Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks

Kim, Jin-Su; Kim, Mingu; Pan, Sung Bum

doi:10.3390/app11156824

Cited by 15 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the convolutional layer, batch normalization is performed. The pooling layer is a filter of size [1 × 2] and reduces the feature dimension with padding 0 and stride [1,2]. Sub-network 1 utilizes as input data a size of [1 × 5000], representing an ECG signal, while sub-network 2 uses an input data size of [1 × 5000], representing an EMG signal.…”

Section: User Recognition Method Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

Kim,

Song,

Kim

et al. 2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal benchmark databases (DBs) for user recognition often suffer from limitations, such as data collection from a small number of subjects in a single session, hindering comprehensive analysis of biosignal variability. This study introduces CSU_MBDB1 and CSU_MBDB2, databases containing electrocardiogram (ECG) and electromyogram (EMG) signals from diverse experimental subjects recorded across multiple sessions. These in-house DBs comprise ECG and EMG data recorded in multiple sessions from 36 and 58 subjects, respectively, with a time interval of more than one day between sessions. During the experiments, subjects performed a total of six gestures while comfortably seated at a desk. CSU_MBDB1 and CSU_MBDB2 consist of three identical gestures, providing expandable data for various applications. When the two DBs are expanded, ECGs and EMGs from 94 subjects can be used, which is the largest number among the multi-biosignal benchmark DBs built by multi-sessions. To assess the usability of the constructed DBs, a user recognition experiment was conducted, resulting in an accuracy of 66.39% for ten subjects. It is important to emphasize that we focused on demonstrating the applicability of the constructed DBs using a basic neural network without signal denoising capabilities. While this approach results in a sacrifice in accuracy, it concurrently provides substantial opportunities for performance enhancement through the implementation of optimized algorithms. Adapting signal denoising processes to the constructed DBs and designing a more sophisticated neural network would undoubtedly contribute to improving the recognition accuracy. Consequently, these constructed DBs hold promise in user recognition, offering valuable research for future investigations. Additionally, DBs can be used in research to analyze the nonlinearity characteristics of ECG and EMG.

show abstract

Section: User Recognition Method Results and Discussionmentioning

confidence: 99%

“…Sci. 2024, 14, x FOR PEER REVIEW 2 of 17 advantages of being unforgeable and variable, biosignals address the challenges of conventional user recognition methods [2].…”

Section: Introductionmentioning

confidence: 99%

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

Kim,

Song,

Kim

et al. 2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among them, Hu [ 26 ], Ding [ 38 ], Gulati [ 33 ], and others only focus on extracting the morphological or temporal features of the signal in the sliding window, ignoring the differences and connections between different electrode channels. The artificial features designed by Tosin [ 40 ], Kim [ 39 ], Wei [ 19 ], and others have high requirements on researchers’ experience, and to some extent destroy the hidden connections between real signals.…”

Section: Discussionmentioning

confidence: 99%

MSFF-Net: Multi-Stream Feature Fusion Network for surface electromyography gesture recognition

Peng

Zhou²,

Zhu³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

In the field of surface electromyography (sEMG) gesture recognition, how to improve recognition accuracy has been a research hotspot. The rapid development of deep learning provides a new solution to this problem. At present, the main applications of deep learning for sEMG gesture feature extraction are based on convolutional neural network (CNN) structures to capture spatial morphological information of the multichannel sEMG or based on long short-term memory network (LSTM) to extract time-dependent information of the single-channel sEMG. However, there are few methods to comprehensively consider the distribution area of the sEMG signal acquisition electrode sensor and the arrangement of the sEMG signal morphological features and electrode spatial features. In this paper, a novel multi-stream feature fusion network (MSFF-Net) model is proposed for sEMG gesture recognition. The model adopts a divide-and-conquer strategy to learn the relationship between different muscle regions and specific gestures. Firstly, a multi-stream convolutional neural network (Multi-stream CNN) and a convolutional block attention module integrated with a resblock (ResCBAM) are used to extract multi-dimensional spatial features from signal morphology, electrode space, and feature map space. Then the learned multi-view depth features are fused by a view aggregation network consisting of an early fusion network and a late fusion network. The results of all subjects and gesture movement validation experiments in the sEMG signal acquired from 12 sensors provided by NinaPro’s DB2 and DB4 sub-databases show that the proposed model in this paper has better performance in terms of gesture recognition accuracy compared with the existing models.

show abstract

“…The time domain uses the morphological features of sEMG, and the frequency domain uses the domain transformation information of sEMG. However, it can be impossible for handcrafted feature extraction to extract optimized data features [12].…”

Section: Handcrafted Feature Extraction Based On Domain Informationmentioning

confidence: 99%

Electromyogram Based Personal Recognition Using Attention Mechanism for IoT Security

Kim,

Pan

2023

CMC

View full text Add to dashboard Cite

As Internet of Things (IoT) technology develops, integrating network functions into diverse equipment introduces new challenges, particularly in dealing with counterfeit issues. Over the past few decades, research efforts have focused on leveraging electromyogram (EMG) for personal recognition, aiming to address security concerns. However, obtaining consistent EMG signals from the same individual is inherently challenging, resulting in data irregularity issues and consequently decreasing the accuracy of personal recognition. Notably, conventional studies in EMG-based personal recognition have overlooked the issue of data irregularities. This paper proposes an innovative approach to personal recognition that combines a siamese fusion network with an auxiliary classifier, effectively mitigating the impact of data irregularities in EMG-based recognition. The proposed method employs empirical mode decomposition (EMD) to extract distinctive features. The model comprises two sub-networks designed to follow the siamese network architecture and a decision network integrated with the novel auxiliary classifier, specifically designed to address data irregularities. The two sub-networks sharing a weight calculate the compatibility function. The auxiliary classifier collaborates with a neural network to implement an attention mechanism. The attention mechanism using the auxiliary classifier solves the data irregularity problem by improving the importance of the EMG gesture section. Experimental results validated the efficacy of the proposed personal recognition method, achieving a remarkable 94.35% accuracy involving 100 subjects from the multisession CU_sEMG database (DB). This performance outperforms the existing approaches by 3%, employing auxiliary classifiers. Furthermore, an additional experiment yielded an improvement of over 0.85% of Ninapro DB, 3% of CU_sEMG DB compared to the existing EMG-based recognition methods. Consequently, the proposed personal recognition using EMG proves to secure IoT devices, offering robustness against data irregularities.

show abstract

Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks

Cited by 15 publications

References 23 publications

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

MSFF-Net: Multi-Stream Feature Fusion Network for surface electromyography gesture recognition

Electromyogram Based Personal Recognition Using Attention Mechanism for IoT Security

Contact Info

Product

Resources

About