Wearable-Based Parkinson’s Disease Severity Monitoring Using Deep Learning

Goschenhofer, Jann; Pfister, Franz; Yüksel, Kamer Ali; Bischl, Bernd; Fietzek, Urban; Thomas, Janek

doi:10.1007/978-3-030-46133-1_24

Cited by 17 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data imbalance is a common problem, which can be addressed by data enhancement and standardization [7]. Goschenhofer et al [12] used a grade-weighted approach to balance data for motion status classification. Shaker et al used the Build-Adversarial Network to balance the data and proposed a deep summary neural network hierarchical approach to classify signals.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Multihead ConvLSTM for Time Series Classification in eHealth Industry 4.0

Wang

Sun

Peng

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Healthcare time series classification is to classify the collected human physiological information based on artificial intelligence technologies. The main purpose is to use pattern recognition technology to enable machines to analyze characteristics of human physiological signals based on deep learning in electronic health (E-health) industry 4.0. Healthcare time series classification can analyze various physiological information of the human body, make correct disease treatments, and reduce medical costs. In this paper, we propose a multiple-head convolutional LSTM (MCL) model for healthcare time series classification. MCL is a convolutional LSTM (ConvLSTM) model with multiple heads. It can extract both time and spatial features of healthcare data and increase the number of features to achieve more accurate classification results.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We chose confusion matrix to visualize the performance of the model, and in confusion matrix, we used accuracy, precision, and recall, F1_score to accurately reflect the performance of the model. Table 1 shows the confusion matrix, and formulas (9) to (12) show the precision, recall, and F1_score.…”

Section: Model Evaluationmentioning

confidence: 99%

A Multihead ConvLSTM for Time Series Classification in eHealth Industry 4.0

Wang

Sun

Peng

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Other bio-data including dopamine transporter data from tomographic images [24] and serum cytokines [25] have also been used for classification performance evaluation via extraction of shape features based on generated areas of interest from images and other indicators, while discrimination of patient motor status via machine learning has also been recently tested on a digital biomarker data set using Neural Network Construction methodology [26]. Deep learning modeling algorithms have also been recently utilized for tracing and identifying Parkinson's via fuzzy recurrence plots [27] and monitoring and predicting of Parkinson's disease via wearable sensors [28,29]. Work has also been done on Parkinson's diagnosis via deep learning through medical imaging [30], handwritten dynamics [31] and voice data sets [32].…”

Section: Introductionmentioning

confidence: 99%

A Study on the Essential and Parkinson’s Arm Tremor Classification

Skaramagkas

Ανδρικόπουλος

Kefalopoulou

et al. 2021

Signals

View full text Add to dashboard Cite

In this article, the challenge of discriminating between essential and Parkinson’s tremor is addressed. Although a variety of methods have been proposed for diagnosing the severity of these highly occurring tremor types, their rapid and effective identification, especially in their early stages, proves particularly difficult and complicated due to their wide range of causes and similarity of symptoms. To this goal, a clinical analysis was performed, where a number of volunteers including essential and Parkinson’s tremor-diagnosed patients underwent a series of pre-defined motion patterns, during which a wearable sensing setup was used to measure their lower arm tremor characteristics from multiple selected points. Extracted features from the acquired accelerometer signals were used to train classification algorithms, including decision trees, discriminant analysis, support vector machine (SVM), K-nearest neighbor (KNN) and ensemble learning algorithms, for providing a comparative study and evaluating the potential of utilizing machine learning to accurately discriminate among different tremor types. Overall, SVM related classifiers proved to be the most successful in terms of classifying between Parkinson’s, essential and no tremor diagnosed with percentages reaching up to 100% for a single accelerometer measurement at the metacarpal area. In general and in motion while holding an object position, Coarse Gaussian SVM classifier reached 82.62% accuracy.

show abstract

“…For instance, in disease monitoring sensor data is collected with low effort but the labelling of this data requires timeconsuming work by medical experts (see, e.g., Goschenhofer et al, 2019). Semi-supervised learning (SSL) addresses this issue by leveraging large amounts of unlabelled data in combination with a small amount of labelled data when training machine learning (ML) models.…”

Section: Introductionmentioning

confidence: 99%

Deep Semi-Supervised Learning for Time Series Classification

Goschenhofer,

Hvingelby,

Rügamer

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

While Semi-supervised learning has gained much attention in computer vision on image data, yet limited research exists on its applicability in the time series domain. In this work, we investigate the transferability of state-of-the-art deep semisupervised models from image to time series classification. We discuss the necessary model adaptations, in particular an appropriate model backbone architecture and the use of tailored data augmentation strategies. Based on these adaptations, we explore the potential of deep semi-supervised learning in the context of time series classification by evaluating our methods on large public time series classification problems with varying amounts of labelled samples. We perform extensive comparisons under a decidedly realistic and appropriate evaluation scheme with a unified reimplementation of all algorithms considered, which is yet lacking in the field. We find that these transferred semi-supervised models show significant performance gains over strong supervised, semi-supervised and self-supervised alternatives, especially for scenarios with very few labelled samples.

show abstract

Wearable-Based Parkinson’s Disease Severity Monitoring Using Deep Learning

Cited by 17 publications

References 32 publications

A Multihead ConvLSTM for Time Series Classification in eHealth Industry 4.0

A Multihead ConvLSTM for Time Series Classification in eHealth Industry 4.0

A Study on the Essential and Parkinson’s Arm Tremor Classification

Deep Semi-Supervised Learning for Time Series Classification

Contact Info

Product

Resources

About