• Journal of Industrial Technology
• /
• v.31 no.A
• /
• pp.63-69
• /
• 2011

A home-based rehabilitation system for patients with uncomfortable hands or arms was developed. By using this system, patients can save time and money of going to the hospital. The system's interface is easy to manipulate. In this paper, we discuss a rehabilitation system using video recognition; the focus is on designing a convenient user interface and rehabilitation training methods. The system consists of two screens: one for recording user's information and the other for training. A first-time user inputs his/her information. The system chooses the training method based on the information and records the training process automatically using video recognition. On the training screen, video clips of the training method and help messages are displayed for the user.

• The Journal of Korean society of community based occupational therapy
• /
• v.4 no.2
• /
• pp.53-61
• /
• 2014

Objective : The purpose of this study was to examine the effects of video observation training on neglect and ability to perform activities of daily living of stroke patients. Methods : Patients diagnosed with stroke were selected as subjects according to criteria to select the research targets. The additional video observation training besides OT and PT was carried out to 15 patients in an experimental group and sham therapy besides OT and PT was performed to 15 patients in a control group. Line-bisection test were conducted to compare the neglect before and after therapy intervention and FIM was conducted to compare the ability to perform the activities of daily living. Results : The result of this study that we found out that degree of neglect in an experimental group where video observation training was carried out improved neglect and the ability to perform activities of daily living. Conclusion : The video observation training the video observation training is expected to be useful in clinics.

• Journal of the Korean Society of Physical Medicine
• /
• v.7 no.4
• /
• pp.401-409
• /
• 2012

PURPOSE: The purpose of this study is to assess the difference in the effect of provision of feedback on knowledge of performance and knowledge of result in the training using somesthetic video game aimed at enhancement of balance of hemiparalysis patients due to stroke. METHODS: 20 stroke patients participated in the study. The participants were randomly divided into 2 groups, namely, the knowledge of performance feedback group (KP group, n=10) and the knowledge of result feedback group (KR group, n=10). Both groups received somesthetic video game training 5 times (30 minutes each) a week for total of 4 weeks. The KP group received feedback on the patterns of movement in execution of somesthetic video game. The KR group received feedback on the scores acquired following execution of somesthetic video game. Verification of the significance of the data was performed through paired t-test and independent t-test. RESULTS: Both groups displayed significant reduction in the movement of center of pressure (COP) and Timed up and Go (TUG), and significant increase in the Berg Balance Scale (BBS) following the training. Although the movement of COP was reduced for the KP group in comparison to the KR group, it was not statistically significant, and there was significant reduction in TUG and significant increase in BBS. CONCLUSION: The above results illustrate that provision of feedback on knowledge of performance is more effective than feedback on knowledge of result in somesthetic video game training for the purpose of enhancement of balance in stroke patients. Therefore, provision of feedback on knowledge of performance is necessary in somesthetic video game training for stroke patients.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1439-1445
• /
• 2013

We present a Taekwondo training system using a hybrid sensing technique of a body sensor and a visual sensor. Using a body sensor (accelerometer), rotational and inertial motion data are captured which are important for Taekwondo motion detection and evaluation. A visual sensor (camera) captures and records the sequential images of the performance. Motion chunk is proposed to structuralize Taekwondo motions and design HMM (Hidden Markov Model) for motion recognition. Trainees can evaluates their trial motions numerically by computing the distance to the standard motion performed by a trainer. For motion training video, the real-time video images captured by a camera is overlayed with a visualized body sensor data so that users can see how the rotational and inertial motion data flow.

• Journal of the Korean Society of Physical Medicine
• /
• v.18 no.2
• /
• pp.71-82
• /
• 2023

PURPOSE: This study examined the effect of training using video content on abdominal muscle thickness, Oswestry disability index (ODI), and pain in college students with chronic back pain. METHODS: Twenty-nine college students with chronic back pain participated in this study. The subjects were assigned randomly to 15 experimental groups who trained using video content and 14 control groups who exercised voluntarily using back exercise leaflets. The video used for the intervention was obtained from YouTube, and the difficulty level of the video was classified into six levels. Both groups participated in the intervention for 40 minutes/day, three times a week for six weeks, and the variables of abdominal muscle thickness, ODI, and pain were compared before and after the intervention. RESULTS: In the experimental group, there were statistically significant changes in the thickness of the internal oblique and transverse abdominis muscles, ODI, and pain after the intervention, except for the external oblique muscle (p < .05). In the control group, there was no statistically significant difference in all variables after the intervention (p > .05). A statistically significant difference in all variables was observed between the experimental group and the control group after the intervention except for the external oblique muscle (p < .05). CONCLUSION: Treatment of chronic low back pain using video content is a possible alternative treatment if quality images are selected and the difficulty levels are adjusted.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• The Journal of Korean Society for Neurotherapy
• /
• v.22 no.3
• /
• pp.7-10
• /
• 2018

Purpose The purpose of this study was to investigate the difference of brain activity during action observation training and image training throughout EEG. Methods This study was participated 1 healthy college student without mental illness or cognitive impairment. The subject was randomly selected from university students and was interested in participating in the experiment. The purpose of this study was to investigate the visual and auditory stimuli (action observation) and brain image training. Results The results of our study, EEG value measured o.1 during resting. But brain activity changed to 0.3 during action observation. Finally, it changed to .05 after brain image training. Conclusion EEG measurement results were showed that after watching the Ball squat video, Brain activity increased.

• The Korean Journal of Emergency Medical Services
• /
• v.24 no.3
• /
• pp.55-63
• /
• 2020

Purpose: This study aimed to establish effective training strategies and methods by comparing the effects of 360° virtual reality video and first-person video in non-face-to-face practical lectures. Methods: This crossover study, implemented May 18-31, 2020, included 27 participants. We compared 360° virtual reality video and first-person video. SPSS version 25.0 was used for statistical analysis. Results: The 360° virtual reality video had a higher score of experience recognition (p=.039), vividness (p=.045), presence (p=.000), fantasy factor (p=.000) than the first-person video, but no significant difference was indicated for satisfaction (p=.348) or interest (p=.441). Conclusion: 360° virtual reality video and first-person video can be used as training alternatives to achieve the standard educational objectives in non-face-to-face practical lectures.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.120-124
• /
• 2021

Recently, human attribute recognition (HAR) attracts a lot of attention due to its wide application in video surveillance systems. Recent deep-learning-based solutions for HAR require time-consuming training processes. In this paper, we propose a post-processing technique that utilizes the historical video frames to improve prediction results without invoking re-training or modifying existing deep-learning-based classifiers. Experiment results on a large-scale benchmark dataset show the effectiveness of our proposed method.