1
|
Sziburis T, Nowak M, Brunelli D. Instance-based learning with prototype reduction for real-time proportional myocontrol: a randomized user study demonstrating accuracy-preserving data reduction for prosthetic embedded systems. Med Biol Eng Comput 2024; 62:275-305. [PMID: 37796400 PMCID: PMC10758379 DOI: 10.1007/s11517-023-02917-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Accepted: 08/21/2023] [Indexed: 10/06/2023]
Abstract
This work presents the design, implementation and validation of learning techniques based on the kNN scheme for gesture detection in prosthetic control. To cope with high computational demands in instance-based prediction, methods of dataset reduction are evaluated considering real-time determinism to allow for the reliable integration into battery-powered portable devices. The influence of parameterization and varying proportionality schemes is analyzed, utilizing an eight-channel-sEMG armband. Besides offline cross-validation accuracy, success rates in real-time pilot experiments (online target achievement tests) are determined. Based on the assessment of specific dataset reduction techniques' adequacy for embedded control applications regarding accuracy and timing behaviour, decision surface mapping (DSM) proves itself promising when applying kNN on the reduced set. A randomized, double-blind user study was conducted to evaluate the respective methods (kNN and kNN with DSM-reduction) against ridge regression (RR) and RR with random Fourier features (RR-RFF). The kNN-based methods performed significantly better ([Formula: see text]) than the regression techniques. Between DSM-kNN and kNN, there was no statistically significant difference (significance level 0.05). This is remarkable in consideration of only one sample per class in the reduced set, thus yielding a reduction rate of over 99% while preserving success rate. The same behaviour could be confirmed in an extended user study. With [Formula: see text], which turned out to be an excellent choice, the runtime complexity of both kNN (in every prediction step) as well as DSM-kNN (in the training phase) becomes linear concerning the number of original samples, favouring dependable wearable prosthesis applications.
Collapse
Affiliation(s)
- Tim Sziburis
- Institute for Neuroinformatics (INI), Ruhr University Bochum, Universitätsstr. 150, Bochum, 44801, Germany.
- German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Münchener Str. 20, 82234, Weßling, Germany.
| | - Markus Nowak
- German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Münchener Str. 20, 82234, Weßling, Germany
| | - Davide Brunelli
- Department of Industrial Engineering, DII, University of Trento, Via Sommarive, 9, 38123, Trento, Italy
| |
Collapse
|
2
|
Xu D, Wang Q. Noninvasive Human-Prosthesis Interfaces for Locomotion Intent Recognition: A Review. CYBORG AND BIONIC SYSTEMS 2021; 2021:9863761. [PMID: 36285130 PMCID: PMC9494705 DOI: 10.34133/2021/9863761] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2020] [Accepted: 03/22/2021] [Indexed: 12/02/2022] Open
Abstract
The lower-limb robotic prostheses can provide assistance for amputees' daily activities by restoring the biomechanical functions of missing limb(s). To set proper control strategies and develop the corresponding controller for robotic prosthesis, a prosthesis user's intent must be acquired in time, which is still a major challenge and has attracted intensive attentions. This work focuses on the robotic prosthesis user's locomotion intent recognition based on the noninvasive sensing methods from the recognition task perspective (locomotion mode recognition, gait event detection, and continuous gait phase estimation) and reviews the state-of-the-art intent recognition techniques in a lower-limb prosthesis scope. The current research status, including recognition approach, progress, challenges, and future prospects in the human's intent recognition, has been reviewed. In particular for the recognition approach, the paper analyzes the recent studies and discusses the role of each element in locomotion intent recognition. This work summarizes the existing research results and problems and contributes a general framework for the intent recognition based on lower-limb prosthesis.
