• Journal of information and communication convergence engineering
• /
• 제11권4호
• /
• pp.258-267
• /
• 2013

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권5호
• /
• pp.629-635
• /
• 1999

A second-order iterative learning control algorithm with feedback is proposed in this paper, in which a feedback term is added in the learning control scheme for the enhancement of convergence speed and robustness to disturbances or system parameter variations. The convergence proof of the proposed algorithm is givenl, and the sufficient condition for the convergence of the algorithm is provided. And it also includes the discussions about the convergence performance of the algorithm when the initial condition at the beginning of each iteration differs from the previous value of the initial. Simulation results show the validity and efficiency of the proposed algorithm.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.116-125
• /
• 2019

The fire should extinguish as soon as possible because it causes economic loss and loses precious life. In this study, we propose a new atypical fire and smoke detection algorithm using deep learning and color histogram of fire and smoke. First, input frame images obtain from the ONVIF surveillance camera mounted in factory search motion candidate frame by motion detection algorithm and mean square error (MSE). Second deep learning (Faster R-CNN) is used to extract the fire and smoke candidate area of motion frame. Third, we apply a novel algorithm to detect the fire and smoke using color histogram algorithm with local area motion, similarity, and MSE. In this study, we developed a novel fire and smoke detection algorithm applied the local motion and color histogram method. Experimental results show that the surveillance camera with the proposed algorithm showed good fire and smoke detection results with very few false positives.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권1호
• /
• pp.16-30
• /
• 2023

The elderly population is increasing owing to a low fertility rate and an aging population. In addition, life expectancy is increasing, and the advancement of medicine has increased the importance of health to most people. Therefore, government and companies are developing and supporting smart healthcare, which is a health-related product or industry, and providing related services. Moreover, with the development of the Internet, many people are managing their health through online searches. The most convenient way to achieve such management is by consuming nutritional supplements or seasonal foods to prevent a nutrient deficiency. However, before implementing such methods, knowing the nutrient status of the individual is difficult, and even if a test method is developed, the cost of the test will be a burden. To solve this problem, we developed a questionnaire related to nutrient classification twice, based upon which an adaptive algorithm was designed. This algorithm was designed as a machine learning based algorithm for nutrient classification and its accuracy was much better than the other machine learning algorithm.

• Journal of Information Processing Systems
• /
• 제19권2호
• /
• pp.232-239
• /
• 2023

Aiming at the poor compression quality of traditional image compression coding (ICC) algorithm, a multi-description ICC algorithm based on depth learning is put forward in this study. In this study, first an image compression algorithm was designed based on multi-description coding theory. Image compression samples were collected, and the measurement matrix was calculated. Then, it processed the multi-description ICC sample set by using the convolutional self-coding neural system in depth learning. Compressing the wavelet coefficients after coding and synthesizing the multi-description image band sparse matrix obtained the multi-description ICC sequence. Averaging the multi-description image coding data in accordance with the effective single point's position could finally realize the compression coding of multi-description images. According to experimental results, the designed algorithm consumes less time for image compression, and exhibits better image compression quality and better image reconstruction effect.

• 정보교육학회논문지
• /
• 제13권2호
• /
• pp.225-236
• /
• 2009

개정된 정보통신기술 운영지침에 따르면 초등학교에서부터 알고리즘을 학습 내용으로 다루도록 하였으며 이에 따라 초등학교 현장에서도 알고리즘을 쉽고 효과적으로 지도하기 위한 다각적인 교육 방법 연구가 필요해졌다. 이에 본 연구 과정에서는 초등학교 저학년을 대상으로 알고리즘의 중요한 부분으로 인식되는 정렬 알고리즘을 학습 내용으로 선정한 후 활동을 통한 교수-학습 방법과 애니메이션 기반의 교수-학습 방법을 적용해보고 학습 효과를 비교 분석하는데 주안점을 두었다. 두 가지 방법으로 정렬 알고리즘 교수-학습을 적용한 후 별도로 제작한 학업 성취도 평가지와 설문지 분석 결과, 크게 두 가지 결론을 얻을 수 있었다. 첫째, 교수-학습 방법에 따른 학업 성취도에는 별다른 차이가 없었으나 초등학교 저학년 학생들도 정렬 알고리즘을 충분히 학습할 수 있다는 점과 둘째, 활동을 통한 알고리즘 교육이 애니메이션 기반의 정렬 알고리즘 교육에 비해 학생의 이해도, 흥미도 및 만족도 측면에서는 좀 더 효과적이라는 것을 알 수 있었다.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.148-157
• /
• 2021

The effectiveness of recommendation systems depends on the performance of the algorithms with which these systems are designed. The quality of the algorithms themselves depends on the quality of the strategies with which they were designed. These strategies differ from author to author. Thus, designing a good recommendation system means implementing the good strategies. It's in this context that several research works have been proposed on various strategies applied to algorithms to meet the needs of recommendations. Researchers are trying indefinitely to address this objective of seeking the qualities of recommendation algorithms. In this paper, we propose a new algorithm for recommending learning items. Learner performance predictions and collaborative recommendation methods are used as strategies for this algorithm. The proposed performance prediction model is based on convolutional neural networks (CNN). The results of the performance predictions are used by the proposed recommendation algorithm. The results of the predictions obtained show the efficiency of Deep Learning compared to the k-nearest neighbor (k-NN) algorithm. The proposed recommendation algorithm improves the recommendations of the learners' learning items. This algorithm also has the particularity of dissuading learning items in the learner's profile that are deemed inadequate for his or her training.

• Korean Journal of Radiology
• /
• 제22권4호
• /
• pp.612-623
• /
• 2021

Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.441-446
• /
• 2010

군집 로봇시스템에서 개개의 로봇은 스스로 주위의 환경과 자신의 상태를 스스로 판단하여 행동하고, 필요에 따라서는 다른 로봇과 협조를 통하여 임의의 주어진 임무를 수행할 수 있어야 한다. 따라서 각 로봇 개체는 동적으로 변화하는 환경에 잘 적응할 수 있도록 하기 위한 학습 및 진화능력을 갖는 것이 필수적이다. 이를 위하여 본 논문에서는 Q-learning 알고리즘을 기반으로 하는 학습과 Harmony Search 알고리즘을 이용한 진화방법을 제안하였으며, 유전 알고리즘이 아닌 Harmony Search 알고리즘을 제안함으로써 정확도를 높이고자 하였다. 그 결과를 이용하여 군집 로봇의 로봇 개체 환경변화에 따른 임무 수행 능력의 향상을 검증한다.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.85-92
• /
• 2005

본 논문에서는 변형된 돌연변이 연산자를 적용한 대화형 유전자 알고리즘을 사용해서 웹-기반 학습 콘텐츠를 개발하였다. 대화형 유전자 알고리즘은 주로 상호 교환(reciprocal exchange) 돌연변이를 사용한다. 그러나 본 논문에서는 학습자의 학습 효과를 높이기 위해 돌연변이 연산자를 변형하였다. 그리고, 대화형 유전자 알고리즘을 이용한 웹 기반 학습 콘텐츠는 동적인 학습 내용과 실시간 테스트 시스템을 제공한다. 특히 학습자가 자신의 특성과 흥미에 따라 대화형 유전자 알고리즘을 수행하면서 효율적인 학습 환경과 콘텐츠 배열 순서를 선택할 수 있다.