• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.4
• /
• pp.382-389
• /
• 2011

Salesperson Monitoring System (SMS) is geographic based information system that supports business auditing, sales area coordinating and customer management for each salesperson. Conventional SMSs focus mainly on the monitoring or logging functions, i.e., a salesperson locating or moving trail tracking. However, the schedules have been planned by human planner, and they have rarely been managed with a software system like SMS. In this paper, a mixed integer programming model for a salesperson routing schedule is provided. Then, 2-phase Genetic Algorithm (GA) is proposed to make salesperson routing schedule. Experimental results show a validity of the proposed method.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.33-38
• /
• 2018

In this study, we try to detect new attacks for vehicle by learning only one class. We use Car-Hacking dataset, an intrusion detection dataset, which is used to evaluate classification performance. The dataset are created by logging CAN (Controller Area Network) traffic through OBD-II port from a real vehicle. The dataset have four attack types. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve high efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data, which are new attacks. In this study, we use one class classifier to detect new attacks that are difficult to detect using signature-based rules on network intrusion detection system. The proposed method suggests a combination of parameters that detect all new attacks and show efficient classification performance for normal dataset.

• Korean Journal of Agricultural Science
• /
• v.23 no.1
• /
• pp.138-149
• /
• 1996

This study was aimed at predicting to running speed related to alignment factors of forest road, and recommending the improvement method of forest road construction using the running speed of vehicles. For these purposes, this study proceeds to select forest roads after reviewing the planning papers and maps, to measure the road alignment factors such as longitudinal gradient, width of roadway, radius of curve, length of curve, superelevation, and conditions of road surface on the subject forest road. It was found that the average running speed of logging truck showed lower value than that of the expected speed of 'Forest Road Construction Regulations and Rules', and the average running speed of loaded truck showed 70-85% of the speed of empty truck. According to the road conditions, speed index (reductive ratio of running speed) was also calculated with respect to radius of curve, longitudinal dradient. The results of the study on the running speed of vehicle subject to the alignment of forest roads make it possible for one to judge the quality of the existed and to be constructed forest roads, to select the structure of forest road to improve the running speed of vehicle on forest road.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.167-174
• /
• 2023

This study evaluated slope stability through a case study to determine the disaster risks associated with increased deforestation in structures, including schools and apartments, located in urban areas adjacent to slopes. The slope behind the ○○ High School in Gwangju, Korea, collapsed owing to heavy rain in August 2018. Historically, rainwater drained well around the slope during the rainy season. However, during the collapse, a large amount of seepage water flowed out of the slope surface and a shallow failure occurred along the saturated soil layer. To analyze the cause of the collapse, the images of the upper area of the slope, which could not be directly identified, were captured using unmanned aerial vehicles (UAVs). A digital elevation model of the slope was constructed through image analysis, making it possible to calculate the rainfall flow direction and the area, width, and length of logging areas. The change in the instability of the slope over time owing to rainfall lasting ten days before the collapse was analyzed through numerical analysis. Imaging techniques based on the UAV images were found to be effective in analyzing ground disaster risk maps in urban areas. Furthermore, the analysis was found to predict the failure before its actual occurrence.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.7
• /
• pp.95-102
• /
• 2014

There are a variety of structures below the surface are buried. In particular, if It is experiencing problems in the city gas pipe or electrical wire, our safety would be greatly jeopardized. Therefore, the underground structures which encounter a variety of pollutants are highly sensitive to corrosion. So if you are not identify the degree of corrosion, it can lead to large accidents such as gas leakage. Until now, person visit directly every underground structure to measure and record manually, but This approach requires a lot of human and material resources and the continuity of management. Therefore, the research to find out the risk factors quickly via the continuous management is needed, and in this paper the structures management systems in the vehicle being moved by combining ICT underground structures for state information wirelessly collects and analyzes system is proposed.