@article{10.11648/j.ijssn.20251302.14,
  author = {Blossom Oluwakorede Remi-Ofakunrin and Gabriel Babatunde Iwasokun and Edafe John Atajeromavwo and Raphael Olufemi Akinyede and Olufunso Alowolodu and Samuel Oluwatayo Ogunlana and David Bamidele Adewole and Ednah Olubunmi Aliyu},
  title = {Design of a Framework for Switch Power Control Using Voice Signal
},
  journal = {International Journal of Sensors and Sensor Networks},
  volume = {13},
  number = {2},
  pages = {56-64},
  doi = {10.11648/j.ijssn.20251302.14},
  url = {https://doi.org/10.11648/j.ijssn.20251302.14},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijssn.20251302.14},
  abstract = {Establishing systems that specifically control electric power switches based on the practical implementation of Artificial Intelligence in everyday life reduces the likelihood of accidental switch activation and potentially increases security by ensuring it responds only to authorised users. Individuals with physical disabilities also require systems devoid of direct human interventions and physical interactions to control electrical and power switches. Existing methods for achieving these tasks include smart objects, the Internet of Things, and biometric technologies, with their attendant strengths and weaknesses. This paper presents the design of a voice signal framework for remote control of power switches. The framework uses a voice sensor connected to an Arduino microcontroller to amplify the volume of the user’s voice, while a voice sensor connected to a power switch relay is used to capture the voice signal for registration, training, verification and processing. The Arduino Nano 33 BLE Sense Rev 2 microcontroller sensor combines a tiny form factor with the capability to operate TinyML and TensorFlow Lite environment sensors while running at reconfigurable operating voltage. The switch relay regulates a high voltage to a minimum acceptable level based on integration with the Arduino microcontrollers. The framework also requires an external ESP8266/ESP32 Wi-Fi module to establish a connection between the microcontroller and the network as well as simple TCP/IP connections using Hayes-style commands. The system requires a power switch, an electromechanical device that uses the flow of electric current to open or close an electrical circuit. The user voice recognition is based on Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) networks. The combination of these two models guarantees an effective capturing of temporal dependencies in sequential data typical of audio signals.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Design of a Framework for Switch Power Control Using Voice Signal

AU  - Blossom Oluwakorede Remi-Ofakunrin
AU  - Gabriel Babatunde Iwasokun
AU  - Edafe John Atajeromavwo
AU  - Raphael Olufemi Akinyede
AU  - Olufunso Alowolodu
AU  - Samuel Oluwatayo Ogunlana
AU  - David Bamidele Adewole
AU  - Ednah Olubunmi Aliyu
Y1  - 2025/11/22
PY  - 2025
N1  - https://doi.org/10.11648/j.ijssn.20251302.14
DO  - 10.11648/j.ijssn.20251302.14
T2  - International Journal of Sensors and Sensor Networks
JF  - International Journal of Sensors and Sensor Networks
JO  - International Journal of Sensors and Sensor Networks
SP  - 56
EP  - 64
PB  - Science Publishing Group
SN  - 2329-1788
UR  - https://doi.org/10.11648/j.ijssn.20251302.14
AB  - Establishing systems that specifically control electric power switches based on the practical implementation of Artificial Intelligence in everyday life reduces the likelihood of accidental switch activation and potentially increases security by ensuring it responds only to authorised users. Individuals with physical disabilities also require systems devoid of direct human interventions and physical interactions to control electrical and power switches. Existing methods for achieving these tasks include smart objects, the Internet of Things, and biometric technologies, with their attendant strengths and weaknesses. This paper presents the design of a voice signal framework for remote control of power switches. The framework uses a voice sensor connected to an Arduino microcontroller to amplify the volume of the user’s voice, while a voice sensor connected to a power switch relay is used to capture the voice signal for registration, training, verification and processing. The Arduino Nano 33 BLE Sense Rev 2 microcontroller sensor combines a tiny form factor with the capability to operate TinyML and TensorFlow Lite environment sensors while running at reconfigurable operating voltage. The switch relay regulates a high voltage to a minimum acceptable level based on integration with the Arduino microcontrollers. The framework also requires an external ESP8266/ESP32 Wi-Fi module to establish a connection between the microcontroller and the network as well as simple TCP/IP connections using Hayes-style commands. The system requires a power switch, an electromechanical device that uses the flow of electric current to open or close an electrical circuit. The user voice recognition is based on Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) networks. The combination of these two models guarantees an effective capturing of temporal dependencies in sequential data typical of audio signals.
VL  - 13
IS  - 2
ER  - 

Copy | Download