• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권3호
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권3호
• /
• pp.163-172
• /
• 2016

Electric load forecasting is essential for effective power system planning and operation. Complex and nonlinear relationships exist between the electric loads and their exogenous factors. In addition, time-series load data has non-stationary characteristics, such as trend, seasonality and anomalous day effects, making it difficult to predict the future loads. This paper proposes a locally-weighted polynomial neural network (LWPNN), which is a combination of a polynomial neural network (PNN) and locally-weighted regression (LWR) for daily shortterm peak load forecasting. Model over-fitting problems can be prevented effectively because PNN has an automatic structure identification mechanism for nonlinear system modeling. LWR applied to optimize the regression coefficients of LWPNN only uses the locally-weighted learning data points located in the neighborhood of the current query point instead of using all data points. LWPNN is very effective and suitable for predicting an electric load series with nonlinear and non-stationary characteristics. To confirm the effectiveness, the proposed LWPNN, standard PNN, support vector regression and artificial neural network are applied to a real world daily peak load dataset in Korea. The proposed LWPNN shows significantly good prediction accuracy compared to the other methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권3호
• /
• pp.216-223
• /
• 2016

This paper proposes a new controller design method for a fork-type lifter (FTL) of a transportation mobile robot. The transportation robot needs to pick up a package from a stack on a storage shelf and move on by a planned path in a logistics center environment. The position of the storage shelf is recognized by reading a QR code on the floor, and using this position, the robot can move to reach the storage shelf and pick up the package. PID controllers and an adaptive controller are designed to control the velocity of two wheels and the position of the FTL. An adaptive controller for the lifter is designed to elevate up and down on a slideway to the correct height position of the package on the stack of the storage shelf. The simulation results show that the PID controllers can respond smoothly to the desired angular velocity and the adaptive controller can adapt quickly and correctly to the desired height.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.1-6
• /
• 2003

The Delayed Feedback Control method (DFC) proposed by Pyragas applies an input based on the difference between the current state of the system, which is generating chaos orbits, and the $\tau$-time delayed state, and stabilizes the chaos orbit into a target. In DFC, the information about a position in the state space is unnecessary if the period of the unstable periodic orbit to stabilize is known. There exists the fault that DFC cannot stabilize the unstable periodic orbit when a linearlized system around the periodic point has an odd number property. There is the chaos control method using the prediction of the $\tau$-time future state (PDFC) proposed by Ushio et al. as the method to compensate this fault. Then, we propose a method such as improving the fault of the DFC. Namely, we combine DFC and PDFC with parameter W, which indicates the balance of both methods, not to lose each advantage. Therefore, we stabilize the state into the $\tau$ periodic orbit, and ask for the ranges of Wand gain K using Jury' method, and determine the quasi-optimum pair of (W, K) using a genetic algorithm. Finally, we apply the proposed method to a discrete-time chaotic system, and show the efficiency through some examples of numerical experiments.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.37-43
• /
• 2003

Current Internet system of the entrance exam information to the university that is depending on searching key to solve the overloaded problem in the network and DB server or other tools to support HTML edit, haven't satisfied user's wants by supplying uniformed searching system. So this thesis will establish EEIS(Entrance Examination Information System) to prevent database overload phenomena when many users request a great amount of data at the same time and improve the decrease of speed and overload problem in DB server. EEIS playa role of bridge between outside client and DB server by placing VVS(Virtual View Server) between web server and DB server. By that method this system give users several usefulness in convenience and variety by supplying realtime data searching function to user. EEIS also give inner system manager more efficiency and speed in control the management system by solving those problem. This system is design and implementation to satisfy user's desire and give them more convenience and bring up the confidence of university that adopt this system at the end.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.295-304
• /
• 2014

Communication infrastructure supports wide variety of mobile services such as photo and file sharing, location tracking, social network services and instant messaging. However, instances like power-loss and natural disasters disrupt these communication infrastructures unable to render support to these mobile services. Delay-tolerant networks (DTNs) offer a solution to these problems at hand. By utilizing mobility and opportunistic contacts among mobile devices, a plausible communication network can be establish and enable support to mobile applications. This paper presents an energy-efficient, reliable message delivery routing scheme with message prioritization rules for DTN. It uses the context information of nodes (mobile devices) such as the contact history (location and time of contact), speed/velocity, moving direction to determine the best forwarders among nodes in the network. The remaining energy of the nodes is also used to determine the message types a node can deliver successfully. The simulation results show that proposed approach outperforms Epidemic and Prophet routing schemes in terms of delivery ratio, overhead ratio, delivered messages per types and remaining energy.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.288-294
• /
• 2014

Understanding a ship's present position has been one of the most important tasks during a ship's voyage, in both ancient and modern times. Particularly, a ship's dead reckoning (DR) has been used for predicting traffic situations and collision avoidance actions. However, the current system that uses the traditional method of calculating DR employs the received position and speed data only. Therefore, it is not applicable for predicting navigation within the harbor limits, owing to the frequent changes in the ship's course and speed in this region. In this study, planned routes were applied for improving the reliability of the proposed system and predicting the traffic patterns in advance. The proposed method of determining the dead reckoning position (DRP) uses not only the ships' received data but also the navigational patterns and tracking data in harbor limits. The Mercator sailing formulas were used for calculating the ships' DRPs and planned routes. The data on the traffic patterns were collected from the automatic identification system and analyzed using MATLAB. Two randomly chosen ships were analyzed for simulating their tracks and comparing the DR method during the timeframes of the ships' movement. The proposed method of calculating DR, combined with the information on planned routes and DRPs, is expected to contribute towards improving the decision-making abilities of operators.

• 한국지능시스템학회논문지
• /
• 제12권1호
• /
• pp.67-72
• /
• 2002

고수준의 정보 서비스를 제공하기 위해서는 소프트웨어의 고품질화를 추구하여야 한다. 기존에 개발된 품질측정방법들은 모듈내에 포함되어 있는 요인항목들을 서로 다른 관점에서 개별적으로 측정하고있어 통합적인 평가방법이 필요하다. 따라서 본 논문에서는 다수의 측정 방법들을 모두 수용할 수 있는 모델을 제안한다. 제안된 모델은 비율척도들을 선택하고, 러프논리를 이용하여 그들의 중요도를 산출한다. 다음으로 모듈의 품질도를 측정하기 위해서 퍼지적분을 이용하여 척도들의 중요도와 측정값을 종합한다. 마지막으로 척도들과 산출된 품질도의 상관관계를 분석하고, 통계적 방법으로 제안된 모델의 타당성을 보인다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권1호
• /
• pp.39-46
• /
• 2006

We propose an global color model based method for tracking motions of multiple human using a networked multiple-camera system in intelligent space as a human-robot coexistent system. An intelligent space is a space where many intelligent devices, such as computers and sensors(color CCD cameras for example), are distributed. Human beings can be a part of intelligent space as well. One of the main goals of intelligent space is to assist humans and to do different services for them. In order to be capable of doing that, intelligent space must be able to do different human related tasks. One of them is to identify and track multiple objects seamlessly. In the environment where many camera modules are distributed on network, it is important to identify object in order to track it, because different cameras may be needed as object moves throughout the space and intelligent space should determine the appropriate one. This paper describes appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.