Comparative Analysis of Unsupervised Methods for Anomaly Detection in IoT-Based Pharmaceutical Cold Chain Temperature

Authors

  • Yusof Zaky Program Studi S2 PJJ Informatika, Fakultas Ilmu Komputer, Universitas Amikom Yogyakarta, Jl. Ring Road Utara, Condong Catur, Sleman, Yogyakarta, 55283
  • Alva Hendi Muhammad Master of Informatics, Universitas Amikom Yogyakarta, Yogyakarta, 55283, Indonesia https://orcid.org/0000-0003-1970-3139

Keywords:

Anomaly Detection, Cold Chain Monitoring, Internet of Things, LSTM, Time Series

Abstract

Maintaining vaccines within the 2°C–8°C range throughout cold chain storage and distribution is essential, since temperature excursions can degrade their biological potency. The growth of IoT-enabled sensors now allows continuous temperature data collection, opening the door to automated anomaly detection via time-series analysis. This research compares several unsupervised approaches for spotting temperature anomalies in an IoT-based pharmaceutical cold chain setup, benchmarking Isolation Forest against three deep learning architectures: Autoencoder, LSTM, and LSTM-Attention. Using roughly 8,640 temperature readings collected at 5-minute intervals over 30 days, the data were normalized with Min-Max Scaling and structured into sequences via a sliding window technique. Performance was assessed using precision, recall, and F1-score, alongside MAE and RMSE for prediction accuracy. Results showed Isolation Forest outperforming the other models (precision: 0.686, recall: 0.418, F1-score: 0.520) while also being the fastest to train and run. The deep learning models underperformed, likely limited by dataset size, making Isolation Forest the more practical choice for balancing detection accuracy with computational cost.

Downloads

Download data is not yet available.

Author Biography

Alva Hendi Muhammad, Master of Informatics, Universitas Amikom Yogyakarta, Yogyakarta, 55283, Indonesia

Alva Hendi Muhammad is an Associate Professor at the Faculty of Computer Science, Universitas Amikom Yogyakarta, Indonesia. He currently serves as the Head of the Doctoral Program in Informatics, after previously holding the position of Secretary of the Master of Informatics (Distance Learning Program). He obtained his doctoral degree from the University of Technology Sydney (UTS), Australia, and completed both his master's and bachelor's degrees in Information Technology at Universitas Gadjah Mada, Indonesia.

His research interests include artificial intelligence, data-driven decision making, information security, and IT governance. His work focuses on the development of decision support systems, expert systems, and the application of AI in engineering and educational technology. He has published in various international journals and conferences, particularly in the area of machine learning for information security risk classification and prediction.

In addition to his roles as a researcher and educator, he actively contributes to the academic community as a reviewer and technical program committee member in international conferences. He is also involved in curriculum development and doctoral program governance, promoting innovative and collaborative research ecosystems.

References

[1] Ali, Y. & Khan, H. U. (2023). IoT platforms assessment methodology for COVID-19 vaccine logistics and transportation. Scientific Reports. 13, from https://doi.org/10.1038/s41598-023-44966-y.

[2] Jiang S, Jia S, Guo H (2024). IoT-enabled framework for sustainable vaccine cold chain management. Heliyon. 10 (4), from http://doi.org/10.1016/j.heliyon.2024.e28910.

[3] Harrabi, M., et al. (2024). Real-time temperature anomaly detection in vaccine refrigeration systems using deep learning on a resource-constrained microcontroller. Frontiers in Artificial Intelligence. 7, from http://doi.org/10.3389/frai.2024.1429602.

[4] Ren, H., Xu, B., Wang, Y. & Yi, C. (2019). Time-series anomaly detection service at Microsoft. ACM SIGKDD Explorations Newsletter. 21 (1), 6–16, from http://doi.org/10.1145/3292500.3330680.

[5] Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation. 9 (8), 1735–1780, from http://doi.org/10.1162/neco.1997.9.8.1735.

[6] Aggarwal, C. C. (2017). Outlier analysis (2nd ed.). Springer. https://doi.org/10.1007/978-3-319-47578-3.

[7] Li, G. & Dai, Y. (2024). Time series anomaly detection using LSTM and attention. Paper presented at the 4th International Conference on Internet of Things and Smart City (IoTSC), Hangzhou, China, from http://doi.org/10.1117/12.3035015.

[8] Malhotra, P., et al. (2019). LSTM-based encoder-decoder for multi-sensor anomaly detection. Expert Systems with Applications. 121, 124–137, from http://doi.org/10.1016/j.eswa.2018.12.044.

