• Journal of Korean Society of Rural Planning
• /
• v.16 no.1
• /
• pp.63-71
• /
• 2010

지난 수십 년 동안 형태지수는 패치의 복잡성을 정량화하여 생물종 다양성 보존과 같은 경관생태계획에 활용되어 왔다. 지역계획 연구자들이나 정책결정자들에게 경관구조와 패턴을 정량화하는 경관생태지수는 대상지역을 모니터링할 수 있는 하나의 수단으로 활용되어 왔다. 그러나 경관생태지수관련 연구를 살펴보면 연구 목적 및 범위에 따라 활용하는 경관생태지수의 종류가 매우 다양하고 복잡한 것을 알 수 있다. 또한 연구목적에 적합한 경관생태지수를 선정하는 것은 복잡한 수학분석과 함께 많은 주의가 필요한 것을 알 수 있다. 따라서 본 연구에서는 형태지수들을 도시지역, 도시외곽지역, 농촌지역 그리고 산림지역 등 4군데 사례지역에 적용하여 그 결과를 통해 형태지수들의 특성을 살펴보았다. 그 결과, 평균형태지수값(MSI)에서는 도시외곽지역이 가장 높게 나타났고, 평균프랙텔차원지수(MPFD)에서는 농촌지역이 높게 나타났다. 넓은 면적을 가진 패치에 가중점을 고려한 평균형태지수값(AWMSI)과 평균프랙텔차원지수값(AWMPFD)에서는 산림지역이 가장 높게 나타났다. 사용한 네 가지 형태지수값의 순위가 4군데 사례지역에서 다르게 나타났다. 특히 둘레와 면적의 로그전환을 이용하고 있는 프랙텔차원지수들의 경우, 도시와 도시외곽지역의 MPFD값은 같고, 도시외곽지역, 농촌지역과 산림지역의 AWMPFD값 차이는 적어 순위 분별력이 떨어졌다. 따라서 넓은 면적을 가진 패치에 가중점을 고려한 평균형태지수(AWMSI)가 지역별 산림패치의 복잡성을 잘 정량화할 수 있음을 본 연구결과에서 보여주고 있다.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.58-68
• /
• 2005

In this paper, we propose a scheme to improve discriminative property in the feature compensation method for robust speech recognition under noisy environments. The estimation of noisy speech model used in existing feature compensation methods do not guarantee the computation of posterior probabilities which discriminate reliably among the Gaussian components. Estimation of Posterior probabilities is a crucial step in determining the discriminative factor of the Gaussian models, which in turn determines the intelligibility of the restored speech signals. The proposed scheme employs minimum classification error (MCE) training for estimating the parameters of the noisy speech model. For applying the MCE training, we propose to identify and determine the 'competing components' that are expected to affect the discriminative ability. The proposed method is applied to feature compensation based on parallel combined mixture model (PCMM). The performance is examined over Aurora 2.0 database and over the speech recorded inside a car during real driving conditions. The experimental results show improved recognition performance in both simulated environments and real-life conditions. The result verifies the effectiveness of the proposed scheme for increasing the performance of robust speech recognition systems.

• Journal of Korean Ophthalmic Optics Society
• /
• v.12 no.2
• /
• pp.25-36
• /
• 2007

We researched the change of astigmatism power when the fixation point moved from far distance to near distance. Astigmatism power was measured by using both eyes open-view auto-refractometer. We divided the ages between 5 and 67 years old into 12 groups with 1,598 healthy eyes(male-698 eyes and female-900 eyes) without eyes problems and experiences of eyes operations. The mean power in far astigmatism showed that with-the-rule of the total astigmatism: -0.79D, with-the-rule of the corneal astigmatism: -1.07D and against-the-rule of the residual astigmatism : -0.79D were found most respectively. The correlation between cornea astigmatism and total astigmatism was y=0.7493 x + 0.5661 r=0.6510, residual astigmatism and total astigmatism was y=0.248 x - 0.5926 r=0.2598 and corneal astigmatism and residual astigmatism was y=-0.4439 x - 0.1813 r=-0.5551 in the far distance. The mean power in near astigmatism showed that with-the-rule of total astigmatism : -0.92D, with-the-rule of corneal astigmatism : -1.12D, against-the-rule of residual astigmatism : -0.87D were found most respectively. In the near distance, The correlation between corneal astigmatism and total astigmatism was y=0.6872 x + 0.5934 r=0.6204, residual astigmatism and total astigmatism was y=0.303 x - 0.6066 r=0.3165, corneal astigmatism and residual astigmatism was y=-0.46 x - 0.0626 r=-0.5322. When the fixation point moved far distance to near distance, the differences of power according to the type of astigmatism were total astigmatism: $-0.07D{\pm}0.44D$, corneal astigmatism: $-0.04D{\pm}0.54D$ residual astigmatism:$0.01D{\pm}0.53D$. Most of astigmatism refractive power was increased except for oblique-the -astigmatism. When the fixation point moved far distance to near distance, the change of astigmatism refractive power showed total astigmatism: 540 eyes(33.7%), corneal astigmatism: 638 eyes(39.9%), residual: 841 eyes(52.6%).

