• Earthquakes and Structures
• /
• 제22권1호
• /
• pp.53-64
• /
• 2022

This study proposes an intelligent semi-active isolation system combining a variable-stiffness control device and ground motion characteristic prediction. To determine the optimal control parameter in real-time, a genetic algorithm (GA)-fuzzy control law was developed in this study. Data on various types of ground motions were collected, and the ground motion characteristics were quantified to derive a near-fault (NF) characteristic ratio by employing an on-site earthquake early warning system. On the basis of the peak ground acceleration (PGA) and the derived NF ratio, a fuzzy inference system (FIS) was developed. The control parameters were optimized using a GA. To support continuity under near-fault and far-field ground motions, the optimal control parameter was linked with the predicted PGA and NF ratio through the FIS. The GA-fuzzy law was then compared with other control laws to verify its effectiveness. The results revealed that the GA-fuzzy control law could reliably predict different ground motion characteristics for real-time control because of the high sensitivity of its control parameter to the ground motion characteristics. Even under near-fault and far-field ground motions, the GA-fuzzy control law outperformed the FPEEA control law in terms of controlling the isolation layer displacement and the superstructure acceleration.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권9호
• /
• pp.430-438
• /
• 2001

In this study, we introduce the adaptive Polynomial Neuro-Fuzzy Networks(PNFN) architecture generated from the fusion of fuzzy inference system and PNN algorithm. The PNFN dwells on the ideas of fuzzy rule-based computing and neural networks. Fuzzy inference system is applied in the 1st layer of PNFN and PNN algorithm is employed in the 2nd layer or higher. From these the multilayer structure of the PNFN is constructed. In order words, in the Fuzzy Inference System(FIS) used in the nodes of the 1st layer of PNFN, either the simplified or regression polynomial inference method is utilized. And as the premise part of the rules, both triangular and Gaussian like membership function are studied. In the 2nd layer or higher, PNN based on GMDH and regression polynomial is generated in a dynamic way, unlike in the case of the popular multilayer perceptron structure. That is, the PNN is an analytic technique for identifying nonlinear relationships between system's inputs and outputs and is a flexible network structure constructed through the successive generation of layers from nodes represented in partial descriptions of I/O relatio of data. The experiment part of the study involves representative time series such as Box-Jenkins gas furnace data used across various neurofuzzy systems and a comparative analysis is included as well.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권4호
• /
• pp.217-231
• /
• 2015

A novel fuzzy learning framework that employs fuzzy inference to solve the problem of Multiple Instance Learning (MIL) is presented. The framework introduces a new class of fuzzy inference systems called Multiple Instance Mamdani Fuzzy Inference Systems (MI-Mamdani). In multiple instance problems, the training data is ambiguously labeled. Instances are grouped into bags, labels of bags are known but not those of individual instances. MIL deals with learning a classifier at the bag level. Over the years, many solutions to this problem have been proposed. However, no MIL formulation employing fuzzy inference exists in the literature. Fuzzy logic is powerful at modeling knowledge uncertainty and measurements imprecision. It is one of the best frameworks to model vagueness. However, in addition to uncertainty and imprecision, there is a third vagueness concept that fuzzy logic does not address quiet well, yet. This vagueness concept is due to the ambiguity that arises when the data have multiple forms of expression, this is the case for multiple instance problems. In this paper, we introduce multiple instance fuzzy logic that enables fuzzy reasoning with bags of instances. Accordingly, a MI-Mamdani that extends the standard Mamdani inference system to compute with multiple instances is introduced. The proposed framework is tested and validated using a synthetic dataset suitable for MIL problems. Additionally, we apply the proposed multiple instance inference to fuse the output of multiple discrimination algorithms for the purpose of landmine detection using Ground Penetrating Radar.

