• Physical Therapy Korea
• /
• v.8 no.1
• /
• pp.20-34
• /
• 2001

This paper presents the relevance between GMFM and the spatiotemporal parameters of gait in children with cerebral palsy. Twenty-one children ($73.11{\pm}30.06$ months) with cerebral palsy participated in this study. GMFM was performed and spatiotemporal parameters of gait were measured by foot print gait analysis. A correlation analysis was used to investigate the correlation between GMFM scores and spatiotemporal parameters of gait. A linear regression analysis was employed to find how much each gait spatiotemporal parameters could be predicted from GMFM scores. The total GMFM scores was significantly correlated with walking speed, cadence, and stride length. Dimensions D (standing) and E (walking, running, and jumping) were more significantly correlated with gait spatiotemporal parameters than dimensions A (lying and rolling), B (sitting), and C (crawling and kneeling). The GMFM scores were useful for predicting spatiotemporal parameters. However, it is difficult to predict the status of gait development using GMFM scores because GMFM scores and gait spatiotemporal parameters are only measured as quantities not qualities. In the field, it is easily found that many children with cerebral palsy are unable to walk in any way. Consequently, gait analysis cannot be performed in many cases. Therefore, it is more reasonable to investigate the influence of GMFM on spatiotemporal parameters, rather than vice versa.

• Physical Therapy Korea
• /
• v.11 no.2
• /
• pp.63-70
• /
• 2004

These were two main purposes of this study. The first was to research the relevance between gross motor function measurement (GMFM) and the spatiotemporal parameters of gait in children with cerebral palsy. The second was to research the relevance between gross motor performance measure (GMPM) and the spatiotemporal gait parameters. Twelve children ($6.0{\pm}1.8$ years) with cerebral palsy participated in this study. GMFM and GMPM were performed and the spatiotemporal parameters of gait were measured by using WalkWay MG-1000. There were no significant correlations between the GMFM score and the stride length, step length, step width, cadence, and velocity (p>.05). The GMPM score also had no significant correlation with the spatiotemporal gait parameter (p>.05).

• ETRI Journal
• /
• v.43 no.3
• /
• pp.538-548
• /
• 2021

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• The Journal of the Society of Stroke on Korean Medicine
• /
• v.14 no.1
• /
• pp.8-14
• /
• 2013

■ Objectives The goal of this study is to find the correlation between the motor function and gait pattern of stroke patients. ■ Methods We measured Manual muscle test(MMT), Motricity index(MI) and Spatiotemporal gait parameters of admitted hemiplegic patients with stroke. The gait parameters were measured using a Treadmill gait system. ■ Results There is a significant correlation between motor function and spatiotemporal parameters such as step length, stride length, step time, stride time, total double support or cadence, in stroke patients. ■ Conclusion The better motor function of stroke was, the more gait improved.

• Physical Therapy Korea
• /
• v.22 no.4
• /
• pp.27-33
• /
• 2015

The purpose of this study was to find which spatiotemporal gait parameters gained from stroke patients could be predictive factors for the gait part of Tinetti Performance-Oriented Mobility Assessment (POMA-G). Two hundred forty-six stroke patients were recruited for this study. They participated in two assessments, the POMA-G and computerized spatiotemporal gait analysis. To analyze the relationship between the POMA-G and spatiotemporal parameters, we used Pearson's correlation coefficients. In addition, multiple linear regression analyses (stepwise method) were used to predict the spatiotemporal gait parameters that correlated most with the POMA-G. The results show that the gait velocity (r=.67, p<.01), cadence (r=.66, p<.01), step length of the affected side (r=.49, p<.01), step length of the non-affected side (r=.53, p<.01), swing percentage of the non-affected side (r=.47, p<.01), and single support percentage of the affected side (r=.53, p<.01) as well as the double support percentage of the non-affected side (r=-.42, p<.01) and the step-length asymmetry (r=-.64, p<.01) correlated with POMA-G. The gait velocity, step-length asymmetry, cadence, and single support percentage of the affected side explained 67%, 2%, 2%, and 1% of the variance in the POMA-G, respectively. In conclusion, gait velocity would be the most predictive factor for the POMA-G.

