• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.739-748
• /
• 2014

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.9 no.5
• /
• pp.420-429
• /
• 2004

This paper proposes a novel current control strategy on active power filters using PQR instantaneous power theory which can compensate the line current harmonics and the neutral line current under the unbalanced and/or distorted source conditions in three-phase four-wire systems. The characteristics of the inverter ac filters are analyzed and a novel digital controller are proposed to overcome the inherent time delay problem in digital controllers with designed control gain in this paper. The proposed current control method is based on a sinusoidal PWM for fully-digital implementation compared with a conventional hysteresis PWM. PSiM simulation results verify the good performance of the proposed current control strategy on shunt type APFs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.815-820
• /
• 2010

Fuel spray characteristics of the gasoline engine injector has been studied experimentally. Wall wetting fuel stream of the 4-hole and 12-hole injectors has been tested and measured with various installation angle and port masking shapes. Spray visualization has been performed to analyze spray formation, spray angle, and penetration length. Test result shows that wall wetting is greatly influenced by the induction air flow and injector installation angle. Wall wetting amount decreased as injector installation angle decreased. Masking decreased wall wetting amount by increasing local intake-air flow velocity due to the decreased section area. Spray visualization showed that the 12-hole injector has robust performance characteristics compared with the 4-hole injector.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.667-680
• /
• 2007

The bio-data processing is used for a suitable purpose with bio-signals, which are obtained from human individuals. Recently, there is increasing demand that the bio-data has been widely applied to various applications. However, it is often that the number of data within each class is limited and the number of classes is large due to the property of problem domain. Therefore, the conventional pattern recognition systems and classification methods are suffering form low generalization performance because the system using the lack of data is influenced by noises of that. To solve this problem, we propose a modified additive factor model for bio-data generation, with two factors; the class factor which affects properties of each individuals and the environment factor such as noises which affects all classes. We then develop a classification system through defining a new similarity function using the proposed model. The proposed method maximizes to use an information of the class classification. So, we can expect to obtain good generalization performances with robust noises from small number of datas for bio-data. Experimental results show that proposed method outperforms significantly conventional method with real bio-data.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.17 no.4
• /
• pp.112-118
• /
• 2013

The selection of appropriate ground motions and reasonable modification are becoming increasingly critical in reliable prediction on seismic performance of structures. A widely used amplitude scaling approach is not sufficient for robust structural evaluation considering a site specific seismic hazard because only one spectral value is matched to the design spectrum typically at the structural fundamental period. Hence alternative approaches for ground motion selection and modifications have been suggested. However, there is no means to evaluate such methodologies yet. In this study, it is focused to describe the main questions resided in the amplitude scaling approach and to propose a regression model for structural damage as point of comparison. Spectrum compatible approach whose resulting spectrum matches the design spectrum at the entire range of the structural period is considered as alternative to be compared to the amplitude scaling approach. The design spectrum is generated according to ASCE7-05.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.1
• /
• pp.13-19
• /
• 2011

In this paper, a visual surveillance system using SOPC based NIOS II embedded processor and C2H compiler was implemented. In this system, the IP is constructed by C2H compiler for the output of the camera images, image processing, serial communication and network communication, then, it is implemented to effectively control each IP based on the SOPC and the NIOS II embedded processor. And, an algorithm which updates the background images for high speed and robust detection of the moving objects is proposed using the Adaptive Gaussian Mixture Model(AGMM). In results, it can detecte the moving objects(pedestrians and vehicles) under day-time and night-time. It is confirmed that the proposed AGMM algorithm has better performance than the Adaptive Threshold Method(ATM) and the Gaussian Mixture Model(GMM) from our experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.320-325
• /
• 2010

This paper is about the method and procedure to register the candidate sequentially in the face recognition system using the PCA(Principal Components Analysis). We use the method to update the principal components sequentially with the SKL algorithm which is improved R-SVD algorithm. This algorithm enable us to solve the re-training problem of the increase the candidates number sequentially in the face recognition using the PCA. Also this algorithm can use in robust tracking system with the bright change based to the principal components. This paper proposes the procedure in the face recognition system which sequentially updates the principal components using the SKL algorithm. Then we compared the face recognition performance with the batch procedure for calculating the principal components using the standard KL algorithm and confirms the effects of the forgetting factor in the SKL algorithm experimentally.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.133-138
• /
• 2006

Learning with Attribute Value Taxonomies (AVT) has shown that it is possible to construct accurate, compact and robust classifiers from a partially missing dataset (dataset that contains attribute values specified with different level of precision). Yet, in many cases AVTs are generated from experts or people with specialized knowledge in their domain. Unfortunately these user-provided AVTs can be time-consuming to construct and misguided during the AVT building process. Moreover experts are occasionally unavailable to provide an AVT for a particular domain. Against these backgrounds, this paper introduces an AVT generating method called GA-AVT-Learner, which finds a near optimal AVT with a given training dataset using a genetic algorithm. This paper conducted experiments generating AVTs through GA-AVT-Learner with a variety of real world datasets. We compared these AVTs with other types of AVTs such as HAC-AVTs and user-provided AVTs. Through the experiments we have proved that GA-AVT-Learner provides AVTs that yield more accurate and compact classifiers and improve performance in learning missing data.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.563-570
• /
• 2002

Robust extraction of 3D facial features and global motion information from 2D image sequence for the MPEG-4 SNHC face model encoding is described. The facial regions are detected from image sequence using multi-modal fusion technique that combines range, color and motion information. 23 facial features among the MPEG-4 FDP (Face Definition Parameters) are extracted automatically inside the facial region using color transform (GSCD, BWCD) and morphological processing. The extracted facial features are used to recover the 3D shape and global motion of the object using paraperspective camera model and SVD (Singular Value Decomposition) factorization method. A 3D synthetic object is designed and tested to show the performance of proposed algorithm. The recovered 3D motion information is transformed into global motion parameters of FAP (Face Animation Parameters) of the MPEG-4 to synchronize a generic face model with a real face.

• Journal of Power Electronics
• /
• v.13 no.6
• /
• pp.939-954
• /
• 2013

The Direct Torque Control (DTC) technique for Permanent Magnet Synchronous Motors (PMSM) is receiving increased attention due to its simplicity and robust dynamic response when compared with other control techniques. The classical switching table based DTC results in large flux and torque ripples in the motors. Several studies have been reported in the literature on classical DTC. However, there are only limited studies that actually discuss or evaluate the classical DTC. This paper proposes, novel switching table / DTC methods for PMSMs to reduce torque ripples. In this paper, two DTC schemes are proposed. The six sector and twelve sector methodology is considered in DTC scheme I and DTC scheme II, respectively. In both DTC schemes a simple modification is made to the classical DTC structure. The two level inverter available in the classical DTC is eliminated by replacing it with a three level Neutral Point Clamped (NPC) inverter. To further improve the performance of the proposed DTC scheme I, the available 27 voltage vectors are allowed to form different groups of voltage vectors such as Large - Zero (LZ), Medium - Zero (MZ) and Small - Zero (SZ), where as in DTC scheme II, all of the voltage vectors are considered to form a switching table. Based on these groups, a novel switching table is proposed. The proposed DTC schemes are comparatively investigated with the classical DTC and existing literatures through theory analysis and computer simulations. The superiority of the proposed DTC method is also confirmed by experimental results. It can be observed that the proposed techniques can significantly reduces the torque ripples and improves the quality of current waveform when compared with traditional and existing methods.