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
Items 401–500 of 869
Enhancing facial recognition accuracy through feature extractions and artificial neural networks
Kusnadi, A., Pane, I. Z., & Tobing, F. A. T. (2025) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i2.pp1056-1066 · Cited by 2
Impression evaluation of product images using deep neural network
Yamagiwa, A., & Goto, M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11129-1 · Cited by 2
“For example, the Convolutional Autoencoder [33] is a commonly used method in image data analysis, and its effectiveness has been demonstrated in various applications [34, 35].”
Extracting the Pneumonia Signature: A Deep Learning Framework for Definitive Diagnosis
Vyas, M., & Mehta, A. A. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-86296-0_21 · Cited by 2
Patient Mortality Prediction Using Clinical Notes
Gana, B., Figueroa, A., Allende‐Cid, H., Nand, P., Zamora, J., & Magna, A. R. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7005-5_5 · Cited by 2
Pclf: Parallel cnn-lstm fusion model for sms spam filtering
Derakhshi, M. R. F., Zafarani-Moattar, E., Al-Kabi, H. A., & Almarashy, A. H. J. (2024) · Springer Link (Chiba Institute of Technology) · doi:10.1051/bioconf/20249700136/pdf · Cited by 2
Aftatah, M., & Zebbara, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4971886 · Cited by 2
Meftah, L. H., & Cherif, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5117781 · Cited by 2
Muñoz Amaya, L. M. (2024) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 2
Prediction of air freight volume based on BP neural network
Han, D., & Peng, Y. (2023) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3650400.3650553 · Cited by 1
El-Latif, E. I. A., El-dosuky, M. A., Darwish, A., & Hassanien, A. E. (2024) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-024-04822-x · Cited by 1
“It constantly serves as the network’s last layer (Krichen et al. 2023; Cong et al. 2023).”
Lu, Y., Ma, C., & Chen, D. (2024) · Biomimetics · doi:10.3390/biomimetics9090567 · Cited by 1
“Through deep learning models like convolution neural networks (CNNs) [14,15], UAVs can efficiently and accurately identify targets such as humans, vehicles, and animals from the image data captured by sensors, laying a solid foundation for subsequent tracking tasks.”
BackgroundPedestrian Target Detection Model Based on Improved Yolov8
Huang, J., Liang, J., & Cao, Y. (2024) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea62095.2024.10692591 · Cited by 1
“With the rapid advancements in deep learning technologies, particularly the breakthroughs in Convolutional Neural Networks (CNNs) [4]the accuracy and efficiency of pedestrian 2024 5th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) detection have seen…”
BackgroundImproving the Polyp Image Segmentation Based on Parallel Reverse Attention Network
Bình, N. T., & Hong, T. V. T. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0434-0_6 · Cited by 1
Volleyball Game Analysis Using Computer Vision Algorithms
Plankelj, M. (2024) · Student Computing Research Symposium (SCORES) · doi:10.18690/um.feri.6.2024.9 · Cited by 1
Lowmunkhong, S., Panphuech, A., Janthawanno, P., Onjun, R., & Kaennakham, S. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia241430 · Cited by 1
Maya-Rodriguez, M. C., Carvajal-Mariscal, I., López-Muñoz, R., Lopez-Pacheco, M. A., & Tolentino-Eslava, R. (2025) · Processes · doi:10.3390/pr13030672 · Cited by 1
He, N., Dong, Z., Lin, L., Wang, J., & Ma, C. (2024) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei64163.2024.10906241 · Cited by 1
“This capability eliminates the need for the cumbersome manual feature design process [14].”
Qasemy, H. E. (2025) · Westcliff International Journal of Applied Research · doi:10.47670/wuwijar20251heq · Cited by 1
“The convolutional layer is the fundamental building block in which most of CNN computation happens (Krichen, 2023).”
Driver Anger Expression Detection: A Review
Xiang, O. J., Yogarayan, S., Mogan, J. N., Min, P. P., Azman, A., & Sivaprakasam, A. (2024) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta64807.2024.10913208 · Cited by 1
“The parameters of these layers are represented by their weights [60].”
Gesture-Based Drone Control Using Wearable Data and 1D CNN
Sa, L. D., Custódio, J., Ribeiro, R., Rodrigues, N. M. M., Ramos, J., & Pereira, A. M. D. J. (2024) · International Conference on Graphics and Interaction (ICGI) · doi:10.1109/icgi64003.2024.10923766 · Cited by 1
“Moreover, variation in the training data is also important to avoid overfitting phenomena [11].”
