State of the Art Convolutional Neural Networks

doi:10.23940/ijpe.23.05.p6.342349

Abstract

Abstract: Convolutional Neural Networks (CNNs) have become a powerful tool for a wide range of computer vision tasks, such as image classification, object detection, and semantic segmentation. This paper provides an overview of the fundamental concepts and architectures of CNNs, highlighting recent advancements and applications. We discuss the key components of CNNs including convolutional layers, pooling layers, and activation functions. The journey of CNN from its genesis to its evolution to the one we are familiar with today is covered. Although CNN is highly capable on its own many researchers have benefitted by hybridizing CNN with quality models. Therefore, we explore various tailor-made hybrid applications of CNN that are designed to solve very specific problems. We also discuss various innovative fields of applications of CNN and discuss the wide range of fields wherein CNN is performing surprisingly well. The paper concludes with future challenges and endeavors with respect to CNN.

Key words: convolution neural network (CNN), Deep learning applications, Deep neural network, GPU

Shreshtha Singh and Arun Sharma. State of the Art Convolutional Neural Networks [J]. Int J Performability Eng, 2023, 19(5): 342-349.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

1. LeCun, Y., Jackel, L.D., Bottou, L., Cortes, C., Denker, J.S., Drucker, H., Guyon, I., Muller, U.A., Sackinger, E., Simard, P. and Vapnik, V. Learning algorithms for classification: A comparison on handwritten digit recognition. Neural networks: the statistical mechanics perspective, vol. 261, no. 276, pp. 2, 1995.
2. Khan A., Sohail A., Zahoora U. and Qureshi A.S.A survey of the recent architectures of deep convolutional neural networks. Artificial intelligence review, vol. 53, pp. 5455-5516, 2020
3. Hasan, R.I., Yusuf, S.M. and Alzubaidi, L.Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion. Plants, vol. 9, no. 10, pp. 1302, 2020.
4. Xiao Y., Tian Z., Yu J., Zhang Y., Liu S., Du S. and Lan X.A review of object detection based on deep learning. Multimedia Tools and Applications, vol. 79, pp. 23729-23791, 2020.
5. Ker J., Wang L., Rao J. and Lim T.Deep learning applications in medical image analysis. IEEE Access, vol. 6, pp. 9375-9389, 2017
6. Zhang, Z., Cui, P. and Zhu, W.Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 1, pp. 249-270, 2020
7. Shrestha, A. and Mahmood, A.Review of deep learning algorithms and architectures. IEEE access, vol. 7, pp. 53040-53065, 2019
8. Krizhevsky, A., Sutskever, I. and Hinton, G.E.Imagenet classification with deep convolutional neural networks. Communications of the ACM, vol. 60, no. 6, pp.84-90, 2017
9. Alzubaidi L., Zhang J., Humaidi A.J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M.A., Al-Amidie, M. and Farhan, L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, vol. 8, pp.1-74, 2021.
10. Zeiler, M.D. and Fergus, R.Visualizing and understanding convolutional networks. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13, Springer International Publishing, pp. 818-833, 2014.
11. Simonyan, K. and Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
12. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V. and Rabinovich A.Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015
13. Srivastava, R.K., Greff, K. and Schmidhuber, J. Highway networks. arXiv preprint arXiv:1505.00387, 2015
14. He K., Zhang X., Ren S. and Sun J.Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016
15. Wu, S., Zhong, S. and Liu, Y.Deep residual learning for image steganalysis. Multimedia tools and applications, vol. 77, pp.10437-10453, 2018.
16. Huang G., Liu Z., Van Der Maaten, L. and Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708, 2017
17. Xie S., Girshick R., Dollár P., Tu Z. and He K.Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1492-1500, 2017
18. Zagoruyko, S. and Komodakis, N. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016
19. Han, D., Kim, J. and Kim, J.Deep pyramidal residual networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5927-5935, 2017
20. Chollet F.Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251-1258, 2017
21. Wang J., Sun K., Cheng T., Jiang B., Deng C., Zhao Y., Liu D., Mu Y., Tan M., Wang X. and Liu W.Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence, vol. 43, no. 10, pp.3349-3364, 2020
22. Cheng B., Xiao B., Wang J., Shi H., Huang T.S. and Zhang L.Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5386-5395, 2020.
23. Dong Y., Pan Y., Zhang J. and Xu, W. Learning to read chest X-ray images from 16000+ examples using CNN. In2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), IEEE, pp. 51-57, 2017, July.
24. Dabeer, S., Khan, M.M. and Islam, S.Cancer diagnosis in histopathological image: CNN based approach. Informatics in Medicine Unlocked, vol. 16, pp. 100231, 2019.
25. Gangurde R., Jagota V., Khan M.S., Sakthi V.S., Boppana U.M., Osei B. and Kishore K.H.Developing an Efficient Cancer Detection and Prediction Tool Using Convolution Neural Network Integrated with Neural Pattern Recognition. BioMed research international, 2023.
26. Kamilaris, A. and Prenafeta-Boldú, F.X. A review of the use of convolutional neural networks in agriculture. The Journal of Agricultural Science, vol. 156, no. 3, pp. 312-322, 2018
27. Neforawati, I., Herman, N.S. and Mohd, O.Precision agriculture classification using convolutional neural networks for paddy growth level. In Journal of Physics: Conference Series (vol. 1193, no. 1, pp. 012026). IOP Publishing, 2019, April.
28. Mehtab, S. and Sen, J.Analysis and forecasting of financial time series using CNN and LSTM-based deep learning models. In Advances in Distributed Computing and Machine Learning: Proceedings of ICADCML 2021 (pp. 405-423). Springer Singapore, 2022.
29. Durairaj, D.M. and Mohan, B.K.A convolutional neural network based approach to financial time series prediction. Neural Computing and Applications, vol. 34, no. 16, pp.13319-13337, 2022
30. Bansal, N., Sharma, A. and Singh, R.K.A review on the application of deep learning in legal domain. In Artificial Intelligence Applications and Innovations: 15th IFIP WG 12.5 International Conference, AIAI 2019, Hersonissos, Crete, Greece, May 24-26, 2019, Proceedings 15 (pp. 374-381). Springer International Publishing, 2019.
