• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.131-138
• /
• 2022

Git's commit message is closely related to the project life cycle, and by this characteristic, it can greatly contribute to cost reduction and improvement of work efficiency by identifying risk factors and project status of project operation activities. Among these related fields, there are many studies that classify commit messages as types of software maintenance, and the maximum accuracy among the studies is 87%. In this paper, the purpose of using a solution using the commit classification model is to design and implement a complex classification model that combines several models to increase the accuracy of the previously published models and increase the reliability of the model. In this paper, a dataset was constructed by extracting automated labeling and source changes and trained using the DistillBERT model. As a result of verification, reliability was secured by obtaining an F1 score of 95%, which is 8% higher than the maximum of 87% reported in previous studies. Using the results of this study, it is expected that the reliability of the model will be increased and it will be possible to apply it to solutions such as software and project management.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.12
• /
• pp.1544-1553
• /
• 1999

Recently, ultrasonic testing techniques have been widely used in the evaluation of the quality of metal. In this experiment, six heat-treated temperature of specimen have been considered : 0, 1200, 1250, 1300, 1350 and 1387$^{\circ}C$. As heat-treated temperature increases, the grain size of stainless steel also increases and then, eventually make it destroy. In this paper, a pattern recognition method is proposed to identify the heat-treated temperature of metals by evidence accumulation based on artificial intelligence with multiple feature parameters; difference absolute mean value(DAMV), variance(VAR), mean frequency(MEANF), auto regressive model coefficient(ARC), linear cepstrum coefficient(LCC) and adaptive cepstrum vector(ACV). The grain signal pattern recognition is carried out through the evidence accumulation procedure using the distances measured with reference parameters. Especially ACV is superior to the other parameters. The results (96% successful pattern classification) are presented to support the feasibility of the suggested approach for ultrasonic grain signal pattern recognition.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.21-26
• /
• 2009

A sensor system capable of automatically recognize activities would allow many potential Ubiquitous applications. This paper presents a new system for recognizing the activities of daily living(ADL) like walking, running, standing, sitting, lying etc. The system based on the state-dependent motion analysis using Tri-Accelerometer and Zigbee tag. Two accelerometers are used for the classification of body and hand activities. Classification of the environment and instrumental activities is performed based on the hand interaction with an object ID using.

• Proceedings of the KIEE Conference
• /
• 2000.07c
• /
• pp.1880-1884
• /
• 2000

The discrete wavelet transform is utilized as preprocessing of Neural Network(NN) to identify aging state of internal partial discharge in transformer. The discrete traveler transform is used to produce wavelet coefficients which are used for Classification. The statistical parameters (maximum of wavelet coefficients, average value, dispersion, skewness, kurtosis) using the wavelet coefficients are input into an back-propagation neural network. The neurons whose weights have obtained through Result of Cross-Validation. The Neural Network learning stops either when the error rate achieves an appropriate minimum or when the learning time overcomes a constant value. The networks, after training, can decide if the test signal is Early Aging State or Last Aging State or normal state.

• Journal of Information Management
• /
• v.37 no.4
• /
• pp.25-47
• /
• 2006

A terminology system capable of providing interpretations and classification information on a multilingual science and technology(S&T) terminology is essential to establish an integrated search environment for multilingual S&T information systems. This paper aims to build a base system to manage an integrated information system for multilingual S&T terminology search. It introduces a method to build a search system for S&T terminologies internally linked through the multilingual semantic network and a search technique on the multiple linked nodes. In order to provide a foundation for further analysis researches, it also attempts to suggest a basic approach to interpret terminology clusters generated with those two search methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• New & Renewable Energy
• /
• v.2 no.2 s.6
• /
• pp.37-43
• /
• 2006

In this paper, the first forecasting system of wind power generation, KIER Forecaster is presented. KIER Forecaster has been constructed based on statistical models and was trained with wind speed data observed at Gosan Weather Station nearby Walryong Site. Due to short period of measurements at Walryong Site for training the model, Gosan wind data were substituted and transplanted to Walryong Site by using Measure-Correlate-Predict(MCP) technique. The results of One to Three-hour advanced forecasting models are consistent with the measurement at Walryong site. In particular, the multiple regression model by classification of wind speed pattern, which has been developed in this work, shows the best performance comparing with neural network and auto-regressive models.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.370-375
• /
• 2007

인터넷과 디지털기기의 발달로 인해 이미지 데이터가 기하급수적으로 증가함에 따라 이미지 데이터의 의미적인 자동분류를 위한 연구가 활발히 진행되고 있다. 기존의 이미지 분류방법은 내용기반 분류와 주석자에 의한 직접 분류 방법이 있다. 하지만 분류 기준이 명확하지 않고, 이미지가 내포하고 있는 정확한 의미 별로 분류가 이루어져 있지 않았다. 이에 본 논문에서는 이미지의 주석간 개념적인 관계를 분석하고 이미지에 의미를 대표할 수 있는 키워드를 추출하여 의미적이고 효율적인 분류 방법을 제안한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.720-725
• /
• 1991

This paper is concerned with the program of the automatic mesh generation for 2-dimensional domain which contains the curved boundaries and holes. This program treats a new vertical - line drawing method. This method starts with 4-subdivisions of problem domain and the classification of the cross points of grid lines and boundaries. And the new node is generated by the vertical line to the line connecting the two intersections of a boundary and two grid lines in general. The boundaries are piecewise-curves composed of lines, circles, arcs, and free curves. The free curves are generated by B-Spline form. Although there were some bad elements for the complex boundary, it was possible to obtain the acceptable elements for the given boundaries. The results of automatic mesh generation can be verified directly by drawing on the computer monitor in executing the program. And it is possible to add the processes - that is, editing, hard copying, etc - using the script file in Auto-CAD.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.581-586
• /
• 1996

This paper presents a feature recognition system for recognizing and extracting feature information needed for machining from design data contained in the CAD database of AutoCAD system. The developed system carries out feature recognition from an orthographic view of a press mold containing not only atomic features such as holes, pockets, and slots, but also compound features. Based on the result of feature recognition, it generates a 3-D modeling of the press mold. Especially, The feature recognition part is designed for detecting feature styles according to feature definition and classification, extracting parameters for various atomic features, and constructing necessary data structures for the recognized features.