• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.88-95
• /
• 1994

This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration. Two neural networks were developed to forecast daily evapotranspiration of the rice crop with back-propagation and counter-propagation algorithm. The neural network trained by back-propagation algorithm with delta learning rule is a three-layer network with input, hidden, and output layers. The other network with counter-propagation algorithm is a four-layer network with input, normalizing, competitive, and output layers. Training neural networks was conducted using daily actual evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity, and pan evaporation. During the training, neural network parameters were calibrated. The trained networks were applied to a set of field data not used in the training. The created response of the back-propagation network was in good agreement with desired values and showed better performances than the counter-propagation network did. Evaluating the neural network performance indicates that the back-propagation neural network may be applied to the estimation of evapotranspiration of the rice crop. This study does not provide with a conclusive statement as to the ability of a neural network to evapotranspiration estimating. More detailed study is required for better understanding and evaluating the behavior of neural networks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1439-1442
• /
• 2010

Time-lag recurrent neural networks model (Time-Lag RNNM) is used to estimate daily pan evaporation (PE) using limited climatic variables such as max temperature ($T_{max}$), min temperature ($T_{min}$), mean wind speed ($W_{mean}$) and mean relative humidity ($RH_{mean}$). And, for the performances of Time-Lag RNNM, it is composed of training and test performances, respectively. The training and test performances are carried out using daily time series data, respectively. From this research, we evaluate the impact of Time-Lag RNNM for the modeling of the nonlinear time series data. We should, thus, construct the credible data of the daily PE using Time-Lag RNNM, and can suggest the methodology for the irrigation and drainage networks system. Furthermore, this research represents that the strong nonlinear relationship such as pan evaporation modeling can be generalized using Time-Lag RNNM.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.3
• /
• pp.93-100
• /
• 2018

This paper proposes a small-scale rehabilitation system that allows stroke patients to perform daily rehabilitation training in a virtual home. Stroke patients have limited activities of daily living due to paralysis, and there are many rehabilitation exercises for them to reproduce activities that take place in the house, such as turning lights on and off, door opening and closing, gas valve locking. In this paper, we have implemented a virtual home with the above mentioned daily rehabilitation training elements, by using virtual reality technology. We use Leap Motion, a hand motion recognition device, for rehabilitation of hands and fingers. It is expected that stroke patients can rehabilitate small muscles without having to visit the clinic with uncomfortable body, and will be able to get interesting rehabilitation training by avoiding monotony of existing rehabilitation tools.

• Journal of The Korean Society of Integrative Medicine
• /
• v.9 no.4
• /
• pp.211-223
• /
• 2021

Purpose : The purpose of this study was to examine the effect of task-oriented circuit training using unstable support surface on balance, gait ability, and balance confidence in subacute stroke patients. Methods : Forty-five patients with subacute stroke were randomly divided into the three following groups of 15: 1) TOCT-US group; task-oriented circuit training using unstable surface (experimental group 1), 2) TOCT-SS group; task-oriented circuit training using stable surface (experimental group 2), and 3) CON group; conventional physical therapy (control group). All patients participated in one of the three training programs for 6 weeks, 30 minutes per session, 3 times per week. Patients' balance ability was assessed using the BT-4, BBS (berg balance scale), TUG (time up and go test), and LOS (limit of stability). Gait speed was measured to examine gait ability. K-ABC (activities-specific balance confidence scale) was also used to assess the level of patients' confidence in daily activities. Results : After the intervention, the sway area in experimental groups 1 and 2 decreased, but that in the control group increased. Experimental group 1 showed significant improvement compared with experimental group 2 and the control group. BBS, TUG, and LOS scores of experimental group 1 were significantly improved compared with those of experimental group 2 and the control group. Also, gait speed significantly improved in experimental group 1 compared with experimental group 2 and the control group. Experimental groups 1 and 2 showed significant improvement in K-ABC scores after training. Conclusion : Patients with subacute stroke had significantly improved balance, gait, and level of confidence in performing activities of daily living following task-oriented circuit training using the unstable surface. This indicates that task-oriented circuit training using unstable surfaces can be an effective treatment method for the recovery of balance and gait in subacute stroke patients.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1648-1652
• /
• 2004

An advanced training machine designed for elderly people is proposed. The training machine allows users to have a safe and effective training through exercise close to ordinal motion appears in daily life such as standing up/down motion. The activation level of user's muscle is real timely monitored during the exercise and the training load is adjusted based on the body information. The training load is exerted and continuously controlled by actuation of an air cylinder.

