IoT-Based Smart Home Automation System with Voice Control, Face Detection, and Intelligent Sensor Integration

Abstract

This paper presents a comprehensive Smart Home Automation System built on Internet of Things (IoT) technology, designed to deliver intelligent, remote, and voice-controlled management of household appliances including lights, fans, washing machines, and air conditioners. The system is implemented using an Arduino Uno microcontroller interfaced with a 4-channel relay module, an HC-05 Bluetooth serial module, an LDR (Light Dependent Resistor) sensor, and resistive voltage divider networks. A custom-developed Android mobile application enables remote appliance control via Bluetooth, supplemented by a voice command feature using the Android SpeechRecognizer API and a face detection access control module using a lightweight on-device machine learning model. Additional features include per-appliance timer scheduling and cumulative daily usage-limit enforcement. Experimental validation confirmed relay response latencies of 45–80 milliseconds, voice command recognition accuracy above 93% in quiet indoor conditions, and face detection accuracy of 94% under standard lighting. LDR-based automatic lighting demonstrated accurate ambient-responsive switching. The system provides a cost-effective, scalable smart home solution without dependency on proprietary cloud platforms.

Introduction

This paper presents a low-cost IoT-based Smart Home Automation System that integrates appliance control, voice commands, automatic lighting, timer scheduling, and face-recognition security into a single platform. Traditional home management often leads to energy wastage, lack of remote control, limited accessibility for elderly or disabled users, and weak access control. The proposed system addresses these issues using an Arduino Uno, HC-05 Bluetooth module, relay circuits, LDR sensor, and an Android application.

The system controls four household appliances—lights, fans, air conditioners, and washing machines—through Bluetooth communication without requiring internet connectivity. The Android app provides manual control, timer scheduling, usage monitoring, voice-command operation, and face-authentication-based access. Automatic lighting is achieved using an LDR sensor that turns lights on or off depending on ambient light conditions.

The architecture follows a two-tier design consisting of a hardware layer (Arduino and sensors) and a mobile application layer. Communication between the smartphone and Arduino uses a simple Bluetooth text-command protocol. Security is enhanced through on-device face detection, which grants access only to authorized users and includes a lockout mechanism after repeated failed attempts.

Experimental results show reliable performance, with relay response times between 45–80 ms, voice recognition accuracy above 93% in quiet environments, and face recognition accuracy of 94% under good lighting conditions. The LDR-based lighting system operated accurately across different lighting scenarios, while timer and usage-limit functions successfully reduced unnecessary appliance operation.

Conclusion

This paper has presented the design, implementation, and experimental validation of a feature-complete IoT-based Smart Home Automation System. The system successfully integrates an Arduino Uno microcontroller, 4-channel relay module, HC-05 Bluetooth module, and LDR sensor with a custom Android application incorporating voice command recognition, face detection access control, timer scheduling, and usage-limit enforcement. Experimental results confirm relay response latencies of 45–80 milliseconds, voice command accuracy above 93% under standard indoor conditions, face detection accuracy of 94% for enrolled users, and reliable automatic LDR-based lighting control. Bluetooth session stability was maintained across 4-hour test sessions. The complete hardware platform is replicable at a component cost below INR 2,000, representing one of the most cost-accessible smart home automation implementations available. Future work will focus on replacing the HC-05 Bluetooth module with an ESP32 Wi-Fi module to enable internet-based remote control, integrating real-time power consumption monitoring via ACS712 current sensors, upgrading to full face recognition for personalized automation profiles, and extending the mobile application to a cross-platform Flutter implementation with a companion web dashboard.

References

[1] K. Gill, S. H. Yang, F. Yao, and X. Lu, “A zigbee-based home automation system,” IEEE Trans. Consumer Electron., vol. 55, no. 2, pp. 422–430, May 2009. [2] R. Piyare and M. Tazil, “Bluetooth based home automation system using cell phone,” in Proc. 15th IEEE Int. Symp. Consumer Electron. (ISCE), Singapore, 2011, pp. 192–195. [3] D. Singh and B. Kumar, “Smart energy management system using IoT and light dependent resistor,” Int. J. Electr. Comput. Eng. (IJECE), vol. 8, no. 4, pp. 2088–2708, Aug. 2018. [4] C. Bhatt, I. Kumar, V. Vijayakumar, K. U. Singh, and A. Kumar, “The state of the art of deep learning models in medical science and their challenges,” Multimedia Syst., vol. 27, pp. 599–613, 2021. [5] J. Vanus et al., “Smart home smart energy management and its communication,” IFAC-PapersOnLine, vol. 48, no. 4, pp. 117–122, 2015. [6] Android Developers, “SpeechRecognizer — Android API Reference,” Google LLC, 2024. [7] T. Rault, A. Bouabdallah, and Y. Challal, “Energy efficiency in wireless sensor networks: A top-down survey,” Comput. Netw., vol. 67, pp. 104–122, Jul. 2014. [8] C. Perera, A. Zaslavsky, P. Christen, and D. Georgakopoulos, “Context aware computing for the

Copyright

Copyright © 2026 Piyush Tyagi, Shaswat Kotnala, Shishant Pal, Naman Sharma, Mrs. Shalini Goel. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.