31. Undavia, S., Meyers, A. and Ortega, J.E. A comparative study of classifying legal documents with neural networks. In2018 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, pp. 515-522, 2018, September.
32. Wang, C. and Jin, X. Study on Prediction of Legal Judgments Based on the CNN-BiGRU Model. In Proceedings of the2020 6th International Conference on Computing and Artificial Intelligence, pp. 63-68, 2020, April.
33. Bhatt D., Patel C., Talsania H., Patel J., Vaghela R., Pandya S., Modi K. and Ghayvat H.CNN variants for computer vision: history, architecture, application, challenges and future scope. Electronics, vol. 10, no. 20, pp. 2470, 2021.
34. Stigeborn P.Generating 3D-objects using neural networks, 2018.
35. Hang, L. and Cai, G.Y.CNN based detection of building roofs from high resolution satellite images. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 42, pp.187-192, 2020.
36. Baek, I. and Kim, S.B.3-Dimensional convolutional neural networks for predicting StarCraft Ⅱ results and extracting key game situations. Plos one, vol. 17, no. 3, pp. e0264550, 2022.
37. Venkatesh A. Object tracking in games using convolutional neural networks, 2018.
38. Wang T., Zhang B., Zhang T., Gu S., Bao J., Baltrusaitis T., Shen J., Chen D., Wen F., Chen Q. and Guo B.Rodin: A generative model for sculpting 3d digital avatars using diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4563-4573, 2023.
39. Cao, Y.H. and Wu, J.A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications. In Proceedings Of The AAAI Conference On Artificial Intelligence, vol. 36, no. 1, pp. 194-202, 2022, June.
40. Gu J., Wang Z., Kuen J., Ma L., Shahroudy A., Shuai B., Liu T., Wang X., Wang G., Cai J. and Chen T.Recent advances in convolutional neural networks. Pattern recognition, vol. 77, pp.354-377, 2018.
41. Karpathy A., Toderici G., Shetty S., Leung T., Sukthankar R. and Fei-Fei, L. Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725-1732, 2014.
42. Alawad W., Alburaidi B., Alzahrani A. and Alflaj F.A comparative study of stand-alone and hybrid CNN models for COVID-19 detection. International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, 2021.
43. Wang Z., Peng J., Song W., Gao X., Zhang Y., Zhang X., Xiao L. and Ma L.A convolutional neural network-based classification and decision-making model for visible defect identification of high-speed train images. Journal of Sensors, pp.1-17, 2021.
44. Kapadia, M.R. and Paunwala, C.N. Improved CBIR system using Multilayer CNN. In2018 International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 840-845). IEEE, 2018, July.
45. Ding P., Li J., Wang L., Wen M. and Guan Y.HYBRID-CNN: An efficient scheme for abnormal flow detection in the SDN-Based Smart Grid. Security and communication networks,, pp.1-20, 2020.
46. Nie Y., Sommella P., Carratù M., O’Nils, M. and Lundgren, J. A Deep CNN Transformer Hybrid Model for Skin Lesion Classification of Dermoscopic Images Using Focal Loss. Diagnostics, vol. 13, no. 1, pp. 72, 2022.
47. Dang C.N.,Moreno-García, M.N. and De la Prieta, F. Hybrid deep learning models for sentiment analysis. Complexity, pp.1-16, 2021.
48. Islam, M.Z., Islam, M.M. and Asraf, A.A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in medicine unlocked, vol.20, p.100412, 2020.
49. Zhang C., Pan X., Li H., Gardiner A., Sargent I., Hare J. and Atkinson P.M.A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS Journal of Photogrammetry and Remote Sensing, vol. 140, pp.133-144, 2018.
50. Ahsan M.M.,E. Alam, T., Trafalis, T. and Huebner, P. Deep MLP-CNN model using mixed-data to distinguish between COVID-19 and Non-COVID-19 patients. Symmetry, vol. 12, no. 9, pp. 1526, 2020.
51. Kumar V., Rana K., Malik J. and Tomar A.Evaluating hybrid cnn-mlp architecture for analyzing novel network traffic attacks. International Journal of Scientific & Technology Research, vol. 9, no. 3, pp. 2277-8616, 2020.
52. Alhussein, M., Aurangzeb, K. and Haider, S.I.Hybrid CNN-LSTM model for short-term individual household load forecasting. IEEE Access, vol. 8, pp.180544-180557, 2020.
53. Tovar, M., Robles, M. and Rashid, F.PV power prediction, using CNN-LSTM hybrid neural network model. Case of study: Temixco-Morelos, México. Energies, vol. 13, no. 24, pp. 6512, 2020.
54. Li, T., Hua, M. and Wu, X.U.A hybrid CNN-LSTM model for forecasting particulate matter (PM2. 5).IEEE Access, vol. 8, pp.26933-26940, 2020.
55. Sun, Y. and Chen, L.Traffic sign recognition based on CNN and twin support vector machine hybrid model. Journal of Applied Mathematics and Physics, vol. 9, no. 12, pp.3122-3142, 2021.
56. Chui K.T., Gupta B.B., Torres-Ruiz, M., Arya, V., Alhalabi, W. and Zamzami, I.F. A Convolutional Neural Network-Based Feature Extraction and Weighted Twin Support Vector Machine Algorithm for Context-Aware Human Activity Recognition. Electronics, vol. 12, no. 8, pp. 1915, 2023
57. Zhao C., Huang X., Li Y. and Yousaf Iqbal, M. A double-channel hybrid deep neural network based on CNN and BiLSTM for remaining useful life prediction. Sensors, vol. 20, no. 24, pp. 7109, 2020
58. Lu W., Li J., Wang J. and Qin L.A CNN-BiLSTM-AM method for stock price prediction. Neural Computing and Applications, vol. 33, pp.4741-4753, 2021.
59. Toma, R.N., Piltan, F. and Kim, J.M.A deep autoencoder-based convolution neural network framework for bearing fault classification in induction motors. Sensors, vol. 21, no. 24, pp. 8453, 2021
60. Jaiswal, G., Sharma, A. and Yadav, S.K.Deep feature extraction for document forgery detection with convolutional autoencoders. Computers and Electrical Engineering, vol. 99, pp. 107770, 2022
61. Yan W., Zhou L., Qian Z., Xiao L. and Zhu H.Sentiment analysis of student texts using the CNN-BiGRU-AT model. Scientific Programming, pp.1-9, 2021
62. Barua, S., Erfani, S.M. and Bailey, J.FCC-GAN: A fully connected and convolutional net architecture for GANs. arXiv preprint arXiv:1905.02417, 2019.
63. Luo, Z., Cheng, S.Y. and Zheng, Q.Y.GAN-based augmentation for improving CNN performance of classification of defective photovoltaic module cells in electroluminescence images. In IOP Conference Series: Earth and Environmental Science (vol. 354, no. 1, pp. 012106). IOP Publishing, 2019, October.
64. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł. and Polosukhin I.Attention is all you need. Advances in neural information processing systems, 2017.

[1]	Shalaka Prasad Deore. SongRec: A Facial Expression Recognition System for Song Recommendation using CNN [J]. Int J Performability Eng, 2023, 19(2): 115-121.
[2]	Sachin Aggarwal and Smriti Sehgal. Text Independent Data-Level Fusion Network for Multimodal Sentiment Analysis [J]. Int J Performability Eng, 2022, 18(9): 605-612.
[3]	Pawan Wawage and Yogesh Deshpande. Real-Time Prediction of Car Driver’s Emotions using Facial Expression with a Convolutional Neural Network-based Intelligent System [J]. Int J Performability Eng, 2022, 18(11): 791-797.
[4]	Hui Li, Cunlong Zhu, Xiaodan Wang, Wenfeng Liu, and Yutao Sun. Parallel Algorithms for Earth Observation Coverage of Satellites [J]. Int J Performability Eng, 2021, 17(8): 657-665.
[5]	Yi-Fan Chen, Yi-Kuei Lin, and Cheng-Fu Huang. Using Deep Neural Networks to Evaluate the System Reliability of Manufacturing Networks [J]. Int J Performability Eng, 2021, 17(7): 600-608.
[6]	Balika J. Chelliah, Anand Sasidharan, Dharmesh Kumar Singh, and Nilesh Dangi. Collaborative and Early Detection of Email Spam using Multitask Learning [J]. Int J Performability Eng, 2021, 17(6): 528-535.
[7]	Jiali Yang, Jiarui Chen, and Sheng Li. Decomposition and Identification of Non-Intrusive Load Equipment Group [J]. Int J Performability Eng, 2021, 17(1): 74-84.
[8]	Minghua Wei. Pedestrian Re-Identification Incorporating Multi-Information Flow Deep Learning Model [J]. Int J Performability Eng, 2020, 16(7): 1027-1037.