Dataset Information

Non-invasive control interfaces for intention detection in active movement-assistive devices.

ABSTRACT: Active movement-assistive devices aim to increase the quality of life for patients with neuromusculoskeletal disorders. This technology requires interaction between the user and the device through a control interface that detects the user's movement intention. Researchers have explored a wide variety of invasive and non-invasive control interfaces. To summarize the wide spectrum of strategies, this paper presents a comprehensive review focused on non-invasive control interfaces used to operate active movement-assistive devices. A novel systematic classification method is proposed to categorize the control interfaces based on: (I) the source of the physiological signal, (II) the physiological phenomena responsible for generating the signal, and (III) the sensors used to measure the physiological signal. The proposed classification method can successfully categorize all the existing control interfaces providing a comprehensive overview of the state of the art. Each sensing modality is briefly described in the body of the paper following the same structure used in the classification method. Furthermore, we discuss several design considerations, challenges, and future directions of non-invasive control interfaces for active movement-assistive devices.

SUBMITTER: Lobo-Prat J

PROVIDER: S-EPMC4459663 | biostudies-literature | 2014 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Non-invasive control interfaces for intention detection in active movement-assistive devices.

Lobo-Prat Joan J Kooren Peter N PN Stienen Arno H A AH Herder Just L JL Koopman Bart F J M BF Veltink Peter H PH

Journal of neuroengineering and rehabilitation 20141217

Active movement-assistive devices aim to increase the quality of life for patients with neuromusculoskeletal disorders. This technology requires interaction between the user and the device through a control interface that detects the user's movement intention. Researchers have explored a wide variety of invasive and non-invasive control interfaces. To summarize the wide spectrum of strategies, this paper presents a comprehensive review focused on non-invasive control interfaces used to operate a ...[more]

PMID: 25516421

Similar Datasets

Project description:Decoding movement related intentions is a key step to implement BMIs. Decoding EEG has been challenging due to its low spatial resolution and signal to noise ratio. Metric learning allows finding a representation of data in a way that captures a desired notion of similarity between data points. In this study, we investigate how metric learning can help finding a representation of the data to efficiently classify EEG movement and pre-movement intentions. We evaluate the effectiveness of the obtained representation by comparing classification the performance of a Support Vector Machine (SVM) as a classifier when trained on the original representation, called Euclidean, and representations obtained with three different metric learning algorithms, including Conditional Entropy Metric Learning (CEML), Neighborhood Component Analysis (NCA), and the Entropy Gap Metric Learning (EGML) algorithms. We examine different types of features, such as time and frequency components, which input to the metric learning algorithm, and both linear and non-linear SVM are applied to compare the classification accuracies on a publicly available EEG data set for two subjects (Subject B and C). Although metric learning algorithms do not increase the classification accuracies, their interpretability using an importance measure we define here, helps understanding data organization and how much each EEG channel contributes to the classification. In addition, among the metric learning algorithms we investigated, EGML shows the most robust performance due to its ability to compensate for differences in scale and correlations among variables. Furthermore, from the observed variations of the importance maps on the scalp and the classification accuracy, selecting an appropriate feature such as clipping the frequency range has a significant effect on the outcome of metric learning and subsequent classification. In our case, reducing the range of the frequency components to 0–5 Hz shows the best interpretability in both Subject B and C and classification accuracy for Subject C. Our experiments support potential benefits of using metric learning algorithms by providing visual explanation of the data projections that explain the inter class separations, using importance. This visualizes the contribution of features that can be related to brain function.

Dataset Information

Non-invasive control interfaces for intention detection in active movement-assistive devices.

Publications

Non-invasive control interfaces for intention detection in active movement-assistive devices.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets