Wristband for Monitoring the Safety of Elderly People Using IoT and Deep Learning Algorithms


  • Mansi Lakshmi Gidugu
  • Krishna Guptha Yanduri
  • Manoj Kumar Paliviri
  • Rajanikanth Aluvalu


This abstract presents a comprehensive solution for fall detection and medication reminders by integrating deep learning techniques with a mobile application and sensor-equipped wristband. The system analyzes real-time sensor data from the wristband using advanced deep learning algorithms, accurately distinguishing between regular activities and potential fall events. Upon detecting a fall, the system activates an alarm mechanism, promptly notifying caregivers or medical professionals for immediate assistance. Additionally, the mobile application serves as a personalized assistant, allowing users to schedule medication reminders effortlessly by capturing an image of their prescription. The seamless integration of fall detection, alarm systems, and medication reminders enhances user safety and promotes proactive healthcare management. Two deep learning models are incorporated into the system architecture: Model-1 leverages Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) layers for spatial and temporal analysis of accelerometer data, while Model-2 combines Bi-LSTM and Conv1D layers for enhanced feature extraction. Through this synergistic combination of technology, the system empowers users to maintain independence while ensuring prompt assistance during fall events and facilitating medication adherence. This abstract highlights the potential of technology-driven solutions to address healthcare challenges and improve quality of life for individuals.


Download data is not yet available.




How to Cite

Mansi Lakshmi Gidugu, Krishna Guptha Yanduri, Manoj Kumar Paliviri, & Rajanikanth Aluvalu. (2024). Wristband for Monitoring the Safety of Elderly People Using IoT and Deep Learning Algorithms . International Journal of Computer Information Systems and Industrial Management Applications, 16(3), 22. Retrieved from https://cspub-ijcisim.org/index.php/ijcisim/article/view/718



Original Articles