• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.1958-1960
• /
• 2001

In this paper, we propose the design methodology of target tracking system using the identification of TS fuzzy model based on genetic algorithm(GA) and RLS algorithm. In general, the objective of target tracking is to estimate the future trajectory of the target based on the past position of the target obtained from the sensor. In the conventional and mathematical nonlinear filtering method such as extended Kalman filter(EKF), the performance of the system may be deteriorated in highly nonlinear situation. In this paper, to resolve these problems of nonlinear filtering technique, the error of EKF by nonlinearity is compensated by identifying TS fuzzy model. In the proposed method, after composing training datum from the parameters of EKF, by identifying the premise and consequent parameters and the rule numbers of TS fuzzy model using GA, and by tuning finely the consequent parameters of TS fuzzy model using recursive least square(RLS) algorithm, the error of EKF is compensated. Finally, the proposed method is applied to three dimensional tracking problem, and the simulation results shows that the tracking performance is improved by the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.8
• /
• pp.1495-1504
• /
• 2008

New license plates have been used since 2007. This paper proposes a new license plate extraction method using a gray labeling and a fuzzy reasoning method. First, the proposed method extracts the candidate plates by the gray labeling which is the enhanced version of a non-recursive flood-filling algorithm. By newly designed fuzzy inference system. fitness of each candidate plates are calculated. Finally, the area of the license plate in a image is extracted as a region of the candidate label which has the highest fitness. In the experiments, various license plate images took from indoor/outdoor parking lot, street, etc. by digital camera or cellular phone were used and the proposed extraction method was showed remarkable results of a 94 percent success.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.667-675
• /
• 2021

The treatments for symptoms of Alzheimer's disease are being provided and for the early diagnosis several researches are undergoing. In this regard, by using T1-weighted images several classification techniques had been proposed to distinguish among AD, MCI, and Healthy Control (HC) patients. In this paper, we also used some traditional Machine Learning (ML) approaches in order to diagnose the AD. This paper consists of an improvised feature selection method which is used to reduce the model complexity which accounted an issue while utilizing the ML approaches. In our presented work, combination of subcortical and cortical features of 308 subjects of ADNI dataset has been used to diagnose AD using structural magnetic resonance (sMRI) images. Three classification experiments were performed: binary classification. i.e., AD vs eMCI, AD vs lMCI, and AD vs HC. Proposed Feature Selection method consist of a combination of Principal Component Analysis and Recursive Feature Elimination method that has been used to reduce the dimension size and selection of best features simultaneously. Experiment on the dataset demonstrated that SVM is best suited for the AD vs lMCI, AD vs HC, and AD vs eMCI classification with the accuracy of 95.83%, 97.83%, and 97.87% respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2719-2724
• /
• 2003

In this paper, we deal with the kinematic and dynamic modeling of hybrid robotic systems that are constructed by combination of parallel and serial modules or series of parallel modules. Previously, open-tree structure has been employed for dynamic modeling of hybrid robotic systems. Though this method is generally used, however, it requires expensive computation as the size of the system increases. Therefore, we propose an efficient dynamic modeling methodology for hybrid robotic systems. Initially, the dynamic model for the proximal module is obtained with respect to the independent joint coordinates. Then, in order to represent the operational dynamics of the proximal module, we model virtual joints attached at the top platform of the proximal module. The dynamic motion of the next module exerts dynamic forces to the virtual joints, which in fact is equivalent to the reaction forces exerted on the platform of the lower module by the dynamics of the upper module. Then, the dynamic forces at the virtual joints are distributed to the independent joints of the proximal module. For multiple modules, this scheme can be constructed as a recursive dynamic formulation, which results in reduction of the complexness of the open-tree structure method for modeling of hybrid robotic systems. Simulation for inverse dynamics is performed to validate the proposed modeling algorithm.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1157-1160
• /
• 2005