Collapse
Affiliation(s)
- Dongfang Xu
- Robotics Research Group, College of Engineering, Peking University, China
- Beijing Engineering Research Center of Intelligent Rehabilitation Engineering, China
| | - Qining Wang
- Robotics Research Group, College of Engineering, Peking University, China
- Beijing Engineering Research Center of Intelligent Rehabilitation Engineering, China
- The Beijing Innovation Center for Engineering Science and Advanced Technology (BIC-ESAT), Peking University, China
| |
Collapse
|
3
|
Wei Y, Zhou J, Wang Y, Liu Y, Liu Q, Luo J, Wang C, Ren F, Huang L. A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2020; 14:145-163. [PMID: 32078560 DOI: 10.1109/tbcas.2020.2974154] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
This paper reviews the state of the arts and trends of the AI-Based biomedical processing algorithms and hardware. The algorithms and hardware for different biomedical applications such as ECG, EEG and hearing aid have been reviewed and discussed. For algorithm design, various widely used biomedical signal classification algorithms have been discussed including support vector machine (SVM), back propagation neural network (BPNN), convolutional neural networks (CNN), probabilistic neural networks (PNN), recurrent neural networks (RNN), Short-term Memory Network (LSTM), fuzzy neural network and etc. The pros and cons of the classification algorithms have been analyzed and compared in the context of application scenarios. The research trends of AI-Based biomedical processing algorithms and applications are also discussed. For hardware design, various AI-Based biomedical processors have been reviewed and discussed, including ECG classification processor, EEG classification processor, EMG classification processor and hearing aid processor. Various techniques on architecture and circuit level have been analyzed and compared. The research trends of the AI-Based biomedical processor have also been discussed.
Collapse
|
4
|
Olsson AE, Björkman A, Antfolk C. Automatic discovery of resource-restricted Convolutional Neural Network topologies for myoelectric pattern recognition. Comput Biol Med 2020; 120:103723. [PMID: 32421642 DOI: 10.1016/j.compbiomed.2020.103723] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2020] [Revised: 03/06/2020] [Accepted: 03/21/2020] [Indexed: 02/02/2023]
Abstract
Convolutional Neural Networks (CNNs) have been subject to extensive attention in the pattern recognition literature due to unprecedented performance in tasks of information extraction from unstructured data. Whereas available methods for supervised training of a CNN with a given network topology are well-defined with rigorous theoretical justification, procedures for the initial selection of topology are currently not. Work incorporating selection of the CNN topology has instead substantially been guided by the domain-specific expertise of the creator(s), followed by iterative improvement via empirical evaluation. This limitation of methodology is restricting in the pursuit of naturally controlled muscle-computer interfaces, where CNNs have been identified as a promising research avenue but effective topology selection heuristics are lacking. With the goal of mitigating ambiguities in topology selection, this paper presents a systematic approach wherein we apply a novel evolutionary algorithm to search a space of candidate topologies. Furthermore, we constrain the search-space by excluding topologies with excessive inference-time computational complexity, making the obtained results implementable in embedded systems. In contrast to manual topology design, our algorithm requires the user to only specify a relatively small set of intuitive hyperparameters. To validate our approach, we use it in order to create topologies for myoelectric pattern recognition via movement decoding of surface electromyography signals. By collating offline classification accuracies obtained from experiments on a collection of publicly available databases, we demonstrate that our method generates computationally lightweight topologies with performance comparable to those of available alternatives.
Collapse
Affiliation(s)
- Alexander E Olsson
- Dept. of Biomedical Engineering, Faculty of Engineering, Lund University, Lund, Sweden.
| | - Anders Björkman
- Dept. of Hand Surgery, Lund University, Skåne University Hospital, Malmö, Sweden; Wallenberg Center for Molecular Medicine, Lund University, Lund, Sweden
| | - Christian Antfolk
- Dept. of Biomedical Engineering, Faculty of Engineering, Lund University, Lund, Sweden.
| |
Collapse
|
5
|
Surface EMG data aggregation processing for intelligent prosthetic action recognition. Neural Comput Appl 2018. [DOI: 10.1007/s00521-018-3909-z] [Citation(s) in RCA: 57] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
6
|
Stacked Sparse Autoencoders for EMG-Based Classification of Hand Motions: A Comparative Multi Day Analyses between Surface and Intramuscular EMG. APPLIED SCIENCES-BASEL 2018. [DOI: 10.3390/app8071126] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
|
7
|
Purushothaman G, Vikas R. Identification of a feature selection based pattern recognition scheme for finger movement recognition from multichannel EMG signals. AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE 2018; 41:549-559. [PMID: 29744809 DOI: 10.1007/s13246-018-0646-7] [Citation(s) in RCA: 33] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/26/2017] [Accepted: 05/01/2018] [Indexed: 11/26/2022]
Abstract
This paper focuses on identification of an effective pattern recognition scheme with the least number of time domain features for dexterous control of prosthetic hand to recognize the various finger movements from surface electromyogram (EMG) signals. Eight channels EMG from 8 able-bodied subjects for 15 individuals and combined finger activities have been considered in this work. In this work, an attempt has been made to recognize a number of classes with the least number of features. Therefore, EMG signals are pre-processed using dual tree complex wavelet transform to improve the discriminating capability of features and time domain features such as zero crossing, slope sign change, mean absolute value, and waveform length is extracted from the pre-processed data. The performance of extracted features is studied with different classifiers such as linear discriminant analysis, naive Bayes classifier, quadratic support vector machine and cubic support vector machine with and without feature selection algorithms. The feature selection has been studied using particle swarm optimization (PSO) and ant colony optimization (ACO) with different number of features to identify the effect of features. The results demonstrated that naive Bayes classifier with ant colony optimization shows an average classification accuracy of 88.89% with a response time of 0.058025 ms for recognizing the 15 different finger movements with 16 features with significant difference in accuracy compared to SVM classifier with feature selection for a significance level of 0.05. There is no significant difference in the accuracy, specificity and sensitivity of an SVM classifier with and without feature selection. But the processing time is significantly more than the LDA and NB classifier. The PSO and ACO results revealed that slope sign changes contribute to recognizing the activity. In PSO, mean absolute value has been found to be effective compared to waveform length, contradictory with ACO. Further, the zero crossings have been found to be not effective in classification of finger movements in both the methods.
