Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN

Hasan, Md. Al Mehedi; Abir, Fuad Al; Siam, Md. Al; Shin, Jungpil

doi:10.1109/access.2022.3168019

Cited by 19 publications

(12 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental procedure was conducted on the CASIA A dataset, and the suggested approach obtained a precision of 88.33%. To enhance gait recognition using low-device wearable sensors, the authors [26] presented a modified residual block and a new shallow convolutional layer to improve gait recognition using low-device sensors on clothing. To analyze the subject's locomotion, they inserted wearable sensors in objects that might be placed on the individual's body, such as watches, necklaces, and cellphones.…”

Section: Related Workmentioning

confidence: 99%

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

Hanif,

Mughal,

Khan

et al. 2024

CMC

View full text Add to dashboard Cite

The demand for a non-contact biometric approach for candidate identification has grown over the past ten years. Based on the most important biometric application, human gait analysis is a significant research topic in computer vision. Researchers have paid a lot of attention to gait recognition, specifically the identification of people based on their walking patterns, due to its potential to correctly identify people far away. Gait recognition systems have been used in a variety of applications, including security, medical examinations, identity management, and access control. These systems require a complex combination of technical, operational, and definitional considerations. The employment of gait recognition techniques and technologies has produced a number of beneficial and wellliked applications. This work proposes a novel deep learning-based framework for human gait classification in video sequences. This framework's main challenge is improving the accuracy of accuracy gait classification under varying conditions, such as carrying a bag and changing clothes. The proposed method's first step is selecting two pretrained deep learning models and training from scratch using deep transfer learning. Next, deep models have been trained using static hyperparameters; however, the learning rate is calculated using the particle swarm optimization (PSO) algorithm. Then, the best features are selected from both trained models using the Harris Hawks controlled Sine-Cosine optimization algorithm. This algorithm chooses the best features, combined in a novel correlationbased fusion technique. Finally, the fused best features are categorized using medium, bi-layer, and tri-layered neural networks. On the publicly accessible dataset known as the CASIA-B dataset, the experimental process of the suggested technique was carried out, and an improved accuracy of 94.14% was achieved. The achieved accuracy of the proposed method is improved by the recent state-of-the-art techniques that show the significance of this work.

show abstract

Section: Related Workmentioning

confidence: 99%

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

Hanif,

Mughal,

Khan

et al. 2024

CMC

View full text Add to dashboard Cite

show abstract

“…To improve network performance and more lightweight, Li et al [26] established a simplified convolution module, which greatly improves the efficiency of the network. Hasan et al [27] modified the residual block and accumulate it in shallow convolutional neural networks, achieving good results. The efficiency problem mainly lies in the storage requirements and the model's prediction speed, which largely determines the actual application ability of the model.…”

Section: Introductionmentioning

confidence: 99%

An efficient robotic-assisted bolt-ball joint looseness monitoring approach using CBAM-enhanced lightweight ResNet

Li,

Yuan,

et al. 2023

Smart Mater. Struct.

View full text Add to dashboard Cite

Bolt-ball joints are widely used in space structures, and their looseness may lead to major safety accidents. The current bolt monitoring methods based on deep learning usually have high computational complexity, and it is difficult to guarantee its computational efficiency under practical scenario. To mitigate this problem, here in this paper, an efficient robotic-assisted bolt-ball joint looseness monitoring approach using convolutional block attention module (CBAM)-enhanced Lightweight ResNet is proposed. Firstly, the robotic-assisted tapping method is applied to bolt-ball joints to generate audio signals, which are constructed into time-frequency maps by continuous wavelet transform (CWT). Secondly, the original ResNet is improved as a lightweight network, which successfully reduces model complexity, and employs time-frequency maps as input. Then, CBAM is introduced to capture global information and focus on the critical feature. Thus, the efficiency of feature extraction is significantly improved. Finally, by the overall optimized structure, a CBAM-enhanced Lightweight ResNet model is established to monitor the bolt-ball joints looseness state accurately. Experimental results demonstrate the high efficiency while maintaining very lightweight structure of the proposed approach, verifying the effectiveness and superiority of the robot-assisted approach using CBAM-enhanced lightweight ResNet over other methods.

show abstract

“…Human activity recognition (HAR) is the foundation of many felds and has become a research hotspot in the past decade on account of its signifcance. At present, this technology has been widely applied in the felds of smart homes [1], indoor navigation [2], identity recognition [3], human-machine interaction [4], gait analysis [5], and the Internet of Healthcare Tings [6,7]. Te identifcation accuracy of corresponding activities has signifcant efects on these applications.…”

Section: Introductionmentioning

confidence: 99%

Human Activity Recognition Based on a Modified Capsule Network

Zhu

Chen

Liu

et al. 2023

Mobile Information Systems

View full text Add to dashboard Cite

Human activity recognition (HAR) has attracted considerable research attention in the past decade with the development of wearable sensor technology and deep learning algorithms. However, most of the existing HAR methods ignored the spatial relationship of features, which may lead to recognition errors. In this paper, a novel model based on a modified capsule network (MCN) is proposed to accurately recognize various human activities. This novel model is composed of a convolution block and a capsule block, which can achieve end-to-end intelligent recognition. In the meantime, the spatial information among features is preserved through a dynamic routing process. To validate the effectiveness of the model, a human activity dataset is constructed by placing an inertial measurement unit (IMU) on the calf of the volunteers to collect their activity data in daily life, including walking, jogging, upstairs, downstairs, up-ramps, and down-ramps. The recognition accuracy of this novel approach can reach 96.08%, which performs better than the convolutional neural network (CNN) with an accuracy of 91.62%. In addition, it is evaluated on two public datasets named WISDM and UCI-HAR, and the accuracies achieve 98.21% and 95.28%, respectively, which presents higher accuracy than the reported results obtained from benchmark algorithms like CNN. The experimental results show that the proposed model has better activity detection capability and achieves outstanding performance for HAR.

show abstract

Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN

Cited by 19 publications

References 102 publications

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

An efficient robotic-assisted bolt-ball joint looseness monitoring approach using CBAM-enhanced lightweight ResNet

Human Activity Recognition Based on a Modified Capsule Network

Contact Info

Product

Resources

About