• International Journal of Highway Engineering
• /
• v.19 no.4
• /
• pp.1-7
• /
• 2017

PURPOSES : This study aims to improve complex modeling of multivariable, nonlinear, and overdispersion data with an artificial neural network that has been a problem in the civil and transport sectors. METHODS: Deep learning, which is a technique employing artificial neural networks, was applied for developing a large bus fuel consumption model as a case study. Estimation characteristics and accuracy were compared with the results of conventional multiple regression modeling. RESULTS : The deep learning model remarkably improved estimation accuracy of regression modeling, from R-sq. 18.76% to 72.22%. In addition, it was very flexible in reflecting large variance and complex relationships between dependent and independent variables. CONCLUSIONS : Deep learning could be a new alternative that solves general problems inherent in conventional statistical methods and it is highly promising in planning and optimizing issues in the civil and transport sectors. Extended applications to other fields, such as pavement management, structure safety, operation of intelligent transport systems, and traffic noise estimation are highly recommended.

• Journal of Advanced Navigation Technology
• /
• v.11 no.4
• /
• pp.359-370
• /
• 2007

Lane tracking and obstacle avoidance are considered two of the key technologies on an unmanned ground vehicle system. In this paper, we propose a method of lane tracking and obstacle avoidance, which can be expressed as vehicle control, modeling, and sensor experiments. First, obstacle avoidance consists of two parts: a longitudinal control system for acceleration and deceleration and a lateral control system for steering control. Each system is used for unmanned ground vehicle control, which notes the vehicle's location, recognizes obstacles surrounding it, and makes a decision how fast to proceed according to circumstances. During the operation, the control strategy of the vehicle can detect obstacle and perform obstacle avoidance on the road, which involves vehicle velocity. Second, we explain a method of lane tracking by means of a vision system, which consists of two parts: First, vehicle control is included in the road model through lateral and longitudinal control. Second, the image processing method deals with the lane tracking method, the image processing algorithm, and the filtering method. Finally, in this paper, we propose a method for vehicle control, modeling, lane tracking, and obstacle avoidance, which are confirmed through vehicles tests.

• Transactions on Electrical and Electronic Materials
• /
• v.11 no.3
• /
• pp.138-144
• /
• 2010

Optical analysis is necessary to optimize light emitting diode (LED) safety street lighting. In this study, optical analysis was conducted for 100 W LED safety street lighting. Experimental research on such a single LED was the first undertaken. Simulation modeling based on the optical properties of the single LED has compared between average road illuminances and has them analyzed with Korean Industrial Standards for LED safety street lighting (KS C7658:2009). The simulation results demonstrated that the illumination performance (average road illuminance) was 75.3 lx at a height of 4 m and an area of $32\;m^2$, 45.25 lx at a height of 5 m and an area of $72\;m^2$, and 30.05 lx at a height of 6 m and an area of $128\;m^2$. 100 W safety street lighting (model CE180-ST-OS) designed by simulation was also compared between product and 100 W simulation modeling, and error rates averaged 5.6%. The 100 W LED safety street lighting base designed in simulation modeling was proven by comparison experiments. Through the simulations and the corresponding analysis, it was found that the tested 100 W LED safety street lamp had reasonable performance. The design method for LED safety street lamps has been summarized based on the optical analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.82-88
• /
• 2018

This study investigated the structure of an 8-pole 8-slot linear generator, which acts as an electromagnetic damper by combining the structure of an electromagnetic suspension device capable of generating electrical energy through energy harvesting by absorbing the vibration energy from the road surface while driving. To compare the energy harvesting effect of the electromagnetic suspension according to the actual road surface, a driving road test was simulated for two actual road conditions, an asphalt road surface and unpacked road surface condition, using a civilian combined vehicle model in conjunction with a vehicle simulation program, Carsim and Simulink. As a result, the relative displacements of the suspensions on the asphalt road surface and the unpaved road were 8 mm and 13 mm, respectively. By applying the suspension displacement value derived by modeling the linear generator coupled to the electromagnetic suspension, the simulation was then performed for an analysis time of 0.3s by applying the same analytical conditions using the commercial electromagnetic analysis program, ANSYS MAXWELL, The average power generation on the unpacked roads and asphalt roads was 198.6W and 98.7W respectively, which was 103.7% higher for unpackaged roads. Finally, to compare the sensitivity of the road surface frequency and the suspension input displacement to the power generation output, the sensitivity of the two variables was 1.725 and 1.283, respectively, and the road surface frequency had a 34.5% higher effect on the average power generation.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.4
• /
• pp.348-356
• /
• 2014

