• Journal of the Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.99-108
• /
• 2008

For video compression, we have to consider two performance factors that are the search speed and coded video's quality. In this paper, we propose an enhanced fast block matching algorithm using the spatial correlation of the video sequence and the center-biased characteristic of motion vectors(MV). The proposed algorithm first finds a predicted motion vector from the adjacent macro blocks of the current frame and determines an exact motion vector using the cross pattern and a flat hexagon search pattern. From the performance evaluations, we can see that our algorithm outperforms both the hexagon-based search(HEXBS) and the cross-hexagon search(CHS) algorithms in terms of the search speed and coded video's quality. Using our algorithm, we can improve the search speed by up to 31%, and also increase the PSNR(Peak Signal Noise Ratio) by at most 0.5 dB, thereby improving the video quality.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.1
• /
• pp.1-8
• /
• 2004

According to the development of the Internet and the pervasion of Data Base, it is not easy to search for necessary information from the huge amounts of data. In order to do efficient analysis of a large amounts of data, this paper proposes a method for pattern classification based on the effective strategy for dimension reduction for narrowing down the whole data to what users wants to search for. To analyze data effectively, Radial Basis Function Networks based on VC-dimension of Support Vector Machine, a model of statistical teaming, is proposed in this paper. The model of Radial Basis Function Networks currently used performed the preprocessing of Perceptron model whereas the model proposed in this paper, performing independent analysis on VD-dimension, classifies each datum putting precise labels on it. The comparison and estimation of various models by using Machine Learning Data shows that the model proposed in this paper proves to be more efficient than various sorts of algorithm previously used.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.11-18
• /
• 2010

In this paper, We suggest new strategies on non-interactive agents applied in a prey pursuit problem of multi agent research. The structure of the prey pursuit problem by grid space(Four agent & one prey). That is allied agents captured over one prey. That problem has long been known in interactive, non-interactive of multi agent research. We trying hard to find its own solution from non-interactive agent method on not in the same original environment(circular environment). We used ACS applied Direction vector to learning and decide on a direction. Exchange of information between agents have been previously presented (an interactive agent) out of the way information exchange ratio (non-interactive agents), applied the new method. Can also solve the problem was to find a solution. This is quite distinct from the other existing multi agent studies, that doesn't apply interactive agents but independent agent to find a solution.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.4
• /
• pp.1-9
• /
• 2017

We propose an efficient method to determine the position of blueprint by using a vector field with optimized MLS(Moving Least Squares). Typically, a professional architectural design office takes a long time to work as well as a high processing cost because the designer manually determines the location to place the buildings in a specific area. In order to solve this inefficient problem, we propose a method to automatically determine the location of the blueprint based on the optimized MLS method. In the proposed framework, the designer selects the desired region in the actual city data and calculates the flow of the vector based on the region. Use the optimized MLS method to extract the vector field and determine the amount of rotation of the drawing based on this field. The location of the blueprint determined by the proposed method is very similar to the flow seen when the actual building is located. As a result, the efficiency of the overall architectural design process is further improved by reducing the designer's inefficient workforce.

• Genomics & Informatics
• /
• v.4 no.2
• /
• pp.71-76
• /
• 2006

We have investigated biological responses to radiofrequency (RF) radiation in in vitro and in vivo models. By measuring the levels of heat shock proteins as well as the activation of mitogen activated protein kinases (MAPKs), we could not detect any differences upon RF exposure. In this study, we used more sensitive method to find the molecular responses to RF radiation. Jurkat, human T-Iymphocyte cells were exposed to 1763 MHz RF radiation at an average specific absorption rate (SAR) of 10 W/kg for one hour and harvested immediately (R0) or after five hours (R5). From the profiles of 30,000 genes, we selected 68 differentially expressed genes among sham (S), R0 and R5 groups using a random-variance F-test. Especially 45 annotated genes were related to metabolism, apoptosis or transcription regulation. Based on support vector machine (SVM) algorithm, we designed prediction model using 68 genes to discriminate three groups. Our prediction model could predict the target class of 19 among 20 examples exactly (95% accuracy). From these data, we could select the 68 biomarkers to predict the RF radiation exposure with high accuracy, which might need to be validated in in vivo models.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.77-85
• /
• 2006

