. (2024) · Technologies · doi:10.3390/technologies12090163 · Cited by 78
Fan, X., Chen, L., Huang, D., Tian, Y., Zhang, X., Jiao, M., & Zhou, Z. P. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202401887 · Cited by 76
AI-POWERED DEEP LEARNING MODELS FOR REAL-TIME CYBERSECURITY RISK ASSESSMENT IN ENTERPRISE IT SYSTEMS
Chowdhury, T. K. (2025) · doi:10.63125/137k6y79 · Cited by 71
Cumbajin, E., Rodrigues, N., Costa, P., Miragaia, R., Frazao, L. A. L., Costa, N., Fernández‐Caballero, A., Carneiro, J., Buruberri, L. H., & Pereira, A. M. D. J. (2023) · Sensors · doi:10.3390/s24010232 · Cited by 66
“We chose three of the most extensively used neural networks based on our systematic review [5] and the recommendations provided by Kermanidis et al. [23].”
MethodArtificial Intelligence in Agro-Food Systems: From Farm to Fork
Aghababaei, A., Aghababaei, F., Pignitter, M., & Hadidi, M. (2025) · Foods · doi:10.3390/foods14030411 · Cited by 66
Improved convolutional neural networks for aircraft type classification in remote sensing images
Alraba’nah, Y., & Hiari, M. O. (2025) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i2.pp1540-1547 · Cited by 64
“This hierarchical feature learning allows the network to build up from simple elements to complex, holistic understanding of image content [31].”
Survey on Blockchain-Based Data Storage Security for Android Mobile Applications
Musa, H. S., Krichen, M., Altun, A. A., & Ammi, M. (2023) · Sensors · doi:10.3390/s23218749 · Cited by 57
Self-citationJafari, S., & Byun, Y.-C. (2023) · Computers · doi:10.3390/computers12110219 · Cited by 56
Imtiaz, N., Wahid, A., Abideen, S. Z. U., Kamal, M. M., Sehito, N., Khan, S. U., Virdee, B. S., Kouhalvandi, L., & Alibakhshikenari, M. (2025) · Photonics · doi:10.3390/photonics12010035 · Cited by 56
Exploring Time Series Models for Wind Speed Forecasting: A Comparative Analysis
Li, X., Li, K., Shen, S., & Tian, Y. (2023) · Energies · doi:10.3390/en16237785 · Cited by 53
Formal Methods and Validation Techniques for Ensuring Automotive Systems Security
Krichen, M. (2023) · Information · doi:10.3390/info14120666 · Cited by 53
Self-citationLightweight marine biodetection model based on improved YOLOv10
Pan, W., Chen, J., Lv, B., & Peng, L. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.01.077 · Cited by 52
A Systematic Literature Review of Waste Identification in Automatic Separation Systems
Arbeláez-Estrada, J. C., Vallejo, P., Aguilar, J., Tabares, M. S., Ríos-Zapata, D., Ruiz-Arenas, S., & Vélez, E. R. (2023) · Recycling · doi:10.3390/recycling8060086 · Cited by 49
“This is due to their ability to learn spatial features and patterns in images using a hierarchical architecture of layers that perform convolution operations and extract features at different levels of abstraction [97].”
BackgroundExplainable Soft Attentive EfficientNet for breast cancer classification in histopathological images
Peta, J., & Koppu, S. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105828 · Cited by 48
Convolutional Neural Networks: A Comprehensive Evaluation and Benchmarking of Pooling Layer Variants
Zafar, A., Saba, N., Ali, A., Alabrah, A. A., Riaz, S., Suleman, M., Zafar, S., & Nadeem, M. (2024) · Symmetry · doi:10.3390/sym16111516 · Cited by 46
AdaBoost Ensemble Approach with Weak Classifiers for Gear Fault Diagnosis and Prognosis in DC Motors
Hussain, S. S., & Zaidi, S. S. H. (2024) · Applied Sciences · doi:10.3390/app14073105 · Cited by 45
“Deep Learning Neural Networks, renowned for capturing intricate patterns, demand substantial computational resources and extensive data for effective training, limiting their practical applicability in resource-constrained environments [37].”
