• Journal of Korean Society of Transportation
• /
• v.28 no.1
• /
• pp.135-142
• /
• 2010

The convenient techniques for predicting the bus arrival time have used the data obtained from the buses belong to the same company only. Consequently, the conventional techniques have often failed to predict the bus arrival time at the downstream bus stops due to the lack of the data during congestion time period. The primary objective of this study is to overcome the weakness of the conventional techniques. The estimation model developed based on the data obtained from Bus Information System(BIS) and Bus management System(BMS). The proposed model predicts the bus arrival time at bus stops by using the data of all buses travelling same roadway section during the same time period. In the tests, the proposed model had a good accuracy of predicting the bus arrival time at the bus stops in terms of statistical measurements (e.g., root mean square error). Overall, the empirical results were very encouraging: the model maintains a prediction job during the morning and evening peak periods and delivers excellent results for the severely congested roadways that are of the most practical interest.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.229-250
• /
• 2022

Since the publication of Markowitz's (1952) mean-variance portfolio model, research on portfolio optimization has been conducted in many fields. The existing mean-variance portfolio model forms a nonlinear convex problem. Applying Dantzig's linear programming method, it was converted to a linear form, which can effectively reduce the algorithm computation time. In this paper, we proposed a Dantzig perturbation portfolio model that can reduce management costs and transaction costs by constructing a portfolio with stable and small (sparse) assets. The average return and risk were adjusted according to the purpose by applying a perturbation method in which a certain part is invested in the existing benchmark and the rest is invested in the assets proposed as a portfolio optimization model. For a covariance estimation, we proposed a Gaussian kernel weight covariance that considers time-dependent weights by reflecting time-series data characteristics. The performance of the proposed model was evaluated by comparing it with the benchmark portfolio with 5 real data sets. Empirical results show that the proposed portfolios provide higher expected returns or lower risks than the benchmark. Further, sparse and stable asset selection was obtained in the proposed portfolios.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.15 no.2
• /
• pp.77-84
• /
• 2012

This study suggested the planting model of Zelkova serrata communities in the areas with the warmth index of both 80~100 and $100{\sim}120^{\circ}C{\cdot}month$. Warmth index was calculated with 449 weather points using inverse distance weighted interpolation method. The planting species were selected by correlation analysis between Z. serrata and each species of four or more frequency among the 36 relev$\acute{e}$ surveyed for this study. The result of this study is summarized as follows : Warmth index of Z. serrata communities was among $74{\sim}118^{\circ}C{\cdot}month$. Results of the correlation analysis between Z. serrata and each species observed that the Z. serrata belongs to the tree layer with warmth index of 80~100 and $100{\sim}120^{\circ}C{\cdot}month$. On the other hand, the species of Carpinus laxiflora, Quercus serrata, Prunus sargentii and Platycarya strobilacea appeared only in the tree layer with warmth index of $80{\sim}100^{\circ}C{\cdot}month$. Z. serrata and Styrax japonica appeared in the subtree layer with the warmth index of 80~100 and $100{\sim}120^{\circ}C{\cdot}month$, while Acer pseudosieboldianum, Lindera erythrocarpa, Acer mono, Quercus serrata, etc. appeared in the subtree layer with the warmth index of $80{\sim}100^{\circ}C{\cdot}month$. Z. serrata, Ligustrum obtusifolium, Lindera obtusiloba, Callicarpa japonica and Zanthoxylum schinifolium all appeared in the shrub layer with the warmth index of 80~100 and $100{\sim}120^{\circ}C{\cdot}month$. Lindera erythrocarpa, Orixa japonica, Staphylea bumalda, Akebia quinata and Sorbus alnifolia appeared in the shrub layer with the warmth index of $80{\sim}100^{\circ}C{\cdot}month$ and Styrax japonica and Stephanandra incisa appeared in the shrub layer with the warmth index of $100{\sim}120^{\circ}C{\cdot}month$, The numbers of each species planted in a $100m^2$ area of the Z. serrata community were suggested as follows : five in tree layer, five in subtree layer and nine in shrub layer. The average area of canopy are suggested to be about $86m^2$ for tree layer, $34m^2$ for subtree layer and $34m^2$ for shrub layer.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.283-298
• /
• 2022

As Synthetic Aperture Radar (SAR) image can be acquired regardless of the weather and day or night, it is highly recommended to be used for Automatic Target Recognition (ATR) in the fields of surveillance, reconnaissance, and national security. However, there are some limitations in terms of cost and operation to build various and vast amounts of target images for the SAR-ATR system. Recently, interest in the development of an ATR system based on simulated SAR images using a target model is increasing. Attributed Scattering Center (ASC) matching and template matching mainly used in SAR-ATR are applied to target classification. The method based on ASC matching was developed by World View Vector (WVV) feature reconstruction and Weighted Bipartite Graph Matching (WBGM). The template matching was carried out by calculating the correlation coefficient between two simulated images reconstructed with adjacent points to each other. For the performance analysis of the two proposed methods, the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset was used, which has been recently published by the U.S. Defense Advanced Research Projects Agency (DARPA). We conducted experiments under standard operating conditions, partial target occlusion, and random occlusion. The performance of the ASC matching is generally superior to that of the template matching. Under the standard operating condition, the average recognition rate of the ASC matching is 85.1%, and the rate of the template matching is 74.4%. Also, the ASC matching has less performance variation across 10 targets. The ASC matching performed about 10% higher than the template matching according to the amount of target partial occlusion, and even with 60% random occlusion, the recognition rate was 73.4%.