Sapna, S., & Mohan, B. R. (2025) · Computational Economics · doi:10.1007/s10614-025-10972-7 · Cited by 1
Fan, X., & Zhang, N. (2025) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece65250.2025.10984434 · Cited by 1
Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets
Sasse, J., Fabre, G., Fortier, I., Zimmermann, P., & Fluck, J. (2025) · Studies in health technology and informatics · doi:10.3233/shti250479 · Cited by 1
Artificial Intelligence-Driven Innovations in SLAM for Robotics and Autonomous Navigation
Wang, Z., & Zhang, X. (2025) · International Conference on Robotics, Control and Automation (ICRCA) · doi:10.1109/icrca64997.2025.11011185 · Cited by 1
“For instance, convolutional neural networks (CNN) can replay camera visual info, improving the recognition of landmarks and obstacles in an area [7].”
Comparison of deep learning models: CNN and VGG-16 in identifying pornographic content
Chandra, R., Suhendra, A., Banowosari, L. Y., & Prihandoko, P. (2025) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i3.pp1884-1899 · Cited by 1
“This model is a form of network evaluation as well as maximizing the depth level by using architecture and very small convolution filters which produces a significant improvement compared to [34], [35].”
Enhancing River Water Level Prediction Using CNN with Attention and Squeeze-and-Excitation Blocks
Hindi, R. J. (2025) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset2512174 · Cited by 1
A Review of Convolutional Neural Networks: Evolution, Applications, and Future Directions
Wang, A. (2025) · Applied and Computational Engineering · doi:10.54254/2755-2721/2025.tj24492 · Cited by 1
Agrawal, N., & Colle, B. A. (2025) · Weather and Forecasting · doi:10.1175/waf-d-24-0157.1 · Cited by 1
An attention-based fuzzy CNN-LTSM network for visual object recognition from fMRI images
Huang, T., Yin, X., & Jiang, E. (2025) · Journal of Computational Neuroscience · doi:10.1007/s10827-025-00905-6 · Cited by 1
“Convolutional neural networks (CNNs) have recently risen in popularity as the top choice for tasks like speech recognition, image classification, as well as natu - ral language processing (Krichen, 2023 ).”
Jasmir, J., Jusia, P. A., Arvita, Y., & Gunardi, G. (2025) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v14i4.9200 · Cited by 1
Zhou, X., Hu, Y., Jia, Q., & Xie, R. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3603175 · Cited by 1
“Advances in convolutional neural networks (CNNs) [1] have signifi-cantly enhanced the accuracy of HPE models.”
Jung, S., Moon, J., Suh, S., & Pyo, J. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103434 · Cited by 1
Vehicle Network Intrusion Detection Method Based on Deep Transfer Learning
Tian, Z., Pan, C., Li, Y., Yang, F., & Li, Z. (2024) · International Conference on Mechanical, Control and Computer Engineering (ICMCCE) · doi:10.1109/icmcce63640.2024.11163506 · Cited by 1
Sepaspour, R., Hajikarimi, P., & Nejad, F. M. (2025) · Theoretical and Applied Climatology · doi:10.1007/s00704-025-05795-3 · Cited by 1
Zhou, Q., & Akdağ, Ş. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3271 · Cited by 1
A novel compression method for Vectorcardiogram signal using hybrid autoencoder model
Vimal, R., Kumar, A., & Tiwari, A. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108796 · Cited by 1
Ong, T. Y., Teoh, P. C., & Tatt, T. K. (2025) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i5.pp4382-4389 · Cited by 1
Hosseini, S. M., & Salmasi, B. S. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202554564 · Cited by 1
Eleeas, K. N., Sudjono, S. H., & Gunawan, A. A. S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.049 · Cited by 1
UFormer:A U-Net Framework For Long-Term Time Series Forecasting
Li, Y., & Liu, T. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228841 · Cited by 1
“Convolutional Long Short-Term Memory Network(ConvLSTM) [7] is a model that combines convolutional neural network (CNN) [8] and LSTM.”
Rashidi, M., Tara, N., Mehrasa, M., Taheri, S., & Vahedi, H. (2025) · IEEE Access · doi:10.1109/access.2025.3631586 · Cited by 1
“It is deduced that better results usually arise from decomposition levels ranging from 24 to 28 and extraction components between 27 and 31.”