BackgroundRustam, F., Al‐Shamayleh, A. S., Shafique, R., Obregón, S. A., Iglesias, R. C., Gonzalez, J. P. M., & Ashraf, I. (2024) · Scientific Reports · doi:10.1038/s41598-024-74357-w · Cited by 45
“CNNs are well-suited for image and sequence processing tasks 38 .”
Recent Advances in Deep Learning for Channel Coding: A Survey
Matsumine, T., & Ochiai, H. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3472094 · Cited by 44
“1) Convolutional Neural Network: Convolutional neural networks (CNNs) have made tremendous success in a vast research field including computer vision and natural language processing (NLP) [133]–[135].”
Hassan, S. A., Beliatis, M. J., Radziwon, A., Menciassi, A., & Oddo, C. M. (2024) · Electronics · doi:10.3390/electronics13214314 · Cited by 44
Wei, M., Zhang, J., Sun, K., Chea, C. P., Zhang, X., Liu, Z., & Jiang, F. (2026) · Energy · doi:10.1016/j.energy.2026.140407 · Cited by 44
Brain-inspired Artificial Intelligence: A Comprehensive ReviewPreprint
Ren, J., & Xia, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.14811 · Cited by 44
Quantum Natural Language Processing: A Comprehensive Survey
Moudina, C. V., Fendji, J. L. E. K., Schöning, J., & Atemkeng, M. (2024) · IEEE Access · doi:10.1109/access.2024.3420707 · Cited by 43
“…neurons, known as neural networks (NN), which have evolved over the years, leading to innovations like convolutional neural networks [58], [59], [60] (used in computer vision), recurrent neural networks [61], [62], [63], [64] (applied in time series and NLP), ResNets [65], and…”
BackgroundArtificial intelligence and its application in clinical microbiology
Mairi, A., Hamza, L., & Touati, A. (2025) · Expert Review of Anti-infective Therapy · doi:10.1080/14787210.2025.2484284 · Cited by 43
“CNNs comprise several specialized layers inspired by animals’ visual systems (Figure 1) [49,50].”
A two-stage approach for aircraft detection with convolutional neural network
Toghuj, W., & Alraba’nah, Y. (2024) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v14i4.pp4627-4635 · Cited by 42
“As the input image traverses through each layer, the CNN progressively identifies larger segments until it ultimately recognizes the entire image [24].”
BackgroundDDEYOLOv9: Network for Detecting and Counting Abnormal Fish Behaviors in Complex Water Environments
Li, Y., Hu, Z., Zhang, Y., Liu, J., Tu, W., & Yu, H. L. (2024) · Fishes · doi:10.3390/fishes9060242 · Cited by 42
Ebtehaj, I., & Bonakdari, H. (2024) · Atmosphere · doi:10.3390/atmos15091082 · Cited by 42
Performance enhancement of artificial intelligence: A survey
Krichen, M., & Abdalzaher, M. S. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.104034 · Cited by 41
Self-citationEfficient Brain Tumor Classification with a Hybrid CNN-SVM Approach in MRI
Suryawanshi, S., & Patil, S. B. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.3.340-354 · Cited by 40
“This process yields a collection of feature maps encompassing various patterns and configurations within the image [18].”
Influential5G AI-IoT System for Bird Species Monitoring and Song Classification
Segura-García, J., Sturley, S., Arevalillo‐Herráez, M., Calero, J. M. A., Felici-Castell, S., & Navarro, E. A. (2024) · Sensors · doi:10.3390/s24113687 · Cited by 36
“For the adoption of this paradigm, we have selected, on one side, light-weight convolutional neural networks (CNNs) [23,24] based on architectures trained with Imagenet-weights, such as EfficientNet-B0 and -B4, and EfficientNetV2-Small and V2-B0, or MobileNet-v2 and -v3 Large and Small; and, on the…”
MethodDeep Complex Gated Recurrent Networks-Based IoT Network Intrusion Detection Systems
El-Shafeiy, E., Elsayed, W. M., Elwahsh, H., Alsabaan, M., Ibrahem, M. I., & Elhady, G. F. (2024) · Sensors · doi:10.3390/s24185933 · Cited by 36
“The combination of convolutional neural networks (CNNs) [34] and gated recurrent networks (GRNs) has been used in IoT anomaly detection applications to effectively capture both spatial and temporal features in sensor data.”
