• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.834-851
• /
• 2017

The amount of sources of information available on the web using ontologies as support continues to increase and is often heterogeneous and distributed. Ontology alignment is the solution to ensure semantic interoperability. In this paper, we describe a new ontology alignment approach, which consists of combining structure-based and reasoning-based approaches in order to discover new semantic correspondences between entities of different ontologies. We used the biblio test of the benchmark series and anatomy series of the Ontology Alignment Evaluation Initiative (OAEI) 2012 evaluation campaign to evaluate the performance of our approach. We compared our approach successively with LogMap and YAM++ systems. We also analyzed the contribution of our method compared to structural and semantic methods. The results obtained show that our performance provides good performance. Indeed, these results are better than those of the LogMap system in terms of precision, recall, and F-measure. Our approach has also been proven to be more relevant than YAM++ for certain types of ontologies and significantly improves the structure-based and reasoningbased methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.186-191
• /
• 2015

Hand gesture is the most common tool used to interact with and control various electronic devices. In this paper, we propose a novel hand gesture recognition method using fuzzy logic based classification with a new type of sensor array. In some cases, feature patterns of hand gesture signals cannot be uniquely distinguished and recognized when people perform the same gesture in different ways. Moreover, differences in the hand shape and skeletal articulation of the arm influence to the process. Manifold features were extracted, and efficient features, which make gestures distinguishable, were selected. However, there exist similar feature patterns across different hand gestures, and fuzzy logic is applied to classify them. Fuzzy rules are defined based on the many feature patterns of the input signal. An adaptive neural fuzzy inference system was used to generate fuzzy rules automatically for classifying hand gestures using low number of feature patterns as input. In addition, emotion expression was conducted after the hand gesture recognition for resultant human-robot interaction. Our proposed method was tested with many hand gesture datasets and validated with different evaluation metrics. Experimental results show that our method detects more hand gestures as compared to the other existing methods with robust hand gesture recognition and corresponding emotion expressions, in real time.

• 제어로봇시스템학회논문지
• /
• 제11권2호
• /
• pp.127-136
• /
• 2005

In this paper, a new architecture and comprehensive design methodology of genetically optimized Rule-based Fuzzy Polynomial Neural Networks(gRFPNN) are introduced and a series of numeric experiments are carried out. The architecture of the resulting gRFPNN results from asynergistic usage of the hybrid system generated by combining rule-based Fuzzy Neural Networks(FNN) with polynomial neural networks (PNN). FNN contributes to the formation of the premise part of the overall rule-based structure of the gRFPNN. The consequence part of the gRFPNN is designed using PNNs. At the premise part of the gRFPNN, FNN exploits fuzzy set based approach designed by using space partitioning in terms of individual variables and comes in two fuzzy inference forms: simplified and linear. As the consequence part of the gRFPNN, the development of the genetically optimized PNN dwells on two general optimization mechanism: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gRFPNN, the models are experimented with the use of several representative numerical examples. A comparative analysis shows that the proposed gRFPNN are models with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 한국ITS학회 논문지
• /
• 제11권4호
• /
• pp.131-143
• /
• 2012

본 논문은 지역적 특징을 빠르게 추출할 수 있는 SURF(Speed Up Robust Features) 알고리즘을 이용해 안경과 조명 등 자동차 환경에 적응적인 새로운 눈 상태 검출방법을 제안하였다. 또한, 베이지안 추론을 이용하여 각 운전자에 대해 세 가지 고유의 눈 상태 템플릿을 실시간적으로 생성함으로써 눈 상태 검출 성능을 향상시켰다. 주 야간, 안경 착용 시, 미착용 시 등 여러 환경에 대한 성능 실험 결과 주 야간 환경에서 각각 평균 98.1%와 96.0%의 검출률을, 공개된 ZJU데이터베이스에 대한 실험 결과 평균 97.8%의 검출률을 보임으로써 제안된 방법의 우수성을 보였다.

• 한국정보통신학회논문지
• /
• 제12권8호
• /
• pp.1495-1504
• /
• 2008

2007년부터 흰색 바탕의 자동차 번호판이 등록되어 사용되고 있다. 본 논문은 그레이 레이블링 기법과 퍼지 추론 방법을 이용하여 새롭게 사용되고 있는 흰색 번호판을 추출하기 위 한 방법을 제안한다. 먼저 비재귀 Flood-filling 알고리즘을 개선한 그레이 레이블링(labeling) 기법으로 번호판 후보 영역을 추출한다. 추출된 레이블에 대한 적합도를 퍼지 추론 시스템에 의해 산출한 후 후보 레이블 중에서 가장 적합도가 높은 레이블 영역을 최종 번호판 영역으로 추출한다. 실내외 주차장 및 거리에서 핸드폰 및 디지털 카메라로 획득한 다양한 자동차 번호판 영상을 대상으로 실험한 결과 94%의 추출 성공율을 나타내었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.606-609
• /
• 2015

