Fall Detection using Deep Learning Algorithms and Analysis of Wearable Sensor Data by Presenting a New Sampling Method
4
TL;DR: In this article , a deep neural network using wearable sensor data to detect falls was developed, and three deep learning models, CNN, LSTM and a hybrid model called Conv-LSTM, were implemented on this dataset, and their performance was evaluated.
read more
Abstract: Fall is one of the most critical health challenges in the community, which can cause severe injuries and even death. The primary purpose of this study is to develop a deep neural network using wearable sensor data to detect falls. Most datasets in this field suffer from the problem of data imbalance so that the instances belonging to the Fall classes are significantly less than the data of the normal class. This study offers a dynamic sampling technique for increasing the balance rate between the samples belonging to fall and normal classes to improve the accuracy of the learning algorithms. The Sisfall dataset was used in which human activity is divided into three categories: normal activity (BKG), moments before the fall (Alert), and role on the ground (Fall). Three deep learning models, CNN, LSTM, and a hybrid model called Conv-LSTM, were implemented on this dataset, and their performance was evaluated. Accordingly, the Conv-LSTM hybrid model presents 96.23%, 98.59%, and 99.38% in the Sensitivity parameter for the BKG, Alert, and Fall classes, respectively. For the accuracy parameter, we have managed to reach 97.12%. In addition, by using noise smoothing and removal techniques, we can hit a 97.83% accuracy rate. The results indicate the proposed model's superiority compared to other similar studies.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Wearable Sensor-Based Human Activity Recognition System Employing Bi-LSTM Algorithm
AmirHassan Majidi Tehrani,Meisam Yadollahzadeh-Tabari,Aidin Zehtab-Salmasi,Rasul Enayatifar +3 more
TL;DR: In this paper , a deep multilayer bidirectional long-short memory (Bi-LSTM) architecture has been implemented to detect human activities and a new novel postprocessing approach has been proposed based on windowing and voting in the last step to improve the average F1 score.
10
Fall detection system for monitoring elderly people using YOLOv7-pose detection model
Pranavan V M,Maunika Shekar,Sri Lasya Pragathi B,Ruzelita Ngadiran,Sindhu Ravindran +4 more
- 08 Jun 2023
TL;DR: An Object detection based Automated Fall Detection System has been proposed wherein, the YOLOv7 (You Only Look Once) pose model is used to discriminate the fall and non-fall activity.
6
Enhanced Face Presentation Attack Prevention Employing Feature Fusion of Pre-trained Deep Convolutional Neural Network Model and Thepade's Sorted Block Truncation Coding
TL;DR: In this article , the authors evaluated the applicability of pre-trained DCNN models to identify human face presentation threats (FPAD) using the NUAA and Replay-Attack benchmark FPAD datasets.
3
Providing an Approach for Early Prediction of Fall in Human Activities Based on Wearable Sensor Data and the Use of Deep Learning Algorithms
07 Mar 2023
TL;DR: In this article , the authors presented a future prediction strategy based on wearable sensors data, which replaces and labels the state of the next T s instead of considering the current state only, leading to predicting falling states at the beginning moments of balance disturbance.
References
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
TL;DR: A generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which is suitable for multimodal wearable sensors, does not require expert knowledge in designing features, and explicitly models the temporal dynamics of feature activations is proposed.
2.5K
Deep learning for sensor-based activity recognition: A survey
TL;DR: The recent advance of deep learning based sensor-based activity recognition is surveyed from three aspects: sensor modality, deep model, and application and detailed insights on existing work are presented and grand challenges for future research are proposed.
Medical Costs of Fatal and Nonfatal Falls in Older Adults.
Curtis S. Florence,Gwen Bergen,Adam Atherly,Elizabeth R. Burns,Judy A. Stevens,Cynthia Drake +5 more
TL;DR: To estimate medical expenditures attributable to older adult falls using a methodology that can be updated annually to track these expenditures over time, a database of hospital admissions and accident and emergency department visits is constructed.
SisFall: A Fall and Movement Dataset.
TL;DR: A dataset of falls and activities of daily living acquired with a self-developed device composed of two types of accelerometer and one gyroscope is presented, validating findings of other authors and encourages developing new strategies with this new dataset as the benchmark.
450