Cited 0 time in webofscience Cited 0 time in scopus

Poster abstract: Maximizing accuracy of fall detection and alert systems based on 3D convolutional neural network

Title
Poster abstract: Maximizing accuracy of fall detection and alert systems based on 3D convolutional neural network
Authors
Hwang, SeokhyunAhn, DaeHanPark, HominPark, Taejoon
DGIST Authors
Hwang, Seokhyun; Ahn, DaeHan; Park, Homin; Park, Taejoon
Issue Date
2017
Citation
2nd IEEE/ACM International Conference on Internet-of-Things Design and Implementation, IoTDI 2017, 343-344
Type
Conference
Article Type
Conference Paper
ISBN
9781450000000
Abstract
We present a deep-learning-based approach to maximize the accuracy and reliability of vision-based fall detection and alert systems. The proposed approach utilizes a 3D convolutional neural network (3D-CNN) to analyze the continuous motion data obtained from depth cameras and exploits a data augmentation method to do away with overfitting. Our preliminary evaluation results demonstrate that it achieves the classification accuracy of up to 96.9%. © 2017 ACM.
URI
http://hdl.handle.net/20.500.11750/4318
DOI
10.1145/3054977.3057314
Publisher
Association for Computing Machinery, Inc
Files:
There are no files associated with this item.
Collection:
Information and Communication EngineeringETC2. Conference Papers
ETC2. Conference Papers
School of Undergraduate Studies2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE