• Plant Biotechnology Reports
• /
• 제3권1호
• /
• pp.87-93
• /
• 2009

To determine whether pattern recognition based on metabolite fingerprinting for whole cell extracts can be used to discriminate cultivars metabolically, leaves and fruits of five commercial strawberry cultivars were subjected to Fourier transform infrared (FT-IR) spectroscopy. FT-IR spectral data from leaves were analyzed by principal component analysis (PCA) and Fisher's linear discriminant function analysis. The dendrogram based on hierarchical clustering analysis of these spectral data separated the five commercial cultivars into two major groups with originality. The first group consisted of Korean cultivars including 'Maehyang', 'Seolhyang', and 'Gumhyang', whereas in the second group, 'Ryukbo' clustered with 'Janghee', both Japanese cultivars. The results from analysis of fruits were the same as of leaves. We therefore conclude that the hierarchical dendrogram based on PCA of FT-IR data from leaves represents the most probable chemotaxonomical relationship between cultivars, enabling discrimination of cultivars in a rapid and simple manner.

• International Journal of Vascular Biomedical Engineering
• /
• 제3권2호
• /
• pp.17-24
• /
• 2005

The main purpose of our study is to propose a new methodology to develop the multi-parametric measure including linear and nonlinear measures of heart rate variability diagnosing cardiovascular disease. We recorded electrocardiogram for three recumbent postures; the supine, left lateral, and right lateral postures. Twenty control subjects (age: $56.70{\pm}9.23$ years), 51 patients with angina pectoris (age: $59.98{\pm}8.41$ years) and 13 patients with acute coronary syndrome (age: $59.08{\pm}9.86$ years) participated in this study. To develop the multi-parametric measure of HRV, we used the multiple discriminant analysis method among statistical techniques. As a result, the multiple discriminant analysis gave 75.0% of goodness of fit. When the linear and nonlinear measures of HRV are individually used as a clinical tool to diagnose cardiac autonomic function, there is quite a possibility that the wrong results will be obtained due to each measure has different characteristics. Although our study is a preliminary one, we suggest that the multi-parametric measure, which takes into consideration the whole possible linear and nonlinear measures of HRV, may be helpful to diagnose the cardiovascular disease as a diagnostic supplementary tool.

• 한국환경복원기술학회지
• /
• 제2권3호
• /
• pp.83-92
• /
• 1999

To investigate the influence of forest road characteristics and site conditions on the stability of forest-road in granite area, four forest roads had been selected in Kyongbuk regions. The total of 13 road characteristic variables were evaluated by the discriminant analysis. The factors influencing the stability of forest road were bed rock, slope length, coverage, hardness, side-ditch erosion and road width. But aspect and soil texture were not significant for the stability in this area. In the correlation between forest environment and road structure, hardness and bed rock was highly significant in stability group, and coverage and side-ditch erosion was highly significant in instability group. 75 of 175 segments were instable whereas the others were stable. The centroids value by discriminant function in the stability and instability were estimated to 3.0585 and -1.9116, respectively. The stability criterion of forest road was discriminated from the centroids value of the each group. The main factors contributing the stability of forest road were significant in order of side-ditch erosion, coverage, soil texture, elevation, gradient, slope length and construction year. The prediction rate of discriminant function for stability evaluation of forest road was as high as 97.44%. In conclusion, the forest road structure factors such as length, coverage and slope gradient were controlled by construction techniques. If the factors like those should be considered in design, construction and forest road management, the stability of forest road may increase more. And also, it is necessary to take slope protection measures like small terraces and retaining walls for stability of cut slope.

• 한국콘텐츠학회논문지
• /
• 제10권12호
• /
• pp.84-90
• /
• 2010

Viola와 Jones가 사용한 Haar-like 특징 기반 약분류기의 분별력을 개선하기 위하여, 2차 판별식에 기반한 판정 경계(decision boundary) 결정 방법을 제안한다. Viola와 Jones가 부스팅된 약분류기 앙상블을 사용해서 강분류기를 만들 때 사용한 단일 판정 경계 기반 약분류기는 특징 공간을 지나치게 단순하게 해석한 산물이어서 대부분의 경우 최적이 아니며, 객체 클래스와 배경 클래스 간을 효율적으로 분별하기에 흔히 너무 약하다. 이 논문에서 제안하는 2차 판별식 분석에 기반한 방법은 객체 클래스와 배경 클래스 사이에 다중 판정 경계를 사용하는 약분류기를 만들어준다. 1000개의 positive 샘플과 3000개의 negative 샘플을 훈련에 사용하고, 500개의 positive와 500개의 negative를 테스트에 사용한 차량 검출 실험을 통해서, 기존의 단일 문턱치 기반 약분류기 방식에 비해, 제안 기법이 더 적은 수의 분류기를 사용하면서도 더 우수한 분류 성능을 제공하는 것을 확인하였다.

