Scholarlink

Bedridden and the maimed elderly person lost their hope latterly mental illness also occupied them. The part of the body and mental health that gets affected due to their age circumstances like people aged over 60. Worldwide an aging population increases and it leads to the demand for health services. Elderly bedridden person counts their days in bed. These issues should be detected and steps can be taken to improve their health and mental strength too. IoT-oriented elder care devices have been widely used in this world; Even though the existing systems are manually operated by the elders and caretakers, this is not practical during emergencies also they fail to focus on maim and bedridden people. The presented work is an entirely automatic alerting system using a mobile application, which does not require manual operation and saves time for the caretaker, helping them to nurse another elder person. Maim, paralyzed, and bedridden people can interact with caretakers with the help of an elder/patient end mobile application with an easily understandable user interface design, and it will help them mentally stable. AI bed consists of IoT sensors, which are connected to an ESP8266, and an IoT camera is connected to a Raspberry Pi. Elder’s vitals are collected and stored on Google firebase (Ramani et al. in 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, 2022, pp. 1192–1197, 2022 1) cloud DB using a machine-learning approach. Elder’s dataset changes are identified frequently if an abnormality is predicted, an emergency alert will be triggered to the caretakers through the mobile application. In this connection, a machine-learning framework that brings enterprise applications closer to data sources is enabled with mobile applications and IoT devices. The presented work fully focused on K-means clustering, DT, and XG boost. These algorithms work in three phases of prediction techniques. Phase1: Monitoring elders sleeping time using KM cluster. Phase2: Analyzing patient live vitals dataset using DT. Phase3: Health issue future prediction through elders live datasets compared with past vital history using XG Boost to predict their upcoming issues.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimized AI Bed for Maim and Bedridden Elder Person Based on Mobile Application

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • T. Jones Daniel,
  • R. Sundar Rajan

摘要

Bedridden and the maimed elderly person lost their hope latterly mental illness also occupied them. The part of the body and mental health that gets affected due to their age circumstances like people aged over 60. Worldwide an aging population increases and it leads to the demand for health services. Elderly bedridden person counts their days in bed. These issues should be detected and steps can be taken to improve their health and mental strength too. IoT-oriented elder care devices have been widely used in this world; Even though the existing systems are manually operated by the elders and caretakers, this is not practical during emergencies also they fail to focus on maim and bedridden people. The presented work is an entirely automatic alerting system using a mobile application, which does not require manual operation and saves time for the caretaker, helping them to nurse another elder person. Maim, paralyzed, and bedridden people can interact with caretakers with the help of an elder/patient end mobile application with an easily understandable user interface design, and it will help them mentally stable. AI bed consists of IoT sensors, which are connected to an ESP8266, and an IoT camera is connected to a Raspberry Pi. Elder’s vitals are collected and stored on Google firebase (Ramani et al. in 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, 2022, pp. 1192–1197, 2022 1) cloud DB using a machine-learning approach. Elder’s dataset changes are identified frequently if an abnormality is predicted, an emergency alert will be triggered to the caretakers through the mobile application. In this connection, a machine-learning framework that brings enterprise applications closer to data sources is enabled with mobile applications and IoT devices. The presented work fully focused on K-means clustering, DT, and XG boost. These algorithms work in three phases of prediction techniques. Phase1: Monitoring elders sleeping time using KM cluster. Phase2: Analyzing patient live vitals dataset using DT. Phase3: Health issue future prediction through elders live datasets compared with past vital history using XG Boost to predict their upcoming issues.