• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.294-297
• /
• 2017

SNS와 스마트기기의 발전으로 온라인을 통한 뉴스 배포가 용이해지면서 악의적으로 조작된 뉴스가 급속도로 생성되어 확산되고 있다. 뉴스 조작은 다양한 형태로 이루어지는데, 이 중에서 정상적인 기사 내에 광고나 낚시성 내용을 포함시켜 독자가 의도하지 않은 정보에 노출되게 하는 형태는 독자가 해당 내용을 진짜 뉴스로 받아들이기 쉽다. 본 논문에서는 뉴스 기사 내에 포함된 문단 중에서 부적합한 문단이 포함 되었는지를 판정하기 위한 방법을 제안한다. 제안하는 방식에서는 자연어 처리에 유용한 Convolutional Neural Network(CNN)모델 중 Word2Vec과 tf-idf 알고리즘, 로지스틱 회귀를 함께 이용하여 뉴스 부적합 문단을 검출한다. 본 시스템에서는 로지스틱 회귀를 이용하여 문단의 카테고리를 분류하여 본문의 카테고리 분포도를 계산하고 Word2Vec을 이용하여 문단간의 유사도를 계산한 결과에 가중치를 부여하여 부적합 문단을 검출한다.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.566-574
• /
• 2021

The arc is one of factors causing electrical fires. Over past decades, various researches have been carried out to detect arc occurrences. Even though frequency analysis, wavelet and statistical features have been used, arc detection performance is degraded due to diverse arc waveforms. On the contray, Deep neural network (DNN) direcly utilizes raw data without feature extraction, based on end-to-end learning. However, a disadvantage of the DNN is processing complexity, posing the difficulty of being migrated into a termnial device. To solve this, this paper proposes an arc detection method using a logistic regression that is one of simple machine learning methods.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.19-27
• /
• 2017

This research was aimed to analyze landslide susceptibility and compare the prediction accuracy using ensemble frequency ratio (FR) and logistic regression at the Inje area, Korea. The landslide locations were identified with the before and after aerial photographs of landslide occurrence that were randomly selected for training (70%) and validation (30%). The total twelve landslide-related factors were elevation, slope, aspect, distance to drainage, topographic wetness index, stream power index, soil texture, soil sickness, timber age, timber diameter, timber density, and timber type. The spatial relationship between landslide occurrence and landslide-related factors was analyzed using FR and ensemble model. The produced LSI maps were validated and compared using relative operating characteristics (ROC) curve. The prediction accuracy of produced ensemble LSI map was about 2% higher than FR LSI map. The LSI map produced in this research could be used to establish land use planning and mitigate the damages caused by disaster.

• 한국IT서비스학회:학술대회논문집
• /
• 2005.05a
• /
• pp.372-380
• /
• 2005

소프트웨어 개발노력 추정에 대한 연구는 소프트웨어가 복잡해지고 범위가 크게 증가함에 따라서 그 중은 지속적으로 부각되고 있다. 관련 프로젝트를 발주하는 업체나, 이를 수주하고 개발을 진행하는 업체에게 원가를 고려하는 측면에서 매우 중요한 부분을 차지하고 있다. 이러한 개발노력 추정을 위하여 다양한 접근 방식들이 고려되어지고 있는데, 그중에서 많이 활용되어지고 있는 방식은 소프트웨어 규모에 기반을 둔 LOC(Line Of Code) 기반 COCOMO (Constructive Cost Model) 모델이나 기능점수(Function Point)를 기반으로 한 회귀분석 모델, 인공지능(Artificial Intelligence)을 활용한 신경망(Neural Network) 모델, 사례분석기법 (CBR, Case Based Reasoning) 등이 있다. 이중에서 최근에 기능점수를 활용한 개발노력 추정에 관한 연구들이 활발히 진행되고 있으나 개발노력 추정에는 소프트웨어 규모의 척도인 기능점수 뿐만 아니라, 개발환경을 구성하는 여러 가지 측면에 대한 고려가 추가되어져야 한다. 이에 본 논문은 최신의 소프트웨어 개발 사례들에 대하여 기능점수 및 추가적인 개발환경 요소들을 면밀히 분석하고, 분석한 내용에 대해서 전문가들의 설문을 통한 빈도분석 및 로지스틱 회귀분석, 데이터마이닝 기법인 신경망 분석 등을 활용하여 개발노력 추정 모델을 구축함으로써, 소프트웨어 개발의 다양한 측면의 중요성을 강조하고, 정확한 추정의 방안을 제시 하고자 노력 하였다.