Deep Learning Techniques for Biomedical Imaging
Vandana, & Sharma, C. (2025) · Wiley eBooks · doi:10.1002/9781394348084.ch2 · Cited by 1
Deep learning analysis of ions accelerated at shocks
Swierc, P., Caprioli, D., Orusa, L., & Černetič, M. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/06/071 · Cited by 1
“[65, 66].”
Ahmad, A., Wanto, A., & Adnan, S. M. (2025) · Bulletin of Computer Science Research · doi:10.47065/bulletincsr.v5i4.545 · Cited by 1
“ResNet50 offers a good compromise, providing deep feature extraction capabilities while maintaining manageable computational costs, making it well-suited for this task [81]-[82].”
Emotion Classification on Social Text Using Deep Learning Models
Xuan, S. K., & Ming, L. T. (2025) · IEEE International Conference on Computation, Big-Data and Engineering (ICCBE) · doi:10.1109/iccbe65177.2025.11256022 · Cited by 1
“Their ability to capture spatial hierarchies in text makes them effective for simple sentiment classification tasks but limits their effectiveness in understanding nuanced emotional expressions [17].”
Farej, Z. K., & MohammedSami, Z. M. (2025) · International Conference on Business Analytics for Technology and Security (ICBATS) · doi:10.1109/icbats66542.2025.11258558 · Cited by 1
“Max Pooling Layer: The max pooling layer reduces the spatial dimensions of the input by taking the maximum value over a defined window, thus down-sampling the input while retaining important features as in equation [29]: (5) 6.”
Rahman, M. Z. F., Nugrahadi, D. T., Faisal, M. R., Farmadi, A., Mazdadi, M. I., Budiman, I., Lumbanraja, F. R., & Umiatin (2025) · International Conference of Computer and Informatics Engineering (IC2IE) · doi:10.1109/ic2ie67206.2025.11283365 · Cited by 1
“CNN is known for its effectiveness in recognizing spatial patterns from one-dimensional signals such as ECG through convolution and pooling operations [19].”
Ortiz-Balsero, A. S. (2024) · Lincoln (University of Nebraska) · Cited by 1
Real-Time Graph-Based Anomaly Detection for Capital Markets Using Stream Processing
Prabhagaran, S. T. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.4211 · Cited by 1
“Cross-market graph analytics is an emerging area that will offer future potential to increase global integrity of capital markets and decrease systemic risk [5] [27-30].”
WORD2VEC OPTIMALIZATION USING TRANSFER LEARNING IN INDONESIAN LANGUAGE FOR HIGHER EDUCATION
Hadianti, S., Riana, D., Tohir, H., Jarwadi, J., Rosdiana, T., Sopandi, E., & Kristiyanti, D. A. (2025) · JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) · doi:10.33480/jitk.v11i2.6051 · Cited by 1
“…while deep learning models provide more precise and interpretable word representations [9], Additionally, transfer learning has emerged as a solution to address vocabulary limitations by leveraging knowledge from resource-rich languages, enhancing word recognition and semantic understanding [10].”
Implementation of the You Look Only Once (YOLOv11) Algorithm to Detect the Ripeness of Golden Melons
Tandoballa, L., & Hartati, E. (2025) · Green Intelligent Systems and Applications · doi:10.53623/gisa.v5i2.934 · Cited by 1
“Convolutional Neural Network (CNN) is a deep learning architecture designed primarily to solve complex image processing problems [17].”
Gbashi, S. M., Olatunji, O. O., Adedeji, P. A., & Madushele, N. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.12.107 · Cited by 1
Evaluating the effectiveness of selected tools in recognizing emotions from facial photos
Wierzbowski, K. (2025) · Journal of Computer Sciences Institute · doi:10.35784/jcsi.7973 · Cited by 1
“The ability of CNNs to learn spatial hierarchies and generalize from raw pixel data has made them a dominant approach in visual recognition problems across a wide range of domains [5].”
Chiu, T.-Y., Chen, J.-L., & Ahmadi, C. (2025) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot66867.2025.00036 · Cited by 1
“These metrics, derived from Equations (7) to (10), are crucial for understanding the classification performance, as they measure the model’s ability to accurately detect malicious traffic while minimizing errors [51] [57].”
