• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.836-850
• /
• 2009

Human posture recognition has attracted tremendous attention in ubiquitous environment, performing arts and robot control so that, recently, many researchers in pattern recognition and computer vision are working to make efficient posture recognition system. However the most of existing studies is very sensitive to human variations such as the rotation or the translation of body. This is why the feature, which is extracted from the feature extraction part as the first step of general posture recognition system, is influenced by these variations. To alleviate these human variations and improve the posture recognition result, this paper presents 3D Star Skeleton and Principle Component Analysis (PCA) based feature extraction methods in the multi-view environment. The proposed system use the 8 projection maps, a kind of depth map, as an input data. And the projection maps are extracted from the visual hull generation process. Though these data, the system constructs 3D Star Skeleton and extracts the rotation invariant feature using PCA. In experimental result, we extract the feature from the 3D Star Skeleton and recognize the human posture using the feature. Finally we prove that the proposed method is robust to human variations.

• Journal of radiological science and technology
• /
• v.30 no.4
• /
• pp.419-426
• /
• 2007

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize taste(bitter, sweet, sour and salty) pattern vectors. The signal intensity of taste are used to compose the input pattern vectors. The SOM(Self Organizing Maps) algorithm for taste pattern recognition is used to learn initial reference vectors and the ot-star learning algorithm is used to determine the class of the output neurons of the sunclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ(Learning Vector Quantization) algorithm. The pattern vectors are classified into subclasses by neurons in the subclass layer, and the weights between subclass layer and output layer are learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors, the proposed algorithm is simulated with ones of the conventional LVQ, and it is confirmed that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.95-103
• /
• 2006

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize EEG pattern vectors. The frequency and amplitude of alpha rhythms and beta rhythms are used to compose the input pattern vectors. And the algorithm for EEG pattern recognition is used SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of the subclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights between subclass layer and output layer is learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors of EEG, the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.113-121
• /
• 2005

In this paper, we design the hybrid learning algorithm of LVQ which is to perform EMG pattern recognition. The proposed hybrid LVQ learning algorithm is the modified Counter Propagation Networks(C.p Net. ) which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVa. The weights of the proposed C.p. Net. which is between input layer and subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVd algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights which is between subclass layer and class layer of C.p. Net. is learned to classify the classified subclass. which is enclosed a class . To classify the pattern vectors of EMG. the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Bulletin of the Korean Space Science Society
• /
• 2003.10a
• /
• pp.44-44
• /
• 2003

위성의 자세를 결정하기 위해서는 위성체에 탑재된 각종 센서들을 사용된다. 이러한 센서 중에서 고정밀도의 자세결정을 위해서는 별추적기를 사용한다. 별 추적기를 통한 위성체의 자세결정은 CCD 이미지로부터 여러 가지 별패턴인식(star pattern recognition) 방법을 통하여 CCD의 FOV(Field of View)내의 별들을 인식, 자세정보를 추출하여 이루어진다. 이러한 과정은 운용중인 위성체내에서 실시간으로 처리되어야 하므로 빠른 처리속도, 높은 신뢰도, 그리고 위성체내에 저장되어지는 자료의 양도 가능한 적어야 한다는 제한 요소들이 있다. 이러한 별추적기의 별패턴인식 방법으로는 CCD의 FOV내에 존재하는 각 쌍의 별들의 각거리를 이용하는데, 위성체의 이전자세정보의 필요 여부, searching phase 등에 따라서 나누어진다. 본 연구에서는 선행자료를 필요로 하지 않는 k-vector SPIT(Star-Pair Identification Technique)를 사용하여 CCD이미지와 위성체에 저장된 별 카탈로그(star catalog)와 비교한 후, 각각의 별들을 인식(identification)할 수 있는 알고리즘을 구현하였다. 또한 선행자세자료를 필요로 하는 패턴인식방법을 구현하여 이들을 비교하였다.

• BMB Reports
• /
• v.41 no.1
• /
• pp.23-28
• /
• 2008

The altered amino acid (AA) levels as neurotransmitter closely correlate to neurodegenerative conditions including Alzheimer's disease (AD). Target profiling analysis of nineteen AAs in brain cortex samples from three Tg2576 mice as AD model and three littermate mice as control model was achieved as their N(O,S)-ethoxycarbonyl/tert-butyldimethylsilyl derivatives by gas chromatography. Subsequently, star pattern recognition analysis was performed on the brain AA levels of AD mice after normalization to the corresponding control median values. As compared to control mice, $\gamma$-aminobutyric acid among ten AAs found in brain samples was significantly reduced (P < 0.01) while leucine was significantly elevated (P < 0.02) in AD mice. The normalized AA levels of the three AD mice were transformed into distorted star patterns which was different from the decagonal shape of control median. The present method allowed visual discrimination of the three AD mice from the controls based on the ten normalized AA levels.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.101-104
• /
• 2011

