• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제41권
• /
• pp.6.1-6.10
• /
• 2019

Background: Osteomyelitis is an intraosseous inflammatory disease characterized by progressive inflammatory osteoclasia and ossification. The use of quantitative analysis to assist interpretation of osteomyelitis is increasingly being considered. The objective of this study was to perform early diagnosis of osteomyelitis on digital panoramic radiographs using basic functions provided by picture archiving and communication system (PACS), a program used to show radiographic images. Methods: This study targeted a total of 95 patients whose symptoms were confirmed as osteomyelitis under clinical, radiologic, pathological diagnosis over 11 years from 2008 to 2017. Five categorized patients were osteoradionecrosis, bisphosphonate-related osteonecrosis of jaw (BRONJ, suppurative and sclerosing type), and bacterial osteomyelitis (suppurative and sclerosing type), and the control group was 117 randomly sampled. The photographic density in a certain area of the digital panoramic radiograph was determined and compared using the "measure area rectangle," one of the basic PACS functions in INFINITT PACS^® (INFINITT Healthcare, Seoul, South Korea). A conditional inference tree, one type of decision making tree, was generated with the program R for statistical analysis with SPSS^®. Results: In the conditional inference tree generated from the obtained data, cases where the difference in average value exceeded 54.49 and the difference in minimum value was less than 54.49 and greater than 12.81 and the difference in minimum value exceeded 39 were considered suspicious of osteomyelitis. From these results, the disease could be correctly classified with a probability of 88.1%. There was no difference in photographic density value of BRONJ and bacterial osteomyelitis; therefore, it was not possible to classify BRONJ and bacterial osteomyelitis by quantitative analysis of panoramic radiographs based on existing research. Conclusions: This study demonstrates that it is feasible to measure photographic density using a basic function in PACS and apply the data to assist in the diagnosis of osteomyelitis.

• 대한토목학회논문집
• /
• 제31권5B호
• /
• pp.405-414
• /
• 2011

본 연구에서는 유역에서 관측되는 강우량과 유출량의 시계열 자료를 바탕으로 최근 시계열 예측 및 시스템 제어 분야에서 성공적으로 적용되고 있는 적응형 네트워크 기반 퍼지추론 시스템(ANFIS)을 갑천 유역에 적용하여 시유출량을 모델링하였다. 입력구조, 소속함수 종류와 개수 등을 다양하게 변화시켜 ANFIS 모형을 학습하고, 평균제곱근오차(RMSE), 평균첨두유량오차(PE) 및 평균첨두시간오차(TE)를 이용하여 ANFIS의 유출해석에 대한 적용성을 평가하였다. 현재시간의 시유출량 Q(t)에 대한 ANFIS의 적용성은 우수한 것으로 평가되었으며, ANFIS 모형은 관측유출량을 적절히 모의하였다. 입력구조가 다른 입력모형을 구성하여 최대 8시간까지 ANFIS의 유출예측 적용성을 평가하였다. 예측시간 증가에 따라서 ANFIS의 유출예측 정확도는 감소하여 예측시간 4시간 이상의 시유출량에 대한 ANFIS의 유출예측 적용성은 제한적이었다. ANFIS는 입력과 출력 자료들만 이용하므로 물리기반 모형에 비교하여 모형구축이 비교적 손쉽기 때문에 홍수 유출모델링에 ANFIS을 유용하게 적용할 수 있을 것으로 판단된다.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.571-579
• /
• 2005

In this paper, we proposed an algorithm for arrhythmia classification, which is associated with the reduction of feature dimensions by linear discriminant analysis (LDA) and a support vector machine (SVM) based classifier. Seventeen original input features were extracted from preprocessed signals by wavelet transform, and attempts were then made to reduce these to 4 features, the linear combination of original features, by LDA. The performance of the SVM classifier with reduced features by LDA showed higher than with that by principal component analysis (PCA) and even with original features. For a cross-validation procedure, this SVM classifier was compared with Multilayer Perceptrons (MLP) and Fuzzy Inference System (FIS) classifiers. When all classifiers used the same reduced features, the overall performance of the SVM classifier was comprehensively superior to all others. Especially, the accuracy of discrimination of normal sinus rhythm (NSR), arterial premature contraction (APC), supraventricular tachycardia (SVT), premature ventricular contraction (PVC), ventricular tachycardia (VT) and ventricular fibrillation (VF) were $99.307\%,\;99.274\%,\;99.854\%,\;98.344\%,\;99.441\%\;and\;99.883\%$, respectively. And, even with smaller learning data, the SVM classifier offered better performance than the MLP classifier.

