Smarter School Labs: Fast and Accurate Anomaly Detection Using Lightweight CNN Technology
DOI:
https://doi.org/10.65126/jocosir.v3i1.70Keywords:
Lightweight CNN, Anomaly Detection, Log Analysis, Computer Lab Monitoring, Edge AIAbstract
This study proposes a lightweight convolutional neural network (CNN) model for anomaly detection in school computer laboratories, aiming to enhance operational reliability and cybersecurity awareness. Real-time event logs were collected from 20 computers (PC01–PC20) at Santo Nicholas School with slight variations in CPU, RAM, and network behavior to simulate real-world heterogeneity. After preprocessing and normalization, the merged dataset contained over 10,000 log entries labeled as normal or anomalous. The proposed lightweight CNN achieved 92.23% F1-score, 91.80% accuracy, and a false positive rate (FPR) of 18.47%, demonstrating a balance between detection precision and computational efficiency. Comparative evaluation shows that this architecture performs competitively while requiring fewer parameters and lower inference latency than conventional CNNs. The results highlight the suitability of the proposed model for deployment in low-resource educational environments, supporting early anomaly detection and preventive maintenance. Future research will explore cross-domain generalization and lightweight deployment through edge-AI integration.
References
A. Yadav and S. Mishra, “Evaluating Deep Learning Algorithms for Log-Based Anomaly Detection,” JISEM Journal, vol. 12, no. 3, pp. 1–12, 2025.
Y. Lu, H. Li, and X. Zhao, “Detecting Anomaly in Big Data System Logs Using Convolutional Neural Network,” Expert Systems with Applications, vol. 125, pp. 55–68, 2019.
A. B. Rashid, “AI Revolutionizing Industry: A Comprehensive Review,” IEEE Access, vol. 12, pp. 12215–12233, 2024.
A. Nambiar, “An Overview of Data Warehouse and Data Lake in Modern Architecture,” Electronics (MDPI), vol. 11, no. 18, 2022.
Y. S. N. Rao, “Bibliometric Insights into Data Mining in Education Research,” Education and Information Technologies (Springer), 2024.
D. Kim, J. Park, and S. Lee, “DeepLog: A Deep Neural Network for Log Anomaly Detection,” IEEE Transactions on Dependable and Secure Computing, 2020.
M. Du, F. Li, and Y. Zheng, “Unsupervised Anomaly Detection via Variational Autoencoder for Logs,” ACM Transactions on Intelligent Systems and Technology, 2021.
T. Nguyen, L. Hu, and J. Chen, “A Review of Machine Learning for Network Anomaly Detection,” Computer Networks (Elsevier), vol. 216, pp. 109105, 2022.
X. Zhang, Y. Zhou, and L. Liu, “Log Event Classification Using CNN with Attention Mechanism,” IEEE Access, vol. 8, pp. 19612–19623, 2020.
J. Han, R. Kim, and T. Choi, “Lightweight CNN for IoT Anomaly Detection,” Sensors (MDPI), vol. 21, no. 19, pp. 6452–6460, 2021.
Z. Sun, W. Zhao, and P. Liu, “Edge-AI Enabled Log Analysis with Pruned CNN,” Future Generation Computer Systems (Elsevier), vol. 150, pp. 80–92, 2023.
R. Maulani, S. Hutagalung, and E. Tambunan, “Implementing Log-Based Security Monitoring in School Laboratories,” Indonesian Journal of Computing and Cybernetics Systems, vol. 16, no. 2, pp. 45–58, 2022.
B. Kurniawan, M. A. Siregar, and F. Lubis, “Rule-Based System for Early Detection of Computer Lab Faults,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 19, no. 5, pp. 1121–1129, 2021.
Y. Jiang, Q. Zhou, and L. Yang, “Hybrid CNN-LSTM for Temporal Log Anomaly Detection,” Neurocomputing (Elsevier), vol. 512, pp. 280–295, 2022.
M. Ahmed, N. Chowdhury, and R. Alam, “Autoencoder-Based Unsupervised Log Analysis,” Information Sciences, vol. 634, pp. 58–75, 2023.
Q. Li, Z. Li, and J. Zhang, “Transformer-Based Sequence Modeling for Anomaly Detection,” IEEE Transactions on Neural Networks and Learning Systems, 2024.
S. Wang, C. Xu, and H. Li, “Anomaly Detection in Edge Computing Environments Using Lightweight Deep Learning,” IEEE Internet of Things Journal, vol. 10, no. 2, pp. 2456–2468, 2023.
K. Sharma and A. Gupta, “Comparative Study of CNN, RNN, and Transformer Models for System Log Analysis,” ACM Computing Surveys, vol. 56, no. 1, 2024.
R. Almeida, T. Santos, and P. Costa, “Optimizing Deep Learning for Low-Power Devices: A Survey,” Journal of Parallel and Distributed Computing (Elsevier), vol. 167, pp. 45–59, 2022.
T. Rahman, A. Fadhilah, and S. Noor, “Machine Learning-Based Log Monitoring in Educational IT Systems,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no. 9, pp. 215–224, 2023.
Z. Zhao and L. Tan, “Deep Learning-Based Anomaly Detection: A Survey on Edge Devices,” Pattern Recognition Letters (Elsevier), vol. 170, pp. 42–58, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ramlan Marbun, Muhammad Iqbal
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