• 한국지능시스템학회논문지
• /
• 제21권4호
• /
• pp.518-524
• /
• 2011

본 논문은 퍼지 추론 시스템(FIS: fuzzy inference system)을 이용하여 자이로스코프를 사용하지 않는 관성 항법 장치(GFINS: gyroscope free inertial navigation system)의 가속도계 데이터를 보정하는 방법에 관한 연구이다. 일반적인 관성항법 장치(INS: inertial navigation system)는 주로 가속도계와 같은 병진운동을 감지하는 관성 센서와 자이로스코프와 같은 회전 운동을 감지하는 관성 센서를 이용하여 위치와 yaw각을 측정하는 장치이다. 하지만 INS는 자이로스코프를 사용하기 때문에 소형화 및 저전력 설계가 어렵다. 이러한 문제를 해결하기 위하여 자이로스코프를 사용하지 않는 GFINS에 대한 연구가 활발히 진행되고 있다. GFINS에 사용되는 가속도계는 적분과 외란에 의한 오차가 시간이 지남에 따라 누적되는 문제가 있다. 따라서 본 논문에서는 가속도계의 누적 오차 문제를 해결하기 위해, 레이저 내비게이션과 가속도계의 선속도 비율과 엔코더와 가속도계의 선속도 비율을 통해 GFINS의 데이터를 보정하는 FIS를 제안한다. 제안된 Fuzzy-GFINS를 평가하기 위해, 직접 제작한 메카넘 휠 AGV(autonomous ground vehicle)에 제안된 GFINS를 적용하였다. 실험 결과, 제안된 방법이 GFINS의 출력 데이터를 효과적으로 보정하는 것을 확인 할 수 있었다.

• 한국전자파학회논문지
• /
• 제24권2호
• /
• pp.198-206
• /
• 2013

본 논문에서는 다기능 레이더의 추적 성능 개선을 위해 임무 우선 순위 선정을 위한 퍼지 추론 시스템 기반의 기법을 제안하였다. 제안한 기법은 추적 임무 수행 시 우선 순위 결정 트리를 구성하고, 퍼지 집합으로 추적 안정도, 위협도, 접근성을 선정하고, 퍼지 규칙을 통한 추적 임무의 우선 순위를 얻는 방식이다. 우선 순위를 높게 책정할 경우, 추적 주기를 변화시켜 추적의 정확도를 높일 수 있도록 설계하였다. 추적 성능 개선 효과를 입증하기 위해 기동 특성이 뚜렷한 표적 궤적을 생성하고, 제안된 기법을 적용한 경우와 적용하지 않은 경우를 시뮬레이션으로 비교 분석하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5568-5587
• /
• 2018

This research uses artificial intelligence methods for computer network intrusion detection system modeling. Primary classification is done using self-organized maps (SOM) in two levels, while the secondary classification of ambiguous data is done using Sugeno type Fuzzy Inference System (FIS). FIS is created by using Adaptive Neuro-Fuzzy Inference System (ANFIS). The main challenge for this system was to successfully detect attacks that are either unknown or that are represented by very small percentage of samples in training dataset. Improved algorithm for SOMs in second layer and for the FIS creation is developed for this purpose. Number of clusters in the second SOM layer is optimized by using our improved algorithm to minimize amount of ambiguous data forwarded to FIS. FIS is created using ANFIS that was built on ambiguous training dataset clustered by another SOM (which size is determined dynamically). Proposed hybrid model is created and tested using NSL KDD dataset. For our research, NSL KDD is especially interesting in terms of class distribution (overlapping). Objectives of this research were: to successfully detect intrusions represented in data with small percentage of the total traffic during early detection stages, to successfully deal with overlapping data (separate ambiguous data), to maximize detection rate (DR) and minimize false alarm rate (FAR). Proposed hybrid model with test data achieved acceptable DR value 0.8883 and FAR value 0.2415. The objectives were successfully achieved as it is presented (compared with the similar researches on NSL KDD dataset). Proposed model can be used not only in further research related to this domain, but also in other research areas.

• 제어로봇시스템학회논문지
• /
• 제12권6호
• /
• pp.554-560
• /
• 2006

In this paper, we propose the topological map building method about unknown environment using the ultrasonic sensors. An ultrasonic sensor inherently has the range error due to the specular reflection. To decrease this error, we estimate the obstacle states(position and velocity) using the local minimum sensor values and Jacobian. Estimated states are used to avoid the obstacles and build the topological map similar to the type that human being memorizes an environment. When a mobile robot is faced with three problems(comer way, cross way and dead end), it senses the movable directions using FIS(Fuzzy Inference System). Among these directions, it can select the target direction using binary decision tree(Turn Side Selector). Proposed algorithm has been verified with three simulations and three implementations.