Analisis Performa CNN Berbasis MobileNetV2 pada Dataset Citra Dokumen Laporan Praktikum
Aryanda, H., Harahap, L. S., & Aptanta, D. A. (2025) · Journal of Educational Science and E-learning · doi:10.62354/jese.v2i2.44 · Cited by 1
“CNN juga merupakan dari pengembangan dari JST, di mana CNN menambahkan lapisan konvolusi dan pooling untuk menangani data spasial seperti gambar, berbeda dengan JST klasik yang hanya menggunakan lapisan penuh (Krichen, 2023).”
Amini, M., Javadi, S., & Soleimani-damaneh, M. (2026) · PLoS ONE · doi:10.1371/journal.pone.0342593 · Cited by 1
“Without nonlinear activation functions, a CNN would be restricted to learning only simple linear mappings and would not be capable of accurately representing or capturing intricate and nonlinear patterns [63].”
Multi-Scale Convolutional Neural Network-Based Classification of Tuberculosis Chest X-ray Images
Ridwan, M., _, S., Djiaulhaq, S. F., Mutmainah, S., & Lorosae, T. A. (2026) · Indonesian Applied Research Computing and Informatics · doi:10.64479/iarci.v1i2.60 · Cited by 1
“The merging layer aims to achieve spatial invariability by reducing the resolution of the matrix by trimming the elements from the spatial density of money having a smaller value[13].”
SMS SPAM DETECTION USING HYBRID DEEP LEARNING
Qasim, Z. K. (., & Saad, Z. M. (. (2025) · Modern American Journal of Engineering, Technology, and Innovation · Cited by 1
Prediction of Cardiac Arrhythmia via an Improved Hierarchical Fused Fuzzy Deep Learning
Daliri, A., & Mahdavi, N. (2025) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme68496.2025.11392540 · Cited by 1
“Algorithms such as multilayer perceptron [13], convolutional neural networks [14], and recurrent neural networks [15] are common examples of the second category referred to as modern machine learning.”
Comparison of Deep Learning Algorithms Performance In Diabetes Prediction
Tominanto, Sani, F. N., & Suryadi, A. (2025) · International Conference of Science and Information Technology in Smart Administration (ICSINTESA) · doi:10.1109/icsintesa68165.2025.11413641 · Cited by 1
“…they can also perform effectively on tabular datasets because convolutional filters are able to capture local feature interactions once the input vector is reshaped, while parameter sharing reduces the number of trainable weights and helps prevent overfitting on small datasets such as PIDD [37].”
Ankam, R. R., Srinivas, B. R., Rao, G. M., & Mallikarjunaiah, S. (2025) · International Journal of Innovations in Engineering and Science · doi:10.46335/ijies.2026.11.1.3 · Cited by 1
CNN-LSTM model optimized by improved sparrow search algorithm for oil well production prediction
Zhang, R., Guo, L., Sun, J., Zhong, X., Zheng, X., Qu, L., Zhang, S., & Qin, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-43674-7 · Cited by 1
Improving Document Layout Analysis Using Synthetic Data Generation and Convolutional Models
Pronina, O. I., Xia, T., Sheliah, K., Piatykop, O. I., Efremenko, V. G., & Balalayeva, E. Y. (2026) · Applied Sciences · doi:10.3390/app16063089 · Cited by 1
Invoice Recognition and Processing System for Small Businesses
Halim, N. A. A. B., Mangshor, N. N. A., Ibrahim, S., Fadzil, A. F. B. A., & Sabri, N. (2026) · International Conference on Cognitive Systems and Computer Interaction (ICoSCI) · doi:10.1109/icosci66700.2026.11447940 · Cited by 1
“Convolutional Neural Networks (CNN) are deep learning models effective for classifying and recognizing visual patterns [15].”
Hassan, S. A., & Beliatis, M. J. (2026) · International Journal of AI for Materials and Design · doi:10.36922/ijamd025340030 · Cited by 1
Abelly, E. N., Yang, F. Y., Kouassi, A. K. F., Zheng, H., Kasala, E. E., Mwakipunda, G. C., Hussain, W., & Mkono, C. N. (2026) · Natural Resources Research · doi:10.1007/s11053-026-10667-2 · Cited by 1
“…and deep recurrent neural networks (Natekar et al., 2020) have been used for automated well log interpretation; however, these approaches rely solely on log values at a specific location, which may contradict the established geological concepts (Li et al., 2021; Krichen, 2023; Zhang et al., 2023).”
