A deep learning approach for detecting tic disorder using wireless channel information

Barua, Arnab; Dong, Chunxi; Yang, Xiaodong

doi:10.1002/ett.3964

Cited by 10 publications

(12 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To monitor pregnant woman that suffers from a disease known as Eclampsia, Daniyal Haider et al 14 uses 5G sensing technology to extract perturbations of WCI, and differentiates eclamptic seizures from other body motions with classifiers such as Support Vector Machine (SVM). Arnab Barua et al 15 presents a work that classifies WCI-based image data by convolutional neural network for the involuntary movement diseases. The multiple ways of monitoring health data give promise to emergency identification, but also cause integration problem in data processing, which needs careful consideration.…”

Section: Data Collectionmentioning

confidence: 99%

Context‐aware emergency detection method for edge computing‐based healthcare monitoring system

Wang

Cai

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

When taking physical exercise, healthcare monitoring systems are needed to detect emergencies, such as sychnosphygmia, and so on. However, heterogeneity and privacy make it more challenging to collect and process multi‐source healthcare data in a real time manner. To support healthcare monitoring, in this research, a multi‐layer edge computing‐based framework is designed to detect emergencies in low latency and secure ways. First, a universal data model is defined to process heterogeneous data from multi‐sources such as sensors or smart devices. Then, Gated Recurrent Units‐based (GRU) model is utilized to capture and process physiological data series. Fine‐grained detection models are built and distinguished according to scenario information and individual health persona. In the proposed edge computing‐based framework, detection algorithm computation and physiological index data storage are close to end user sides to support low latency. Meanwhile encryption algorithm is used to protect data privacy. Finally, a case study in the Physical Education Class scenario is implemented to demonstrate the feasibility of our methods. The experimental result shows that our GRU model is more accurate and is three times faster for emergency identification compared with Support Vector Classification model.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Context‐aware emergency detection method for edge computing‐based healthcare monitoring system

Wang

Cai

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…It turns out that deep learning can eliminate the need for artificial feature extraction. Barua et al (2021) propose a deep learning approach for detecting TD using wireless channel information and achieved an accuracy above 97%. The data used in the task are simulated using healthy human subjects.…”

Section: Introductionmentioning

confidence: 99%

Light-efficient channel attention in convolutional neural networks for tic recognition in the children with tic disorders

Geng

Ding

et al. 2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Tic is a combination of a series of static facial and limb movements over a certain period in some children. However, due to the scarcity of tic disorder (TD) datasets, the existing work on tic recognition using deep learning does not work well. It is that spatial complexity and time-domain variability directly affect the accuracy of tic recognition. How to extract effective visual information for temporal and spatial expression and classification of tic movement is the key of tic recognition. We designed the slow-fast and light-efficient channel attention network (SFLCA-Net) to identify tic action. The whole network adopted two fast and slow branch subnetworks, and light-efficient channel attention (LCA) module, which was designed to solve the problem of insufficient complementarity of spatial-temporal channel information. The SFLCA-Net is verified on our TD dataset and the experimental results demonstrate the effectiveness of our method.

show abstract

“…[9] used support vector machines to classify tics based on segmented temporal windows of deep brain simulation signals. [10] used LeNet-5 to classify tics based on segmented temporal windows of wireless channel information signals. [11] used LSTM to classify tics based on well-trimmed temporal windows of deep features extracted from the videos of patients using a convolutional neural network.…”

Section: Introductionmentioning

confidence: 99%

Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients

Tang

Béjar

Essoe

et al. 2022

2022 26th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Tourette Syndrome (TS) is a behavioral disorder that onsets in childhood and is characterized by the expression of involuntary movements and sounds commonly referred to as tics. Behavioral therapy is the first-line treatment for patients with TS, and it helps patients raise awareness about tic occurrence as well as develop tic inhibition strategies. However, the limited availability of therapists and the difficulties for in-home follow up work limits its effectiveness. An automatic tic detection system that is easy to deploy could alleviate the difficulties of hometherapy by providing feedback to the patients while exercising tic awareness. In this work, we propose a novel architecture (T-Net) for automatic tic detection and classification from untrimmed videos. T-Net combines temporal detection and segmentation and operates on features that are interpretable to a clinician. We compare T-Net to several state-of-the-art systems working on deep features extracted from the raw videos and T-Net achieves comparable performance in terms of average precision while relying on interpretable features needed in clinical practice.

show abstract

A deep learning approach for detecting tic disorder using wireless channel information

Cited by 10 publications

References 51 publications

Context‐aware emergency detection method for edge computing‐based healthcare monitoring system

Context‐aware emergency detection method for edge computing‐based healthcare monitoring system

Light-efficient channel attention in convolutional neural networks for tic recognition in the children with tic disorders

Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients

Contact Info

Product

Resources

About