• 한국안전학회지
• /
• 제37권1호
• /
• pp.78-87
• /
• 2022

In the risk assessment of urban railway systems, a hazard log is created by identifying hazards from accident and failure data. Then, based on a risk matrix, evaluators analyze the frequency and severity of the occurrence of the hazards, conduct the risk assessment, and then establish safety measures for the risk factors prior to risk control. However, because subjective judgments based on the evaluators' experiences affect the risk assessment results, a more objective and automated risk assessment system must be established. In this study, we propose a risk assessment model in which an adaptive neuro-fuzzy inference system (ANFIS), which is combined in artificial neural networks (ANN) and fuzzy inference system (FIS), is applied to the risk assessment of urban railway systems. The newly proposed model is more objective and automated, alleviating the limitations of risk assessments that use a risk matrix. In addition, the reliability of the model was verified by comparing the risk assessment results and risk control priorities between the newly proposed ANFIS-based risk assessment model and the risk assessment using a risk matrix. Results of the comparison indicate that a high level of accuracy was demonstrated in the risk assessment results of the proposed model, and uncertainty and subjectivity were mitigated in the risk control priority.

• Smart Structures and Systems
• /
• 제13권1호
• /
• pp.81-98
• /
• 2014

This paper presents the elastic buckling of smart lightweight column structures integrated with a pair of surface piezoelectric layers using artificial intelligence. The finite element modeling of Smart lightweight columns is found using $ANSYS^{(R)}$ software. Then, the first buckling load of the structure is calculated using eigenvalue buckling analysis. To determine the accuracy of the present finite element analysis, a compression study is carried out with literature. Later, parametric studies for length variations, width, and thickness of the elastic core and of the piezoelectric outer layers are performed and the associated buckling load data sets for artificial intelligence are gathered. Finally, the application of soft computing-based methods including artificial neural network (ANN), fuzzy inference system (FIS), and adaptive neuro fuzzy inference system (ANFIS) were carried out. A comparative study is then made between the mentioned soft computing methods and the performance of the models is evaluated using statistic measurements. The comparison of the results reveal that, the ANFIS model with Gaussian membership function provides high accuracy on the prediction of the buckling load in smart lightweight columns, providing better predictions compared to other methods. However, the results obtained from the ANN model using the feed-forward algorithm are also accurate and reliable.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.383-388
• /
• 2011

본 논문은 FIS(fuzzy inference system)와 신뢰도를 이용한 레이저 내비게이션의 정밀도 향상에 관한 것이다. 레이저 내비게이션은 무선 유도 장치로써 헤드가 $360^{\circ}$ 회전을 하며 벽에 부착된 반사체(reflector)를 읽어 AGV(automatic guided vehicle)의 위치를 측정하는 장치이다. 기존의 대표적인 유도 장치들의 타입은 유선 유도 방식이다. 이들은 정밀도가 매우 높고 반응속도가 빠르기 때문에 대부분의 현장에서는 이들을 채택하고 있다. 하지만, 이들 센서는 바닥 밑 1인치 안에 설치하거나 바닥에 심어야하기 때문에 설치비용은 매우 높고 유지 보수가 어렵다. 이러한 문제를 해결하기 위해서 레이저 내비게이션이 개발되었다. 이것은 바닥 시공 하는 것이 필요 없고 설치비용이 최소화되며 배치(layout) 변경이 쉽다. 하지만 외란에 영향을 많이 받아 데이터의 손실 손상이 크고 반응속도가 느리기 때문에 안전이 최우선인 산업현장에 사용이 어렵다. 이에 본 논문에서는 레이저 내비게이션의 정밀도 향상에 관한 연구를 하였다. 제안된 방법은 레이저 내비게이션의 특성을 분석하여 FIS를 통해 위치측정 정밀도의 신뢰도를 계산한 후에 이를 통해 레이저 내비게이션의 정밀도를 보정하는 방법이다. 본 논문에서는 실험을 위해서 직접 설계한 AGV를 이용하였으며, 레이저 내비게이션의 위치와 레이저 내비게이션의 신뢰도를 통해 보정된 위치를 제안된 방법과 비교 하였다. 실험 결과, FIS를 신뢰도로 보정한 결과가 다른 방법들에 비해 약 50% 성능이 향상됨을 확인하였다.