• Journal of the Ergonomics Society of Korea
• /
• v.35 no.5
• /
• pp.449-464
• /
• 2016

Objective: The objective of this study is to identify essential requirements of the instrument cluster's features and layout for elderly drivers through interview and paper prototyping. Background: Recent updates implemented in passenger vehicles require more complex information to be processed by drivers. Concurrently, a large portion of the US population, the baby boomer generation has aged, causing their physical and cognitive abilities to deter. Thus it is crucial that new methods be implemented into vehicle design in order to accommodate for the deterioration of mental and physical abilities. Method: Forty elderly drivers and twenty young drivers participated in this study. The test included three sessions including: 1) location value assessment to identify the priority of areas within the instrument cluster; 2) component value assessment to capture rankings of the degree of importance and frequency of use for possible instrument cluster components; and 3) paper prototyping to collect self-designed cluster with selection of designs for each component and location of features from each participant. Results: Results revealed differences in the area priority of the instrument cluster as well as the shape and location of component features for age and gender groups. Conclusion: The study provided insights on instrument cluster layout guidelines by proving elderly driver's mental model and preferred cluster design configurations to improve driving safety. Application: LCD-based vehicle instrument cluster design, with an adaptable feature configuration for cluster components and layouts.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.124-130
• /
• 2004

Microarray expression datasets are incessantly cumulated with the aid of recent technological advances. One of the first steps for analyzing these data under various experimental conditions is determining differentially expressed genes (DEGs) in each condition. Reasonable choices of thresholds for determining differentially expressed genes are used for the next -step-analysis with suitable statistical significances. We present a model for identifying DEGs using pathway information based on the global connectivity structure. Pathway information can be regarded as a collection of biological knowledge, thus we are tying to determine the optimal threshold so that the consequential connectivity structure can be the most compatible with the existing pathway information. The significant feature of our model is that it uses established knowledge as a reference to determine the direction of analyzing microarray dataset. In the most of previous work, only intrinsic information in the miroarray is used for the identifying DEGs. We hope that our proposed method could contribute to construct biologically meaningful network structure from microarray datasets.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1264-1274
• /
• 2015

Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.2
• /
• pp.723-735
• /
• 2019

This paper employs computational tools to investigate the cause of resistance reductions in calm water and waves of the sharp bow form compared to the blunt bow in 66,000 DWT bulk carriers. A more slender shape at the fore-shoulder without a bulbous bow is a prominent feature of the sharp bow. The blunt bow incorporates a bulbous shape. A two-phase unsteady Reynolds averaged Navier-Stokes equations have been solved; and a realizable k-ε model has been applied for the turbulent closure. The free-surface is obtained by solving a VOF equation. The computational results have been validated with model tests carried out at a towing tank. The pressure component of resistance in the sharp bow is reduced by 8.9% in calm water, and 6.4-12.7% in regular head waves. The frictional components of resistance in the sharp and blunt bows are largely the same.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.368-373
• /
• 2007

In recent year s there have been increasing interests in real-time object tracking with image information. This dissertation presents a real-time object tracking method through the object recognition based on neural networks that have robust characteristics under various illuminations. This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. The experiment result shows the usefulness of the proposed method is verified.

• Journal of Communications and Networks
• /
• v.4 no.3
• /
• pp.221-229
• /
• 2002

Adaptability is the most promising feature to be applied in future robust multimedia applications. In this paper, we propose the Direct Algorithm to improve the degree of satisfaction at heterogeneous receivers in multi-layered multicast video environments. The algorithm relies on a mechanism that dynamically controls the rates of the video layers and is based on feedback control packets sent by the receivers. The algorithm also addresses scalability issues by implementing a merging procedure at intermediate nodes in order to avoid packet implosion at the source in the case of large multicast groups. The proposed scheme is optimized to achieve high global video quality and reduced bandwidth requirements. We also propose the Direct Algorithm with a virtual number of layers. The virtual layering scheme induces intermediate nodes to keep extra states of the multicast session, which reduces the video degradation for all the receivers. The results show that the proposed scheme leads to improved global video quality at heterogeneous receivers with no cost of extra bandwidth.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.4
• /
• pp.9-16
• /
• 2002

Content based Image retrieval methods in the multimedia information retrievals use primary visual features such as color, texture and shape. Color and texture generally are used as features of the image retrieval systems. But these systems may produce errors in similar image retrieval because two images with different shapes can represent very different contents. Therefore, the use of shape describing features is essential in an efficient content based image retrieval system. In this paper, after the global features filtering process by the boundary of objects, we have created a better shape similarity image retrieval system by a histogram of shape information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.997-1003
• /
• 2007

In this paper, we propose a global approach for automatic inspection of defects in the polarizer film image. The proposed method does not rely on local feature of the defect. It is based on a global image reconstruction scheme using the singular value decomposition(SVD). SVD is used to decompose the image and then obtain a diagonal matrix of the singular values. Among the singular values, the first singular value is used to reconstruct a image. In reconstructed image, the normal pixels in background region have a different characteristics from the pixels in defect region. It is obtained the ratio of pixels in the reconstructed image to ones in the original image and then the defects are detected based on the the statistical process of the ratio. The experiment results show that the proposed method is efficient for defect inspection of polarizer lam image.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.21-39
• /
• 2020

Recently, deep learning has shown high performance in various applications such as pattern analysis and image classification. Especially known as a difficult task in the field of machine learning research, stock market forecasting is an area where the effectiveness of deep learning techniques is being verified by many researchers. This study proposed a deep learning Convolutional Neural Network (CNN) model to predict the direction of stock prices. We then used the feature selection method to improve the performance of the model. We compared the performance of machine learning classifiers against CNN. The classifiers used in this study are as follows: Logistic Regression, Decision Tree, Neural Network, Support Vector Machine, Adaboost, Bagging, and Random Forest. The results of this study confirmed that the CNN showed higher performancecompared with other classifiers in the case of feature selection. The results show that the CNN model effectively predicted the stock price direction by analyzing the embedded values of the financial data