• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2399-2413
• /
• 2021

A recommendation system is an information filter tool, which uses the ratings and reviews of users to generate a personalized recommendation service for users. However, the cold-start problem of users and items is still a major research hotspot on service recommendations. To address this challenge, this paper proposes a high-efficient hybrid recommendation system based on Fuzzy C-Means (FCM) clustering and supervised learning models. The proposed recommendation method includes two aspects: on the one hand, FCM clustering technique has been applied to the item-based collaborative filtering framework to solve the cold start problem; on the other hand, the content information is integrated into the collaborative filtering. The algorithm constructs the user and item membership degree feature vector, and adopts the data representation form of the scoring matrix to the supervised learning algorithm, as well as by combining the subjective membership degree feature vector and the objective membership degree feature vector in a linear combination, the prediction accuracy is significantly improved on the public datasets with different sparsity. The efficiency of the proposed system is illustrated by conducting several experiments on MovieLens dataset.

• Journal of Sensor Science and Technology
• /
• v.12 no.2
• /
• pp.79-87
• /
• 2003

In this paper, we propose a method to obtain a linear characteristic using soft computing for systems which have array sensors of nonlinear characteristics. Also a procedure utilizing the pattern information of array sensors without additional sensors is proposed to reduce disturbance effects. For a typical example, even a single CdS cell for CdS array has nonlinear characteristics. Overall linear characteristic for CdS array is obtained using fuzzy logic for each cell and overlapped portion. In addition, further improvement for linearization is obtained applying genetic algorithms for the parameters of membership functions. Also the effect of disturbing external light changes to the CdS array can be reduced without using any additional sensors for calibration. The proposed method based on fuzzy logic shows improvements for position measurements and disturbance reduction to external light changes due to the fuzziness of the shadow boundary as well as the inherent nonlinearity of the CdS array. This improvement is shown by applying the proposed method to the ball position measurements of a magnetic levitation system.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• 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.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.83-87
• /
• 2005

This paper deals with the design and evaluation of the robust controller for a synchronous generator excitation system to improve the steady state and transient stability. The nonlinear characteristics of the system is treated as model uncertainties, and then the robust control techniques are introduced into the power system stability design to take into account these uncertainties at the controller design stage. The performance of the designed controller is examined by extensive non-linear time domain simulation. It is shown that the performance of the robust controller is superior to that of the conventional PI controller. This paper also proposes an improved digital exciter control system for a synchronized generator using a digitally designed controller with database. Results show that the proposed control system manifests excellent control performance compared to existing control systems. It has also been confirmed that it is easy for the proposed control system to implement digital control.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.477-484
• /
• 2016

Small industrial appliances such as fan, audio, electric rice cooker mostly consist of ABS, PP, PS materials. In colored plastics, it is possible to classify by near infrared(NIR) spectroscopy, while in black plastics, it is very difficult to classify black plastic because of the characteristic of black material that absorbs the light. So the RBFNNs pattern classifier is introduced for sorting electrical and electronic waste plastics through LIBS(Laser Induced Breakdown Spectroscopy) spectrometer. At the preprocessing part, PCA(Principle Component Analysis), as a kind of dimension reduction algorithms, is used to improve processing speed as well as to extract the effective data characteristics. In the condition part, FCM(Fuzzy C-Means) clustering is exploited. In the conclusion part, the coefficients of linear function of being polynomial type are used as connection weights. PSO and 5-fold cross validation are used to improve the reliability of performance as well as to enhance classification rate. The performance of the proposed classifier is described based on both optimization and no optimization.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.132-137
• /
• 1993

