• Journal of Fisheries and Marine Sciences Education
• /
• v.27 no.5
• /
• pp.1404-1412
• /
• 2015

This study aimed at exploring, based on the current states and status of onboard training ship, plans to improve the boarding training management for fisheries high school. The results were as follows. The problems with the management of onboard training ship were summarized as the following four types. Firstly, The most training ships throughout the country became superannuated. Secondly, the safe equipments for training ships were necessary to compensate the defects to fall short of the international safety management standards. Thirdly, the problems could result from the dualized system between ownership and management, since training ships were owned by metropolitan and provincial education offices and operated by management centered schools. Fourthly, middle technicians such as professional fisheries manpower were not easily supplied with. The plans to improve the above problems were as in the following. Firstly, support and help of Ministry of Maritime Affairs and Fisheries were needed to launch new onboard training ships which substitute for the superannuated. Secondly, new onboard ships were required to be launched according to the updated international safety management standards. Thirdly, Korea Institute of Maritime and Fisheries Technology should hold onboard training. Fourthly, on-site onboard training expertise, systemic management, safety, etc. should be compensated through industry-university-institute collaboration.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.123-125
• /
• 2022

In this paper, we introduce a system applied to long short-term memory using Yolo-pose. Using Yolo-pose from image data, data divided into daily life and falls are extracted and applied to LSTM for learning. In order to prevent overfitting, training is performed 8 to 2 validation and is represented by a confusion matrix. The result of Yolo-pose recorded 100% of both sensitivity and specificity, confirming that daily life and falls were well distinguished.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.971-976
• /
• 1994

A speech display system is developed for the evaluation and the training of speech utterance. The speech is analyzed by linear predictive technique every 5 ms and the frequencies of the lowest two spectral local peaks P1 and P2 are extracted. The vowel trakectory is displayed using those frequencies on th P1-P2 plane. In most cases, P1 and P2 correspond to the first and the second formants, but in the case of indistinct utterance, the correspondence between the local spectral peaks and the formants tends to fall into disorder. And the system is considered to be useful for the evaluation of speech quality. The examples of some words uttered by normal speakers and some patients with difficulty in utterance are compared each other for the discussion of the effectiveness of the system.

• The Journal of Korean Physical Therapy
• /
• v.32 no.3
• /
• pp.185-190
• /
• 2020

Purpose: Gait and cognitive impairment in stroke patients exacerbate fall risk and mobility difficulties during multi-task walking. Virtual reality can provide interesting and challenging training in a community setting. This study evaluated the effect of community-based virtual reality gait training (VRGT) using a 360-degree image on the gait ability of chronic stroke patients. Methods: Forty-five chronic stroke patients who were admitted to a rehabilitation hospital participated in this study. Patients meeting the selection criteria were randomly divided into a VRGT group (n=23) and a control group (n=22). Both these groups received general rehabilitation. The VRGT group was evaluated using a 360-degree image that was recorded for 50 minutes a day, 5 days per week for a total of 6 weeks after their training. The control group received general treadmill training for the same amount of time as that of the VRGT group. The improvement in the spatiotemporal parameters of gait was evaluated using a gait analyzer system before and after training. Results: The spatiotemporal gait parameters showed significant improvements in both groups compare with the baseline measurements (p<0.05), and the VRGT group showed more improvement than the control group (p<0.05). Conclusion: Community-based VRGT has been shown to improve the walking ability of chronic stroke patients and is expected to be used in rehabilitation of stroke patients in the future.

• The Journal of Korean Physical Therapy
• /
• v.27 no.3
• /
• pp.169-173
• /
• 2015

Purpose: This study aimed to improve the asymmetrical weight-bearing ratio, by applying different repetitive sit-to-stand training methods to the paretic-side foot of hemiplegic patients, as well as to provide the necessary information for applying balance training with hemiplegic patients. Methods: The subjects were divided into two groups: a spontaneous foot group and an asymmetrical foot group. They all performed repetitive sit-to-stand training five times a week for a total of six weeks. The sit-to-standing movement was studied using standardized clinical tests. The Biodex Balance System, Time up and go test (TUG), 5 times sit-to-stand test (5XSST), and functional reach test (FRT) were used to measure the static and dynamic standing balance of the patients. Results: In the balance system measurement, the results for the overall index, ant-post index, med-lat index, fall risk index, 5XSST, and FRT after the training differed significantly between the comparison groups (p<0.05). In the evaluation of dynamic balance, the differences in TUG did not differ significantly between the comparison groups after the training (p>0.05). Conclusion: The study found that the asymmetrical group showed significant increases in static and dynamic balance in comparison to the spontaneous group after repetitive sit-to-stand training. Based on this result, it is clear that training in an asymmetrical position with the paretic foot back can increase the left-right stability limit and the anterior-posterior stability limit, thus improving balance control.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.155-161
• /
• 2023

Vertigo refers to a state in which awareness related to the location, posture, movement, etc. of a helicopter is insufficient in space. It is easy to fall into flight illusion when flying in dense fog or night flight, and even if it has a wide field of view, it can be caused by visual causes such as cloud shapes, wind conditions, conditions of ground objects, and sensory causes such as changes in air posture or gravitational acceleration. The design and program of the motion system are studied that applied a six-axis motion system to a conventional commercial flight simulator program for pilot training, depending on the specificity of helicopter flight training that requires perception and sensitivity. Using the motion-based helicopter simulator produced in this study to train pilots, it is expected to have a positive effect in prevent of vertigo, where high performance could not be confirmed in the previously used visual-based simulation training device.

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.147-149
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.379-381
• /
• 2011

Dynamic Neural Unit(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.443-445
• /
• 2009

Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Proceedings of the KAIS Fall Conference
• /
• 2006.11a
• /
• pp.186-190
• /
• 2006

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.