MethodLi, J., Tao, R., Chen, R., Chen, Y., Zhao, C., & Huang, X. (2024) · Computers & Industrial Engineering · doi:10.1016/j.cie.2024.110209 · Cited by 35
Bbouzidi, S., Hcini, G., Jdey, I., & Drira, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.03478 · Cited by 35
“The most common CNN architectures are LeNet, AlexNet, VGGNet, ResNet, InceptionNet and DenseNet[87]: – LeNet: is a convolutional neural network (CNN) architecture introduced by LeCun et al. in 1998 [88].”
MethodDeep Learning Methods in Soft Robotics: Architectures and Applications
Čakurda, T., Trojanová, M., Pomin, P., & Hošovský, A. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202400576 · Cited by 34
Maleki, S. F., Yousefi, M., Afshar, S., Pedrammehr, S., Lim, C. P., Jafarizadeh, A., & Asadi, H. (2023) · Seminars in Ophthalmology · doi:10.1080/08820538.2023.2293030 · Cited by 33
“49 Garcia-Martin et al. created an ANN capable of detecting MS by RNFL thickness data from OCT.”
MethodGrignaffini, F., Simeoni, P., Alisi, A., & Frezza, F. (2024) · Electronics · doi:10.3390/electronics13163174 · Cited by 32
Hong, R., Tong, Y., Tang, H., Zeng, T., & Liu, R. (2024) · Research · doi:10.34133/research.0522 · Cited by 31
Feature optimization-guided high-precision and real-time metal surface defect detection network
Chan, S., Li, S., Zhang, H., Zhou, X., Mao, J., & Hong, F. (2024) · Scientific Reports · doi:10.1038/s41598-024-83430-3 · Cited by 31
Rakesh, S., Navuri, N. K., Thrimurthulu, V., Ravi, G., Karmakonda, K., & Vardhan, K. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-08475-4 · Cited by 31
“Testing in real-world conditions: • Perform thorough testing in a range of driving situations, including extreme weather and different traffic conditions, to demonstrate the robustness and reliability of the system, as stated by Guindel et al. 5,12 .”
Xing, D., Wang, Z., Zhang, M., Liu, S. N., Yang, W., Yin, R., Liu, H., Liu, H., & Shen, C. (2025) · Advanced Functional Materials · doi:10.1002/adfm.202529907 · Cited by 31
Integrating Machine Learning With Sensor Technology for Multiphase Flow Measurement: A Review
Bao, M., Wang, M., Li, K., & Jia, X. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3437292 · Cited by 30
“Formally, this can be expressed as follows [42]: where S is the feature map resulting from the convolution.”
BackgroundGhribi, F., & Hamdaoui, F. (2025) · The Visual Computer · doi:10.1007/s00371-025-04122-1 · Cited by 30
Slesinski, J., & Wierzbicki, D. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3589804 · Cited by 30
“The ability of these networks to learn patterns to extract features from visual data makes them indispensable for computer vision tasks such as image classification and recognition [93].”
Improved 5G network slicing for enhanced QoS against attack in SDN environment using deep learning
Abood, M. S., Wang, H., Virdee, B. S., He, D., Fathy, M., Yusuf, A. A., Jamal, O., Elwi, T. A., Alibakhshikenari, M., Kouhalvandi, L., et al. (2024) · IET Communications · doi:10.1049/cmu2.12735 · Cited by 29
Deep CNN-based detection of cardiac rhythm disorders using PPG signals from wearable devices
Bulut, M. G., Ünal, S., Hammad, M. A., & Pławiak, P. (2025) · PLoS ONE · doi:10.1371/journal.pone.0314154 · Cited by 28
“In the field of biomedical signal processing, CNNs are used for various tasks such as ECG analysis and medical image analysis [39].”
