Towards Intelligent Care: Human Behavior Analysis Using Energy Consumption and Door Operation Patterns in the Internet of Care Things

Sokulieva, Svitlana; Twieg, Ibrahim

doi:10.25673/123089

Proceedings of International Conference on Applied Innovation in IT · 2025/12/22 · Vol. 13 · Issue 5 · pp. 613–619

Towards Intelligent Care: Human Behavior Analysis Using Energy Consumption and Door Operation Patterns in the Internet of Care Things

Svitlana Sokulieva, Ibrahim Kovan and Stefan Twieg

📄 Download PDF DOI: 10.25673/123089

Abstract

The analysis of human behavior is an interdisciplinary science aimed at recognizing, describing, and predicting patterns of human behavior and emotional states. With the development of sensor technologies and data-driven approaches, new opportunities have emerged for observing and modeling everyday human activity. This study is based on a real-world dataset collected over one month from five participants in a residential environment. The data were gathered using environmental sensors, specifically contact sensors and energy consumption sensors, which enabled monitoring of user interactions with their surroundings. A set of statistical and machine learning methods was applied, including K-means clustering, correlation analysis, time-series representation, calculation of mean values, and aggregation of correlations. The results show how contact sensors and energy consumption sensors are related, how daily load is distributed, how periodic the data are, which sensors behave in a similar way within groups and across the system, and how individual behavioral models of each user can be formed. These findings highlight the potential of sensor-based analysis for advancing behavioral research and its practical applications.

Keywords

Human Behavior Analysis Unsupervised Learning Clustering Pearson Correlation Environmental Sensors Internet-of-Care-Things (IoCT) Intelligent Algorithm Anomaly Detection.

References

World Health Organization, ADVOCACY BRIEF: Social isolation and loneliness among older people, Jul. 2021. [Online]. Available: https://iris.who.int/bitstream/handle/10665/343206/9789240030749-eng.pdf?sequence=1.
P. Müller et al., “Making complex technologies accessible through simple controllability: Initial results of a feasibility study,” Applied Sciences, vol. 15, no. 2, p. 1002, 2025, doi: 10.3390/app15021002.
S. Essahraui et al., “Human behavior analysis: a comprehensive survey on techniques, applications, challenges, and future directions,” IEEE Access, vol. 13, pp. 128379–128419, 2025, doi: 10.1109/ACCESS.2025.3589938.
H. Liu, H. Gamboa, and T. Schultz, “Sensor-based human activity and behavior research: where advanced sensing and recognition technologies meet,” Sensors, vol. 23, no. 1, p. 125, 2023, doi: 10.3390/s23010125.
Y. Li, G. Yang, Z. Su, S. Li, and Y. Wang, “Human activity recognition based on multienvironment sensor data,” Information Fusion, vol. 91, pp. 47–63, 2023, doi: 10.1016/j.inffus.2022.10.015.
I. Kovan and S. Twieg, “Forecasting the energy consumption impact of electric vehicles by means of machine learning approaches,” in Proc. Int. Conf., 2022, doi: 10.1201/9781003293989-3.
P. Malik et al., “An analysis of time series analysis and forecasting techniques,” IJARCCE, vol. 9, 2023.
M. N. Martinez and M. J. Bartholomew, “What does it ‘mean’? A review of interpreting and calculating different types of means and standard deviations,” Pharmaceutics, vol. 9, no. 2, p. 14, 2017, doi: 10.3390/pharmaceutics9020014.
A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data,” Information Sciences, vol. 622, pp. 178–210, 2023, doi: 10.1016/j.ins.2022.11.139.
P. Sedgwick, “Pearson's correlation coefficient,” BMJ, vol. 345, p. e4483, 2012, doi: 10.1136/bmj.e4483.
P. Schober, C. Boer, and L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesthesia & Analgesia, vol. 126, no. 5, pp. 1763–1768, May 2018, doi: 10.1213/ANE.0000000000002864.