• Journal of the Korean Society of Physical Medicine
• /
• v.15 no.4
• /
• pp.163-174
• /
• 2020

PURPOSE: This study examined the effects of Robot Tilt-table Training (RTT) on the lower extremity strength, balance, gait, and satisfaction with rehabilitation, in patients with subacute stroke (less than six months after stroke onset), and requiring intensive rehabilitation. METHODS: A total of 29 subacute stroke patients were divided into an RTT group (n = 14) and a Body Weight Support Treadmill Training (BWSTT) group (n = 15). The mean age of patients was 62 years. RTT and BWSTT were performed for four weeks, three times a week, for 30 minutes. Isometric strength of the lower extremities before and after intervention was compared by measuring the maximal voluntary isometric contraction of the lower extremity muscles. To compare the balance function, the center of pressure (COP) path-length and COP velocity were measured. Timed Up & Go test (TUG) and 10 Meter Walking Test (10 MWT) were evaluated to compare the gait function. A satisfaction with rehabilitation survey was conducted for subjective evaluation of the subject's satisfaction with the rehabilitation training imparted. RESULTS: In the intra-group comparison, both groups showed significant improvement in lower extremity strength, balance, gait, and satisfaction with rehabilitation, by comparing the parameters before and after the intervention (p < .05). Comparison of the amount of change between groups revealed significant improvement for all parameters in the RTT group, except for the 10 MWT (p < .05). CONCLUSION: Both groups are effective for all variables, but the RTT group showed enhanced efficacy for variables such as lower extremity strength, balance, gait, and satisfaction with rehabilitation, as compared to the BWSTT group.

• Journal of Biomedical Engineering Research
• /
• v.28 no.3
• /
• pp.410-416
• /
• 2007

This paper presents quantitative analysis of a training system based on an unstable platform and a visual interactive system for improving sense of equilibrium. The training system consists of an unstable platform, a force plate, a safety harness, a monitoring device, and a personal-computer. To confirm the effects of the training system, fifteen young volunteers and five elderly volunteers went through a series of balance training using the system. During the training, we measured relevant parameters such as the time a subject maintain his or her center of pressure on a target, the time a subject moves his or her center of pressure to the target, and the mean absolute deviation of the trace before and after training with this system and training programs to evaluate the effects of the training. The results showed that the training system can successfully assess the gradual improvement of the postural control capability of the subject in the system and showed a possibility of improving balance of the subject. Moreover, the significant improvement in the postural capability of the elderly subject suggests that elderly subjects can benefit more from the training using the system for the improvement of sense of equilibrium.

• Transactions of Materials Processing
• /
• v.29 no.4
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.

• Physical Therapy Rehabilitation Science
• /
• v.12 no.3
• /
• pp.300-309
• /
• 2023

Objective: The purpose of this study was to investigate the effects of gastrocnemius neuromuscular electrical stimulation training on ankle mobility and gait in patients with stroke. Design: A randomized controlled trial. Methods: 31 patients with stroke were selected and classified into an experimental group (n=16) and a control group (n=15). Both groups were assessed for ankle mobility using the Knee to Wall Test and gait parameters using G-walk before and after the intervention. The intervention was applied five times a week for four weeks. The experimental group performed gastrocnemius neuromuscular electrical stimulation followed by ankle control exercises, while the control group only applied NMES to the tibialis anterior muscle of the paretic side for 30 min per session five times a week for 4 weeks. Results: Experimental group showed significant improvements in Knee to wall test. and lumbar flexibility after the intervention. both group showed significant improvements in gait parameters after the intervention. However, when comparing between the two groups, the experimental group showed a more significant effect than the control group. Conclusions: Gastrocnemius neuromuscular electrical stimulation training can be considered an effective approach to improve ankle mobility and gait ability in patients with stroke.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.2266-2273
• /
• 2024

A machine learning platform is proposed for the diagnosis of a severe accident progression in a nuclear power plant. To predict the key parameters for accident management including lost signals, a long short term memory (LSTM) network is proposed, where multiple accident scenarios are used for training. Training and test data were produced by MELCOR simulation of the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident at unit 3. Feature variables were selected among plant parameters, where the importance ranking was determined by a recursive feature elimination technique using RandomForestRegressor. To answer the question of whether a reduced order ML model could predict the complex transient response, we performed a systematic sensitivity study for the choices of target variables, the combination of training and test data, the number of feature variables, and the number of neurons to evaluate the performance of the proposed ML platform. The number of sensitivity cases was chosen to guarantee a 95 % tolerance limit with a 95 % confidence level based on Wilks' formula to quantify the uncertainty of predictions. The results of investigations indicate that the proposed ML platform consistently predicts the target variable. The median and mean predictions were close to the true value.