본 연구에서는 support vector regression (SVR) 및 매개변수 최적화 알고리즘을 이용한 하천수위 예측모델을 구축하고 이를 실제 유역에 적용하여 모델 효율성을 평가하였다. 여기서, SVR은 하천수위를 예측하기 위한 예측모델로서 채택되었으며, 커널함수 (Kernel function)로서는 radial basis function (RBF)을 선택하였다. 최적화 알고리즘은 SVR의 최적 매개변수 (C?, cost parameter or regularization parameter; ${\gamma}$, RBF parameter; ${\epsilon}$, insensitive loss function parameter)를 탐색하기 위하여 적용되었다. 매개변수 최적화 알고리즘으로는 grid search (GS), genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC) 알고리즘을 채택하였으며, 비교분석을 통해 최적화 알고리즘의 적용성을 평가하였다. 또한 SVR과 최적화 알고리즘을 결합한 모델 (SVR-GS, SVR-GA, SVR-PSO, SVR-ABC)은 기존에 수자원 분야에서 널리 적용되어온 신경망(Artificial neural network, ANN) 및 뉴로퍼지 (Adaptive neuro-fuzzy inference system, ANFIS) 모델과 비교하였다. 그 결과, 모델 효율성 측면에서 SVR-GS, SVR-GA, SVR-PSO 및 SVR-ABC는 ANN보다 우수한 결과를 나타내었으며, ANFIS와는 비슷한 결과를 나타내었다. 또한 SVR-GA, SVR-PSO 및 SVR-ABC는 SVR-GS보다 상대적으로 우수한 결과를 나타내었으며, 모델 효율성 측면에서 SVR-PSO 및 SVR-ABC는 가장 우수한 모델 성능을 나타내었다. 따라서 본 연구에서 적용한 매개변수 최적화 알고리즘은 SVR의 매개변수를 최적화하는데 효과적임을 확인할 수 있었다. SVR과 최적화 알고리즘을 이용한 하천수위 예측모델은 기존의 ANN 및 ANFIS 모델과 더불어 하천수위 예측을 위한 효과적인 도구로 사용될 수 있을 것으로 판단된다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.147-158
• /
• 2021

Versatile Video Coding (VVC) is the latest video coding standard developed by Joint Video Exploration Team (JVET). In VVC, the quadtree plus multi-type tree (QT+MTT) structure of coding unit (CU) partition is adopted, and its computational complexity is considerably high due to the brute-force search for recursive rate-distortion (RD) optimization. In this paper, we aim to reduce the time complexity of inter-picture prediction mode since the inter prediction accounts for a large portion of the total encoding time. The problem can be defined as classifying the split mode of each CU. To classify the split mode effectively, a novel convolutional neural network (CNN) called multi-level tree (MLT-CNN) architecture is introduced. For boosting classification performance, we utilize additional information including inter-picture information while training the CNN. The overall algorithm including the MLT-CNN inference process is implemented on VVC Test Model (VTM) 11.0. The CUs of size 128×128 can be the inputs of the CNN. The sequences are encoded at the random access (RA) configuration with five QP values {22, 27, 32, 37, 42}. The experimental results show that the proposed algorithm can reduce the computational complexity by 11.53% on average, and 26.14% for the maximum with an average 1.01% of the increase in Bjøntegaard delta bit rate (BDBR). Especially, the proposed method shows higher performance on the sequences of the A and B classes, reducing 9.81%~26.14% of encoding time with 0.95%~3.28% of the BDBR increase.

• Communications for Statistical Applications and Methods
• /
• 제26권1호
• /
• pp.1-9
• /
• 2019

Various probabilistic methods have been proposed for using interpopulation allele frequency differences to infer the ethnic group of a DNA specimen. The selection of the statistical method is critical because the accuracy of the statistical classification results vary. For the ancestry classification, we proposed a new ancestry evaluation method that estimate the combined ethnicity index as well as compared its performance with various classical classification methods using two real data sets. We selected 13 SNPs that are useful for the inference of ethnic origin. These single nucleotide polymorphisms (SNPs) were analyzed by restriction fragment mass polymorphism assay and followed by classification among ethnic groups. We genotyped 400 individuals from four ethnic groups (100 African-American, 100 Caucasian, 100 Korean, and 100 Mexican-American) for 13 SNPs and allele frequencies that differed among the four ethnic groups. Additionally, we applied our new method to HapMap SNP genotypes for 1,011 samples from 4 populations (African, European, East Asian, and Central-South Asian). Our proposed method yielded the highest accuracy among statistical classification methods. Our ethnic group classification system based on the analysis of ancestry informative SNP markers can provide a useful statistical tool to identify ethnic groups.

• 한국전자통신학회논문지
• /
• 제14권4호
• /
• pp.775-780
• /
• 2019

미래를 예측하는 기법은 통계에 기반을 둔 것과 딥러닝에 기반을 둔 기술로 분류할 수 있다. 그중 통계에 기반을 둔 것이 간단하고 정확성이 높아서 많이 사용된다. 하지만 실무자들은 많은 분석기법의 올바른 사용에 어려움이 많다. 이번 연구에서는 마케팅에 관련된 데이터에 다항로지스틱회귀, 의사결정나무, 랜덤포레스트, 서포트벡터머신, 베이지안 추론을 적용하여 예측의 정확성을 비교하였다. 동일한 마케팅 데이터를 대상으로 하였고, R을 활용하여 분석을 진행하였다. 마케팅 분야의 데이터 특성을 반영한 다양한 기법의 예측 결과가 실무자들에게 좋은 참고가 될 것으로 생각한다.