Scholarlink

In order to collect data regarding people and surroundings for many uses, mobile communications and the Internet of Things (IoT) have emerged in recent years. In smart homes, aging and disabled inhabitants are particularly challenging to remotely monitor due to routine behaviors that could cause accidents, such as falls. Fall is measured as a main issue due to the fact that might cause older people to experience post-traumatic difficulties. It is therefore essential to identify older adults who fall in smart homes as soon as probable so as to amplify their probability of survival. These days, fall detection identification systems for smart homecare are required due to wearables, smart phones, wearable artificial intelligence (AI), and various other technologies. Frequent fall detection can assist in identifying the person whom has fallen and make it possible to provide them with immediate medical assistance. Operators of current wearable technologies may find it unpleasant. In this sense, the project concept provides a camera-based fall recognition system that monitors a person’s motions and any falls that may occur. The CNN-Inception v3 deep convolutional neural network-based IoT-empowered Elderly Fall Exposure Model for Smart Home Care is shown in the proposed solution. The multiple cameras fall dataset and the UR fall dataset are applied to produce the recommended representation.

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

Analysis on Deep Learning and IoT-Based Human Fall Detection and Identification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shyam Sundar Yerra,
  • Amit Kumar Singh,
  • Maughal Ahmed Ali Baig,
  • N. Shweta,
  • Yogita Gupta,
  • R. Suhasini

摘要

In order to collect data regarding people and surroundings for many uses, mobile communications and the Internet of Things (IoT) have emerged in recent years. In smart homes, aging and disabled inhabitants are particularly challenging to remotely monitor due to routine behaviors that could cause accidents, such as falls. Fall is measured as a main issue due to the fact that might cause older people to experience post-traumatic difficulties. It is therefore essential to identify older adults who fall in smart homes as soon as probable so as to amplify their probability of survival. These days, fall detection identification systems for smart homecare are required due to wearables, smart phones, wearable artificial intelligence (AI), and various other technologies. Frequent fall detection can assist in identifying the person whom has fallen and make it possible to provide them with immediate medical assistance. Operators of current wearable technologies may find it unpleasant. In this sense, the project concept provides a camera-based fall recognition system that monitors a person’s motions and any falls that may occur. The CNN-Inception v3 deep convolutional neural network-based IoT-empowered Elderly Fall Exposure Model for Smart Home Care is shown in the proposed solution. The multiple cameras fall dataset and the UR fall dataset are applied to produce the recommended representation.