• Journal of the Korean Geotechnical Society
• /
• v.30 no.10
• /
• pp.55-65
• /
• 2014

Recent researches on debris flow is focused on understanding its movement mechanism and building a numerical simulator to predict its behavior. However, previous simulators emulating fluid-like debris flow have limitations in numerical stability, geometric modeling and application of various boundary conditions. In this study, depth integration is applied to continuity equation and force equilibrium for debris flow. Thickness of sediment, and average velocities in x and y flow direction are chosen for main variables in the analysis, which improve numerical stability in the area with zero thickness. Petrov-Galerkin formulation uses a discontinuous test function of the weighted matrix from DG scheme. Presented mechanical constitutive model combines fluid and granular behaviors for debris flow. Effects on slope angle, inducing debris height, and bottom friction resistance are investigated for a simple slope. Numerical results also show the effect of embankment at the bottom of the slope. Developed numerical simulator can assess various risk factors for the expected area of debris flow, and facilitate embankment design in order to minimize damage.

• Korean Journal of Computational Design and Engineering
• /
• v.17 no.4
• /
• pp.253-261
• /
• 2012

In order to make dental implant surgery successful, it is important to perform proper planning for dental implant placement. In this paper, we propose a decent approach to dental implant placement planning based on geometric processing of 3D models of jawbones, a nerve curve and neighboring teeth around a missing tooth. Basically, the minimum enclosing cylinders of the neighboring teeth around the missing tooth are properly used to determine the position and direction of the implant placement. The position is computed according to the radii of the cylinders and the center points of their top faces. The direction is computed by the weighted average of the axes of the cylinders. For a cylinder whose axis passes the position along the direction, its largest radius and longest length are estimated such that it does not interfere with the neighboring teeth and the nerve curve, and they are used to select the size and type of an implant fixture. From the geometric and spatial information of the jawbones, the teeth and the fixture, we can construct the 3D model of a surgical guide stent which is crucial to perform the drilling operation with ease and accuracy. We have shown the validity of the proposed approach by performing the finite element analysis of the influence of implant placement on bone stress distribution. Adopted in 3D simulation of dental implant placement, the approach can be used to provide dental students with good educational contents. It is also expected that, with further work, the approach can be used as a useful tool to plan for dental implant surgery.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.385-396
• /
• 2005

In this paper, a new structural approach to on-line signature verification is presented. A primitive pattern is defined as a part segmented by a local minimal position of speed. And a structural description of signature is composed of subpatterns which are defined as such forms as rotation shape, cusp shape and bell shape, acquired by composition of the primitives regarding the directional changes. As the matching method to find identical parts between two signatures, a modified DP(dynamic programming) matching algorithm is presented. And also, variation and complexity of local parts are computed from the training samples, and reference model and decision boundary are derived from these. Error rate, execution time and memory usage are compared among the functional approach, the parametric approach and the proposed structural approach. It is found that the average error rate can be reduced from 14.2% to 4.05% when the local parts of a signature are weighted and the complexity is used as a factor of decision threshold. Though the error rate is similar to that of functional approaches. time consumption and memory usage of the proposed structural approach are shown to be very effective.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1595-1603
• /
• 2020

Online defamation incidents such as Internet news comments on portal sites, SNS, and community sites are increasing in recent years. Bias and hate expressions threaten online service users in various forms, such as invasion of privacy and personal attacks, and defamation issues. In the past few years, academia and industry have been approaching in various ways to solve this problem The purpose of this study is to build a dataset and experiment with deep learning classification modeling for detecting various bias expressions as well as hate expressions. The dataset was annotated 7 labels that 10 personnel cross-checked. In this study, each of the 7 classes in a dataset of about 137,111 Korean internet news comments is binary classified and analyzed through deep learning techniques. The Proposed technique used in this study is multi-channel CNN model with attention. As a result of the experiment, the weighted average f1 score was 70.32% of performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.163-170
• /
• 2022

This paper introduces a method of extracting facial features due to unrefined inputs in real life and improving the problem of not guaranteeing the ideal performance and speed of the object recognition model through a storage algorithm through weight summation. Many facial recognition processes ensure accuracy in ideal situations, but the problem of not being able to cope with numerous biases that can occur in real life is drawing attention, which may soon lead to serious problems in the face recognition process closely related to security. This paper presents a method of quickly and accurately recognizing faces in real time by comparing feature points extracted as input with a small number of feature points that are not overfit to multiple biases, using that various variables such as picture composition eventually take an average form.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.259-266
• /
• 2023

In this paper, we propose an algorithm that can improve the accuracy performance of collaborative filtering using attribute-based opinion mining (ABOM). For the experiment, a total of 1,227 online consumer review data about smartphone apps from domestic smartphone users were used for analysis. After morpheme analysis using the KKMA (Kkokkoma) analyzer and emotional word analysis using KOSAC, attribute extraction is performed using LDA topic modeling, and the topic modeling results for each weighted review are used to add up the ratings of collaborative filtering and the sentiment score. MAE, MAPE, and RMSE, which are statistical model performance evaluations that calculate the average accuracy error, were used. Through experiments, we predicted the accuracy of online customers' app ratings (APP_Score) by combining traditional collaborative filtering among the recommendation algorithms and the attribute-based opinion mining (ABOM) technique, which combines LDA attribute extraction and sentiment analysis. As a result of the analysis, it was found that the prediction accuracy of ratings using attribute-based opinion mining CF was better than that of ratings implementing traditional collaborative filtering.