• Physical Therapy Rehabilitation Science
• /
• v.12 no.2
• /
• pp.192-200
• /
• 2023

Objective: This study aimed to assess the effectiveness of a balance training program in improving balance and functional independence to reduce fall risks among community-dwelling elders. Design: A multi-center randomized controlled trial Methods: A total of 66participants were randomly assigned to a balance training group or a control group. The balance training program, conducted three times a week for 32 weeks, included warm-up exercises, main balance training exercises, and cooldown stretch exercises. Outcome measures included the Berg Balance Scale (BBS), Timed Up and Go Test (TUGT), and Modified Barthel Index (MBI). Results: The balance training group demonstrated significant improvements in all outcome measures, indicating enhanced balance, improved functional mobility, and increased independence in activities of daily living. In contrast, the control group showed only slight improvements in BBS, TUGT and MBI scores. Conclusions: These findings provide evidence supporting the effectiveness of balance training programs in reducing fall risk and promoting health and wellbeing among community-dwelling elders. Future research should aim to refine the design of these programs and assess the sustainability of the observed improvements.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.537-550
• /
• 2000

In this study, Neural Networks models were used to forecast daily streamflow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily streamflow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily streamflow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Mode(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more sysmatic approach, reduce model parameters, and shorten the time spent in the model development.

• Journal of Korean Academy of Nursing
• /
• v.31 no.3
• /
• pp.432-442
• /
• 2001

Purpose: The purpose of this study was to investigate the effects of biofeedback exercise training on muscle activity and activities of daily livings (ADL) in hemiplegic patients. An experimental group consisting of 17 people, was given biofeedback exercise training for 30- 60 minutes per week for 5 weeks, while a control group consisting of 18 people, was given normal exercise with quasi-experimental design. Result: The results of the study show that biofeedback exercise is effective for improving muscle activity in hemiplegic patients, especially in the hemiplegic limbs. However, this study found no significant differences in ADL and IADL between the experimental and the control groups. It implies that ADL and IADL may not be improved for a short period of time, such as 5 weeks, for people with more than five years of hemiplegia. The study suggests that the effect of biofeedback exercise on ADL and IADL should be determined in hemiplegic patients in acute stage.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.1
• /
• pp.123-130
• /
• 2014

The aim of this study was to determine the effect of action observational physical training on upper extremity function and activities of daily living in stroke patient. 19 hemiparetic patients participated in this study and were randomly selected into an experimental group and a control group. An experimental group observed performance actions of purposeful activity task through a video and imitated actions with the traditional occupational therapy, and a control group only observed actions with the traditional occupational therapy. Traing was performed 3 times a week and 30 min for each round for 4 weeks. WMFT were performed for an upper extremity function and MBI were performed for activities of daily living. As a result, WMFT and MBI showed significant difference between before and after in two groups but didn't show significant difference between two groups.

• PNF and Movement
• /
• v.17 no.3
• /
• pp.369-378
• /
• 2019

Purpose: This study investigated the effects of virtual reality-based task training (VRBTT) using a smart glove on upper extremity function and activity of daily living in stroke patients. Methods: Twenty-nine patients with chronic stroke disease were randomly allocated to two groups: the VRBTT group (n=14) and the control group (n=15). All patients received 30 minutes of standard occupational therapy, 5 times a week, for 8 weeks. The VRBTT group performed an additional 30 minutes of virtual reality-based rehabilitation training, 5 times a week, for 8 weeks. Results: Both groups showed significant improvements in upper extremity function, yielding an increase in FMA and K-WMFT (p<0.05). There was a more significant increase in the VRBTT group before and after interventions (p<0.05). There was no significant difference in MAS for the control group (p>0.05); however, there was a significant increase for the VRBTT group (p<0.05). In the activities of daily living, there was a significant difference in the values for K-MBI (p<0.05). In addition, both groups showed a significant increase for K-MBI and K-RNLI (p<0.05). Conclusion: This study showed that VRBTT using smart gloves can have a more positive effect on upper extremity function and activities of daily living in stroke patients than conventional intervention methods. A variety of virtual reality-based contents and glove-shaped wearable devices will help stroke patients in rehabilitation clinics recover and return to society.