Mekruksavanich, S., & Jitpattanakul, A. (2026) · Technologies · doi:10.3390/technologies14050272 · Cited by 1
Zhang, H., Choi, J. P., Liu, X., Liang, N., Yu, Y., Kim, Y., Shin, D., Moon, S. K., & Yoon, Y.-J. (2026) · Engineering · doi:10.1016/j.eng.2026.03.021 · Cited by 1
Deep Learning-Based Hybrid CNN Model for Heart Disease Diagnosis Using ECG Images
Abdusalomov, A., Rakhimov, M., Nasimov, R., Khojamurotov, A., Djurayeva, N., & Javliev, S. (2025) · International Conference on Future Networks and Distributed Systems (ICFNDS) · doi:10.1145/3789692.3789774 · Cited by 1
“CNN is an advanced type of Artificial Intelligence Network (ANN) and is mainly designed to extract features from a lattice matrix database [30].”
Towards transferrable landslide mapping: a style synchronization framework
Yu, B., Chen, W., Wang, S., Chen, F., Muhamad, N., Wang, L., Zhang, X., & Wang, N. (2026) · GIScience & Remote Sensing · doi:10.1080/15481603.2026.2668221 · Cited by 1
Saleh, H. A., & Isa, N. A. M. (2026) · Results in Control and Optimization · doi:10.1016/j.rico.2026.100731 · Cited by 1
Mutawa, A. M. (2026) · Information Processing in Agriculture · doi:10.1016/j.inpa.2026.05.005 · Cited by 1
Li, J., Li, W., Yang, F., Zhang, R., Pan, X., Zhao, D., & Zhang, K. F. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3694392 · Cited by 1
Yavuzdeğer, A., Aksu, İ. Ö., & Demirdelen, T. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08595-2 · Cited by 1
“Originally introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, LSTMs were developed to overcome the shortcomings of conventional RNNs, which face difficulties in retaining information over long sequences due to problems such as vanishing and exploding gradients [56].”
A polymer wire wetware synapse with improved endurance for physical neuromorphic implementation
Go, A. D., Watanabe, S., Kato, H., & Akai‐Kasaya, M. (2026) · Materials Advances · doi:10.1039/d5ma01448d · Cited by 1
Narmatha, S., & Mythili, D. S. (2026) · Archives for Technical Sciences · doi:10.70102/afts.2026.1835.558 · Cited by 1
Yin, W., Wang, H., Lin, S., Yan, Y., Lu, Y., & Suter, D. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3705535 · Cited by 1
“Third, while CNN-based methods [20] capture local patterns effectively, they are insufficient to model global discriminative features, leading to model estimation deviations and inlier correspondence fragmentation.”
Automatic assessment of rust level on screws using convolutional neural networks
Mandolini, M., Manuguerra, L., Dimanche, S., & Formentini, G. (2026) · Proceedings of the Design Society · doi:10.1017/pds.2026.10602 · Cited by 1
“As a result, automated approaches using computer vision and machine learning have gained momentum (Krichen, 2023).”
Deep Learning-Based Robust 3D Face Recognition Under Diverse Pose and Facial Expression Variations
Mishra, S. N., & Jain, D. (2026) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn70047.2026.11594274 · Cited by 1
Rusdiana, S., Rusyana, A., Juwita, Putri, M., Rafiki, A., & Das, S. (2026) · Journal of Electronics Electromedical Engineering and Medical Informatics · doi:10.35882/jeeemi.v8i3.1727 · Cited by 1
“For classification, convolutional neural networks have demonstrated strong capability in learning complex spatial representations from image data [14], [15].”
Li, M., Shan, X., & Chen, X. (2026) · Journal of Mechanics in Medicine and Biology · doi:10.1142/s0219519426400981 · Cited by 1
The Evolution of Image Segmentation from Classical Techniques to Deep Learning: A Survey
Shirzi, M. A., & Kermani, M. R. (2026) · Robotics · doi:10.3390/robotics15090169 · Cited by 1
“One key drawback is their computational expense [37], which makes them less suitable for real-time inference.”
Yu, B., Huang, Y., Cheng, G., Huang, D., & Ding, Y. (2023) · Electronics · doi:10.3390/electronics12194120 · Cited by 1
“They extend the capabilities of traditional CNNs [22] by conducting convolution operations on non-Euclidean graph-structured data.”
BackgroundSecurity and Privacy Challenges of Participatory Sensing in Natural Disaster Management
Alswailim, M. A. (2023) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa59173.2023.10479256 · Cited by 1
Shallow convolutional neural network structure for vegetable recognition
Zhao, Y. (2024) · International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP) · doi:10.1117/12.3029629 · Cited by 1
“The output feature map size can be calculated using the following formula [9] : considering the previously mentioned parameters, with no zero-padding, and a stride of 2, the calculation yields a feature map size of 3x3 with a quantity of 2.”