• 성인간호학회지
• /
• 제19권3호
• /
• pp.389-400
• /
• 2007

Purposes: This study was designed to explore the stage distribution of subjects according to stage of change for calcium intake and for exercise, and to identify factors that could discriminate among subjects in various stages. Methods: The sample consisted of 142 subjects who had taken bone mineral densitometry tests. The instruments used in this study were the Stage Placement Instrument for Calcium Intake and Exercise, the Osteoporosis Health Belief Scale and the Osteoporosis Knowledge Test, and the Osteoporosis Self Efficacy Scale. Data were analyzed using chi square, ANOVA, and discriminant analysis by using the SPSS 12.0 program. Results: For calcium stages, economic level, calcium knowledge, positive social norms for calcium intake, & educational level showed high standardized canonical discriminant function coefficients. For exercise stages, exercise efficacy, susceptibility, exercise benefit, educational level, positive social norm to exercise, educational level, and exercise barrier showed high standardized canonical discriminant function coefficients. Conclusion: This study implies that bone mass promoting program incorporating a stages of change model can be applied as useful nursing intervention.

• 한국멀티미디어학회논문지
• /
• 제16권11호
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• 대한치과교정학회지
• /
• 제25권6호
• /
• pp.665-674
• /
• 1995

The purpose of this study is to investigate the cephalometric characteristics of the open-bite patients with DJD of TMJ. The DJD open-bite cases were compared with normal samples and Class II open-bite cases with normal TMJ respectively. Twenty three open-bite patients with bilateral DJD of TMJ($13.9\~35.3$ yens old, Group I) were selected from the Department of Orthodontics, SNUDH. Group ll consisted of thirteen Class II open-bite cases($13.2\~27.4$ years old) with no TMD signs/symtoms and good condylar shapes. Group III samples were the forty eight healthy dental students who have Class I molar relationships with no history of orthodontic treatment, good facial balance and no TMD symptoms($20.0\~26.8$ years old). First, sixty measurements in the lateral cephalometric radiographs and analysis of variance(P<0.05, Scheffe) were used to compare these three groups. The seven measurements showed significant difference(p<0.05) between Group I and Group II. After analysis of variance, six of them were used for the discriminant analysis(Wilks' stepwise analysis) and the discrminant function for Group I/Group II was obtained. The results and conclusions were as follows : In most of the measurments, Group I and Group II showed the same skeletal and dental characteristics. But seven of the sixty measurements(FH-PP angle, SNB, FH-ArGo angle, articulare angle, genial angle, upper gonial angle and Ar-Go length) were significantly different(p<0.05) between Group I and Group II. These differences may be explained by the fact that in DJD cases the mandible rotated backward due to the shortening of the ramus following the degenerative destruction of condylar head and its surrounding structures. The resulting discriminant function was : $D={-0.120X}_1+{0.066X}_2+{0.144X}_3-{0.058X}_4+2000,\;where\;X_1=ArGo\;length(mm),\;X_2=SArGo\;angle(degree),\;X_3=FH-PP\;angle(degree),\;X_4=Gonial\;angle(degree)$. Mean of the group centroids was -0.555 and percent of the 'grouped' cases correctly classified was $88.89\%$.