• ETRI Journal
• /
• v.31 no.2
• /
• pp.151-161
• /
• 2009

In this paper, we propose an adaptive multiview video coding scheme based on spatiotemporal correlation analyses using hierarchical B picture (AMVC-HBP) for the integrative encoding performances, including high compression efficiency, low complexity, fast random access, and view scalability, by integrating multiple prediction structures. We also propose an in-coding mode-switching algorithm that enables AMVC-HBP to adaptively select a better prediction structure in the encoding process without any additional complexity. Experimental results show that AMVC-HBP outperforms the previous multiview video coding scheme based on H.264/MPEG-4 AVC using the hierarchical B picture (MVC-HBP) on low complexity for 21.5%, on fast random access for about 20%, and on view scalability for 11% to 15% on average. In addition, distinct coding gain can be achieved by AMVC-HBP for dense and fast-moving sequences compared with MVC-HBP.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.4
• /
• pp.251-257
• /
• 2016

The Pediatric Balance Scale (PBS) was balance measurement equipment for school-age children with mild to moderate motor impairments. The aims of this study are to examine the correlation between PBS and spatiotemporal gait parameter and to identify the walking function with cerebral palsy through balance scale. The PBS consists of 14 items such as sitting of standing, standing to sitting, transfers, standing unsupported, standing on one foot, turning 360 degrees, turing to look behind, etc., and the spatiotemporal parameters include walking speed, stride length, step length, step width, cadence, double-limb support. All subjects were independently ambulatory children with spastic diplegic cerebral palsy, and they were assessed on PBS and spatiotemporal gait parameters by an experienced pediatric physical therapist. Pearson's correlation coefficient was used to assess the correlation between PBS and spatiotemporal gait parameters, and the level of significance was set at ${\alpha}$ = 0.05. Total score of PBS(r=.49~.58), standing to sitting(r=.48~.60), turning to look behind(r=.47~.53), and pick up object(r=.52~.69) were positively correlated with walking speed, stride length, step length, and cadence. Most items of the PBS were negatively correlated with double-limb support(r=-.48~-.92). These findings suggest that the pediatric balance scale can be applied to estimate gait function level for children with spastic diplegic cerebral palsy.

• Physical Therapy Korea
• /
• v.20 no.4
• /
• pp.40-46
• /
• 2013

The purpose of this study was to determine which spatiotemporal gait parameters obtained during hemiplegic walking could be a predictive factor for the Timed Up and Go test (TUG). Two hundreds nine subjects who had suffered a stroke were recruited for this study. They were participated in two assessments; the TUG test and gait analysis. The relationship between the TUG test and spatiotemporal parameters was analyzed using Pearson's correlation coefficients. In addition, to predict the spatiotemporal gait parameters that correlated most with the TUG scores, we used multiple linear regression analyses (stepwise method). The results show that the normalized velocity was strongly correlated with the TUG performance (r=-.72, p<.001). Additionally, single support percentage (SSP), double support percentage (DSP), step time difference (STD), and step length difference (SLD) significantly were correlated with the TUG test. Normalized velocity, STD, DSP of affected side, and SSP of non-affected side explained 53%, 8%, 3%, 2%, of variance in the TUG test respectively. In conclusion, an increase in gait velocity and a decrease in STD would be effective indicators of improvement on the functional mobility in the stroke rehabilitation.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.661-671
• /
• 2022

Stayed cables are the key components for transmitting loads in cable-stayed bridges. Therefore, it is very important to evaluate the cable force condition to ensure bridge safety. An online condition assessment and anomaly localization method is proposed for cables based on the spatiotemporal correlation of grouped cable forces. First, an anomaly sensitive feature index is obtained based on the distribution characteristics of grouped cable forces. Second, an adaptive anomaly detection method based on the k-nearest neighbor rule is used to perform dissimilarity measurements on the extracted feature index, and such a method can effectively remove the interference of environment factors and vehicle loads on online condition assessment of the grouped cable forces. Furthermore, an online anomaly isolation and localization method for stay cables is established, and the complete decomposition contributions method is used to decompose the feature matrix of the grouped cable forces and build an anomaly isolation index. Finally, case studies were carried out to validate the proposed method using an in-service cable-stayed bridge equipped with a structural health monitoring system. The results show that the proposed approach is sensitive to the abnormal distribution of grouped cable forces and is robust to the influence of interference factors. In addition, the proposed approach can also localize the cables with abnormal cable forces online, which can be successfully applied to the field monitoring of cables for cable-stayed bridges.