BackgroundMethodVALIDAÇÃO CRUZADA NA APRENDIZAGEM DE REDES NEURAIS CONVOLUCIONAIS PARA TRIAGEM DE CÂNCER CERVICAL
Dec, A. T. D. S., Guimarães, A. M., Etlinger-Colonel, D., Machado, E. P., Gueiber, E., Paulino, F. R., da Rocha, J. C. F., Lopes, M. L., & Psybyloski, P. H. (2024) · Editora Científica Digital eBooks · doi:10.37885/240416434 · Cited by 1
Evolving Deep Architectures: A New Blend of CNNs and Transformers Without Pre-training Dependencies
Kiiskilä, M., & Kiiskilä, P. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-66694-0_10 · Cited by 1
Ramachandran, K. K., Takhar, S., Jha, M. K., Patel, J. D., Randhawa, N., & Lourens, M. (2024) · International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT) · doi:10.1109/tqcebt59414.2024.10545285 · Cited by 1
Research Statutes and Prospects of AI in Domestic Robot Manufacturing
Fan, L., & Ruan, S. (2024) · Advances in engineering research/Advances in Engineering Research · doi:10.2991/978-94-6463-518-8_67 · Cited by 1
-, S. D., Khairari, A., Thatoi, P., Selvarathinam, A. L., & Rout, S. S. (2024) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2024.v06i05.27789 · Cited by 1
“• Deep Learning: Different models of DL, particularly those neural networks comprising CNNs [20], [21] and RNNs [22], [23] find their wide applications in medical imagining, genomics, and drug discovery.”
BackgroundGirepunje, S., & Singh, P. (2024) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon60325.2024.10687731 · Cited by 1
“In deep learning model, combining a multi-scale approach with channel attention mechanisms offers a potent framework for extracting and utilizing hierarchical features at many levels of abstraction[25].”
BackgroundOptimizing CNN Hyperparameters for Accurate Brain Computed Tomography Image Classification
Khoerunnisa, G., Mone, B. V., Nastiti, M. D., Sulistiyo, M. D., & Yunanto, P. E. (2024) · doi:10.1109/icoict61617.2024.10698323 · Cited by 1
Sound-Based Industrial Machine Malfunction Identification System by Deep Learning Approach
(2024) · International journal of intelligent engineering and systems · doi:10.22266/ijies2024.1231.31 · Cited by 1
Use of GAN Models and CNN Heatmaps in Malware
Diez, X. C., Requejo, I. G., Navarro, A. M., Aramburu, E. J. S., de la Puerta, J. G., & Pastor-López, I. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-75016-8_14 · Cited by 1
Deep Learning-Based Fruit and Vegetable Detection
Kang, H. J., Yogarayan, S., Mogan, J. N., & Min, P. P. (2024) · International Conference on Information Technology and Digital Applications (ICITDA) · doi:10.1109/icitda64560.2024.10809769 · Cited by 1
AÇÃO DE REDES NEURAIS CONVOLUCIONAIS NA CLASSIFICAÇÃO DE IMAGENS: ABORDAGENS E RESULTADOS
Guimarães, A. J. S., Barbosa, D. S., Sousa, G. D. S., & Santos, A. J. D. S. (2025) · Revista Contemporânea · doi:10.56083/rcv5n1-012 · Cited by 1
ActionFusion: Framework of Large Action Model Enablement
Shan, R., & Shan, T. C. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825136 · Cited by 1
Sentiment Analysis in Code-Mixed Telugu-English Text (CMTET) Using Deep Learning Techniques
Suraj, N. V., Manda, A. K., & Raj, V. (2024) · IEEE Delhi Section Conference (DELCON) · doi:10.1109/delcon64804.2024.10866784 · Cited by 1
Pedestrian Behavior Recognition on Roads Based on Deep Learning
He, X., Wang, W., Zeng, H., & Fu, L. (2024) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc62609.2024.10941882 · Cited by 1
“With the rapid development of deep learning algorithms and GPU hardware, 2D Convolutional Neural Networks (CNN) have achieved great success [3] in image classification tasks.”
Accelerating Solar PV Site Selection: YOLO-Based Identification of Sound Barriers Along Highways
Tavares, J., & Silva, C. (2025) · Energies · doi:10.3390/en18092366 · Cited by 1
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.