In this paper, a fish drying process control system is proposed, which predicts the proper change with time in weight of the material fish and the drying conditions in advance, based on the performance of skilled worker. In order to implement a human expertise into an automated fish drying process control system, an experimental analysis is made and a model for the process is built. The proposed system divided into two procedures: The procedure before drying and the one during drying. The procedure before drying is for the prediction of necessary drying time. To estimate the necessary drying time, first, the proper change in weight for the product is obtained by using fuzzy reasoning. The condition part of the production rule consists of the factors of fish body and the expected degree of dryness. Kext, the necessary drying time is obtained by regression models. The variables employed in the models are the factors, inferred change in weight and drying conditions. The model for the procedure during drying is also proposed for more accurate estimation, which is described by a system of linear-differential equations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.40
• /
• pp.81-90
• /
• 1996

It is one of the most important thing to select pneumatic components in pneumatic system design. For the purpose of selecting pneumatic components, case objects are described as a knowledge representation and the most similar case object must be selected by decision making in computer. In this paper, case objects are represented using the methodology that is used for CBR(Case Base Reasoning) and methodology that the most similar case can be selected is Proposed. Algorithm VIWNNR(Varying Index Weight-based Nearer Neighbor Retrieval) is accomplished by varying index weight, that is not considering a index matching as true or false but varying a size of weight according to the degree of matching and enhance the flexibility of SCRM(Similar Case Retrieval Module) involving fuzzy concept in matching the cases. SCRM is tested In verify the feasibility to select pneumatic linear components and is peformed effectively.

• Journal of Energy Engineering
• /
• v.4 no.2
• /
• pp.278-287
• /
• 1995

본 논문은 산업체의 열병합발전시스템이 각종 보조설비와 연계되어 운전되고 있을 경우의 최적운전 계획을 수립하였다. 최적운전계획을 수립하기 위하여 열병합발전시스템의 수리적 모델링은 물론 각종 보조설비들의 모델링도 수립하였으며, 사례연구를 통하여 모델링의 효용성을 검토하였다. 본 논문에서는 열병합발전시스템의 방식에서 버터밍사이클을 대상으로 삼았다. 시뮬레이션은 우선 선형계획법을 이용하여 운전계획을 수립한 후에 그 결과를 바탕으로 퍼지선형계획법을 적용하였으며, 퍼지화의 정도에 따라 여러 Case를 구성하여 단기운전계획을 수립하였다. 사례연구를 통해 각종 보조설비들이 버터밍사이클 방식에서 효과적으로 운전될 수 있음을 확인하였으며 퍼지선형계획법의 도입전후에서 얻은 운전계획 결과와의 상호 비교, 검토를 통하여 퍼지선형계획법을 도입시켰을 경우 수립된 운전계획의 효용성을 평가하였다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.5
• /
• pp.30-41
• /
• 1999

본 논문에서는 연속시간과 이산시간에서 파라미터 불확실성과 시간지연을 가지는 비선형시스템에 대한 퍼지 견실 H∞ 제어기 설계방법을 제시한다. 비선형시스템은 변형한 T-S(Takagi- Sugeno) 퍼지모델을 사용하여 나타내고, 퍼지제어는 PDC(parallel distributed compensation) 개념을 이용한다. 또한 Lyapunov 접근방법을 이용하여 불확실성, 외란과 시간지연을 가지는 변형한 T-S 퍼지모델의 H∞ 노옴 한계를 가지는 자승적 안정성을 언급하고, LMI(linear matrix inequality) 기법을 이용하여 퍼지 견실 H∞ 제어기의 존재 조건과 제어기 설계방법을 제시한다. 그러므로 제시한 기법은 구하여진 충분조건을 만족하는 해를 찾음과 동시에 제어기를 한번에 설계할 수 있다. 마지막으로 예제를 통하여 제시한 방법의 타당성을 확인한다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.11
• /
• pp.2119-2130
• /
• 2011

This paper proposes new delay-dependent robust stability criteria for neural networks with time-varying delays. By construction of a suitable Lyapunov-Krasovskii's (L-K) functional and use of Finsler's lemma, new stability criteria for the networks are established in terms of linear matrix inequalities (LMIs) which can be easily solved by various effective optimization algorithms. Two numerical examples are given to illustrate the effectiveness of the proposed methods.