MindHive: An HCI-Based Assistive Smart Home System for Paralyzed Individuals

Abstract

Paralysis is a severe medical condition that affects millions of people worldwide, often resulting in the partial or complete loss of voluntary motor functions. For individuals living with paralysis, basic daily activities can become significant challenges, impacting physical well-being and increasing depen-dence. This paper presents MindHive, an assistive smart home system designed to address these challenges. The system inte-grates Human–Computer Interaction (HCI), Electromyography (EMG), and Internet of Things (IoT) technologies to empower paralyzed individuals. We detail the system’s architecture, which leverages non-invasive surface EMG signals to control household appliances and communication tools. The algorithmic approach, including signal preprocessing, feature extraction, and machine learning classification (LDA, SVM, and 1D-CNN), is discussed. MindHive focuses on creating an adaptive, affordable, and user-friendly environment, transforming minimal muscle activity into actionable smart home commands, thereby aiming to restore a degree of autonomy to its users.

Introduction

The text reviews assistive smart home technologies designed to improve independence for individuals with paralysis, who often struggle with basic daily activities and rely heavily on caregivers. Advances in Human–Computer Interaction (HCI), Brain–Computer Interfaces (BCI), Electromyography (EMG), and Internet of Things (IoT) systems have enabled new solutions that translate biological signals into control commands for home automation and communication.

The review focuses on how EMG- and BCI-based HCI systems can be applied to smart homes, highlighting ongoing challenges such as accuracy, usability, adaptability, and cost. It establishes the foundation for MindHive, a proposed assistive smart home framework tailored to paralyzed users.

The theoretical background explains the roles of HCI (accessible interface design), BCI (direct brain-signal control), EMG (muscle-signal detection for faster, less invasive control), and IoT (connected device automation). Their integration enables hybrid, more reliable assistive systems.

MindHive’s technical framework centers on surface EMG signal acquisition, edge computing, machine learning–based signal classification, and secure IoT communication. EMG signals are filtered, segmented, and processed to extract features, which are then classified using algorithms such as LDA, SVM, or 1D-CNNs. Decision smoothing and safety checks reduce false activations before commands are sent to smart home devices.

Conclusion

This paper presented MindHive, an HCI-based assistive smart home system designed for paralyzed individuals. The system integrates EMG-based signal acquisition, machine learning classification, and IoT automation to provide a non-invasive and adaptive means of environmental control. By translating minimal muscle activity into commands for smart home devices, MindHive aims to significantly improve accessibility, independence, and quality of life for individuals with severe motor impairments. The methodological frame-work, technological components, and evaluation strategies have been detailed, highlighting the system’s potential. Future work will focus on clinical validation, enhancing model adaptability through cloud-based learning, and developing low-cost, wearable hardware to ensure broader accessibility.

References

[1] R. Mahajan and I. Siddavatam, “Phishing Website Detection Using Machine Learning Algorithms,” 2018. [2] IEEE Editorial Style Manual, IEEE Publications, 2021. [3] A. Subasi, “Automatic Detection of EMG Signals Using Machine Learning,” Biomedical Signal Processing, 2020. [4] S. J. Pan et al., “Transfer Learning for Human Activity Recognition Using EMG,” IEEE Transactions on Neural Systems, 2019. [5] M. M. Hassan, M. Z. Uddin, A. Mohamed, and A. Almogren, “A robust human activity recognition system using smartphone sensors and deep learning,” Future Generation Computer Systems, vol. 81, pp. 307–313, 2018. [6] R. Piyare, “Internet of Things-based smart home automation system for disabled persons,” in Proc. 2nd Int. Conf. Trends Electronics and Informatics (ICOEI), Tirunelveli, India, 2018, pp. 1046–1050. [7] A. Sears and J. A. Jacko, The Human–Computer Interaction Handbook: Fundamentals, Evolving Technologies and Emerging Applications. CRC Press, 2007. [8] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan, “Brain–computer interfaces for communication and control,” Clinical Neurophysiology, vol. 113, no. 6, pp. 767–791, 2002. [9] R. F. F. da Silva, E. L. M. Naves, and A. O. Andrade, “EMG signal-based control of a smart home environment for subjects with motor disabilities,” Journal of Ambient Intelligence and Humanized Computing, vol. 11, no. 8, pp. 3385–3399, 2020. [10] S. M. R. Islam, D. Kwak, M. H. Kabir, M. Hossain, and K. S. Kwak, “The Internet of Things for health care: a comprehensive survey,” IEEE Access, vol. 3, pp. 678–708, 2015. [11] R. Leeb and G. Pfurtscheller, “A hybrid BCI based on sensorimotor rhythms and SSVEPs for the control of an orthosis,” IEEE Trans. Biomedical Engineering, vol. 57, no. 12, pp. 2887–2895, 2010. [12] A. Banks and R. Gupta, “MQTT for sensor networks,” IEEE Internet of Things Journal, vol. 1, no. 2, pp. 120–128, 2014. [13] K. B. Englehart and B. S. Hudgins, “A robust, real-time control scheme for multifunction myoelectric control,” IEEE Trans. Biomedical Engineering, vol. 50, no. 7, pp. 848–854, 2003. [14] M. Atzori, A. Gijsberts, C. Castellini, B. Caputo, and H. J. Mu¨ller, “Deep learning with convolutional neural networks for EMG signal classification in big data,” IEEE Trans. Industrial Informatics, vol. 13, no. 4, pp. 1852–1861, 2017. [15] A. Phinyomark, S. Limsakul, and P. Phukpattaranont, “A novel feature extraction for robust EMG pattern recognition,” Journal of Computing, vol. 1, no. 1, pp. 71–80, 2009. [16] J. Brooke, “SUS: A ‘quick and dirty’ usability scale,” in Usability Evaluation in Industry, P. W. Jordan et al., Eds. London, UK: Taylor & Francis, 1996, pp. 189–194. [17] A. J. Jara, M. A. Zamora, and A. F. G. Skarmeta, “An Internet of Things–based personal device for diabetes therapy management in ambient assisted living (AAL),” Personal and Ubiquitous Computing, vol. 17, no. 6, pp. 1201–1212, 2013. [18] Y. S. Ha et al., “A wearable sensor-based smart home system for the elderly,” in Proc. 8th Int. Conf. Sensing Technology (ICST), Liverpool, UK, 2014, pp. 433–438. [19] M. A. Al-Garadi, A. Mohamed, A. K. Al-Ali, X. Du, I. Ali, and M. Guizani, “A survey of machine and deep learning methods for Internet of Things (IoT) security,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 1646–1685, 2020. [20] S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2010. [21] M. Benatti, L. Benini, E. Farella, and B. Milosevic, “Analysis of EMG-based hand gesture recognition using low-power wearable devices,” IEEE Trans. Biomedical Circuits and Systems, vol. 10, no. 6, pp. 1088–1096, 2016. [22] F. J. Ortiz, C. C. Parra, and M. T. Rivas, “IoT-based adaptive smart home for the elderly and disabled,” Sensors, vol. 21, no. 13, pp. 4359–4371, 2021. [23] G. Kumar and R. P. S. Chandna, “Design and development of an IoT-based home automation system for paraplegic patients,” IEEE Access, vol. 9, pp. 128344–128357, 2021. [24] T. Yang, Y. Huang, J. Zhang, and S. H. Chen, “Surface EMG pattern recognition with feature fusion for prosthetic control,” IEEE Trans. Human-Machine Systems, vol. 49, no. 1, pp. 28–37, 2019. [25] H. Zhou, Y. Chen, and Z. Wu, “A cloud-edge collaborative architecture for real-time IoT healthcare monitoring,” IEEE Internet of Things Journal, vol. 8, no. 17, pp. 13428–13439, 2021.

Copyright

Copyright © 2026 Mrs. Sindhu M. P., Devika Subhash, Giana Don, Yeldho Mathai, Sivani R Nair. 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.