scholarly journals Fusion Models for Generalized Classification of Multi-Axial Human Movement: Validation in Sport Performance

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8409
Author(s):  
Rajesh Amerineni ◽  
Lalit Gupta ◽  
Nathan Steadman ◽  
Keshwyn Annauth ◽  
Charles Burr ◽  
...  
Keyword(s):  
Human Performance ◽  
Wearable Sensors ◽  
Human Movement ◽  
Sport Performance ◽  
Time Warping ◽  
Action Classification ◽  
Human Movements ◽  
Non Linear ◽  
Dynamic Time

We introduce a set of input models for fusing information from ensembles of wearable sensors supporting human performance and telemedicine. Veracity is demonstrated in action classification related to sport, specifically strikes in boxing and taekwondo. Four input models, formulated to be compatible with a broad range of classifiers, are introduced and two diverse classifiers, dynamic time warping (DTW) and convolutional neural networks (CNNs) are implemented in conjunction with the input models. Seven classification models fusing information at the input-level, output-level, and a combination of both are formulated. Action classification for 18 boxing punches and 24 taekwondo kicks demonstrate our fusion classifiers outperform the best DTW and CNN uni-axial classifiers. Furthermore, although DTW is ostensibly an ideal choice for human movements experiencing non-linear variations, our results demonstrate deep learning fusion classifiers outperform DTW. This is a novel finding given that CNNs are normally designed for multi-dimensional data and do not specifically compensate for non-linear variations within signal classes. The generalized formulation enables subject-specific movement classification in a feature-blind fashion with trivial computational expense for trained CNNs. A commercial boxing system, ‘Corner’, has been produced for real-world mass-market use based on this investigation providing a basis for future telemedicine translation.

Continuous Motion Classification and Segmentation Based on Improved Dynamic Time Warping Algorithm

2017 ◽  
Vol 32 (02) ◽  
pp. 1850002 ◽  
Author(s):  
Mingqin Liu ◽  
Xiaoguang Zhang ◽  
Guiyun Xu
Keyword(s):  
Action Recognition ◽  
Dynamic Time Warping ◽  
The Other ◽  
Continuous Image ◽  
Single Image ◽  
Time Warping ◽  
Continuous Action ◽  
Template Sequence ◽  
Dynamic Time

The continuous image sequence recognition is more difficult than the single image recognition because the classification of continuous image sequences and the image edge recognition must be very accurate. Hence, a method based on sequence alignment for action segmentation and classification is proposed to reconstruct a template sequence by estimating the mean action of a class category, which calculates the distance between a single image and a template sequence by sparse coding in Dynamic Time Warping. The proposed method, the methods of Kulkarni et al. [Continuous action recognition based on sequence alignment, Int. J. Comput. Vis. pp. 1–26.] and Hoai et al. [Joint segmentation and classification of human actions in video, IEEE Conf. Computer Vision and Pattern Recognition, 2008, pp. 108–119.] are compared on the recognition accuracy of the continuous recognition and isolated recognition, which clearly shows that the proposed method outperforms the other methods. When applied to continuous gesture classification, it not only can recognize the gesture categories more quickly and accurately, but is more realistic in solving continuous action recognition problems in a video than the other existing methods.

FRACTAL-BASED CLASSIFICATION OF ELECTROMYOGRAPHY (EMG) SIGNAL BETWEEN FINGERS AND HAND’S BASIC MOVEMENTS, FUNCTIONAL MOVEMENTS, AND FORCE PATTERNS

Fractals ◽  
2019 ◽  
Vol 27 (04) ◽  
pp. 1950050 ◽  
Author(s):  
HAMIDREZA NAMAZI
Keyword(s):  
Linear Structure ◽  
Human Movement ◽  
The Body ◽  
Emg Signal ◽  
Human Movements ◽  
Main Indicator ◽  
Human Ability ◽  
Rehabilitation Science ◽  
Functional Movements

Analysis of human ability to move the body (hand, feet, etc.) is one of the major issues in rehabilitation science. For this purpose, scientists analyze different signals govern from human body. Electromyography (EMG) signal is the main indicator of human movement that can be analyzed using different techniques in order to classify different movements. In this paper, we analyze the complex non-linear structure of EMG signal from subjects while they underwent three exercises that include basic movements of the fingers and of the wrist, grasping and functional movements, and force patterns. For this purpose, we employ fractal dimension as indicator of complexity. The result of our analysis showed that the EMG signal experiences the greatest complexity when subjects think to press combinations of fingers with an increasing force (force pattern). The method of analysis employed in this research can be widely applied to analyze and classify different types of human movements.

