• Smart Structures and Systems
• /
• v.30 no.1
• /
• pp.17-34
• /
• 2022

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

• Korean Journal of Applied Biomechanics
• /
• v.33 no.2
• /
• pp.45-51
• /
• 2023

Objective: The aim of this study was to examine the effect of strength training targeting medial quadriceps/hamstrings and non-targeting strength training on dynamic balance. Method: A total of 51 healthy subjects were randomly assigned to control, targeting strength training, or non-targeting training groups. To measure the dynamic balance, the star excursion balance test (SEBT) was performed before and after training. The SEBT parameters were compared using repeated measures ANOVA, and post-hoc paired t test at a significance level of 0.05. Results: Greater anterior (p= .011), anteromedial (p= .001), medial (p< .001), lateral (p< .001), and anterolateral (p= .001) reach distances were found between pre- and post-training in the strength training targeting medial thigh muscles group. Only greater lateral reach distance was found after non-targeting strength training (p= .029). In addition, no differences were found for any SEBT scores in the control group. Conclusion: Strength training targeting medial quadriceps and hamstrings can improve the dynamic balance, thereby it positively affected in lower extremity injury risk, whereas non-targeting strength training rarely changes the dynamic balance.

• Journal of Biomedical Engineering Research
• /
• v.13 no.4
• /
• pp.275-284
• /
• 1992

Development of Integrated Speech Training Aids for Hearing Impaired In this study, a spepch lralnlng aids that can do real-time display of vocal tract shape and other speech parameters together in a single system is implemenLed and self-training program for this system is developed. To estimate vocal tract shape, speech production process is assumed to be AR model. Through LPC analysis, vocal tract shape, intensity, and log spcclrum are calculated. And, fundamental frequency and nasality are measured using vibration sensors.

• Journal of the Korean Society of Physical Medicine
• /
• v.8 no.4
• /
• pp.559-566
• /
• 2013

PURPOSE: The present study examines how feedback respiratory exercise affects gait performance of stroke patients. METHODS: Forty stroke patients were randomly divided into an experiment group and a control group. For the former group, patients went through a half-hour of training therapy and a half-hour of feedback respiratory device exercise. For the latter group, patients went through 30 minutes of training therapy and a half-hour of motomed exercise. All participants had five training sessions each week for four weeks. For measurement, a GAITRite system was used to examine spatial parameters, and functional ambulation performance before and after the training. RESULT: In terms of spatial parameters, double support ratio, stance phase increased significantly in the experiment group after the walking exercise(p<.05). FAP rose more significantly in the experiment group than in the control group(p<.05). In comparison of two exercise groups, double support ratio, Stance phase, gait velocity, FAP was significant difference(p<.05). CONCLUSION: The experiment results showed that feedback respiratory exercise is effective in enhancing gait performance.

• Nuclear Engineering and Technology
• /
• v.39 no.4
• /
• pp.337-348
• /
• 2007

A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding conditions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership function parameters and a least squares method to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization data set and verified by means of a test data set that was different (independent) from the training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.

• Journal of Nutrition and Health
• /
• v.26 no.1
• /
• pp.47-55
• /
• 1993

To investigate the effects of exercise-training on serum lipids, fat distribution and several parameters of body fatness(percent body fat, skinfolds thickness, body circumference) were assessed in 24 healthy male subjects submitted to an 8-wk high intensive exercise-training. Blood sample was taken twice, per and post exercise-training, Exercise-training took place 5 days a week and daily energy intake and expenditure were observed. The results obtained are summarized as follows: 1) Through exercise-training body weight (changes : 1.1$\pm$1.1kg ; p=0.000) and percent body fat (changes : 2.4$\pm$1.3% ; p=0.000) decreased significantly . 2) Suprailiac was the most reduced site by exercise-training among eight site skinfolds. Central skinfolds were changed more by exercise-training than peripheral skinfolds with reduction of 1.7$\pm$1.7mm and 0.2$\pm$1.9mm. Central site circumferences were reduced more by exercise-training than peripheral site circumferences. 3) Total cholesterol, HDL-cholesterol and LDL-cholesterol were not significantly changed by exercise-training while only triglyceride decreased (changes : 20.7$\pm$44.8mg/dl ; p<0.05). Changes in body weight were grately related to changes in total cholesterol. Changes in deep abdominal adipose tissue were related to changes in triglyceride.

