• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.390-395
• /
• 2009

In this paper, we design an on-road vehicle detection system based on the combination of a camera and a LIDAR system. In the proposed system, the candidate area is selected from the LIDAR data using a grouping algorithm. Then, the selected candidate area is scanned by an SVM to find an actual vehicle. The morphological edged images are used as features in a camera. The principal components of the edged images called eigencar are employed to train the SVM. We conducted experiments to show that the on-road vehicle detection system developed in this paper demonstrates about 80% accuracy and runs with 20 scans per second on LIDAR and 10 frames per second on camera.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.1 no.3
• /
• pp.266-273
• /
• 2012

In conventional direct torque control (DTC) using space-vector modulation (SVM) of induction machine (IM) drives, at least three current sensors are needed. In this paper, a low-cost SVM-DTC strategy is proposed, in which only a single current sensor is used. The position of the voltage space vector is divided into two areas: effective and non-effective area. If it is located in the non-effective area, the voltage space vector will be shifted into the effective area with minimum distortion. Further, the switching frequency remains constant. The simulation is carried out on a MATLAB/Simulink platform and the simulated results verify the effectiveness of the proposed strategy.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.6
• /
• pp.513-518
• /
• 2007

In this paper, we propose a fault diagnosis scheme tor induction motor by adopting a hierarchical classifier consisting of k-Nearest Neighbors(k-NN) and Support Vector Machine(SVM). First, some motor conditions are classified by a simple k-NN classifier in advance. And then, more complicated classes are distinguished by SVM. To obtain the normal and fault data, we established an experimental unit with induction motor system and data acquisition module. Feature extraction is performed by Principal Component Analysis(PCA). To show its effectiveness, the proposed fault diagnostic system has been intensively tested with various data acquired under the different electrical and mechanical faults with varying load.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1656-1657
• /
• 2007

In this paper, a sliding mode controller with SVM sliding surface is proposed. In the conventional sliding mode control, the dynamic of sliding surface is not as same as nominal dynamic of original system. Therefore the aim of this paper is to design sliding surface without defining any additional dynamic state by using support vector machines. As a result, the proposed controller can have the same dynamic of nominal system controlled by $H_{\infty}$ controller.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1646-1647
• /
• 2007

In the conventional sliding mode control(SMC), the states of controlled systems are linearly dependent because of the characteristic of the sliding surface. This means that conventional SMC can not add its robustness to other control methods. To overcome this problem, a special sliding surface with additional dynamic states has been proposed. However the additional dynamic states make it difficult to design a controller because the order ofa controller becomes higher. So, in this paper, a novel sliding surface design method, which does not require any additional dynamic state, is proposed. The relationships between the states with desirable responses can be expressed by using SVM and included in a sliding mode dynamics. The robust optimal controller with the optimal performanceand the robustness of SMC is considered.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.11-17
• /
• 2010

In this parer, face recognition method which can be applied to ITCS (interactive TV control system) is proposed. We extracted ULBP(uniform local binary pattern) histogram feature from infra-red images, and we detected left-right eyes and face region by using SVM classifier. Then, We implemented face recognition system which is using Gabor transform and ULBP histogram feature and applied to personal verification for ITCS.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.637-644
• /
• 2006

Biomedical image is often complex. An applied image analysis system should deal with the images which are of quite low quality and are challenging to segment. This paper presents a framework for color cell image segmentation by learning and classification online. It is a robust two-stage scheme using kernel method and watershed transform. In first stage, a two-class SVM is employed to discriminate the pixels of object from background; where the SVM is trained on the data which has been analyzed using the mean shift procedure. A real-time training strategy is also developed for SVM. In second stage, as the post-processing, local watershed transform is used to separate clustering cells. Comparison with the SSF (Scale space filter) and classical watershed-based algorithm (those are often employed for cell image segmentation) is given. Experimental results demonstrate that the new method is more accurate and robust than compared methods.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.79.2-79.2
• /
• 2010

FCEV(Fuel Cell Electric Vehicle)는 연료전지스택의 각 셀에서 반응하는 화학에너지를 전기에너지로 변환하여 차량을 구동하는 시스템이다. 이러한 연료전지 셀이 정상적인 발전이 되지 않을 경우 비정상적인 전압이 발전되고 이것을 방치한다면 연료전지 스택의 영구적인 고장을 야기할 수 있다. 이를 방지하기 위해 SVM(Stack Voltage monitor) 제어기는 각 셀의 전압을 측정하고 그 정보를 상위 제어기인 FCU(Fuel cell Control Unit)에 전달한다. 이에 FCU는 연료전지스택의 고장을 운전자에게 알리고 연료전지스택의 발전을 멈추게 한다. 기존에 SVM 제어기는 각 셀마다 분압저항을 통하여 측정하며 이 전압의 차를 이용하여 셀 전압을 계산하는 방식이었다. 이는 상위 셀로 갈수록 오차가 커지는 문제가 있고 다수의 CPU 및 DC/DC 컨버터가 적용이 필요하여 복잡한 구성과 가격이 높은 문제가 있었다. 이러한 문제점을 해결하기 위하여 cell monitoring IC를 적용하였고 좀 더 정밀한 측정과 간단한 인터페이스를 구성할 수 있었다. 본 연구에서는 기존 SVM 제어기보다 안정되고 정밀한 SVM 제어기의 개발에 대해 기술하였다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.2
• /
• pp.119-125
• /
• 2008

This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2337-2341
• /
• 2005

This paper presents the target detection method using Support Vector Machines(SVMs) and the navigation system using behavior-based fuzzy controller. SVM is a machine-learning method based on the principle of structural risk minimization, which performs well when applied to data outside the training set. We formulate detection of target objects as a supervised-learning problem and apply SVM to detect at each location in the image whether a target object is present or not. The behavior-based fuzzy controller is implemented as an individual priority behavior: the highest level behavior is target-seeking, the middle level behavior is obstacle-avoidance, the lowest level is an emergency behavior. We have implemented and tested the proposed method in our mobile robot "Pioneer2-AT". Comparing with a neural-network based detection method, a SVM illustrate the excellence of the proposed method.