IoT-blockchain empowered Trinet: optimized fall detection system for elderly safety

被引:4
作者
Alfayez, Fayez [1 ]
Khan, Surbhi Bhatia [2 ]
机构
[1] Majmaah Univ, Coll Sci Al Zulfi, Dept Comp Sci & Informat, Al Majmaah, Saudi Arabia
[2] Univ Salford, Sch Sci Engn & Environm, Dept Data Sci, Salford, England
关键词
IoT; blockchain; elderly people; deep learning; SSA; TLBO; DETECTION FRAMEWORK; PEOPLE;
D O I
10.3389/fbioe.2023.1257676
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Numerous elderly folks reside alone in their homes. Seniors may find it difficult to ask for assistance if they fall. As the elderly population keeps growing, elderly fall incidents are becoming a critical public health concern. Creating a fall detection system for the elderly using IoT and blockchain is the aim of this study. Data collection, pre-processing, feature extraction, feature selection, fall detection, and emergency response and assistance are the six fundamental aspects of the proposed model. The sensor data is collected from wearable devices using elderly such as accelerometers and gyroscopes. The collected data is pre-processed using missing value removal, null value handling. The features are extracted after pre-processed data using statistical features, autocorrelation, and Principal Component Analysis The proposed approach utilizes a novel hybrid HSSTL combines Teaching-Learning-Based Optimization and Spring Search Algorithm to select the optimal features. The proposed approach employs TriNet, including Long Short-Term Memory, optimized Convolutional Neural Network (CNN), and Recurrent Neural Network for accurate fall detection. To enhance fall detection accuracy, use the optimized Convolutional Neural Network obtained through the hybrid optimization model HSSTL. Securely store fall detection information in the Blockchain network when a fall occurs. Alert neighbours, family members, or those providing immediate assistance about the fall occurrence using Blockchain network. The proposed model is implemented in Python. The effectiveness of the suggested model is evaluated using metrics for accuracy, precision, recall, sensitivity, specificity, f-measure, NPV, FPR, FNR, and MCC. The proposed model outperformed with the maximum accuracy of 0.974015 at an 80% learning rate, whereas the suggested model had the best accuracy score of 0.955679 at a 70% learning rate.
引用
收藏
页数:18
相关论文
共 28 条
[1]   FallDeF5: A Fall Detection Framework Using 5G-Based Deep Gated Recurrent Unit Networks [J].
Al-Rakhami, Mabrook S. ;
Gumaei, Abdu ;
Altaf, Meteb ;
Hassan, Mohammad Mehedi ;
Alkhamees, Bader Fahad ;
Muhammad, Khan ;
Fortino, Giancarlo .
IEEE ACCESS, 2021, 9 (09) :94299-94308
[2]  
[Anonymous], 2023, The MobiFall and MobiAct datasets
[3]   Fall Detection Based on Key Points of Human-Skeleton Using OpenPose [J].
Chen, Weiming ;
Jiang, Zijie ;
Guo, Hailin ;
Ni, Xiaoyang .
SYMMETRY-BASEL, 2020, 12 (05)
[4]   Smart Seismic Sensing for Indoor Fall Detection, Location, and Notification [J].
Clemente, Jose ;
Li, Fangyu ;
Valero, Maria ;
Song, WenZhan .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (02) :524-532
[5]   A Smartphone-Enabled Fall Detection Framework for Elderly People in Connected Home Healthcare [J].
Hassan, Mohammad Mehedi ;
Gumaei, Abdu ;
Aloi, Gianluca ;
Fortino, Giancarlo ;
Zhou, Mengchu .
IEEE NETWORK, 2019, 33 (06) :58-63
[6]  
Kaggle, 2023, Dataset2 taken from
[7]  
Kaggle, 2023, Dataset1 taken from
[8]   Improving Fall Detection Using an On-Wrist Wearable Accelerometer [J].
Khojasteh, Samad Barri ;
Villar, Jose R. ;
Chira, Camelia ;
Gonzalez, Victor M. ;
de la Cal, Enrique .
SENSORS, 2018, 18 (05)
[9]   Development of an Enhanced Threshold-Based Fall Detection System Using Smartphones With Built-In Accelerometers [J].
Lee, Jin-Shyan ;
Tseng, Hsuan-Han .
IEEE SENSORS JOURNAL, 2019, 19 (18) :8293-8302
[10]   Impact of Sampling Rate on Wearable-Based Fall Detection Systems Based on Machine Learning Models [J].
Liu, Kai-Chun ;
Hsieh, Chia-Yeh ;
Hsu, Steen Jun-Ping ;
Chan, Chia-Tai .
IEEE SENSORS JOURNAL, 2018, 18 (23) :9882-9890