To understand the relationship between road-traffic noise and urban components such as population, building, road-traffic and land-use, the city of Cheongju that already has road-traffic noise maps of daytime and nighttime was selected for this study. The whole area of the city is divided into square cells of a uniform size and for each cell, the urban components are estimated. A spatial representative noise level for each cell is determined by averaging out population-weighted facade noise levels for noise exposure population within the cell during nighttime. The relationship between the representative noise level and the urban components is statistically modeled at the cell level. Specially, we introduce a spatial auto regressive model and a spatial error model that turns out to explain above 85 % of the noise level. These findings and modeling methods can be used as a preliminary tool for environmental planning and urban design in modern cities in consideration of noise exposure.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.396-404
• /
• 2011

Recently, the wide spread popularity of smart phones causes the advent of various mobile applications base on the location information. Since previous pedestrian navigations are applied by extending car navigations, these are not only difficult to provide the appropriate route information, but also raise limitations in the efficient query processing by data structures of car road networks. In addition, these increase the power consumption caused by the growth of I/O frequency. In this paper, we propose a pedestrian road network model for the accurate route information and a storage structure for the pedestrian road network based on POI to reduce the I/O frequency. The proposed method enables efficient route searches over POI reflecting the characteristics and requirements of pedestrian roads. Also, a reduction of query processing costs for the route searching by a data structure considered with POI can save the power consumption more than previous approaches.

• Journal of the Economic Geographical Society of Korea
• /
• v.16 no.2
• /
• pp.262-274
• /
• 2013

Heavy rain and heavy snow as representative extreme weather are recently an issue in urban area. The paper aims at modeling the scenarios of evacuation that minimizes economic loss of the designated urban area with improving travel efficiency by providing road closure information facing an extremely heavy rainfall. The paper develops a model by using a NetLogo toolkit applied to the study area of Seocho-dong, Seocho-gu, Seoul. The model conducts a simulation of travel time under different scenarios of information provision. The simulation results show that it is efficient to provide the information of road closure to 20~40% of the drivers under the scenario of humid road or rainfall less than 20mm, whereas to 40~60% of the drivers under the scenario of heavy rainfall more than 20mm.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2001.03a
• /
• pp.17-24
• /
• 2001

Several underground cavities were found during construction of a road tunnel in 600m length . The area belong to Whasoon coalfield where extensive ground subsidences have occurred. It is necessary to find other underground cavities which might be located just near the road tunnel for safety, The field surveys and laboratory tests were conducted such as surface geological survey(672m), surface reflection seismic exploration(399m), drilling test(3 NX holes), 9 laboratory tests for rocks, 3 boreholes televiewer tests, reflection seismic exploration in tunnel(2, 342m). To estimate the effects of underground cavities on the road tunnel, 3 geological section were analysed with FLAC-2D modeling. The effects of the ground reinforcement were also analysed.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.176-190
• /
• 2002

According as vehicles increases, system such as Advanced Drivers Assistance System(ADAS ) to inform forward situation to driver is required. In this paper, we proposes method to detect forward vehicles and lane from sequential color images by basis process to inform forward situation to driver. We detect a front vehicle using that shadow area exists on part under vehicles and that road area occupies many parts even if road traffic is confused. We detect lane information using that lane part is white order by reverse characteristic of shadow area. This method shows good result in case road is confused or there is direction indication to road. HSV color space is selected for color modeling. This method uses saturation component and value component in HSV color model to detect vehicles and lane. It uses statistics features of HSV component and position to know whether detected vehicles area is vehicles such as vehicles previous frame. To verify the effects of the proposed method, we capture the road images with notebook and CCD camera for PC and Present the results such as processing time, accuracy and vehicles detection against the images.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1542-1549
• /
• 2011

The Transitional zone between bridge abutment and earthwork is one of the representative vulnerable zones in railway where differential settlements may take place due to the different supportive stiffness. Although transitional zones are managed with stricter standards than those of the other earthwork zones either in the design and construction stages, it is very difficult to prevent differential settlement perfectly. A three-dimensional numerical analyses were performed by applying train moving load in this study. The analytical model including abutments and earthwork zones was constituted with rail, sleepers, track concrete layer (TCL), hydraulic stabilized base (HSB), reinforced road bed, and road bed using railway and road base structure. The clamp connecting the rail and sleeper were also modeled as the element with spring coefficient. The train wheel is modeled in the actual size and moved on the rail with 300 km/hr speed. The deformation characteristics at each point of the rail and the ground were considered in detail when moving the train wheel. The analysis results were compared with those from the two-dimensional analysis without considering moving load. The research results show that displacement and stress were greater in the three-dimensional analysis than in other analyses, and the three-dimensional analysis with moving load should be performed to evaluate railway performance.