• 자원환경지질
• /
• 제38권3호
• /
• pp.207-219
• /
• 2005

본 연구에서는 회동저수지 상류 수영강 유역에 발달된 토양을 대상으로 지질 및 토지이용별로 토양의 물리화학적 특성을 조사하고 그 영향을 다변량 통계분석법인 주성분 및 판별분석을 이용하여 고찰하였다. 연구지역내 토양의 토성은 안산암에서 발달한 토양이 화강암의 것보다 세립질이며 용출 무기성분, 점토 및 유색광물의 함량도 높았다. 경작지 토양 내 염류 집적(EC, 양이온, 음이온)과 pH증가는 대부분 경작과정에 투입된 비료의 영향에 의한 것이며 임야 토양에 비해 상대적으로 낮은 유기물 농도는 경운에 의한 유기물의 산화 촉진 및 작물 수확에 기인하는 것이다. 토지이용별 무기성분의 함량은 밭>과수원>논>임야 토양 순으로 나타났으며, 논 토양의 높은 $SO_4\;^{2-}$함량은 담수 상태 환원조건하 침전된 황화광물형태가 산화조건의 용출 실험에 의해 용해되어 증가되는 것에 기인한다. 주성분 분석결과는 토지 이용이나 지질에 따른 토양 특성을 잘 나타내었으며, 주성분 1은 시비, 광물 풍화작용 및 질소질 비료에 의한 이온교환 반응의 영향을 나타내었다. 토양 용출 성분과 성분비를 이용한 두 종류의 판별분석결과는 모두 토지이용별로 판별함수 1과 2에 의해 뚜렷하게 구분되며, 토양 성분을 이용한 판별분석에서 판별함수 1은 경작에 의한 비료의 영향을 나타내며 밭, 과수원, 논, 임야 토양 순서로 증가하였다. 판별분석에 의한 토지이용 특성의 조사 및 예측자료는 비교적 잘 일치하였으며 토지 이용의 변화를 확인할 수 있는 방법으로도 사용될 수 있었다.

• 한국생활과학회지
• /
• 제12권5호
• /
• pp.767-776
• /
• 2003

The purpose of this study was to classify side somatotypes of the trunk by analysing photographic data. Then their distribution according to the age groups was studied. The subjects were 315 females of 18 to 49 year-old. Thirty one photographic measurements were taken to each subject. The factors affecting the side somatotype of the trunk were obtained by principal component analysis, vertical size, posterior/anterior depth and neck posture. The side somatotypes of the trunk were classified into 4 types and their differences were shown by analysing photographic data. The side silhouettes of 4 types were compared with balanced type. By suggesting the canonical discriminant function with the unstandardized canonical coefficient, individual somatotype of the trunk could be discriminated from the photographic data of anterior neck height, anterior waist height, posterior waist depth, buttock height, and anterior depth at the level of back protrusion. The frequency distribution of the side somatotypes of the trunk according to the age groups could be applied for clothing construction and the rate of clothing production.

• 한국식품과학회지
• /
• 제49권4호
• /
• pp.349-354
• /
• 2017

전자혀 분석을 통해 국내산과 중국산 수삼(Panax ginseng C. A. Meyer)의 신속하고 정확한 판별법을 개발하고자 하였다. 전자혀를 이용하여 센서 감응도 값(raw data)을 분석한 뒤 taste screening하여 맛 스코어로 나타낸 결과, 국내산 수삼과 중국산 수삼은 감칠맛(UMS)에서 가장 큰 차이를 나타냈고 쓴맛(BRS)과 단맛(SWS)도 상대적으로 차이를 나타냈다. 국내산 수삼이 중국산 수삼에 비해 상대적으로 강한 감칠맛을 나타냈고, 쓴맛과 단맛은 그 반대로 나타났다. 판별함수분석 결과, DF1 (discriminant function first score) 상으로 국내산 수삼 그룹과 중국산 수삼 그룹이 구별되는 것을 볼 수 있었다. Discriminant power 값은 UMS 센서가 0.522으로 두 그룹에 가장 큰 차별성을 부여했다. CDA(canonical discriminant analysis) 분석 결과 두 수삼 그룹의 distance between centroids값은 2.7463으로 판별이 잘 된 것을 볼 수 있었다. 또한, 국내산 수삼 77점에서 67점이 국내산으로, 중국산 수삼은 77점 중 73점이 중국산으로 판별되어, 최종 판별정확도는 90.91%로 나타났다. 간단한 전처리 및 여러 가지 통계 처리를 통해 전자혀를 이용한 수삼의 원산지 판별이 가능하다고 판단되었으며, 신속하고 정확하게 판별을 수행할 수 있을 것으로 기대된다.