Design of Optimal Deep Learning Based Human Activity Recognition on Sensor Enabled Internet of Things Environment

被引:5
作者
Al-Wesabi, Fahd N. [1 ,2 ]
Albraikan, Amani Abdulrahman [3 ]
Hilal, Anwer Mustafa [4 ]
Al-Shargabi, Asma Abdulghani [5 ,6 ]
Alhazbi, Saleh [7 ]
Al Duhayyim, Mesfer [8 ]
Rizwanullah, Mohammed [4 ]
Hamza, Manar Ahmed [4 ]
机构
[1] King Khalid Univ, Dept Comp Sci, Abha 62529, Saudi Arabia
[2] Sanaa Univ, Fac Comp & IT, Sanaa, Yemen
[3] Princess Nourah Bint Abdulrahman Univ, Coll Comp & Informat Sci, Dept Comp Sci, Riyadh 11564, Saudi Arabia
[4] Prince Sattam Bin Abdulaziz Univ, Dept Comp & Self Dev, Al Kharj 11942, Saudi Arabia
[5] Qassim Univ, Coll Comp, Dept Informat Technol, Buraydah 52571, Saudi Arabia
[6] Univ Sci & Technol, Dept Comp Sci, Collage Comp & IT, Sanaa, Yemen
[7] Qatar Univ, Dept Comp Sci & Engn, Doha, Qatar
[8] Prince Sattam Bin Abdulaziz Univ, Coll Community Aflaj, Dept Nat & Appl Sci, Al Kharj 11942, Saudi Arabia
关键词
Feature extraction; Wearable computers; Optimization; Activity recognition; Data models; Internet of Things; Deep learning; human activity recognition; wearables; metaheuristics; feature extraction;
D O I
10.1109/ACCESS.2021.3112973
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In recent times, Human Activity Recognition (HAR) has become a major challenge to overcome among computer vision applications in day-to-day lives. HAR is mainly envisioned to be utilized in coordination with other technologies namely, Internet of Things (IoT) and sensor technologies. Due to the advancements made in Deep Learning (DL) approaches, the automated high level feature extraction process can be utilized to improve the outcomes of HAR process. In addition, DL techniques can also be employed in different domains of sensor-enabled HAR. In this aspect, the current study designs an Optimal DL-based HAR (ODL-HAR) model on sensor-enabled IoT environments. The proposed ODL-HAR technique aims at determining the human activities in day-to-day lives using wearables and IoT devices. ODL-HAR technique involves different stages of operations namely, data acquisition, data preprocessing, feature extraction, classification, and parameter optimization. The proposed ODL-HAR technique uses MobileNet-v2 model as a feature extractor and Bidirectional Long Short-Term Memory (BiLSTM) model as a classifier. In order to fine tune the hyperparameters involved in BiLSTM model optimally, Chaos Game Optimization (CGO) algorithm is employed which in turn increases the recognition performance. The novelty of the work lies in the deployment of CGO algorithm for hyperparameter optimization of HAR. A wide range of simulations was conducted to validate the supremacy of the proposed ODL-HAR technique and two benchmark datasets were used for this simulation process. The experimental results portrayed the enhanced performance of ODL-HAR technique over other recent HAR approaches under different evaluation parameters.
引用
收藏
页码:143988 / 143996
页数:9
相关论文
共 22 条
[1]   An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones [J].
Ankita ;
Rani, Shalli ;
Babbar, Himanshi ;
Coleman, Sonya ;
Singh, Aman ;
Aljahdali, Hani Moaiteq .
SENSORS, 2021, 21 (11)
[2]  
Ashraf I., 2021, INT J MACH LEARN CYB, V1, P1
[3]   Particle swarm optimization with deep learning for human action recognition [J].
Berlin, S. Jeba ;
John, Mala .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (25-26) :17349-17371
[4]   Human action recognition using two-stream attention based LSTM networks [J].
Dai, Cheng ;
Liu, Xingang ;
Lai, Jinfeng .
APPLIED SOFT COMPUTING, 2020, 86
[5]   Spatiotemporal analysis of human activities for biometric authentication [J].
Drosou, Anastasios ;
Ioannidis, Dimosthenis ;
Moustakas, Konstantinos ;
Tzovaras, Dimitrios .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2012, 116 (03) :411-421
[6]   Human Activity Recognition: From Sensors to Applications [J].
Fereidoonian, Faeghe ;
Firouzi, Farshad ;
Farahani, Bahar .
2020 INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2020), 2020, :121-128
[7]   BSN-Care: A Secure IoT-Based Modern Healthcare System Using Body Sensor Network [J].
Gope, Prosanta ;
Hwang, Tzonelih .
IEEE SENSORS JOURNAL, 2016, 16 (05) :1368-1376
[8]  
Mekruksavanich S., ICT SYSTEMS SUSTAINA, V2021, P753
[9]   Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models [J].
Mekruksavanich, Sakorn ;
Jitpattanakul, Anuchit .
ELECTRONICS, 2021, 10 (03) :1-21
[10]   Sensor-Based Human Activity Recognition with Spatio-Temporal Deep Learning [J].
Nafea, Ohoud ;
Abdul, Wadood ;
Muhammad, Ghulam ;
Alsulaiman, Mansour .
SENSORS, 2021, 21 (06) :1-20