• Wind and Structures
• /
• v.37 no.5
• /
• pp.383-397
• /
• 2023

In the Structural Health Monitoring (SHM) system of civil engineering, data missing inevitably occurs during the data acquisition and transmission process, which brings great difficulties to data analysis and poses challenges to structural health monitoring. In this paper, Convolution Neural Network (CNN) is used to recover the nonstationary wind speed data missing randomly at sampling points. Given the technical constraints and financial implications, field monitoring data samples are often insufficient to train a deep learning model for the task at hand. Thus, simulation combined transfer learning strategy is proposed to address issues of overfitting and instability of the deep learning model caused by the paucity of training samples. According to a portion of target data samples, a substantial quantity of simulated data consistent with the characteristics of target data can be obtained by nonstationary wind-field simulation and are subsequently deployed for training an auxiliary CNN model. Afterwards, parameters of the pretrained auxiliary model are transferred to the target model as initial parameters, greatly enhancing training efficiency for the target task. Simulation synergy strategy effectively promotes the accuracy and stability of the target model to a great extent. Finally, the structural dynamic response analysis verifies the efficiency of the simulation synergy strategy.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.11 no.1
• /
• pp.1-12
• /
• 2005

Feed conversion efficiency contributes directly or indirectly on the cost benefit ratio of silkworm rearing and is considered to be an important physiological criterion for evaluating the superiority of silkworm breeds/hybrids. Food intake, assimilation and conversion of indigenous as well as exotic silkworm races are well studied by many researchers. In this review, an attempt has been made to consolidate works on feed conversion aspects of indigenous and exotic silkworm races. The paper also deals with the effect of various factors viz., nutritional, environmental and feeding on food assimilation and conversion parameters of mulberry silkworm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.746-751
• /
• 1991

Deafs train articulation by observing mouth of a tutor. sensing tactually the notions of the vocal organs, or using speech training aids. Present speech training aids for deafs can measure only single speech ter, or display only frequency spectra in histogrm or pseudo-color. In this study, a speech training aids that can display subject's articulation in the form of a cross section of the vocal organs and other speech parameters together in a single system Is aimed to develop and this system makes a subject to know where to correct. For our objective, first, speech production mechanism is assumed to be AR model in order to estimate articulatory notions of the vocal tract from speech signal. Next, a vocal tract profile mode using LPC analysis is made up. And using this model, articulatory notions for Korean vowels are estimated and displayed in the vocal tract profile graphics.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3515-3524
• /
• 2023

A reinforcement learning framework is proposed for the control problem of outlet steam pressure of the once-through steam generator(OTSG) in this paper. The double-layer controller using Proximal Policy Optimization(PPO) algorithm is applied in the control structure of the OTSG. The PPO algorithm can train the neural networks continuously according to the process of interaction with the environment and then the trained controller can realize better control for the OTSG. Meanwhile, reinforcement learning has the characteristic of difficult application in real-world objects, this paper proposes an innovative pretraining method to solve this problem. The difficulty in the application of reinforcement learning lies in training. The optimal strategy of each step is summed up through trial and error, and the training cost is very high. In this paper, the LSTM model is adopted as the training environment for pretraining, which saves training time and improves efficiency. The experimental results show that this method can realize the self-adjustment of control parameters under various working conditions, and the control effect has the advantages of small overshoot, fast stabilization speed, and strong adaptive ability.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.161-168
• /
• 2024

As the size of big data models grows, distributed training is emerging as an essential element for large-scale machine learning tasks. In this paper, we propose ParamHub for distributed data training. During the training process, this agent utilizes the provided data to adjust various conditions of the model's parameters, such as the model structure, learning algorithm, hyperparameters, and bias, aiming to minimize the error between the model's predictions and the actual values. Furthermore, it operates autonomously, collecting and updating data in a distributed environment, thereby reducing the burden of load balancing that occurs in a centralized system. And Through communication between agents, resource management and learning processes can be coordinated, enabling efficient management of distributed data and resources. This approach enhances the scalability and stability of distributed machine learning systems while providing flexibility to be applied in various learning environments.