International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 05 | May 2025
p-ISSN: 2395-0072
www.irjet.net
Smart Elderly Assistant System Prof. Rajesh Bulbule1, Prathamesh Sonawane2, Bhavesh Choudhary3, Mayur Thube4 1 Professor, Department Of ENTC, Dr. D. Y. Patil Institute of Technology Pimpri, Pune, India
2,3,4UG Student, Department Of ENTC, Dr. D. Y. Patil Institute of Technology Pimpri, Pune, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - As the global population ages, many elderly individuals—especially those over 60—face distinct challenges in maintaining their independence and quality of life. Numerous older adults, particularly those living alone, lack consistent oversight and personal care, which can lead to significant health and safety issues. Without regular check-ins, problems like falls, medication mismanagement, and unreported emergencies can occur, often resulting in serious health complications or even tragic outcomes. These situations not only affect the individuals involved but also place emotional and financial burdens on their families and healthcare systems.
a decline. Currently a relatively young nation, India is on the path to becoming an aging society in the coming decades. When elderly individuals live alone, there is a significant risk that if they fall, no one will be there to help. This can result in severe consequences, including life-threatening injuries or even fatalities. To mitigate such risks, it is crucial to implement systems that can detect falls and promptly alert caregivers, family members, or emergency services. Various studies have proposed monitoring home appliances to assess the well-being of elderly individuals. However, these systems often struggle to adapt to changes in daily habits. Real-time fall detection and interpreting an elderly person’s expressions remain challenging. While surveillance cameras are commonly used in public areas, their application in private homes is limited due to privacy issues. Wearable devices such as rings, pendants, and watches can assist in fall detection, but they depend on the elderly wearing them consistently and keeping them charged, which may not always be feasible.
To tackle these challenges, innovative e-health solutions are becoming increasingly vital. Advances in technology—especially artificial intelligence (AI) and the Internet of Things (IoT)—have the potential to transform elder care. Smart sensors, wearable devices, and intelligent monitoring systems can provide more than just fall prevention; they can deliver continuous, real-time support tailored to each individual’s needs. Picture an AI-powered assistant that re- minds an elderly person to take their medications, tracks their overall health, monitors their emotional well-being, and even alerts caregivers in case of an emergency. These smart solutions create a safety net, enabling older adults to live more independently while ensuring they are never truly alone. By embracing these technologies, we can help our aging loved ones feel more secure, supported, and connected in their daily lives.
Research in robot therapy has indicated that user-friendly robots can offer support without inducing stress for their users.
2. LITERATURE REVIEW In recent years, the use of machine learning and deep learning models in healthcare has surged, significantly enhancing diagnosis, treatment, and patient care, particularly in monitoring and assisting the elderly. These models are highly effective in detecting health issues and ensuring safety, offering improved accuracy and efficiency. Among many methodologies, this project draws from several key studies in the domain.
Index terms: Artificial Intelligence (AI) Internet of Things (IoT) E-health Smart Sensors.
1.INTRODUCTION
Convolutional neural networks (CNNs) like ResNet50 and MobileNetv2 have been discussed extensively in the literature for image-based classification tasks. ResNet50, a popular architecture for residual learning, helps address the vanishing gradient problem that arises in deep networks, making it suitable for complex pattern identification. MobileNetv2, on the other hand, is a lightweight architecture that provides an extremely efficient solution for mobile applications, particularly in scenarios where high accuracy must be achieved with low computational power. This makes MobileNetv2 a suitable choice especially in real-time mobile solutions for elderly care.
In 2022, there were approximately 149 million individuals aged 60 and older in the country, accounting for about 10.5 percent of the total population as of July 1. This figure is projected to double by 2050, reaching 20.8 percent, which translates to around 347 million people. By the end of the century, the elderly will represent over 36 percent of the nation’s population. By 2046, the elderly population in India is expected to exceed the number of children aged 0-14 years. Additionally, the proportion of individuals aged 15–59 years will also see
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 1841