Collapse
Affiliation(s)
| | - Raunak Vikas
- School of Electrical Engineering, VIT, Vellore, TN, 632 014, India
| |
Collapse
|
8
|
Ghaderi P, Marateb HR. Muscle Activity Map Reconstruction from High Density Surface EMG Signals With Missing Channels Using Image Inpainting and Surface Reconstruction Methods. IEEE Trans Biomed Eng 2017; 64:1513-1523. [PMID: 28113298 DOI: 10.1109/tbme.2016.2603463] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
OBJECTIVE The aim of this study was to reconstruct low-quality High-density surface EMG (HDsEMG) signals, recorded with 2-D electrode arrays, using image inpainting and surface reconstruction methods. METHODS It is common that some fraction of the electrodes may provide low-quality signals. We used variety of image inpainting methods, based on partial differential equations (PDEs), and surface reconstruction methods to reconstruct the time-averaged or instantaneous muscle activity maps of those outlier channels. Two novel reconstruction algorithms were also proposed. HDsEMG signals were recorded from the biceps femoris and brachial biceps muscles during low-to-moderate-level isometric contractions, and some of the channels (5-25%) were randomly marked as outliers. The root-mean-square error (RMSE) between the original and reconstructed maps was then calculated. RESULTS Overall, the proposed Poisson and wave PDE outperformed the other methods (average RMSE 8.7 μVrms ± 6.1 μVrms and 7.5 μVrms ± 5.9 μVrms) for the time-averaged single-differential and monopolar map reconstruction, respectively. Biharmonic Spline, the discrete cosine transform, and the Poisson PDE outperformed the other methods for the instantaneous map reconstruction. The running time of the proposed Poisson and wave PDE methods, implemented using a Vectorization package, was 4.6 ± 5.7 ms and 0.6 ± 0.5 ms, respectively, for each signal epoch or time sample in each channel. CONCLUSION The proposed reconstruction algorithms could be promising new tools for reconstructing muscle activity maps in real-time applications. SIGNIFICANCE Proper reconstruction methods could recover the information of low-quality recorded channels in HDsEMG signals.
Collapse
|
9
|
Yang Z, Chen Y. Surface EMG-based Sketching Recognition Using Two Analysis Windows and Gene Expression Programming. Front Neurosci 2016; 10:445. [PMID: 27790083 PMCID: PMC5064664 DOI: 10.3389/fnins.2016.00445] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2016] [Accepted: 09/14/2016] [Indexed: 11/13/2022] Open
Abstract
Sketching is one of the most important processes in the conceptual stage of design. Previous studies have relied largely on the analyses of sketching process and outcomes; whereas surface electromyographic (sEMG) signals associated with sketching have received little attention. In this study, we propose a method in which 11 basic one-stroke sketching shapes are identified from the sEMG signals generated by the forearm and upper arm muscles from 4 subjects. Time domain features such as integrated electromyography, root mean square and mean absolute value were extracted with analysis windows of two length conditions for pattern recognition. After reducing data dimensionality using principal component analysis, the shapes were classified using Gene Expression Programming (GEP). The performance of the GEP classifier was compared to the Back Propagation neural network (BPNN) and the Elman neural network (ENN). Feature extraction with the short analysis window (250 ms with a 250 ms increment) improved the recognition rate by around 6.4% averagely compared with the long analysis window (2500 ms with a 2500 ms increment). The average recognition rate for the eleven basic one-stroke sketching patterns achieved by the GEP classifier was 96.26% in the training set and 95.62% in the test set, which was superior to the performance of the BPNN and ENN classifiers. The results show that the GEP classifier is able to perform well with either length of the analysis window. Thus, the proposed GEP model show promise for recognizing sketching based on sEMG signals.
