• Journal of Korean Society of Rural Planning
• /
• v.18 no.3
• /
• pp.123-135
• /
• 2012

This study aims to make a comparison of the attitudes between residents, officials and experts towards the rural landscape management polices. It is also designed to suggest the improvements to the rural landscape management policies. This study showed that there were differences in awareness of the rural landscape management polices depending on stakeholder who are residents, officials and experts and experienced groups of rural landscape projects. The directions of improvement of rural landscape policies are as follows: First, it's necessary that the various rural landscape management polices is made of considering the differences on the interest group's recognition. Second, the related rural landscape improvement programs should be implemented based on those plan. Third, the various programs which are to lead voluntary residents participation and to strengthen participant's capabilities have to be arranged to manage the rural landscape effectively.

• PNF and Movement
• /
• v.10 no.1
• /
• pp.25-33
• /
• 2012

Purpose : The purpose of this study was to compare the effect of treadmill training and cognitive task with in the course of treadmill training at the same time with chronic stroke patients. Methods : Fourteen chronic stroke patients participated. Participants were randomly assigned to the control and experimental group(7 experimental, 7 control). All of participants were in-patients at local hospital and had been receiving a traditional rehabilitation program, five days a week. The both groups have undergone 4weeks. The experimental group trained in treadmill and cognitive task at the same time, but control group trained only treadmill. 10m walking test, Timed Up & Go (TUG) test and 6 Minutes walking(6M walking) test to measure the walking speed, dynamic balance and waling endurance ability were carried out before and after the training. Results : The result of the study were as follow:10m walking test were significantly increased both groups(p<.01), but not significant between groups(p>.05). TUG test were significantly increased both groups(p<.001) and between groups(p<.01). 6M walking test were significantly increased both groups(p<.001), but not significant between groups(p>.05). Conclusion : Ahead of return to the community to patients with stroke, cognitive task with in the course of treadmill training at the same time was effective in improving the dynamic balance ability.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2003.11a
• /
• pp.255-261
• /
• 2003

Tunnelling in poor and heterogeneous ground is a difficult task. Even with a good geological investigation, uncertainties with respect to the local rock mass structure will remain. Especially for such conditions, a reliable short-term prediction of the conditions ahead and outside the tunnel profile are of paramount importance for the choice of appropriate excavation and support methods. The information contained in the absolute displacement monitoring data allows a comprehensive evaluation of the displacements and the determination of the behaviour and influence of an anisotropic rock mass. Case histories and with numerical simulations show, that changes in the displacement vector orientation can indicate changing rock mass conditions ahead of the tunnel face (Schubert & Budil 1995, Steindorfer & Schubert 1997). Further research has been conducted to quantify the influence of weak zones on stresses and displacements (Grossauer 2001). Sellner (2000) developed software, which allows predicting displacements (GeoFit$\circledR$). The function parameters describe the time and advance dependent deformation of a tunnel. Routinely applying this method at each measuring section allows determining trends of those parameters. It shows, that the trends of parameter sets indicate changes in the stiffness of the rock mass outside the tunnel in a similar way, as the displacement vector orientation does. Three-dimensional Finite Element simulations of different weakness zone properties, thicknesses, and orientations relative to the tunnel axis were carried out and the function parameters evaluated from the results. The results are compared to monitoring results from alpine tunnels in heterogeneous rock. The good qualitative correlation between trends observed on site and numerical results gives hope that by a routine determination of the function parameters during excavation the prediction of rock mass conditions ahead of the tunnel face can be improved. Implementing the rules developed from experience and simulations into the monitoring data evaluation program allows to automatically issuing information on the expected rock mass quality ahead of the tunnel.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.140-140
• /
• 2021

Urban flood management is a crucial and challenging task, particularly in developed cities. Therefore, accurate prediction of urban flooding under heavy precipitation is critically important to address such a challenge. In recent years, machine learning techniques have received considerable attention for their strong learning ability and suitability for modeling complex and nonlinear hydrological processes. Moreover, a survey of the published literature finds that hybrid computational intelligent methods using nature-inspired algorithms have been increasingly employed to predict or simulate the streamflow with high reliability. The present study is aimed to propose a novel approach, an ensemble tree, Bayesian Additive Regression Trees (BART) model incorporating a nature-inspired algorithm to predict hourly multi-step ahead streamflow. For this reason, a hybrid intelligent model was developed, namely GA-BART, containing BART model integrating with Genetic algorithm (GA). The Jungrang urban basin located in Seoul, South Korea, was selected as a case study for the purpose. A database was established based on 39 heavy rainfall events during 2003 and 2020 that collected from the rain gauges and monitoring stations system in the basin. For the goal of this study, the different step ahead models will be developed based in the methods, including 1-hour, 2-hour, 3-hour, 4-hour, 5-hour, and 6-hour step ahead streamflow predictions. In addition, the comparison of the hybrid BART model with a baseline model such as super vector regression models is examined in this study. It is expected that the hybrid BART model has a robust performance and can be an optional choice in streamflow forecasting for urban basins.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.3
• /
• pp.257-272
• /
• 2016

It is usually not an easy task to counter-measure on time and appropriately when confronting with troubles in mechanized tunnelling job-sites because of the limitation of available spaces to perform those actions with the existence of disk cutter, cutter head, chamber and other various apparatus in Tunnel Boring Machine (TBM). So, it is important to predict the ground condition ahead of a tunnel face during tunnel excavation. Efforts have been made to utilize geophysical methods such as elastic wave survey, electromagnetic wave survey, electrical resistivity survey, etc for predicting the ground condition ahead of the TBM tunnel face. Each prediction method among these geophysical methods has its own advantage and disadvantage. Therefore, it might be needed to apply several geophysical methods rather than just one to predict the ground condition ahead of the tunnel face in the complex and/or mixed grounds since those methods will compensate among others. The problem is that each prediction method will give us different answer on the predicted ground condition; how to combine different solutions into a most reasonable and representative predicted value might be important. Therefore, in this study, we proposed a methodology how to systematically combine each prediction method utilizing probabilistic analysis as well as analytic hierarchy process. The proposed methods is applied to a virtual job site to confirm the applicability of the model to predict the ground condition ahead of the tunnel face in the mechanized tunnelling.

• The Journal of the Korea Contents Association
• /
• v.12 no.8
• /
• pp.29-36
• /
• 2012

In CCPM Technique, as the buffer size calculation method, the Cut and Paste(C&P) method and the Root Square Error (RSE) method for all tasks carried out the same treatment, without considering the actual situation and characteristics of the task, the lack of reasonable judgment, is too simple and hasty. In this paper, taking into account the limitations of existing methods, a new method of buffer sizing method based on statistical analysis was introduced. It makes statistical analysis for the relationship between each worker and a variety of tasks, and use the information to predict the next task time. In order to verify the effectiveness of the new method, according to different task difficulty and the number of tasks set up the project. Use C&P, RSE method and new methods to predict the time of the project. Through Monte Carlo Simulation to simulate the project time, a comparison of three methods of performance. The results show that the new method can achieve the managers expect the probability of completion, and for those tasks can be completed ahead of schedule, the new method can save project time.

• Water Engineering Research
• /
• v.1 no.2
• /
• pp.129-136
• /
• 2000

Predicting water levels is a difficult task because a lot of uncertainties are included. Therefore the neural network which is appropriate to such a problem, is introduced. One day ahead forecasting of river stage in the Bocheong River is carried out by using the neural network model. Historical water levels at Snagye gauging point which is located at the downstream of the Bocheong River and average rainfall of the Bocheong River basin are selected as training data sets. With these data sets, the training process has been done by using back propagation algorithm. Then waters levels in 1997 and 1998 are predicted with the trained algorithm. To improve the accuracy, a filtering method is introduced as predicting scheme. It is shown that predicted results are in a good agreement with observed water levels and that a filtering method can overcome the lack of training patterns.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.101-108
• /
• 2023

Optimizing the performance of deep neural networks on embedded systems is a challenging task that requires efficient compilers and runtime systems. We propose a TVM-based approach that consists of three steps: quantization, auto-scheduling, and ahead-of-time compilation. Our approach reduces the computational complexity of models without significant loss of accuracy, and generates optimized code for various hardware platforms. We evaluate our approach on three representative CNNs using ImageNet Dataset on the NVIDIA Jetson AGX Xavier board and show that it outperforms baseline methods in terms of processing speed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.1
• /
• pp.23-31
• /
• 2011

In this paper, the intelligent smart monitor system is implemented for the next generation vehicle. to mitigate the numerous effects of distractions within the vehicle, it is vital to put critical information where the driver can use it without affection focus on the road ahead. Audible alarms are useful supplements when used in conjunction with visual displays. But driving is an overwhelmingly visual task. To optimize a vehicle's active safety systems, more than just audible alarms are necessary. The driver needs a visual interface that focuses his or her attention on the road ahead. The most commonly viewed information in a vehicle is from the instrument cluster, where speed, tachometer, fuel, engine temperature, fuel gauge, turn indicators and warning lights provide the driver with an array of fundamental information. TFT LCD, LCD Back light led, plane mirror, lens and controllers parts were designed to intelligent integrated smart monitor system. Finally, in this paper, we analyze intelligent integrated smart monitor system for driver safety vehicles.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.113-122
• /
• 2018

In level 3 automated vehicles, drivers are expected to encounter transition of control when the system reaches its limit. Drivers need to refocus their attention on the road ahead and gain situational awareness. Appropriate information should be conveyed during this period in order to prevent human errors. In this paper, we defined the takeover process as 'in-the-middle-of-the-loop' and conducted Task Analysis and Work Domain Analysis to find out information requirements. As a result, we specified required information types and interface considerations. Moreover, we conducted an experimental study to find how the information types affect drivers on situation awareness, cognitive load and reaction time. Consequently, we found different information on system transparency should be conveyed depending on the urgency of takeover situation and driver guidance could help drivers with better situation awareness after the takeover.