sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges
Authors: Maurício Cagliari Tosin, Juliano Costa Machado, Alexandre Balbinot
JAIR 2022 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | A systematic review was conducted, and the retrieved papers were organized according to the system step related to the proposed method. Then, for each stage of the upper limb motion recognition system, the works were described and compared in terms of strategy, methodology and issue addressed. An additional section was destined for the description of works related to signal contamination that is often neglected in reviews focused on s EMG based motion classifiers. Therefore, this section is the main contribution of this paper. Deep learning methods are a current trend for classification stage, providing strategies based on time-series and transfer learning to address the issues related to limb position, temporal/inter-subject variation, and electrode displacement. Despite the promising strategies presented for contaminant detection, identification, and removal, there are still some factors to be considered, such as the occurrence of simultaneous contaminants. This review exposes the current scenario of the movement classification system, providing valuable information for new researchers and guiding future works towards myo-controlled devices. |
| Researcher Affiliation | Academia | Maurício Cagliari Tosin (Corresponding author) EMAIL Juliano Costa Machado EMAIL Alexandre Balbinot Federal University of Rio Grande do Sul EMAIL |
| Pseudocode | No | No structured pseudocode or algorithm blocks are present in the paper. Methodologies are described narratively and summarized in tables. |
| Open Source Code | No | The paper does not provide explicit statements about releasing source code for the methodology described, nor does it include any links to code repositories. |
| Open Datasets | Yes | Table 1 shows a description of the works that focused in provide publicly available s EMG datasets of hand gestures. The works conducted by Palermo et al. (2017), Du et al. (2017), Cene et al. (2019a) and Kaczmarek et al. (2019) stand out for performing acquisitions with the same volunteer on different days. Thus, all temporal variability sources present in the s EMG signal, already mentioned, are included in the available data. Hence, it is possible for a confounding factor to be considered in the development and evaluation of classification systems designed by other researchers, enabling the creation of more robust algorithms. These data form Dataset #6 of the Nina Pro project. |
| Dataset Splits | No | This paper is a systematic review and does not conduct its own experiments or define dataset splits. It discusses dataset splitting methodologies (e.g., 'leave-one-subject-out cross-validation technique') used in other research papers that it reviews, but does not provide specific splits for its own work. |
| Hardware Specification | No | This paper is a systematic review and does not conduct its own experiments, therefore, it does not provide specific hardware details used for running experiments. It discusses hardware used for data acquisition in other reviewed papers, such as 'Cometa manufacturer Mini Wave model' or 'Myo Armband units'. |
| Software Dependencies | No | This paper is a systematic review and does not implement its own software. While it discusses various algorithms and software tools used in other research (e.g., CNN, LSTM, SVM), it does not provide specific version numbers for any software dependencies required to replicate its own work. |
| Experiment Setup | No | This paper is a systematic review and does not describe any specific experimental setup, hyperparameters, or training configurations for its own work. |