Billah, M. M., Sultana, A., Aftab, R. S., Ahmed, M. M., & Uddin, M. S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10283-2 · Cited by 28
“[19] measured the performance of different sets of real-world datasets and provided insight into quantitative methods.”
dos Santos, W. M., Martins, L. D. C. D. S., Bezerra, A. C., de Souza, L. S. B., Jardim, A. M. D. R. F., da Silva, M. V., de Souza, C. A. A., & da Silva, T. G. F. (2024) · Drones · doi:10.3390/drones8100585 · Cited by 27
Advances in Machine Learning Models for Predicting Enzyme Kinetic Parameters
Malli, A., Vasyutyn, D., & Kim, J. R. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02428 · Cited by 27
“44 The number of features from n -grams can grow extremely large, potentially becoming a high dimensional feature space as n increases.”
Riaz, M., He, J., Xie, K., AlSagri, H. S., Moqurrab, S. A., Alhakbani, H. A., & Obidallah, W. J. (2023) · Electronics · doi:10.3390/electronics12224675 · Cited by 27
IMU-Based Energy Expenditure Estimation for Various Walking Conditions Using a Hybrid CNN–LSTM Model
Lee, C. J., & Lee, J. K. (2024) · Sensors · doi:10.3390/s24020414 · Cited by 27
“CNN is a type of neural network architecture commonly used in computer vision tasks or time series estimation [33,34].”
A Deep Learning and Explainable AI-Based Approach for the Classification of Discomycetes Species
Korkmaz, A. F., Ekinci, F., Altaş, Ş., Kumru, E., Güzel, M. S., & Akata, İ. (2025) · Biology · doi:10.3390/biology14060719 · Cited by 26
“By implementing standardized training protocols, we aimed to provide a thorough and unbiased comparison of different convolutional neural network (CNN) architectures [33].”
Hwang, E. E., Chen, D., Han, Y., Lin, J., & Shan, J. (2023) · Bioengineering · doi:10.3390/bioengineering10111266 · Cited by 26
Deep Convolutional Neural Networks: A Comprehensive ReviewPreprint
Mienye, I. D., Swart, T. G., Obaido, G., Jordan, M., & Ilono, P. (2024) · Preprints.org · doi:10.20944/preprints202408.1288.v1 · Cited by 26
Hoseinzade, Z., Shojaei, M., Khademi, F., Mokhtari, A. R., & Saremi, M. (2025) · Modeling Earth Systems and Environment · doi:10.1007/s40808-025-02342-x · Cited by 25
“The pooling layer reduces the size of the feature map while retaining key information, and the fully connected layer acts like traditional networks, mapping the extracted features to the final output (Krichen 2023).”
A Hybrid Deep Learning Approach for Crude Oil Price Prediction
Aldabagh, H., Zheng, X., & Mukkamala, R. (2023) · Journal of risk and financial management · doi:10.3390/jrfm16120503 · Cited by 25
“…techniques such as support vector machines (SVM) (Cervantes et al. 2020), artificial neural networks (ANN) (Abiodun et al. 2018), convolutional neural networks (CNN) (Krichen 2023), deep belief networks (DBN) (Ghojogh et al. 2021), and recurrent neural networks (RNN) (Ghojogh and Ghodsi 2023).”
MethodAlif, M. A. R., Hussain, M., Tucker, G., & Iwnicki, S. (2024) · Machines · doi:10.3390/machines12020093 · Cited by 25
“As deep learning technology continues to evolve [36], these findings are poised to catalyse further research and foster the implementation of efficient and reliable safety inspection mechanisms in the railway industry.”
BackgroundEstimation of Weight and Body Measurement Model for Pigs Based on Back Point Cloud Data
Liu, Y., Zhou, J., Bian, Y., Wang, T., Xue, H., & Liu, L. (2024) · Animals · doi:10.3390/ani14071046 · Cited by 25
“For each voxel, the surrounding neighboring voxels are averaged with weighted values, and the weights are determined based on the position and distance of the neighboring voxels, reducing the data volume and achieving filtering and down-sampling effects, as shown in Figure 6.”
