• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.4
• /
• pp.255-262
• /
• 2016

There has been intense research on self-diagnosis systems in railway applications, since stability and reliability have become more and more significant issues. Wired sensors have been widely used in the railway vehicles, but because of the difficulty in their maintenance and accessibility, they ar not considered for self-diagnosis systems. To have a self-monitoring system, wireless data transmission and self-powered sensors are required. For this purpose, a thermoelectric energy harvesting module that can generate electricity from temperature gradient between the bogie axle box and ambient environment was introduced in this work. The temperature gradient was measured under actual operation conditions, and the behavior of the thermoelectric module with an external load resistance and booster circuits was studied. The proposed energy harvesting system can be applied for wireless sensor nodes in railroad vehicles with optimization of thermal management.

• Journal of Construction Engineering and Project Management
• /
• v.3 no.4
• /
• pp.12-19
• /
• 2013

Green Frame is an environmentally friendly column-beam system composed of composite PC members that can increase buildings' life spans while reducing resource consumption. Typically, connections of PC and RC columns occur at the boundaries of each floor, which is at the upper section of slabs, causing the boundary of each floor to generate the maximum moment. Although it is not optimal in terms of structural safety to connect members at a location where the moment is high, this approach is highly adopted due to its constructability. We propose that a superior approach that employs the concept of connecting columns at the low bending moment zone can be applied to quickly and safely install green columns, the main structural members of Green Frame. Connection of green columns at the low bending moment zone can be classified into three techniques, depending on the method of reinforcing the joints, which have different connection characteristics and construction methods. Research is needed to compare the features of each method of reinforcing the joints so that the most appropriate column connection method can be chosen for the site conditions. This study aims to confirm the structural safety of the connection component at the low bending moment zone and to compare and analyze the construction duration, unit price, quality and safety performance of each column connection method. The study results are anticipated to activate the use of composite precast concrete and to be used as development data in the future.

• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.385-395
• /
• 2005

Long sentence analysis has been a critical problem in machine translation because of high complexity. The methods of intra-sentence segmentation have been proposed to reduce parsing complexity. This paper presents the intra-sentence segmentation method based on maximum entropy probability model to increase the coverage and accuracy of the segmentation. We construct the rules for choosing candidate segmentation positions by a teaming method using the lexical context of the words tagged as segmentation position. We also generate the model that gives probability value to each candidate segmentation positions. The lexical contexts are extracted from the corpus tagged with segmentation positions and are incorporated into the probability model. We construct training data using the sentences from Wall Street Journal and experiment the intra-sentence segmentation on the sentences from four different domains. The experiments show about $88\%$ accuracy and about $98\%$ coverage of the segmentation. Also, the proposed method results in parsing efficiency improvement by 4.8 times in speed and 3.6 times in space.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1386-1399
• /
• 2004

This paper presents correlation-based automatic image captioning. Given a training set of annotated images, we want to discover correlations between visual features and textual features, so that we can automatically generate descriptive textual features for a new unseen image. We develop models with multiple design alternatives such as 1) adaptively clustering visual features, 2) weighting visual features and textual features, and 3) reducing dimensionality for noise sup-Pression. We experiment thoroughly on 10 data sets of various content styles from the Corel image database, about 680MB. The major contributions of this work are: (a) we show that careful weighting visual and textual features, as well as clustering visual features adaptively leads to consistent performance improvements, and (b) our proposed methods achieve a relative improvement of up to 45% on annotation accuracy over the state-of-the-art, EM approach.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.199-206
• /
• 2006

Sequential pattern mining is an important data mining task with broad applications. However, conventional methods may meet inherent difficulties in mining databases with long sequences and noise. They may generate a huge number of short and trivial patterns but fail to find interesting patterns shared by many sequences. In this paper, to overcome these problems, we propose the theme of approximate sequential pattern mining roughly defined as identifying patterns approximately shared by many sequences. The proposed method works in two steps: one is to cluster target sequences by their similarities and the other is to find consensus patterns that ire similar to the sequences in each cluster directly through multiple alignment. For this purpose, a novel structure called weighted sequence is presented to compress the alignment result, and the longest consensus pattern that represents each cluster is generated from its weighted sequence. Finally, the effectiveness of the proposed method is verified by a set of experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.388-396
• /
• 2009