본 논문에서는 레이저 센서를 장착한 자율 이동 로봇을 이용하여 실내에서 장애물들을 검출한다. 데이터에서 나오는 패턴을 인식해 사람과 정적 장애물을 실시간으로 구분한 후 사람의 속도와 로봇의 속도를 각각 비교하여 따로 지정해준 안전거리를 유지하며 주행한다. 예상치 못한 상황이 발생될 것을 대비해 로봇의 전방에 범퍼 센서를 장착하여 안전성을 고려하였다. 로봇의 자기 위치 인식을 위해 StarGazer센서를 이용하였다. 패턴은 레이저 센서 데이터의 거리, 각 값을 이용하여 다리 패턴의 너비를 구하고 너비의 가운데 점을 중심점으로 지정해 추적하며 구동하는 알고리즘을 구현하였다.

• BMB Reports
• /
• v.40 no.1
• /
• pp.119-124
• /
• 2007

Adenoviral vectors are among the most promising vectors available for human gene therapy. However, the use of recombinant adenoviral vectors, including replicationcompetent adenovirus (RCA), raises a variety of safety concerns in relation to the development of new therapies based on gene therapy. To examine how organic compounds change in rat plasma following the injection of adenovirus, $\beta$-galactosidase expressing recombinant adenovirus (designated rAdLacZ) or RCA, we investigated the content of fatty acids (FAs), which are important biochemical indicators in pathological conditions. Pattern recognition analysis on the level of FAs in rat plasma is described for the visual discrimination of adenovirus infection groups from normal controls. Plasma FAs from four control rats (normal group), and from four rats with rAdLacZ infection and six rats with RCA infection (the two abnormal groups), were examined by gas chromatography-mass spectrometry in selected ion monitoring modes as their tert-butyldimethylsilyl derivatives. In total, 20 FAs were positively detected and quantified. The results of the Student's t-test on the normal mean of two abnormal groups, the levels of three FAs (p<0.05) from rAdLacZ group and eleven FAs (p<0.05) from RCA group were significantly different. When star symbol plotting was applied to the group mean values of 20 FAs after normalization to the corresponding normal mean values, the resulting eicosagonal star patterns of the two infected groups were distorted into similar shapes, but were distinguishable from each other. Thus, these approaches will be useful for screening and monitoring of diagnostic markers for the effects of infection following the use of adenoviral vectors in gene therapy.

• Mass Spectrometry Letters
• /
• v.3 no.3
• /
• pp.74-77
• /
• 2012

Organic acid (OA) profiling analysis was performed in culture media from Lactobacillus pentosus K34 (L. pentosus K34) and Pediococcus lolli PL24 (P. lolli PL24) by gas chromatography-mass spectrometry (GC-MS) following methoxime/tert-butyldimethylsilyl derivatives. 12 OAs were positively identified in culture media. Most of OA levels from L. pentosus K34 of hetero lactic fermentation were found to be higher when compared with those from P. lolli PL24 of homo lactic fermentation, which may explain different OA metabolism in each strain. In addition, the distorted dodecagonal star patterns were readily distinguishable, and the characteristics of each strain were well represented. The present study demonstrates that the OA metabolic profiling method by GC-MS combined with star pattern recognition is useful for the monitoring study of characteristic OA metabolism in various microorganisms.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.5
• /
• pp.1569-1574
• /
• 2011

The presence of replication-competent adenovirus (RCA) subpopulations in adenoviral vector products raises a variety of safety issues for development of therapies based on gene therapy. To analyze the differing effects of adenoviral vector and RCA in vivo, we examined alterations in amino acids (AAs) using rat plasma following injection of ${\beta}$-galactosidase expressing recombinant adenovirus (designated rAdLacZ) or RCA. Plasma AAs were examined by gas chromatography-mass spectrometry. A total of 16 AAs were positively measured. In the rAdLacZ group compared to the control group, the level of aspartic acid was significantly increased (Student's t-test), while the level of glutamic acid was significantly reduced. Additionally, in the RCA group compared to the control group, the level of four AAs, valine, leucine, and isoleucine as branched-chain amino acids, and proline were significantly increased, whereas the levels of three AAs, glycine, threonine, and glutamic acid were significantly reduced. Altered plasma free AA metabolic patterns in rAdLacZ and RCA groups, compared with the control group, may explain the disturbance of AA metabolism related to viral infection.