• Journal of Software Assessment and Valuation
• /
• v.15 no.1
• /
• pp.43-53
• /
• 2019

BigCloneBench has recently been used for performance evaluation of code clone detection tool using machine learning. However, since BigCloneBench is not a benchmark that is optimized for machine learning, incorrect learning data can be created. In this paper, we have shown through experiments using machine learning that the set of Type-4 clone methods provided by BigCloneBench can additionally be found. Experimental results using Tree-Based Convolutional Neural Network show that our proposed method is effective in improving BigCloneBench's dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.39-46
• /
• 2020

Recently, for designing virtual characters in the battle game field effectively, some methods are very needed to predicate the win rates of the battle of them efficiently. In this paper, we propose a method to solve this problem by combining simulation and machine learning. Firstly, a simulation is used to analyze the win rates of the battle of virtual characters in the battle game. In addition, we apply a regression model based machine learning scheme to predict win rates of the battle of virtual characters according to their abilities. Our experimental results using suggested method show that it is almost no difference between the win rates of the simulation and the prediction results using the machine learning scheme. And also, we can obtain good performance in the experiment using only simple regression based machine learning model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.117-126
• /
• 2013

Recently, as Social Network Services(SNS), such as Twitter, Facebook, are becoming more popular, much research has been doing on opinion mining. However, current related researches are mostly focused on sentiment classification or feature selection, but there were few studies about opinion document retrieval. In this paper, we propose a new retrieval method of short opinion documents. Proposed method utilizes previous sentiment classification methodology, and applies several features of documents for evaluating the quality of the opinion documents. For generating the retrieval model, we adopt Learning-to-rank technique and integrate sentiment classification model to Learning-to-rank. Experimental results show that proposed method can be applied successfully in opinion search.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

• Journal of The Korean Association For Science Education
• /
• v.40 no.3
• /
• pp.321-336
• /
• 2020

We explore automated scoring models of scientific argumentation. We consider how a new analytical approach using a machine learning technique may enhance the understanding of spoken argumentation in the classroom. We sampled 2,605 utterances that occurred during a high school student's science class on molecular structure and classified the utterances into five argumentative elements. Next, we performed Text Preprocessing for the classified utterances. As machine learning techniques, we applied support vector machines, decision tree, random forest, and artificial neural network. For enhancing the identification of rebuttal elements, we used a heuristic feature-engineering method that applies experts' classification of morphemes of scientific argumentation.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.199-203
• /
• 2018

음식과 맛집에 대한 사용자의 정보검색 니즈가 나날이 증가하면서 서비스 제공자가 정보 제공의 대상이 되는 맛집 상호명을 파악하는 것은 중요한 이슈다. 그러나 업종의 특성상 점포가 새로 생겨나는 주기는 매우 짧은 반면, 신규 점포의 서비스 등록 시점에는 시간적 차이가 존재하는 문제가 있다. 본 논문에서는 신규 상호명을 능동적으로 파악하기 위해 위치기반 서비스 로그에서 맛집 상호명을 추출하는 문자 기반의 딥러닝 모델 및 방법론을 제시한다. 자체 구축한 학습 데이터셋으로 실험한 결과, 제안하는 모델이 기존 기계학습 모델보다 높은 정확도로 상호명을 분류할 수 있음을 확인하였다. 또한, 사전 학습된 모델을 검색로그에 적용하여 신규 상호명 후보를 추출함으로써 향후 상호명 DB를 능동적으로 업데이트 할 수 있는 가능성을 타진하였다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.517-520
• /
• 2022

지능형 대화 시스템은 줄곧 서비스의 목표와 무관한 사용자 입력을 전달받아, 그 처리 성능을 의심받는다. 특히 종단간 대화 이해 생성 모델이나, 기계학습 기반 대화 이해 모델은 학습 시간대에 한정된 범위의 도메인 입력에만 노출됨으로, 사용자 발화를 자신이 처리 가능한 도메인으로 과신하는 경향이 있다. 본 연구에서는 대화 생성 모델이 처리할 수 없는 입력과 신뢰도가 낮은 생성 결과를 배제하기 위해 불확실성 정량화 기법을 대화 의도 분류 모델에 적용한다. 여러 번의 추론 샘플링이 필요 없는 실용적인 예측 신뢰도 획득 방법과 함께, 평가 시간대와 또다른 도메인으로 구성된 분포 외 입력 데이터를 학습에 노출시키는 것이 분포 외 입력을 구분하는데 도움이 되는지를 실험으로 확인한다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.1
• /
• pp.11-18
• /
• 2022

In order to improve the accuracy of particle tracking prediction techniques near the Korean Strait, this study compared and analyzed a particle tracking model based on a seawater flow numerical model and a machine learning based on a particle tracking model using field observation data. The data used in the study were the surface drifter buoy movement trajectory data observed in the Korea Strait, prediction data by machine learning (linear regression, decision tree) using the tide and wind data from three observation stations (Gageo Island, Geoje Island, Gyoboncho), and prediciton data by numerical models (ROMS, MOHID). The above three data were compared through three error evaluation methods (Correlation Coefficient (CC), Root Mean Square Errors (RMSE), and Normalized Cumulative Lagrangian Separation (NCLS)). As a final result, the decision tree model had the best prediction accuracy in CC and RMSE, and the MOHID model had the best prediction results in NCLS.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.29-35
• /
• 2020

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.