This paper proposes a new fire-smoke detection method by using extracted features from camera images and pattern recognition technique. First, moving regions are detected by analyzing the frame difference between two consecutive images and generate candidate smoke regions by applying smoke color model. A smoke region generally has a few characteristics such as similar color, simple texture and upward motion. From these characteristics, we extract brightness, wavelet high frequency and motion vector as features. Also probability density functions of three features are generated using training data. Probabilistic models of smoke region are then applied to observation nodes of our proposed Dynamic Bayesian Networks (DBN) for considering time continuity. The proposed algorithm was successfully applied to various fire-smoke tasks not only forest smokes but also real-world smokes and showed better detection performance than previous method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.652-660
• /
• 2008

Applications running under embedded systems require various device drivers designed for different types and versions of the OS to manage resources effectively. In this paper, an automated device driver generator system which can generate the device drivers to be used in newer versions the target OS is proposed. In the proposed system, the structures of device drivers of specific OS are designed in the templates and stored in a library, and the target device drivers are generated by adding codes to the stored templates. Once device drivers are generated, they are registered into the kernel. The experimental results show that data transfer time has been slightly increased when compared against manually created drivers for TFT-LCD driver, USB interface keyboard/mouse driver, and AC'97 controller drivers. The code size for the generated drivers after compilation has also been increased slightly when compared with manually designed device drivers.

• Journal of KIISE:Software and Applications
• /
• v.35 no.7
• /
• pp.442-451
• /
• 2008

Most plagiarism detection systems evaluate the similarity of source codes and detect plagiarized program pairs. If we use the source codes in plagiarism detection, the source code security can be a significant problem. Plagiarism detection based on target code can be used for protecting the security of source codes. In this paper, we propose a new plagiarism detection technique for Java programs using bytecodes without referring their source codes. The plagiarism detection procedure using bytecode consists of two major steps. First, we generate the token sequences from the Java class file by analyzing the code area of methods. Then, we evaluate the similarity between token sequences using the adaptive local alignment. According to the experimental results, we can find the distributions of similarities of the source codes and that of bytecodes are very similar. Also, the correlation between the similarities of source code pairs and those of bytecode pairs is high enough for typical test data. The plagiarism detection system using bytecode can be used as a preliminary verifying tool before detecting the plagiarism by source code comparison.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.2 s.32
• /
• pp.45-50
• /
• 2005

Recently, slope failures are disastrous when they occur in mountainous area adjoining highways. The accidents associated with Slope failures have increased due to rapid urbanization of mountainous area. Therefore, the inspection of slope is conducted to maintain road safety as well as road function. In this study, we apply to the remedy which is comparing existent description to advanced technology using GIS. we utilize a 3D scanner, one of the advanced method, to generate precise and complete road slope model from expert point of view. In result, we are transferred practical data from external slope stability to hazard slope information. We suggest not only the database but also the method of road risk evaluation based on GIS.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.1 s.31
• /
• pp.55-61
• /
• 2005

Digital Elevation Model (DEM) generation from remotely sensed imagery is crucial for a variety of mapping applications such as ortho-photo generation, city modeling. High resolution imaging satellites such as SPOT-5, IKONOS, QUICK-BIRD, ORBVIEW constitute an excellent source for efficient and economic generation of DEM data. However, prerequisite knowledge in the areas of sensor modeling, epipolar resampling, and image matching is required to generate DEM from these high resolution satellite imagery. From the above requirements, epipolar resampling emerges as the most important factors. Research attempts in this area are still in high demand and short supply. Another cause that adds to the complication of the problem is that most studies of DEM generation from IKONOS scenes have been based on rational function model. In this paper, we proposed a new methodology for DEM generation from satellite scenes using parallel projection model which is sensor independent, makes it possible for sensor modeling and epipolar resampling by only few control points. The performance and feasibility of the developed methodology is evaluated through real dataset captured by IKONOS.