• 융합신호처리학회논문지
• /
• 제7권3호
• /
• pp.149-154
• /
• 2006

본 논문에서는 온도제어에 있어서 수동식 로온도 제어 전문가의 행위와 유사한 결과를 나타낼 수 있도록 퍼지 제어 룰과 퍼지 변수 및 퍼지 추론 등을 이용하여 밸브의 Gas-to-Air 비율을 조절하는 적응 퍼지 제어기를 설계하였다. 이를 적용한 가스로 자동온도조절 시스템을 개발하고 온도와 소결된 세라믹 시료의 불량률 평가를 통해 그 성능이 우수함을 확인하였다. 적응 퍼지 제어를 이용한 제안 시스템의 온도오차의 경우 학습 전은 약 ${\pm}20^{\circ}C$ 이상 생기던 것이 학습 후에는 ${\pm}2^{\circ}C$ 내외로써 입력 온도 프로파일을 우수하게 추종해 냄을 확인할 수 있었다. 또한 기존 수동로 시스템과 제안된 시스템 간에 세라믹 제품 소결 후의 불량률을 비교하기 위해 시료 A와 B에 대해 각각 두 번에 걸쳐 실험하였다. 불량률을 확 인한 결과 개선효과가 시료 A와 시료 B에 대해 각각 평균 50.5% 와 48.4%로 상당히 좋아짐을 확인하였다.

• 정보처리학회논문지C
• /
• 제14C권7호
• /
• pp.611-620
• /
• 2007

무선 센서 네트워크에서 네트워크 수명을 오래 유지하기 위하여 라우팅 경로를 네트워크 전체에 분산시키는 방법이 연구되고 있다. 본 논문은 퍼지 제어 규칙을 기반으로 라우팅 경로를 선택하는 퍼지 라우팅 프로토콜을 제안한다. 여러 가지 라우팅 경로에 대하여 에너지, 거리, 홉수를 입력으로 하여 퍼지 추론 엔진으로 적합도를 산출하고, 적합도가 높은 한 개의 경로를 최종 라우팅 경로로 선정한다. 한 번 데이터 패킷을 전달한 경로에 속한 노드들의 에너지를 감소시킴으로써 다음에 경로를 선정할 때 동일한 경로를 선택하지 않도록 설계하였으며, 결과적으로 라우팅 경로가 분산되어 센서 네트워크의 유지시간을 길게 만드는 효과가 있다. TinyOS 시뮬레이터에서 실험한 결과, 제안하는 라우팅 프로토콜이 기존의 방법보다 에너지 효율 면에서 우수함을 입증하였고, 또한 센서 네트워크의 유지시간이 길어짐을 확인하였다.

• 대한전기학회논문지:전력기술부문A
• /
• 제53권11호
• /
• pp.596-603
• /
• 2004

This paper proposes an expert system based on the pattern recognition method which can enhance the accuracy and effectiveness of real-time bus reconfiguration strategy for the transfer of faulted load when a main transformer fault occurs in the automated substation. The minimum distance classification method is adopted as the pattern recognition method of expert system. The training pattern set is designed MTr by MTr to minimize the searching time for target load pattern which is similar to the real-time load pattern. But the control pattern set, which is required to determine the corresponding bus reconfiguration strategy to these trained load pattern set is designed as one table by considering the efficiency of knowledge base design because its size is small. The training load pattern generator based on load level and the training load pattern generator based on load profile are designed, which are can reduce the size of each training pattern set from max L/sup (m+f)/ to the size of effective level. Here, L is the number of load level, m and f are the number of main transformers and the number of feeders. The one reduces the number of trained load pattern by setting the sawmiller patterns to a same pattern, the other reduces by considering only load pattern while the given period. And control pattern generator based on exhaustive search method with breadth-limit is designed, which generates the corresponding bus reconfiguration strategy to these trained load pattern set. The inference engine of the expert system and the substation database and knowledge base is implemented in MFC function of Visual C++ Finally, the performance and effectiveness of the proposed expert system is verified by comparing the best-first search solution and pattern recognition solution based on diversity event simulations for typical distribution substation.