The denoising and reconstruction of color images are increasingly studied in the field of computer vision and image processing. Especially, the denoising and reconstruction of color face images are more difficult than those of natural images because of the structural characteristics of human faces as well as the subtleties of color interactions. In this paper, we propose a denoising method based on PCA reconstruction for removing complex color noises on human faces, which is not easy to remove by using vectorial color filters. The proposed method is composed of the following five steps; training of canonical eigenface space using PCA, automatic extracting of face features using active appearance model, relighing of reconstructed color image using bilateral filter, extraction of noise regions using the variance of training data, and reconstruction using partial information of input images (except the noise regions) and blending of the reconstructed image with the original image. Experimental results show that the proposed denosing method efficiently removes complex color noises on input face images.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.3
• /
• pp.188-195
• /
• 2004

This paper presents neural load torque observer that is used to deadbeat load torque observer and gain compensation by parameter estimator As a result, the response of the PMSM(permanent magnet synchronous motor) follows that nominal plant. The load torque compensation method is composed of a neural deadbeat observer To reduce the noise effect, the post-filter implemented by MA(moving average) process, is adopted. The parameter compensator with RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller The parameter estimator is combined with a high performance neural load torque observer to resolve the problems. The neural network is trained in on-line phases and it is composed by a feed forward recall and error back-propagation training. During the normal operation, the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against the load torque and the Parameter variation. A stability and usefulness are verified by computer simulation and experiment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.3
• /
• pp.376-382
• /
• 2014

E-Actuator is an essential part of an eVGT, it receives the command from the main ECU and controls the vane. An e-Actuator failure can cause an abrupt change in engine output and it may induce an accident. Therefore, it is required to detect anomalies in the e-Actuator in real time to prevent accidents. In this paper, an e-Actuator fault detection method using on-line parameter identification is proposed. To implement on-line fault detection algorithm, many constraints are considered. The test input and sampling rate are selected considering the constraints. And new recursive system identification algorithm is proposed which reduces the memory and MCU power dramatically. The relationship between the identified parameters and real elements such as gears, spring and motor are derived. The fault detection method using the relationship is proposed. The experiments with the real broken gears show the effectiveness of the proposed algorithm. It is expected that the real time fault detection is possible and it can improve the safety of eVGT system.

• Journal of Advanced Navigation Technology
• /
• v.5 no.2
• /
• pp.111-122
• /
• 2001

In this paper, we study the performance of eigencanceller which use a eigenvector and eigenvalue in order to update a weighter vector. Eigencanceller can suppress directional interferences and noise effectively while maintaining specified beam pattern constraints. The constraints and optimal weight vector of eigencanceller vary by using interference and noise or desired signal, interference signal and noise as array input signal. From the analysis results in the steady state, We show that weight vectors in each case are simplified the form of projection equation that belongs to desired subspace orthogonal to interference subspace and eigencanceller has the better performance than RLS method through mathematical analysis and simulation.

• International Journal of Contents
• /
• v.3 no.2
• /
• pp.18-24
• /
• 2007

Biological sequences such as DNA and amino acid sequences typically contain a large number of items. They have contiguous sequences that ordinarily consist of more than hundreds of frequent items. In biological sequences analysis(BSA), a frequent contiguous sequence search is one of the most important operations. Many studies have been done for mining sequential patterns efficiently. Most of the existing methods for mining sequential patterns are based on the Apriori algorithm. In particular, the prefixSpan algorithm is one of the most efficient sequential pattern mining schemes based on the Apriori algorithm. However, since the algorithm expands the sequential patterns from frequent patterns with length-1, it is not suitable for biological datasets with long frequent contiguous sequences. In recent years, the MacosVSpan algorithm was proposed based on the idea of the prefixSpan algorithm to significantly reduce its recursive process. However, the algorithm is still inefficient for mining frequent contiguous sequences from long biological data sequences. In this paper, we propose an efficient method to mine maximal frequent contiguous sequences in large biological data sequences by constructing the spanning tree with a fixed length. To verify the superiority of the proposed method, we perform experiments in various environments. The experiments show that the proposed method is much more efficient than MacosVSpan in terms of retrieval performance.