• The Journal of Korean Physical Therapy
• /
• v.32 no.2
• /
• pp.107-113
• /
• 2020

Purpose: This study compared the walking ability of chronic stroke patients following either treadmill training with knowledge of the result (KR group) or treadmill training with knowledge of the performance (KP group). Methods: Nineteen patients with chronic stroke were recruited from a rehabilitation hospital. The patients were divided into two groups: a KR group (10 patients) and a KP group (9 patients). They received 30 minutes of neuro-developmental therapy and treadmill training 30 minutes, five times a week for three weeks. The gait parameters were measured before and after training using the Optogait system. Results: After the training periods, the KR group showed significant improvement in gait speed, cadence, step length of the unaffected limb, stance time of the affected limb, and functional gait assessment compared to the KP group (p<0.05). Conclusion: The results showed that treadmill training with KR was more effective in improving the gait speed and cadence, step length of the unaffected limb, stance time of the affected limb, and functional gait ability than the treadmill training with KP. Therefore, to improve the walking ability of stroke patients, it is necessary to consider treadmill training with KR. If it can be combined with conventional neurological physiotherapy, it would be an effective rehabilitation for stroke patients.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.155-162
• /
• 2002

Neural networks have been focused on as a robust classifier for the remotely sensed imagery due to its statistical independency and teaming ability. Also the artificial neural networks have been reported to be more tolerant to noise and missing data. However, unlike the conventional statistical classifiers which use the statistical parameters for the classification, a neural network classifier uses individual training sample in teaming stage. The training performance of a neural network is know to be very sensitive to the discrepancy of the number of the training samples of each class. In this paper, the effect of the population discrepancy of training samples of each class was analyzed with three layered feed forward network. And a method for reducing the effect was proposed and experimented with Landsat TM image. The results showed that the effect of the training sample size discrepancy should be carefully considered for faster and more accurate training of the network. Also, it was found that the proposed method which makes teaming rate as a function of the number of training samples in each class resulted in faster and more accurate training of the network.

• The Journal of Korean Physical Therapy
• /
• v.35 no.5
• /
• pp.132-138
• /
• 2023

Purpose: This study compared the effects of the elastic resistance and general training for college Taekwondo athletes, and investigated the biomechanical ability and lower extremity function according to the movement speed of the knee joint. Methods: Twenty university student Taekwondo athletes participated voluntarily in this study. The subjects performed general resistance training for four weeks, followed by elastic resistance training for another four weeks. The biomechanical parameters during the fast and slow isokinetic conditions, Y-balance ability, and vertical jump ability were measured three times: before training, after general resistance training, and after elastic resistance training. Statistical analysis was performed under isokinetic conditions and the intervention effect. Results: The biomechanical ability differed significantly between fast and slow isokinetic conditions (p<0.05). An analysis of the training method revealed a significant difference in the maximum knee extension speed and the posterior-lateral direction of the Y-balance test (p<0.05). Conclusion: Elastic resistance training had a more positive effect on the functional task performance than biomechanical factors related to muscular strength compared to general resistance training. In addition, speed-related knee biomechanical information of subjects with strong physical abilities could be utilized in sports physiotherapy.

• Physical Therapy Rehabilitation Science
• /
• v.4 no.2
• /
• pp.94-102
• /
• 2015

Objective: The purpose of this study is to investigate the effect of treadmill gait training with patellar taping on gait abilities in chronic stroke patients. Design: Randomized controlled trial. Methods: Thirty chronic stroke patients who have been diagnosed at least six months or before were recruited in Gyeongin Rehabilitation Center Hospital, located in Incheon. Patients who were enrolled in this study were randomized to experimental group (n=15) or control group (n=15). Treadmill with patella taping training group patients were applied with patellar taping when they were being trained on a treadmill. Control group patients were being trained on a treadmill without any kind of taping. Gait parameters were measured with a GAITRite$^{(R)}$ system which evaluated gait performances. Gait trainings were done for 30 min/day, 5 days/week, for 4 weeks. Results: After treadmill training, treadmill with patella taping training group showed a significant improvement in gait abilities, including velocity, cadence, paretic and non-paretic step length, and double support period (p<0.05). However, in general treadmill group, there were no significant differences in gait parameters except velocity and cadence. There was a significant difference in gait performance in the experimental group compared with the control group, except for the gait symmetry ratio (p<0.05). Conclusions: According to this result of this study, it seems that application of patellar taping in treadmill gait training for chronic stroke patients significantly improved gait abilities of these patients. Also, we can conclude that patella taping is thought to be useful in real clinical settings where there are many chronic patients who are in need of improvement in their gait abilities.