EDUANOM: Deep Learning Approach for Anomaly Detection in the Classroom Environment
EDUANOM: Deep Learning Approach for Anomaly Detection in the Classroom Environment |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-3 |
||
| Year of Publication : 2025 | ||
| Author : Dhatri Pandya, Keyur Rana |
||
| DOI : 10.14445/22315381/IJETT-V73I3P133 | ||
How to Cite?
Dhatri Pandya, Keyur Rana, "EDUANOM: Deep Learning Approach for Anomaly Detection in the Classroom Environment," International Journal of Engineering Trends and Technology, vol. 73, no. 3, pp. 473-486, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I3P133
Abstract
Anomaly detection is a prominent area of research in the field of deep learning. With the substantial increase in the number of CCTV located at various places, monitoring abnormal behavior is required to ensure safety and prevent the violation of rules at particular places. Anomaly detection in the classroom environment is important to ensure the safety of the students. Early detection of abnormal behavior will help educational institutions to take preventive measures against the students. Deep learning requires a huge amount of labeled data to achieve good accuracy. The data obtained from CCTV footage is currently unannotated, requiring manual annotation to facilitate the application of supervised deep learning architecture application. In addition, there is urge need for deep learning architecture trained on real-time datasets for anomaly detection in the classroom environment. To address this, we proposed a methodology based on unsupervised deep learning architecture by proposing a custom convolutional auto-encoder for anomaly detection in the classroom environment. Anomaly detection is accomplished through the utilization of a convolutional encoder, which evaluates the reconstruction loss between testing samples and training samples. This approach is effective for accurately identifying anomalies within the dataset. To implement this, similarity measures such as Mean Square Error (MSE), Kernel Density Estimation (KDE), and Structured Similarity Index Measure (SSIM) are applied. We evaluate the trained model on real-time data collected from the classroom environment with a comparative analysis of different similarity metrics. In this research work, we achieved 98% accuracy for anomaly detection in the classroom environment using the proposed methodology with similarity metrics SSIM. This research helps identify the role of unsupervised deep learning architecture and various similarity measures to identify anomalies in the classroom environment.
Keywords
Anomaly detection, Auto encoders, Education, Structured Similarity Index Measure, Deep Learning.
References
[1] QinMin Ma, “Abnormal Event Detection in Videos Based on Deep Neural Networks,” Scientific Programming, vol. 2021, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Mahmood Yousefi-Azar et al., “Autoencoder-Based Feature Learning for Cyber Security Applications,” 2017 International Joint Conference on Neural Networks, Anchorage, AK, USA, pp. 3854-3861, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Pierre Baldi, “Autoencoders, Unsupervised Learning, and Deep Architectures,” Proceedings of ICML Workshop on Unsupervised and Transfer Learning, PMLR 27, pp. 37-50, 2012.
[Google Scholar] [Publisher Link]
[4] Junhai Zhai et al., “Autoencoder and Its Various Variants,” 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, pp. 415-419, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Markus Goldstein, and Seiichi Uchida, “A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data,” PloS one, vol. 11, no. 4, pp. 1-31, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Charu C. Aggarwal, An Introduction to Outlier Analysis, Outlier Analysis, Springer, pp. 1-34, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Durgesh Samariya, and Amit Thakkar, “A Comprehensive Survey of Anomaly Detection Algorithms,” Annals of Data Science, vol. 10, no. 3, pp. 829-850, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jyothi Honnegowda, Komala Mallikarjunaiah, and Mallikarjunaswamy Srikantaswamy, “An Efficient Abnormal Event Detection System in Video Surveillance using Deep Learning-Based Reconfigurable Autoencoder,” Information Systems Engineering, vol. 29, no. 2, pp. 677-686, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Mehmet Saygın Seyfioğlu, Ahmet Murat Özbayoğlu, and Sevgi Zubeyde Gürbüz, “Deep Convolutional Autoencoder for Radar-Based Classification of Similar Aided and Unaided Human Activities,” IEEE Transactions on Aerospace and Electronic Systems, vol. 54, no. 4, pp. 1709-1723, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Dan Xu et al., “Learning Deep Representations of Appearance and Motion for Anomalous Event Detection,” British Machine Vision Conference, pp. 1-12, 2015.