• 대한인간공학회지
• /
• 제17권3호
• /
• pp.23-39
• /
• 1998

Several recent aircraft accidents occurred due to goal conflicts between human and machine actors. To facilitate the management of the cockpit activities considering these observations. a computational aid. the Agenda Manager (AM) has been developed for use in simulated cockpit environments. It is important to know pilot intentions performing cockpit operations accurately to improve AM performance. Without accurate knowledge of pilot goals or intentions, the information from AM may lead to the wrong direction to the pilot who is using the information. To provide a reliable flight simulation environment regarding goal conflicts. a pilot goal communication method (GCM) was developed to facilitate accurate recognition of pilot goals. Embedded within AM, the GCM was used to recognize pilot goals and to declare them to the AM. Two approaches to the recognition of pilots goals were considered: (1) The use of an Automatic Speech Recognition (ASR) system to recognize overtly or explicitly declared pilot goals. and (2) inference of covertly or implicitly declared pilot goals via the use of an intent inferencing mechanism. The integrated mode of these two methods could overcome the covert goal mis-understanding by use of overt GCM. And also could it overcome workload concern with overt mode by the use of covert GCM. Through simulated flight environment experimentation with real pilot subjects, the proposed GCM has demonstrated its capability to recognize pilot intentions with a certain degree of accuracy and to handle incorrectly declared goals. and was validated in terms of subjective workload and pilot flight control performance. The GCM communicating pilot goals were implemented within the AM to provide a rich environment for the study of human-machine interactions in the supervisory control of complex dynamic systems.

• 한국지능시스템학회논문지
• /
• 제24권1호
• /
• pp.64-70
• /
• 2014

오늘날 일상생활에서 인간과 함께 생활하는 로봇들은 자연스러운 의사소통 방법이 요구된다. 따라서 기존의 단순한 로봇 제어 방식을 이용하여 제어하는 것 보다 실제 사람과 상호작용 하는 것과 같은 방식의 제어방식이 요구되고 있다. 기존의 연구들은 사람의 행동 자체를 인식하는 것에 초점이 맞추어져 있어서 자연스러운 의사소통을 하기 어렵다. 본 논문에서는 모바일 로봇을 제어하는 방법으로 자연스러운 손동작을 은닉 마르코프 모델(HMM: hidden markov model) 과 퍼지추론을 이용하는 방법을 제안한다. 키넥트 센서를 이용해 색상 데이터와 깊이 데이터를 획득하고 사람의 손을 검색하고 HMM과 Mamdani 퍼지추론을 이용하여 손동작을 인식한다. 인식된 결과를 로봇에게 전달하여 원하는 방향으로 이동시킨다.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• 한국정보통신학회논문지
• /
• 제5권4호
• /
• pp.738-745
• /
• 2001

본 논문에서는 추적시스템이 3차원 공간을 움직이는 이동물체를 추적한다. 오차없이 추적하기 위하여 제어시스템은 인공지능을 가진 퍼지제어기를 사용하였다. 추적시스템은 요(yaw)운동과 롤(roll) 운동을 통해 3차원 공간을 추적한다. 추적시스템으로는 2링크 매니플레이터를 사용하였고, 매니플레이터의 관절각 $\theta_1는 0^{\circ}에서\; 360^{\circ}$까지 회전 할 수 있으며, 관절각 $\theta_a는 0^{\circ}에서\; 180^{\circ}$까지 회전할 수 있다. 퍼지제어기의 퍼지화 방법은 싱클톤방법, 제어 규칙은 25개, 추론법은 간략화된 Mamdani의 추론법, 비퍼지화 방법은 간략화된 무게 중심법을 사용하였다. 시뮬레이션은 퍼지제어기의 성능을 평가하기 위해 같은 조건하에 CTM제어기와 비교하였다. 매니플레이터에 외란 토크를 적용하지 않았을 때 두 제어기 모두 추적오차가 0에 가까웠으며, 외란토크가 0.4N 일 때 CTM제어기를 사용한 경우에는 퍼지제어기를 사용한 경우보다 시뮬레이션결과 절대 오차 합이 10배 이상 큼을 알 수 있다. 퍼지 제어기가 CTM제어기보다 외란토크의 추가시 강함을 검증하였다.