• Journal of The Geomorphological Association of Korea
• /
• v.26 no.2
• /
• pp.1-14
• /
• 2019

This study analyzed the relativity between block stream and talus distributions by employing a likelihood ratio approach. Possible distribution sites for each debris slope landform were extracted by applying a spatial integration model, in which we combined fuzzy set model, Bayesian predictive model, and logistic regression model. Moreover, to verify model performance, a success rate curve was prepared by cross-validation. The results showed that elevation, slope, curvature, topographic wetness index, geology, soil drainage, and soil depth were closely related to the debris slope landform sites. In addition, all spatial integration models displayed an accuracy of over 90%. The accuracy of the distribution potential area map of the block stream was highest in the logistic regression model (93.79%). Eventually, the accuracy of the distribution potential area map of the talus was also highest in the logistic regression model (97.02%). We expect that the present results will provide essential data and propose methodologies to improve the performance of efficient and systematic micro-landform studies. Moreover, our research will potentially help to enhance field research and topographic resource management.

• Fire Science and Engineering
• /
• v.33 no.6
• /
• pp.72-79
• /
• 2019

Through this study, we developed a model for predicting chemical accidents lead to casualties. The model was derived from the logistic regression analysis model and applied to the variables affecting the accident. The accident data used in the model was analyzed by studying the statistics of past chemical accidents, and applying independent variables that were statistically significant through data analysis, such as the type of accident, cause, place of occurrence, status of casualties, and type of chemical accident that caused the casualties. A significance of p < 0.05 was applied. The model developed in this study is meaningful for the prevention of casualties caused by chemical accidents and the establishment of safety systems in the workplace. The analysis using the model found that the most influential factor in the occurrence of casualty in accidents was chemical explosions. Therefore, there is an urgent need to prepare countermeasures to prevent chemical accidents, specifically explosions, from occurring in the workplace.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.827-833
• /
• 2020

In this paper, to reduce the unpaid rate of local governments, the internal data elements affecting the arrears in Water-INFOS are searched through interviews with meter readers in certain local governments. Candidate data affecting arrears from national statistical data were derived. The influence of the independent variable on the dependent variable was sampled by examining the disorder of the dependent variable in the data set called information gain. We also evaluated the higher prediction rates of decision tree and logistic regression using n-fold cross-validation. The results confirmed that the decision tree can find more accurate customer payment patterns than logistic regression. In the process of developing an analysis algorithm model using machine learning, the optimal values of two environmental variables, the minimum number of data and the maximum purity, which directly affect the complexity and accuracy of the decision tree, are derived to improve the accuracy of the algorithm.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3D
• /
• pp.381-389
• /
• 2009

Korean government is investing 1.8 billion won on infrastructure and investment on PPP projects constitutes 16.3%. This phenomenon is to promote private investment as well as lessening government burdens of public budgeting. However, the only criterion to be considered is government financial status in selecting public or private highway investment projects. So systematic decision support model is required in choosing public or private highway investment projects. So, this paper suggests a systematic decision support model for deciding public or private highway investment at the early stage of project planning. Furthermore, this paper identifies key decision variables with respect to economic, politic, project management criterions based on the related literatures and feedbacks from experts. This paper analyzed 30 cases of government investment and PPP projects and got the survey result from highway specialists. As a result, this paper presents an interval with respect to economic criteria using mean and standard deviation and a logistic regression equation which can predict the possibility of PPP project. Through this study, decision maker of central or local government can decide public or PPP highway project more systematically and reasonably.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.