MethodA hybrid approach for gearbox fault diagnosis based on deep learning techniques
Bessaoudi, M., Habbouche, H., Benkedjouh, T., & Mesloub, A. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-13873-5 · Cited by 25
“The convolution layer uses filters of varying sizes to generate detailed output characteristics, serving as inputs for the next layer [36].”
An effective deep CNN-LSTM based intrusion detection system for network security
Jablaoui, R., & Liouane, N. (2024) · International Conference on Control, Automation and Diagnosis (ICCAD) · doi:10.1109/iccad60883.2024.10553826 · Cited by 25
Abumihsan, A., Owda, A. Y., Owda, M., Abumohsen, M., Stergioulas, L. K., & Amer, M. A. A. (2025) · IEEE Access · doi:10.1109/access.2025.3549269 · Cited by 24
“Furthermore, deep learning models, like convolutional neural networks (CNNs) are especially effective for processing CT images because they are well-suited for spatial data [8], [17], [18].”
Development of Context-Based Sentiment Classification for Intelligent Stock Market Prediction
Smatov, N., Калашников, Р., & Kartbayev, A. Z. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8060051 · Cited by 24
Alzheimers Disease Classification with a Hybrid CNN-SVM Approach on Enhanced MRI Data
Rahman, M., Hossain, M. S., Eva, A. A., Kabir, M. M., Mridha, M. F., & Shin, J. (2024) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict64318.2024.10824633 · Cited by 24
RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and AccelerationPreprint
Wang, B., & Kindratenko, V. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.06463 · Cited by 24
Edge Computing-Based Ensemble Learning Model for Health Care Decision Systems
Vincent, A. C. S. R., & Sengan, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-78225-5 · Cited by 23
An Improved Ensemble Method With Data Resampling for Credit Risk Prediction
Aruleba, I., & Sun, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3563432 · Cited by 23
“CNNs utilize multiple layers of convolutional operations that filter inputs for useful information, transforming them through a hierarchical structure of layers to capture and recombine properties into higher-level features [44], [45], [46].”
Hassan, S. A., Khalil, M. A., Auletta, F., Filosa, M., Camboni, D., Menciassi, A., & Oddo, C. M. (2023) · Electronics · doi:10.3390/electronics12204260 · Cited by 23
VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles
Ye, L., Wang, D., Yang, D., Ma, Z., & Zhang, Q. (2024) · Sensors · doi:10.3390/s24041345 · Cited by 23
A High-Precision Fall Detection Model Based on Dynamic Convolution in Complex Scenes
Qin, Y., Miao, W., & Qian, C. (2024) · Electronics · doi:10.3390/electronics13061141 · Cited by 23
A High-Precision Human Fall Detection Model Based on FasterNet and Deformable Convolution
Zheng, X., Cao, J., Wang, C., & Ma, P. (2024) · Electronics · doi:10.3390/electronics13142798 · Cited by 23
MEFP-Net: A Dual-Encoding Multi-Scale Edge Feature Perception Network for Skin Lesion Segmentation
Hao, S., Yu, Z., Zhang, B., Dai, C., Fan, Z., Ji, Z., & Ганчев, И. (2024) · IEEE Access · doi:10.1109/access.2024.3467678 · Cited by 23
“Initially, Krichen et al. [15] proposed a CNN that achieved remarkable results in image recognition tasks.”
Background
Metadata
- Authors
- Krichen, M.
- Affiliations
- University of Sfax (TN)
- Corresponding author
- Krichen, Moez
- ORCID
- Krichen, Moez
- Venue
- Computers
- Publisher
- MDPI AG
- Published
- 2023-07-28
- Volume
- 12
- Issue
- 8
- Pages
- 151
- ISSN
- 2073-431X (ISSN-L)
- OpenAlex
- W4385342469
- Cited by
- 623
- References
- 199
- Citations by year
- 2026: 144 · 2025: 242 · 2024: 189 · 2023: 48
- FWCI
- 56.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Computers (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- convolutional neural networks, image recognition, convolutional neural network architecture, LeNet, AlexNet, VGG, ResNet, InceptionNet, activation functions, hyperparameter optimization, deep learning libraries, attention mechanism, capsule networks, transfer learning, adversarial training, model compression, formal verification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.