Supervised Machine Learning Based Behavioral Pattern Recognition for Autonomous Non-Invasive Smart Switch Actuation Using a Fingerbot System

The proliferation of smart home technologies has intensified demand for adaptive, low-cost automation solutions deployable without altering existing electrical infrastructure. This paper presents an AI-driven Fingerbot, a non-invasive electromechanical actuator that physically operates conventional wall switches through a micro servo motor governed by an ESP32-C3 microcontroller. Unlike solutions that require electrical rewiring or hardware replacement, the device mounts externally on standard switches and automates their operation through learned behavioral patterns. Three supervised classifiers; Logistic Regression, Decision Tree, and Random Forest were trained on 1,440 time-stamped user interaction records capturing hour, minute, day of week, and weekend indicator features to predict binary switch states. The Decision Tree classifier achieved 99.7% accuracy, 99.6% precision, and 99.4% recall. Random Forest recorded 97.1% accuracy with the highest precision of 99.8%, while Logistic Regression served as a linear baseline at 87.9% accuracy. Response time evaluation across three control modes showed that physical switch interaction averaged 311.67 ms (maximum 400 ms), Wi-Fi virtual control averaged 2,597.33 ms (maximum 3,750 ms), and mobile hotspot control averaged 3,257.67 ms (maximum 5,750 ms). The embedded AI activation logic commenced switch-on at approximately between 18:35 to 18:45 and enforced mandatory deactivation at 23:59 to minimize unnecessary energy consumption. Monthly energy monitoring of a 25 W test load yielded figures ranging from 121.80 kWh to 143.53 kWh across three consecutive months. The results confirm that integrating lightweight machine learning with low-cost actuator hardware constitutes a practical and cost-effective pathway for retrofit smart home automation.

Smart home automation; Fingerbot actuator

1. D. Xu, W. He, and S. Li, "Internet of Things in industries: A survey," IEEE Trans. Ind. Informat., vol. 10, no. 4, pp. 2233-2243, 2014. [Google Scholar] [Crossref]

2. A. Zanella, N. Bui, A. Castellani, L. Vangelista, and M. Zorzi, "Internet of Things for smart homes: A comprehensive survey," IEEE Commun. Surveys Tuts., vol. 16, no. 1, pp. 1190-1220, 2014. [Google Scholar] [Crossref]

3. R. Singh and S. Kumar, "Non-intrusive smart home automation using actuator-based IoT devices," IEEE Sensors J., vol. 23, pp. 8421-8430, 2023. [Google Scholar] [Crossref]

4. M. A. Kholik, N. A. Fajrin, and S. F. Budi, "Design and implementation of a smart home system with the Internet of Things (IoT) using ESP32," Inspirasi J. Teknol. Inf. Komunikasi, vol. 13, no. 1, pp. 22-30, 2023. [Google Scholar] [Crossref]

5. Y. Yang, W. Wang, P. Peng, J. Wang, and Y. Zhang, "User behavior learning for smart home energy management using machine learning," IEEE Access, vol. 9, pp. 118452-118463, 2021. [Google Scholar] [Crossref]

6. A. S. Ali, M. Ghani, K. Talib, and A. S. Ahmad, "Intelligent home automation using machine learning and IoT," IEEE Access, vol. 10, pp. 55840-55852, 2022. [Google Scholar] [Crossref]

7. M. M. Gad, W. Gad, T. Abdelkader, and K. Naik, "Personalized smart home automation using machine learning: Predicting user activities," Sensors, vol. 25, no. 19, p. 6082, 2025, doi: 10.3390/s25196082. [Google Scholar] [Crossref]

8. J. Park and H. Kim, "Predictive control of smart home devices based on user behavior modeling," IEEE Trans. Consum. Electron., vol. 68, no. 3, pp. 289-298, 2022. [Google Scholar] [Crossref]

9. S. Alotaibi and M. A. Hossain, "User trust and acceptance of intelligent home automation systems with manual override," IEEE Access, vol. 8, pp. 168345-168356, 2020. [Google Scholar] [Crossref]

10. D. Chikurtev, B. Karkov, and E. Blagoeva, "An overview of ESP32 microcontroller application in embedded systems, robotics and IoT," Springer Proc. Math. Stat., vol. 514, 2026. [Google Scholar] [Crossref]

11. S. O. Lawrence and D. M. Soomro, "IoT-based smart home switch system using the ESP32 microcontroller," Evol. Electr. Electron. Eng., vol. 3, no. 2, pp. 856-862, 2022. [Google Scholar] [Crossref]

12. H. A. Garcia-Vazquez et al., "Design and implementation of the E-Switch for a smart home," Sensors, vol. 21, no. 11, pp. 1-17, 2021. [Google Scholar] [Crossref]

13. P. Kumar, D. S. K. Singh, M. S. H. A. Mishra, and R. H. S. P. Sharma, "Design and fabrication of IoT switch with manual override," IOP Conf. Ser.: Mater. Sci. Eng., 2021. [Google Scholar] [Crossref]

14. P. Manikannan and M. S. Gopal, "IoT enabled smart switch with user-friendly electrical interfacing," in Proc. ICSTSN, 2022, pp. 1-6. [Google Scholar] [Crossref]

15. A. Almusaed, I. Yitmen, and A. A. Al-Amri, "Enhancing smart home design with AI models: A case study of living spaces implementation review," Energies, vol. 16, no. 6, p. 2636, 2023. [Google Scholar] [Crossref]

16. L. Chen, Y. Zhang, and H. Wang, "Lightweight machine learning models for edge-based smart home applications," IEEE Internet Things J., vol. 9, no. 7, pp. 5150-5160, 2022. [Google Scholar] [Crossref]

17. M. Salama and B. Raslen, "MQTT in action: Building reliable and scalable home automation systems," Sakarya Univ. J. Comput. Inf. Sci., vol. 7, no. 3, pp. 494-509, 2024. [Google Scholar] [Crossref]

18. H. Liu, Y. Wang, and X. Zhang, "Time-series prediction of appliance usage for smart homes using deep learning," IEEE Access, vol. 11, pp. 10321-10332, 2023. [Google Scholar] [Crossref]

19. W. A. Abd Elkhalik, "AI-driven smart homes: Challenges and opportunities," J. Intell. Syst. Internet Things, vol. 8, no. 2, pp. 54-62, 2023. [Google Scholar] [Crossref]

20. P. R. Kumar and S. K. Panda, "Data-driven decision making in IoT-based smart home automation," J. Ambient Intell. Humaniz. Comput., vol. 12, no. 4, pp. 3891-3902, 2021. [Google Scholar] [Crossref]

21. R. A. Rahman, M. S. H. Shah, and G. M. A. Alam, "AI-enabled smart home systems: Architecture, challenges, and future directions," IEEE Access, vol. 12, pp. 15011-15025, 2024. [Google Scholar] [Crossref]

22. A. R. K. Singh and K. Singh, "IoT based smart switchboard technology for smart home," J. Univ. Shanghai Sci. Technol., vol. 23, no. 9, pp. 724-737, 2021. [Google Scholar] [Crossref]

23. T. M. Thomas et al., "Analysis of challenges and solutions of IoT in smart grids using AI and machine learning techniques: A review," Electronics, vol. 12, no. 1, p. 242, 2023. [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset