The week's pick
Random Articles
Reseach Article
MINDGUARD: An AI-Powered Smart Assistant for Alzheimer's Patients using Voice and Activity Recognition
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 86 |
| Year of Publication: 2026 |
| Authors: Fahmida Hakim Suchita, Saleha Akter Shetu, Most.Jannatul Fardous, Sumaya Akter, Md Zahurul Haque |
10.5120/ijca2026926486
|
Fahmida Hakim Suchita, Saleha Akter Shetu, Most.Jannatul Fardous, Sumaya Akter, Md Zahurul Haque . MINDGUARD: An AI-Powered Smart Assistant for Alzheimer's Patients using Voice and Activity Recognition. International Journal of Computer Applications. 187, 86 ( Mar 2026), 19-26. DOI=10.5120/ijca2026926486
Abstract
Alzheimer disease (AD) is a progressive neurological condition, which causes loss of memory, cognitive and impairment of daily functions. Faced with the current increase in the prevalence of AD globally, it is imperative to develop assistive technologies that would help to improve patient autonomy, safety, and caregiver burden. The modern innovations in artificial intelligence (AI), Internet of Things (IoT), mobile applications, and wearable devices have made it possible to create smart help systems to support Alzheimer patients. These systems use facial recognition, activity recognition, real time monitoring and location tracking to provide independent living and enhance communication. The review offers an in-depth analysis of the state-of-the-art assistive systems and compares methodologies and technological solutions as well as outcomes. The results indicate that AI-based diagnostic systems and IoT-based monitoring tools have a great potential to alleviate the issues related to AD care. Nevertheless, the challenge of usability, scalability, data imbalance, and patient privacy are critical and still cause difficulties. The paper wraps up by providing research analysis that include the framework suggested will be the integration of the Artificial Intelligence (AI), Internet of Things (IoT), and wearable technology to deliver the real-time assistance based on a platform that is related to a smartwatch. The system applies a voice recognition model trained with Mel Frequency Cepstral Coefficients (MFCC) features and a Convolutional Neural Network (CNN) on a self-created dataset of 345 voice samples categorized into family, friends, and unknown Speakers. This makes the device to identify familiar voices and provide contextual notifications and alerts. Furthermore, IoT-based modules monitor movement and activity in real-time, facilitating caregiver- patient communication. The results of the experiment indicate that the proposed model achieves encouraging results when it comes to the identification of the speaker, which confirms that it can be utilized in the real world. In the subsequent work, the optimization of the model will be determined so that lightweight processing on the device will be possible, data balance, and scalability will be improved, and it will be ensured that the model does not violate the ethics in long- term patient monitoring and in nature with clinical validation that fits well into the lifestyle of the patients.
References
- N. Aljojo, R. Al-Otaibi, A. Alshutayri, and A. Banjar, “Alzheimer assistant: a mobile application using machine learning,” Romanian Journal of Information Technology and Automatic Control, vol. 30, no. 4, pp. 7–26, 2020.
- T. A. Kadhim, N. S. Zghal, W. Hariri, and D. B. Aissa, “A Review of Alzheimer’s Disease and Emerging Patient Support Systems,” 2023 20th International Multi-Conference on Systems, Signals and Devices (SSD), 2023.
- M. Li, H. Liu, Y. Li, Z. Wang, Y. Yuan, and H. Dai, “Early diagnosis of Alzheimer’s disease using machine learning models,” China University of Petroleum–Beijing, Feb. 2024.
- L. N., S. M., V. S., A. R. K. P., S. M., G. S., and others, “Smart assistance systems for Alzheimer’s patients,” 2024 8th International Conference on Computational System and Information Technology for Sustainable Solutions (CSITSS), 2024
- R. Chakraborty, M. Pandharipande, C. Bhat, and S. K. Kopparapu, “Acoustic biomarkers for dementia identification,” TCS Research and Innovation, Mumbai, India, Feb. 2020.
- A. Balaji, H. V., A. P. N., and S. K. Kanithan, “SMART BIOMEDICAL ASSISTED SYSTEM FOR ALZHEIMER PATIENT,” 7th International Conference on Design Innovation, 2023.
- Wafa Ben Taleb, Ahmed Snoun, Tahani Bouchrika, and Olfa Jemai, “Reinforcement learning for assistance of Alzheimer’s disease patients,” 8th International Conference on Control, Design and Information Tech- nologies, 2022.
- P. K., A. Aftab, V. B. Citla, and S. Kamanth, “LSTM-Based Assistance for People with Alzheimer’s Disease,” Nitte Meenakshi Institute of Technology, 2023.
- Pashaei, H., Zareapoor, M., et al. (2023). Activity recognition using deep learning techniques for healthcare applications. IEEE Transactions on Neural Networks and Learning Systems.
- Abiwinanda, N. (2022). Real-time abnormal activity detection using convolutional neural networks. Journal of Ambient Intelligence and Humanized Computing.
- Li, Y., Wu, H., et al. (2024). Early diagnosis of Alzheimer’s disease using machine learning models. Expert Systems with Applications.
- M. M. Mielke, M. T. Ferretti, M. F. Iulita, K. Hayden, and A. S. Khachaturian, “Sex and gender in Alzheimer’s disease – Does itmat- ter?,” Alzheimer’s Dement., vol. 14, no. 9, pp. 1101–1103, 2018,doi: 10.1016/j.jalz.2018.08.003.
- K. M. Langa et al., “A comparison of the prevalence of dementia in the United States in 2000 and 2012,” JAMA Intern. Med., vol. 177, no. 1,pp. 51–58, 2017, doi: 10.1001/jamainternmed.2016.6807.
- A. Deb, J. D. Thornton, U. Sambamoorthi, and K. Innes, “Direct and indirect cost of managing Alzheimer’s disease and related dementias in the United States,” Expert Rev. Pharmacoeconomics Outcomes Res.,vol. 17, no. 2, pp. 189–202, 2017, doi:10.1080/14737167.2017.1313118.
- N. Saleh, A. Ali, and O. Ezzat, “Face Recognition-Based Smart Glass for Alzheimer’s Patients,” 2022 10th International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC), Cairo, Egypt, 2022, pp. 1-4, doi: 10.1109/JAC-ECC56395.2022.10044070.
- Z. Breijyeh and R. Karaman, “Comprehensive Review on Alzheimer’s Disease: Causes and Treatment,” Mol. J. Chem., vol. 25, no. 24, p.5789, 2020.
- Arlene J Astell “Technology and personhood in dementia care” Quality in Ageing Volume 7 Issue 1 March 2006.
- Ashok J. Bharucha, Vivek Anand, Jodi Forlizzi, Mary Amanda Dew, Charles F. Reynolds, Scott Stevens, Howard Wactlar”Intelligent Assis- tive Technology Applications to Dementia Care: Current Capabilities, Limitations, and Future Challenges” Am J Geriatr Psychiatry 17:2, February 2009.
- Eleanor Bantry White University College, Paul Montgomery University “Electronic tracking for people with dementia: An exploratory study of the ethical issues experienced by carers in making decisions about usage” Dementia 2014, Vol. 13(2) 216–232.
- Sara Paivaa and Carlos Abreua, “Low-Cost GPS Tracking for the Elderly and Alzheimer Patients” Procedia Technology 5 (2012 )793 – 802.
- Arkham Zahri Rakhmani, Lukito Edi Nugrohoi and Widyawani,Kurnianingsihi “Fall Detection System Using Accelerometer and Gyroscope Based on Smartphone” International Journal of Computer Science Issues, 2011, Vol. 8, No. 2, pp. 433-444.
- Hai Anh TRAN, Quynh Thu NGO and Van TONG” A new fall detection system on Android smartphone: application to an SDN-based IoT system “, 2017.
- Drew Dara-Abrams” Cognitive Surveying: A Framework for Mobile Data Collection, Analysis, and Visualization of Spatial Knowledge and Navigation Practices” pp. 138–153, 2008.
- Christoph Zetzsche, Torben Gerkensmeyer, Falko Schmid, Kerstin Schill “Sensorimotor Representation of Space: Application in Autonomous Systems and in a Wayfinding Assistant for Alzheimer’s Disease” pp. 212-224, 2012
Index Terms
Keywords