Collapse
Affiliation(s)
- Zhongliang Yang
- College of Mechanical Engineering, Donghua University Shanghai, China
| | - Yumiao Chen
- Fashion and Art Design Institute, Donghua University Shanghai, China
| |
Collapse
|
10
|
|
11
|
Geethanjali P. A mechatronics platform to study prosthetic hand control using EMG signals. AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE 2016; 39:765-71. [PMID: 27278475 DOI: 10.1007/s13246-016-0458-6] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/27/2015] [Accepted: 06/05/2016] [Indexed: 11/24/2022]
Abstract
In this paper, a low-cost mechatronics platform for the design and development of robotic hands as well as a surface electromyogram (EMG) pattern recognition system is proposed. This paper also explores various EMG classification techniques using a low-cost electronics system in prosthetic hand applications. The proposed platform involves the development of a four channel EMG signal acquisition system; pattern recognition of acquired EMG signals; and development of a digital controller for a robotic hand. Four-channel surface EMG signals, acquired from ten healthy subjects for six different movements of the hand, were used to analyse pattern recognition in prosthetic hand control. Various time domain features were extracted and grouped into five ensembles to compare the influence of features in feature-selective classifiers (SLR) with widely considered non-feature-selective classifiers, such as neural networks (NN), linear discriminant analysis (LDA) and support vector machines (SVM) applied with different kernels. The results divulged that the average classification accuracy of the SVM, with a linear kernel function, outperforms other classifiers with feature ensembles, Hudgin's feature set and auto regression (AR) coefficients. However, the slight improvement in classification accuracy of SVM incurs more processing time and memory space in the low-level controller. The Kruskal-Wallis (KW) test also shows that there is no significant difference in the classification performance of SLR with Hudgin's feature set to that of SVM with Hudgin's features along with AR coefficients. In addition, the KW test shows that SLR was found to be better in respect to computation time and memory space, which is vital in a low-level controller. Similar to SVM, with a linear kernel function, other non-feature selective LDA and NN classifiers also show a slight improvement in performance using twice the features but with the drawback of increased memory space requirement and time. This prototype facilitated the study of various issues of pattern recognition and identified an efficient classifier, along with a feature ensemble, in the implementation of EMG controlled prosthetic hands in a laboratory setting at low-cost. This platform may help to motivate and facilitate prosthetic hand research in developing countries.
Collapse
Affiliation(s)
- P Geethanjali
- School of Electrical Engineering, VIT University, Vellore, Tamil Nadu, 632 014, India.
| |
Collapse
|
12
|
A sparse Bayesian learning based scheme for multi-movement recognition using sEMG. AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE 2015; 39:59-69. [PMID: 26577712 DOI: 10.1007/s13246-015-0395-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/09/2015] [Accepted: 11/01/2015] [Indexed: 10/22/2022]
Abstract
This paper proposed a feature extraction scheme based on sparse representation considering the non-stationary property of surface electromyography (sEMG). Sparse Bayesian learning was introduced to extract the feature with optimal class separability to improve recognition accuracy of multi-movement patterns. The extracted feature, sparse representation coefficients (SRC), represented time-varying characteristics of sEMG effectively because of the compressibility (or weak sparsity) of the signal in some transformed domains. We investigated the effect of the proposed feature by comparing with other fourteen individual features in offline recognition. The results demonstrated the proposed feature revealed important dynamic information in the sEMG signals. The multi-feature sets formed by the SRC and other single feature yielded more superior performance on recognition accuracy, compared with the single features. The best average recognition accuracy of 94.33% was gained by using SVM classifier with the multi-feature set combining the feature SRC, Williston amplitude (WAMP), wavelength (WL) and the coefficients of the fourth order autoregressive model (ARC4) via multiple kernel learning framework. The proposed feature extraction scheme (known as SRC + WAMP + WL + ARC4) is a promising method for multi-movement recognition with high accuracy.
Collapse
|