[9] Wang, S., Jiang, R., Wang, Z., & Zhou, Y. (2024). Deep Learning-based Anomaly Detection and Log Analysis for Computer Networks. Journal of Information and Computing, 2(2), 34-63. https://doi.org/10.30211/JIC.202402.005.

[10] Zhao, Y., Zhang, X., Shang, Z. & Cao, Z. (2022). DA-LSTM-VAE: dual-stage attention-based LSTM-VAE for KPI anomaly detection. Entropy. 24 (11), from http://doi.org/10.3390/e24111613.

[11] Pang, G., Shen, C., Cao, L. & van den Hengel, A. (2021). Deep learning for anomaly detection: A review. ACM Computing Surveys. 54 (2), from http://doi.org/10.1145/3439950.

[12] Xu, L. D., He, W. & Li, S. (2014). Internet of Things in industries: A survey. IEEE Transactions on Industrial Informatics. 10 (4), 2233–2243, from http://doi.org/10.1109/TII.2014.2300753.

[13] World Health Organization. (2014). Temperature Sensitivity of Vaccines. Geneva, Switzerland: World Health Organization. Retrieved from https://apps.who.int/iris/handle/10665/137427.

[14] Nurwarsito, H. & Resnu, M. (2024). Pengembangan Internet of Things (IoT) dalam perekaman data iklim mikro menggunakan platform ThingsBoard. Jurnal Teknologi Informasi dan Ilmu Komputer. 11 (6), 1385–1394, from http://doi.org/10.25126/jtiik.2024118987.

[15] Susantok, M. (2025). Peningkatan akurasi sistem pemantauan suhu dan kelembapan pada laboratorium pengujian benih tanaman menggunakan inversi regresi linier. Jurnal Teknologi Informasi dan Ilmu Komputer. 12 (1), 153–164, from http://doi.org/10.25126/jtiik.2025129083.

[16] Candra, R. & Elvantio, Z. (2025). Pembuka kunci pintu ruang isolasi mandiri menggunakan suhu tubuh dengan notifikasi foto menggunakan konsep IoT. Jurnal Teknologi Informasi dan Ilmu Komputer. 12 (1), 93–98, from http://doi.org/10.25126/jtiik.2025128759.

[17] Chandola, V., Banerjee, A. & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys. 41 (3), from http://doi.org/10.1145/1541880.1541882.

[18] Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. Paper presented at the International Conference on Learning Representations (ICLR), San Diego, CA, USA. Retrieved from https://arxiv.org/abs/1409.0473.

[19] Sakurada, M. & Yairi, T. (2014). Anomaly detection using autoencoders with nonlinear dimensionality reduction. Paper presented at MLSDA Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, Australia, 4–11. Retrieved from https://dl.acm.org/doi/10.1145/2689746.2689747.

[20] Hariri, S., Kind, M. C., & Brunner, R. J. (2021). Extended isolation forest. IEEE Transactions on Knowledge and Data Engineering, 33(4), 1479–1489. From https://doi.org/10.1109/TKDE.2019.2947676.

[21] Schmidl, S., Wenig, P. & Papenbrock, T. (2022). Anomaly detection in time series: A comprehensive evaluation. Proceedings of the VLDB Endowment. 15 (9), 1779–1797. Retrieved from https://vldb.org/pvldb/vol15/p1779-wenig.pdf.

[22] Malhotra, P., Vig, L., Shroff, G. & Agarwal, P. (2015). Long short term memory networks for anomaly detection in time series. Paper presented at the 23rd European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, 89–94. Retrieved from https://www.esann.org/sites/default/files/proceedings/legacy/es2015-56.pdf.

[23] Wen, X., Wu, L. & Wang, Y. (2023). Deep learning for time series anomaly detection: A survey. IEEE Access. 11, 12345–12367. Retrieved from https://arxiv.org/html/2211.05244v3.

[24] Xu, J., Wu, H. & Chen, M. (2022). Anomaly Transformer: time series anomaly detection with association discrepancy. Paper presented at the International Conference on Learning Representations (ICLR). Retrieved from https://arxiv.org/abs/2110.02642.

[25] Liso, A., Cardellicchio, A., Patruno, C., Nitti, M., Ardino, P., Stella, E. & Renò, V. (2024). A review of deep learning-based anomaly detection strategies in Industry 4.0 focused on application fields, sensing equipment, and algorithms. IEEE Access. 12, 93911–93923, from http://doi.org/10.1109/ACCESS.2024.3424488.

Downloads

Published

30-06-2026

Issue

Vol. 12 No. 1 (2026): Juni 2026

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

(1) Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the journal.

(2) Publisher of JTMI: Jurnal Teknologi dan Manajemen Informatika is University of Merdeka Malang.

(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.