There is the spatial correlation of the video sequence between the motion vector of current blocks. In this paper, we propose the enhanced fast block matching algorithm using the spatial correlation of the video sequence and the center-biased properly of motion vectors. The proposed algorithm determines an exact motion vector using the predicted motion vector from the adjacent macro blocks of the current frame and the Cross-Hexagonal search pattern. From the of experimental results, we can see that our proposed algorithm outperforms both the prediction search algorithm (NNS) and the fast block matching algorithm (CHS) in terms of the search speed and the coded video's quality. Using our algorithm, we can improve the search speed by up to $0.1{\sim}38%$ and also diminish the PSNR (Peak Signal Noise Ratio) by at nst $0.05{\sim}2.5dB$, thereby improving the video qualify.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.67-80
• /
• 2021

The node embedding technique for learning graph representation plays an important role in obtaining good quality results in graph mining. Until now, representative node embedding techniques have been studied for homogeneous graphs, and thus it is difficult to learn knowledge graphs with unique meanings for each edge. To resolve this problem, the conventional Triple2Vec technique builds an embedding model by learning a triple graph having a node pair and an edge of the knowledge graph as one node. However, the Triple2 Vec embedding model has limitations in improving performance because it calculates the relationship between triple nodes as a simple measure. Therefore, this paper proposes a feature extraction technique based on a graph convolutional neural network to improve the Triple2Vec embedding model. The proposed method extracts the neighborliness vector of the triple graph and learns the relationship between neighboring nodes for each node in the triple graph. We proves that the embedding model applying the proposed method is superior to the existing Triple2Vec model through category classification experiments using DBLP, DBpedia, and IMDB datasets.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.335-340
• /
• 2018

Commercialized speech recognition systems that have an accuracy recognition rates are used a learning model from a type of speaker dependent isolated data. However, it has a problem that shows a decrease in the speech recognition performance according to the quantity of data in noise environments. In this paper, we proposed the vector quantization based speech recognition performance improvement using maximum log likelihood in Gaussian distribution. The proposed method is the best learning model configuration method for increasing the accuracy of speech recognition for similar speech using the vector quantization and Maximum Log Likelihood with speech characteristic extraction method. It is used a method of extracting a speech feature based on the hidden markov model. It can improve the accuracy of inaccurate speech model for speech models been produced at the existing system with the use of the proposed system may constitute a robust model for speech recognition. The proposed method shows the improved recognition accuracy in a speech recognition system.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.5
• /
• pp.15-24
• /
• 2020

We present a supervised learning method that estimates the simulation parameters required to simulate the fabric from the static drape shape of a given fabric sample. The static drape shape was inspired by Cusick's drape, which is used in the apparel industry to classify fabrics according to their mechanical properties. The input vector of the training model consists of the feature vector extracted from the static drape and the density value of a fabric specimen. The output vector consists of six simulation parameters that have a significant influence on deriving the corresponding drape result. To generate a plausible and unbiased training data set, we first collect simulation parameters for 400 knit fabrics and generate a Gaussian Mixed Model (GMM) generation model from them. Next, a large number of simulation parameters are randomly sampled from the GMM model, and cloth simulation is performed for each sampled simulation parameter to create a virtual static drape. The generated training data is fitted with a log-linear regression model. To evaluate our method, we check the accuracy of the training results with a test data set and compare the visual similarity of the simulated drapes.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.47-55
• /
• 2023

This paper presents a method for predicting the threat index of combat systems using Gradient Boosting Regressors and Support Vector Regressors among machine learning models. Currently, combat systems are software that emphasizes safety and reliability, so the application of AI technology that is not guaranteed to be reliable is restricted by policy, and as a result, the electrified domestic combat systems are not equipped with AI technology. However, in order to respond to the policy direction of the Ministry of National Defense, which aims to electrify AI, we conducted a study to secure the basic technology required for the application of machine learning in combat systems. After collecting the data required for threat index evaluation, the study determined the prediction accuracy of the trained model by processing and refining the data, selecting the machine learning model, and selecting the optimal hyper-parameters. As a result, the model score for the test data was over 99 points, confirming the applicability of machine learning models to combat systems.