Applying Deep Learning to Stereotypical Motor Movement Detection in Autism Spectrum Disorders

Rad, Nastaran Mohammadian; Furlanello, Cesare

doi:10.1109/icdmw.2016.0178

Cited by 57 publications

(40 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For comparison purposes, all the neural networks used in our experiments employed the Adam [29] Aside from the two architectures described earlier, namely stacked-LSTM and dual-stream LSTM, we use a CNN, a Conv-LSTM and a Bi-LSTM proposed in HAR scenarios [24,22,17] for comparison. An optimization experiment was conducted to find the optimal hyper-parameter settings of these methods: i) For stacked-LSTM, three LSTM layers each with 32 hidden units followed by a dropout layer with probability of 0.5 are used; ii) For dual-stream LSTM, two sets of 3 LSTM layers each with 24 hidden units and 8 hidden units followed by dropout layer with probability of 0.5 are used respectively for the MoCap and sEMG streams; iii) For CNN [24], three convolutional layers each with 10 kernels of size 1 × 10 and followed by 1 × 2 max-pooling layer are used, and a softmax layer in the end is used for classification; iv) For Conv-LSTM [22], the architecture is used with 10 kernels of size 1 × 10 in each convolutional layer followed by max-pooling of size 1 × 2, and the number of hidden units of each LSTM layer is set to 32; v) For Bi-LSTM [17], 3 bidirectional LSTM layers with 16 hidden units in each are used.…”

Section: Methodsmentioning

confidence: 99%

Recurrent network based automatic detection of chronic pain protective behavior using MoCap and sEMG data

Wang

Olugbade

Mathur

et al. 2019

Proceedings of the 23rd International Symposium on Wearable Computers

View full text Add to dashboard Cite

In chronic pain physical rehabilitation, physiotherapists adapt exercise sessions according to the movement behavior of patients. As rehabilitation moves beyond clinical sessions, technology is needed to similarly assess movement behaviors and provide such personalized support. In this paper, as a first step, we investigate automatic detection of protective behavior (movement behavior due to pain-related fear or pain) based on wearable motion capture and electromyography sensor data. We investigate two recurrent networks (RNN) referred to as stacked-LSTM and dual-stream LSTM, which we compare with related deep learning (DL) architectures. We further explore data augmentation techniques and additionally analyze the impact of segmentation window lengths on detection performance. The leading performance of 0.815 mean F1 score achieved by stacked-LSTM provides important grounding for the development of wearable technology to support chronic pain physical rehabilitation during daily activities.

show abstract

Section: Methodsmentioning

confidence: 99%

Recurrent network based automatic detection of chronic pain protective behavior using MoCap and sEMG data

Wang

Olugbade

Mathur

et al. 2019

Proceedings of the 23rd International Symposium on Wearable Computers

View full text Add to dashboard Cite

show abstract

“…Naive Bayes Classification or Support Vector Machine [31]). CNN is commonly applied in various areas ( [32], [33]) where a convenient description can be made by a 2D matrix like in our case. 2D feature map structure is used because time (or space) are assumed to be locally related features.…”

Section: Classification Of Planar Segmentsmentioning

confidence: 99%

Object Detection From a Few LIDAR Scanning Planes

Rózsa

Szirányi

2019

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

LIDAR sensors enable object and free-space detection for intelligent transportation systems and vehicles. This paper proposes a recognition method for LIDARs based on only a few detection planes. This method is useful especially in the case when the angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. We use Fourier descriptor to characterize a scan plane and Convolutional Neural Network for classification. Our method exploits both time varying shape information and contours from multiple scan planes if available. The method performs at least as well as the state of the art algorithms in case of near field, and it also expands the detection range. It was evaluated on tens of thousands of samples from large public datasets and we did separate evaluation for far field objects as well.

show abstract

“…Recent studies on automatic SMM and FOG detection using wearable sensors have mainly focused on applying supervised machine learning and deep learning approaches, such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), to distinguish between the normal and abnormal movements [ 9 , 32 , 33 , 34 , 35 , 36 , 37 ]. These methods are based on extracting or learning a set of robust features from the original signals and then applying the supervised algorithms for abnormal movement detection.…”

Section: Related Workmentioning

confidence: 99%

Novelty Detection using Deep Normative Modeling for IMU-Based Abnormal Movement Monitoring in Parkinson’s Disease and Autism Spectrum Disorders

Rad

Laarhoven

Furlanello

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Detecting and monitoring of abnormal movement behaviors in patients with Parkinson’s Disease (PD) and individuals with Autism Spectrum Disorders (ASD) are beneficial for adjusting care and medical treatment in order to improve the patient’s quality of life. Supervised methods commonly used in the literature need annotation of data, which is a time-consuming and costly process. In this paper, we propose deep normative modeling as a probabilistic novelty detection method, in which we model the distribution of normal human movements recorded by wearable sensors and try to detect abnormal movements in patients with PD and ASD in a novelty detection framework. In the proposed deep normative model, a movement disorder behavior is treated as an extreme of the normal range or, equivalently, as a deviation from the normal movements. Our experiments on three benchmark datasets indicate the effectiveness of the proposed method, which outperforms one-class SVM and the reconstruction-based novelty detection approaches. Our contribution opens the door toward modeling normal human movements during daily activities using wearable sensors and eventually real-time abnormal movement detection in neuro-developmental and neuro-degenerative disorders.

show abstract

Applying Deep Learning to Stereotypical Motor Movement Detection in Autism Spectrum Disorders

Cited by 57 publications

References 35 publications

Recurrent network based automatic detection of chronic pain protective behavior using MoCap and sEMG data

Recurrent network based automatic detection of chronic pain protective behavior using MoCap and sEMG data

Object Detection From a Few LIDAR Scanning Planes

Novelty Detection using Deep Normative Modeling for IMU-Based Abnormal Movement Monitoring in Parkinson’s Disease and Autism Spectrum Disorders

Contact Info

Product

Resources

About