[Google Scholar] [Publisher Link]
[11] Yingying Zhu, Nandita Nayak, and Amit Roy-Chowdhury, “Context-Aware Activity Recognition and Anomaly Detection in Video,” IEEE Journal of Selected Topics in Signal Processing, vol. 7, no. 1, pp. 91-101, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Nasaruddin Nasaruddin et al., “Deep Anomaly Detection through Visual Attention in Surveillance Videos,” Journal of Big Data, vol. 7, no. 1, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mahmudul Hasan et al., “Learning Temporal Regularity in Video Sequences,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 733-742, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Shifu Zhou et al., “Spatial-Temporal Convolutional Neural Networks for Anomaly Detection and Localization in Crowded Scenes,” Signal Processing: Image Communication, vol. 47, pp. 358-368, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Waqas Sultani, Chen Chen, and Mubarak Shah “Real-World Anomaly Detection in Surveillance Videos,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 6479-6488, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Trong Nguyen Nguyen, and Jean Meunier “Anomaly Detection in Video Sequence with Appearance-Motion Correspondence,” 2019 IEEE International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 1273-1283, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Yong Shean Chong, and Yong Haur Tay, “Abnormal Event Detection in Videos using Spatiotemporal Autoencoder,” Proceedings Part II 14th International Symposium Advances in Neural Networks ISNN, Lecture Notes in Computer Science, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, pp. 189-196, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] K. Chidananda, and A.P. Siva Kumar, “VidAnomalyNet: An Efficient Anomaly Detection in Public Surveillance Videos through Deep Learning Architectures,” International Journal of Safety and Security Engineering, vol. 14, no. 3, pp. 953-966, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Karishma Pawar, and Vahida Attar, “Application of Deep Learning for Crowd Anomaly Detection from Surveillance Videos,” 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India, pp. 506-511, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Jaroslav Kopcan, Ondrej Skvarek, and Martin Klimo, “Anomaly Detection using Autoencoders and Deep Convolution Generative Adversarial Networks,” Transportation Research Procedia, vol. 55, pp. 1296-1303, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Kamal Berahmand et al., “Autoencoders and Their Applications in Machine Learning: A Survey,” Artificial Intelligence Review, vol. 57, no. 2, pp. 1-52, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Xing Fang, “Understanding Deep Learning Via Backtracking and Deconvolution,” Journal of Big Data, vol. 4, no. 1, 1-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Timothy O. Hodson, “Root-Mean-Square Error (RMSE) or Mean Absolute Error (MAE): when to use them or not,” Geoscientific Model Development, vol. 15, no. 14, pp. 5481-5487, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Stanisław Węglarczyk, “Kernel Density Estimation and its Application,” ITM Web Conference, vol. 23, pp. 1-8, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Adriano Z. Zambom, and Ronaldo Dias, “A Review of Kernel Density Estimation with Applications to Econometrics,” International Econometric Review (IER), vol. 5, no. 1, pp. 20-42, 2013.
[Google Scholar] [Publisher Link]
[26] Jim Nilsson, and Tomas Akenine-Möller, “Understanding SSIM,” Image and Video Processing, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Paul Bergmann et al., “MVTec AD-A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 9584-9592, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Abdelhafid Berroukham et al., “Deep Learning-Based Methods for Anomaly Detection in Video Surveillance: A Review,” Bulletin of Electrical Engineering and Informatics, vol. 12, no. 1, pp. 314-327, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Vijay Mahadevan et al., “Anomaly Detection in Crowded Scenes,” 2010 IEEE Transactions on Pattern Analysis and Machine Intelligence, San Francisco, CA, USA, pp.1975-1981, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Mahdyar Ravanbakhsh et al., “Abnormal Event Detection in Videos using Generative Adversarial Nets,” Computer Vision and Pattern Recognition, pp. 1-5, 2017.
[CrossRef] [Google Scholar] [Publisher Link]