• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.537-544
• /
• 2013

This study was to determine the effect of 12-week balance training with visual feedback on balance and walking functions in patients with post-stroke hemiparesis. Twenty individuals with chronic stroke volunteered to participate in this study. They were randomly allocated to either experimental group (EG) or control group (CG), with 10 subjects in each group. Subjects from the group 1 underwent 15-min balance training with visual feedback and 15-min routine-scheduled physical therapy, and subjects from the group 2 performed 30-min routine-scheduled physical therapy only, which comprised mat exercise, strengthening, postural correction, and functional practice. Assessment tools were made with the Functional Reach Test (FRT), Timed Up and Go Test (TUGT), and 6 Min Walk Test (6MWT). In within-group comparison, the EG showed significant differences in all parameters (p<0.05), while significant differences were not found for the CG (p>0.05). In between-group comparison, the change values of the FRT and 6MWT appeared to be significantly greater for the EG than those of the CG (p<0.05). These findings suggest that balance training with visual feedback may be favorably used to improve balance and walking functions in patients with chronic post-stroke hemiparesis. Further studies with larger sample and long-term follow-up period need to generalize the results of this study.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.77-89
• /
• 2022

It has been proven through many previous researches that the pretrained language model with a large corpus helps improve performance in various natural language processing tasks. However, there is a limit to building a large-capacity corpus for training in a language environment where resources are scarce. Using the Cross-lingual Post-Training (XPT) method, we analyze the method's efficiency in Korean, which is a low resource language. XPT selectively reuses the English pretrained language model parameters, which is a high resource and uses an adaptation layer to learn the relationship between the two languages. This confirmed that only a small amount of the target language dataset in the relationship extraction shows better performance than the target pretrained language model. In addition, we analyze the characteristics of each model on the Korean language model and the Korean multilingual model disclosed by domestic and foreign researchers and companies.

• Fibers and Polymers
• /
• v.7 no.4
• /
• pp.344-351
• /
• 2006

This paper is intended to determine the optimal processing parameters applied to the dyeing procedure so that the desired color strength of a raw fabric can be achieved. Moreover, the processing parameters are also used for constructing a system to predict the fabric quality. The fabric selected is the nylon and Lycra blend. The dyestuff used for dyeing is acid dyestuff and the dyeing method is one-bath-two-section. The Taguchi quality method is applied for parameter design. The analysis of variance (ANOVA) is applied to arrange the optimal condition, significant factors and the percentage contributions. In the experiment, according to the target value, a confirmation experiment is conducted to evaluate the reliability. Furthermore, the genetic algorithm (GA) is combined with the back propagation neural network (BPNN) in order to establish the forecasting system for searching the best connecting weights of BPNN. It can be shown that this combination not only enhances the efficiency of the learning algorithm, but also decreases the dependency of the initial condition during the network training. Most of all, the robustness of the learning algorithm will be increased and the quality characteristic of fabric will be precisely predicted.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.1-7
• /
• 2012

Hemorrhagic shock is a common cause of death in emergency rooms. Early diagnosis of hemorrhagic shock makes it possible for physicians to treat patients successfully. Therefore, the purpose of this study was to select an optimal survival prediction model using physiological parameters for the two analyzed periods: two and five minutes before and after the bleeding end. We obtained heart rates, mean arterial pressures, respiration rates and temperatures from 45 rats. These physiological parameters were used for the training and testing data sets of survival prediction models using an artificial neural network (ANN) and support vector machine (SVM). We applied a 5-fold cross validation method to avoid over-fitting and to select the optimal survival prediction model. In conclusion, SVM model showed slightly better accuracy than ANN model for survival prediction during the entire analysis period.

• Physical Therapy Rehabilitation Science
• /
• v.1 no.1
• /
• pp.17-21
• /
• 2012

Objective: To investigate the effect of long-term water exercise on gait parameters in the elderly post stroke patients. Design: One group pretest-posttest design. Methods: Twenty elderly post stroke patients (age: $56.5{\pm}10.1$ years, height: $168.6{\pm}5.8cm$, body mass: $69.3{\pm}6.9kg$, handicapped level: $2.5{\pm}0.8$) participated in this study. Participants took part in gait training of 1 hour per day, three days per week, for three months. Participants' gaits were analyzed to find the effect of 3 months water exercise by a 3-D motion analysis with 8 infrared camera and 1 force plate (sampling frequency: 100 and 1,000 Hz, respectively). A paired t-test was used to find the significance with significant level as 0.05. Results: Gait velocity, step length & step width significantly increased, and asymmetric index for gait parameters significantly decreased after the water exercise (p<0.05). Conclusions: The water exercise effectively affect on patients' gait ability and electromyography analysis will be needed further study.

• Physical Therapy Rehabilitation Science
• /
• v.2 no.2
• /
• pp.81-86
• /
• 2013

Objective: The objective of this study was to investigate the feasibility and effects of balance training using a newly developed elastic band orthosis (aider) for improvement of mobility and balance in chronic stroke patients. Design: Cross-sectional study. Methods: Ten patients with chronic hemiplegia participated in this study. There were six males and four females; two patients had right hemiplegia and eight had left hemiplegia. This study investigated the effect of the elastic band orthosis on balance and gait ability compared with bare foot condition. Gait parameters were measured using the opto-gait system for analysis of the spatial and temporal parameters of walking in stroke patients. In addition, balance ability in stroke patients was evaluated using the Timed Up and Go (TUG) and Berg Balance Scale (BBS). Results: This study investigated the effect of the elastic band orthosis on balance compared with bare foot condition. The TUG and BBS showed significant improvement with use of the elastic band orthosis (p<0.05). Use of the Elastic band orthosis resulted in significantly improved velocity, cadence, less-affected step length, less-affected stride length, and less-affected single limb support in stroke patients (p<0.05). Conclusions: We demonstrated a significant improvement in dynamic balance and gait ability in chronic stroke patients using the elastic band orthosis. This orthosis may aid in prevention of spastic foot drop, leading to improvement of walking ability.

• Clinical and Experimental Pediatrics
• /
• v.63 no.3
• /
• pp.110-114
• /
• 2020

Background: Subclinical hypothyroidism (SH) is a common condition in obese children. However, its effect on glucose and lipid metabolism in obese children remains controversial. Purpose: The present study aimed to investigate the association between SH and metabolic parameters. Methods: A total of 215 obese children and adolescents aged 6-18 years were included in this retrospective cross-sectional study. The patients' anthropometric measurements such as thyrotropin (TSH), free thyroxine (fT4), fasting plasma glucose, and insulin levels, as well as homeostasis model assessment for insulin resistance (HOMA-IR) index, and lipid profiles were evaluated. The patients were allocated to the SH group (fT4 normal, TSH 5-10 mIU/L) (n=77) or the control group (fT4 normal, TSH<5 mIU/L) (n=138). The glucose and lipid metabolisms of the 2 groups were compared. Results: SH was identified in 77 of 215 patients (36%). Mean body mass index was similar in both groups. The mean serum insulin, HOMA-IR, and triglyceride (TG) levels were higher and the mean high-density lipoprotein cholesterol level was lower in the SH group than in the control group (P=0.007, P=0.004, P=0.01, and P=0.02, respectively). A positive correlation was observed between TSH level and insulin level, HOMA-IR, and TG level. Conclusion: SH was identified in some of the obese children and adolescents. A clear association was observed between SH, insulin resistance, and dyslipidemia in obese children.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4367-4385
• /
• 2016

With millions of people across the globe suffering from Parkinson's disease (PD), an objective, confirmatory test for the same is yet to be developed. This research aims to develop a system which can assist the doctor in objectively saying whether the patient is normal or under risk of PD. The proposed work combines the eye-hand co-ordination behaviour with the DaTscan images in order to determine the risk of this disorder. Initially, eye-hand coordination level of the patient is assessed through a hardware module. Then, the DaTscan image is analysed and used to extract certain geometrical parameters which shall indicate the presence of PD. These parameters are then finally fed into a Multi-Layer Perceptron Neural Network using Levenberg-Marquardt (LM) Back propagation training algorithm. Experimental results indicate that the proposed system exhibits an accuracy of around 93%.

• Journal of the Korean Society of Physical Medicine
• /
• v.2 no.1
• /
• pp.73-84
• /
• 2007

Purpose : The purpose of this study was to determine risk factors and methods in balance assessment associated with fall in older adults. Methods : This article describes many of the tools that can be used to evaluate the physical parameters associated with fall risk in older adults. Results : Composite ratings of performance(Tinetti balance assessment, Guralnik test battery, Berg balance scale, modified-physical performance test) measures the score compounding the balance measure to determine fall risk. Static balance instruments are composed of FICSIT-4 that measures the ability of maintaining foot positions and CTSIB that measures postural stability. Dynamic balance instrument is composed of functional reach test. To measure walking velocity and mobility, 8-foot up-and-go test and walking around two cones are used. We can use 1-RM and to measure muscular strength, isokinetic dynamometery, and 30-second chair stand to measure lower extremity muscle strength. Conclusion : The described instruments are easy to use and widespread. To select and use these tool kits carefully is considered to be helpful in identifying those who are most likely to fall. The final part of the article includes a brief discussion of the potential role of exercise training interventions to improve these physical parameters and prevent falls.