scholarly journals A Comprehensive Survey on On-line Handwriting Recognition Technology and its Real Application to the Nepalese Natural Handwriting

1970 ◽  
Vol 5 (1) ◽  
pp. 31-55 ◽  
Author(s):  
Santosh KC ◽  
Cholwich Nattee
Keyword(s):  
Dynamic Time Warping ◽  
Feature Vector ◽  
Handwriting Recognition ◽  
Recognition System ◽  
Time Warping ◽  
Real Application ◽  
Non Linear ◽  
Comprehensive Survey ◽  
On Line ◽  
Dynamic Time

Handwriting Recognition Technology has been improving much under the purview of pattern recognition and image processing since a few decades. This paper focuses on the comprehensive survey on on-line handwriting recognition system along with the real application by taking Nepali natural handwriting (a real example of one of the cursive handwritings). The survey mainly includes pre-processing, feature vector and similarity measures in between the non-linear 2D sequences of coordinates, and their effective applications. A very highlighting topic "Dynamic Time Warping Algorithm'' (DTW) is introduced, which has been popular in determining the distance between two non-linear sequences ranging from handwriting to speech recognition. Besides these contemporary research issues/areas, stroke number and order free Nepalese natural handwritten recognition system is presented in the second step. Writing one's own style brings unevenness in writing units, which is the most difficult part to classify. Writing units reveal number, shape, size, order of stroke, and speed in writing. Variation in the number of strokes, their order, shapes and sizes, tilting angles and similarities among characters from one another are the important factors, which are to be considered in classification for Nepali. This paper utilizes structural properties of those alphanumeric characters, which have variable writing units. It uses a string of pen tip's positions and tangent angles of every consecutive point as a feature vector sequence of a stroke. We constructed a prototype recognizer that uses the DTW algorithm to align handwritten strokes with stored strokes' templates and determine their similarity. Separate system is trained for original and preprocessed writing samples and achieved recognition rates of 85.87% and 88.59% respectively. This introduces novel real time handwriting recognition on Nepalese alphanumeric characters, which are independent of number of strokes, as well as their order. Key Words: Handwriting Recognition System; Pre-processing; Feature Vector; Dynamic Time Warping; Agglomerating Hierarchical Clustering; Nepali. DOI: 10.3126/kuset.v5i1.2845 Kathmandu University Journal of Science, Engineering and Technology Vol.5, No.1, January 2009, pp 31-55

Dynamic time warping based connectivity classification of event-related potentials

2019 ◽  
Author(s):  
Kadhum Kareem Al-rubaye ◽  
Oğuz Bayat ◽  
Osman Nuri Ucan ◽  
Dilek Göksel Duru ◽  
Adil Deniz Duru
Keyword(s):  
Dynamic Time Warping ◽  
Event Related Potentials ◽  
Time Warping ◽  
Related Potentials ◽  
Dynamic Time

scholarly journals Efficient Kernel-Based Subsequence Search for Enabling Health Monitoring Services in IoT-Based Home Setting

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5192 ◽  
Author(s):  
Antonio Candelieri ◽  
Stanislav Fedorov ◽  
Enza Messina
Keyword(s):  
Time Series ◽  
Wearable Sensors ◽  
Real Life ◽  
Streaming Data ◽  
Elderly Subjects ◽  
Time Warping ◽  
Home Setting ◽  
Benchmark Datasets ◽  
Dynamic Time ◽  
The Given

This paper presents an efficient approach for subsequence search in data streams. The problem consists of identifying coherent repetitions of a given reference time-series, also in the multivariate case, within a longer data stream. The most widely adopted metric to address this problem is Dynamic Time Warping (DTW), but its computational complexity is a well-known issue. In this paper, we present an approach aimed at learning a kernel approximating DTW for efficiently analyzing streaming data collected from wearable sensors, while reducing the burden of DTW computation. Contrary to kernel, DTW allows for comparing two time-series with different length. To enable the use of kernel for comparing two time-series with different length, a feature embedding is required in order to obtain a fixed length vector representation. Each vector component is the DTW between the given time-series and a set of “basis” series, randomly chosen. The approach has been validated on two benchmark datasets and on a real-life application for supporting self-rehabilitation in elderly subjects has been addressed. A comparison with traditional DTW implementations and other state-of-the-art algorithms is provided: results show a slight decrease in accuracy, which is counterbalanced by a significant reduction in computational costs.

Sign in / Sign up

Export Citation Format

Share Document