• International journal of advanced smart convergence
• /
• 제8권3호
• /
• pp.131-137
• /
• 2019

This study proposes a method of learning and recognizing the characteristics that are the classification criteria of Hangul using Mask R-CNN, one of the deep learning techniques, to recognize and classify atypical Hangul characters. The atypical characters on the Hangul signboard have a lot of deformed and colorful shapes beyond the general characters. Therefore, in order to recognize the Hangul signboard character, it is necessary to learn a separate atypical Hangul character rather than the existing formulaic one. We selected the Hangul character '닭' as sample data and constructed 5,383 Hangul image data sets and used them for learning and verifying the deep learning model. The accuracy of the results of analyzing the performance of the learning model using the test set constructed to verify the reliability of the learning model was about 92.65% (the area detection rate). Therefore we confirmed that the proposed method is very useful for Hangul signboard character recognition, and we plan to extend it to various Hangul data.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.313-316
• /
• 2004

Model selection is the process that sets up the regularization parameter in the support vector machine or regularization network by using the external methods such as general cross validation or L-curve criterion. This paper suggests that the regularization parameter can be obtained simultaneously within the learning process of neural networks without resort to separate selection methods. In this paper, extended kernel method is introduced. The relationship between regularization parameter and the bias term in the extended kernel is established. Experimental results show the effectiveness of the new model selection method.

• 천문학회보
• /
• 제43권1호
• /
• pp.40.3-40.3
• /
• 2018

We present results from our two experiments of using machine learning algorithms in processing and analyzing the KMTNet imaging data. First, density estimation and clustering methods find meaningful structures in the metric space of imaging quality measurements described by photometric quantities. Second, we also develop a method to separate out light curves of reliable microlensing event candidates from spurious events, estimating reliability scores of the candidates.

• Journal of applied mathematics & informatics
• /
• 제37권3_4호
• /
• pp.271-279
• /
• 2019

We investigate how a feedforward neural network works to separate a geometric region from its complement. Our investigations are restricted to regions in ${\mathbb{R}}$ or ${\mathbb{R}}^2$ including an interval, a triangular region, a disk and the union of two disjoint disks. We also examine what happens at each layer of the network.

• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.239-246
• /
• 2003

Statisticians, or data miners, are often requested to assess the importances of input variables in the given supervised learning model. For the purpose, one may rely on separate ad hoc measures depending on modeling types, such as linear regressions, the neural networks or trees. Consequently, the conceptual consistency in input variable importance measures is lacking, so that the measures cannot be directly used in comparing different types of models, which is often done in data mining processes, In this short communication, we propose a unified approach to the importance measurement of input variables. Our method uses sensitivity analysis which begins by perturbing the values of input variables and monitors the output change. Research scope is limited to the models for continuous output, although it is not difficult to extend the method to supervised learning models for categorical outcomes.

• 디지털산업정보학회논문지
• /
• 제16권4호
• /
• pp.19-28
• /
• 2020

Vehicle license plate recognition system is not generalized in Malaysia due to the loose character layout rule and the varying number of characters as well as the mixed capital English characters and italic English words. Because the italic English word is hard to segmentation, a separate method is required to recognize in Malaysian license plate. In this paper, we propose a mixed character level and word level English license plate recognition algorithm using deep learning neural networks. The difference of Gaussian method is used to segment character and word by generating a black and white image with emphasized character strokes and separated touching characters. The proposed deep learning neural networks are implemented on the LPR system at the gate of a building in Kuala-Lumpur for the collection of database and the evaluation of algorithm performance. The evaluation results show that the proposed Malaysian English LPR can be used in commercial market with 98.01% accuracy.

• 한국추진공학회지
• /
• 제11권1호
• /
• pp.43-50
• /
• 2007

본 논문에서는 고도 변화만을 고려한 탈설계 영역에서 항공기용 터보 축 엔진의 결함 진단을 위해 지지 벡터 장치(SVM)과 인공신경망(ANN)을 Hybrid로 사용한 분할 학습 알고리즘을 사용하였다. 지상 정지 상태에서보다 학습 데이터와 테스트 데이터 수가 크게 증가하지만, 분할 학습 알고리즘을 이용한 가스터빈 엔진의 결함 진단이 고도 변화를 고려한 탈설계 영역에서도 높은 결함 예측 정확성을 가짐을 확인하였다.

• 한국인터넷방송통신학회논문지
• /
• 제13권5호
• /
• pp.27-35
• /
• 2013

최근 들어 SNS가 대중화됨에 따라, 이들로 부터 오피니언을 분석하여 특정 이슈에 대한 여론을 파악하려는 다양한 연구가 진행되고 있다. SNS 환경에서 오피니언 분석을 위해서는 우선 게시글 중에서 오피니언 문서와 그렇지 않은 문서(객관적 문서)를 분리해야한다. 본 논문에서는 트위터 문서로 부터 오피니언 문서만을 추출하는 새로운 방법을 제안한다. 트위터 환경에서 오피니언 문서에 대한 분류나 검색의 어려운 점은 충분한 학습 자료가 존재하지 않다는데 있다 이를 위해 제안된 방법에서는 감성 분류를 위해 트위터와 유사한 외부의 정보를 이용하여 기계학습기반 분류 모델을 생성하고, 이를 응용하여 트위터에서의 오피니언 문서 추출에 적용하였다. 또한 실험을 통하여 제안된 방법의 적용 가능성을 평가하였다.

• 한국추진공학회지
• /
• 제10권2호
• /
• pp.102-109
• /
• 2006

본 논문에서 항공기용 터보 축 엔진의 결함 진단 알고리즘을 개발하기 위해 Support Vector Machine(SVM)과 인공신경망(ANN)을 이용하였다. 신경망을 이용한 시스템은 비선형성이 과도한 데이터를 학습할 때 지역 최소점(Local Minima)에 빠져 분류 정확률이 낮아질 수 있다. 이러한 위험성을 보안하기 위해 SVM에 의한 ANN의 분할 학습 알고리즘(SLA)을 제안하였다. 이것은 SVM을 이용하여 결함 위치를 판별 한 후 신경망이 선택적으로 학습을 하는 방법으로 학습 데이터의 비선형성을 줄여 분류 정확률을 높이기 때문에 신경망을 단독으로 사용할 때보다 개선된 성능을 보여주었다.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1139-1146
• /
• 2020

Recently, as e-learning technology advances, interaction and data exchange between lecturers and learners have become very important. In addition, accuracy of data delivery and efficiency of system implementation should be ensured. Considering these aspects, SignalR is the most suitable communication method for constructing an audience response system in e-learning. Existing audience response systems require separate wireless devices and have problems with system compatibility. SignalR, on the other hand, is capable of operating in all environments including PC programs, web, Android, and iOS, and has an advantage of being easy to develop applications. As such, SignalR is widely used in chatting functions for small scale, real-time communication system, and it has never been used to implement an audience response system. Thus, for the first time in this paper, an audience response system using SignalR was proposed and an experiment was conducted on whether it was applicable at the e-learning education field. Therefore, from the results fo an experiment, a variety of e-learning environments can be built through the audience response system using SignalR proposed in this paper.