• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.4
• /
• pp.54-64
• /
• 2005

The study investigated genetic algorithms for the optimal control model of maximum height vertical jumping. The model includes forward dynamic simulations by the neural excitation-control variables. Convergence of genetic algorithms is very slow. In this paper the micro genetic algorithm(micro-GA) was used to reduce the computation time. Then a near optimal solution from micro-GA was an initial solution for VF02, which is one of well-developed and proven nonlinear programming algorithms. This approach provided the successful optimal solution for maximum-height jumping without a reasonable initial guess.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.73-78
• /
• 2020

Musculoskeletal disease is often caused by sitting down for long period's time or by bad posture habits. In order to prevent musculoskeletal disease in daily life, it is the most important to correct the bad sitting posture to the right one through real-time monitoring. In this study, to detect the sitting information of user's without any constraints, we propose posture measurement system based on multi-channel pressure sensor and CNN model for classifying sitting posture types. The proposed CNN model can analyze 5 types of sitting postures based on sitting posture information. For the performance assessment of posture classification CNN model through field test, the accuracy, recall, precision, and F1 of the classification results were checked with 10 subjects. As the experiment results, 99.84% of accuracy, 99.6% of recall, 99.6% of precision, and 99.6% of F1 were verified.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.491-500
• /
• 2021

In this study, we propose a method for detecting fall behavior using MS Kinect v2 RGBD Camera-based Human-Skeleton Keypoints and a 2-Stacked Bi-LSTM model. In previous studies, skeletal information was extracted from RGB images using a deep learning model such as OpenPose, and then recognition was performed using a recurrent neural network model such as LSTM and GRU. The proposed method receives skeletal information directly from the camera, extracts 2 time-series features of acceleration and distance, and then recognizes the fall behavior using the 2-Stacked Bi-LSTM model. The central joint was obtained for the major skeletons such as the shoulder, spine, and pelvis, and the movement acceleration and distance from the floor were proposed as features of the central joint. The extracted features were compared with models such as Stacked LSTM and Bi-LSTM, and improved detection performance compared to existing studies such as GRU and LSTM was demonstrated through experiments.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.6 s.171
• /
• pp.207-212
• /
• 2005

The purpose of this work is to develop the FES controller that can cope with the muscle fatigue which is one of the most important problems of current FES (Functional Electrical Stimulation). The feasibility of the proposed FES controller was evaluated by simulation. We used a fitness function to describe the effect of muscle fatigue and recovery process. The FES control system was developed based on the biological neuronal system. Specifically, we used PD (Proportional and Derivative) and GC (Gravity Compensation) control, which was described by the neuronal feedback structure. It was possible to control of multiple joints and muscles by using the phase-based PD and GC control method and the static optimization. As a result, the proposed FES control system could maintain the cycling motion in spite of the muscle fatigue. It is expected that the proposed FES controller will play an important role in the rehabilitation of SCI patient.