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.4
• /
• pp.923-932
• /
• 1997

In this paper, we propose a two-level hybrid signature file method(THM) to dffciently deal with large txt databases that use a term discrimination concept.In addition, we apply Yoo's clustering scheme to the two-level hybeid signature file method. The clustering schme groups similar signatures together according to the similarity of the highly discriminatiory tems so that we may achive better performance on retrival. The space-time ana-lyhtical model of the proposed two-level hybrid method is provided. Based on the analytical model and experiments, we compare it with the exsting methods, i.e. the bit-sliced method(BM), the-level method(TM), and the hybrid method(HM). As a result, we show that THM achives the best retrival performance in a large database with 100,000 records when the mumber fo matching records is less than 160.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.3
• /
• pp.61-69
• /
• 2015

This study presents a probabilistic knowledge discovery method to interpret heart rate variability (HRV) based on time and frequency domain indexes, extracted using discrete wavelet transform. The knowledge induction algorithm was composed of two phases: rule generation and rule estimation. Firstly, a rule generation converts numerical attributes to intervals using ROC curve analysis and constructs a reduced ruleset by comparing consistency degree between attribute-value pairs with different decision values. Then, we estimated three measures such as rule support, confidence, and coverage to a probabilistic interpretation for each rule. To show the effectiveness of proposed model, we evaluated the statistical discriminant power of five rules (3 for atrial fibrillation, 1 for normal sinus rhythm, and 1 for both atrial fibrillation and normal sinus rhythm) generated using a data (n=58) collected from 1 channel wireless holter electrocardiogram (ECG), i.e., HeartCall$^{(R)}$, U-Heart Inc. The experimental result showed the performance of approximately 0.93 (93%) in terms of accuracy, sensitivity, specificity, and AUC measures, respectively.

• Korean Journal of Applied Biomechanics
• /
• v.18 no.2
• /
• pp.19-27
• /
• 2008

The purpose of this study was to investigate of assessment of the ability of balance control using COP 95% confidence ellipse area while executing single-leg stance with eyes open and eyes closed through GRF system. The subjects participated in this study were 7 female yoga group and 7 female control group. The yoga training affected to improve the ability of balance control because the yoga group's COP AP and ML standard deviation and COP 95% confidence ellipse area were smaller than control group in both a single-leg stance with eyes open and eyes closed. Visual affected to the ability of balance control in a single-leg stance. I consider COP 95% confidence ellipse area as a high variable for determining the ability of balance control, and therefore suggest that additional studies for various groups and subjects will be required in the future.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.2
• /
• pp.31-47
• /
• 2013

The purpose of this study is to develop a measurement tool for self-image of the teacher librarian by semantic differential meaning scale and to analyse the correlation between their self-image and individual characteristics. This study suggests that the teacher librarians have regarded themselves as friendly, planned, sensitive and cooperative persons as well as persons with discernment. On the other hand, there are some negative self-images such as partial, poor and uninfluential persons plus disregarder and a reserved persons. The educational career of teacher librarians' background has influence on evaluation area of the self-image. This result shows that senior teacher librarians' role performance as a adviser or a leader is very important. So mediator role of KLA and KSLA has to be reinforced to beat the exchange and collaboration between the senior and the junior teacher librarians. It is necessary to appoint the teacher librarians obligatorily in oder to feel their professional security and sense of achievement, also to appreciate expertise of them through role clarification among the human resources of the school library.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.681-687
• /
• 2001

In order to raise a class discrimination power by combining multiple classifiers under the Bayesian decision theory, the upper bound of a Bayes error rate bounded by the conditional entropy of a class variable and decision variables obtained from training data samples should be minimized. Wang and Wong proposed a tree dependence first-order approximation scheme of a high order probability distribution composed of the class and multiple feature pattern variables for minimizing the upper bound of the Bayes error rate. This paper presents an extended high order product approximation scheme dealing with higher order dependency more than the first-order tree dependence, based on the minimization of the upper bound of the Bayes error rate. Multiple recognizers for unconstrained handwritten numerals from CENPARMI were combined by the proposed approximation scheme using the Bayesian formalism, and the high recognition rates were obtained by them.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.8
• /
• pp.372-377
• /
• 2008

Multiclass cancer classification has been actively investigated based on gene expression profiles, where it determines the type of cancer by analyzing the large amount of gene expression data collected by the DNA microarray technology. Since gene expression data include many genes not related to a target cancer, it is required to select informative genes in order to obtain highly accurate classification. Conventional rank-based gene selection methods often use ideal marker genes basically devised for binary classification, so it is difficult to directly apply them to multiclass classification. In this paper, we propose a novel method for multiclass gene selection, which does not use ideal marker genes but directly analyzes the distribution of gene expression. It measures the class-discriminability by discretizing gene expression levels into several regions and analyzing the frequency of training samples for each region, and then classifies samples by using the naive Bayes classifier. We have demonstrated the usefulness of the proposed method for various representative benchmark datasets of multiclass cancer classification.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.808-816
• /
• 2012

Face recognition has been actively studied and developed in various fields. In recent years, interest point extraction algorithms mainly used for object recognition were being applied to face recognition. The SURF(Speeded Up Robust Features) algorithm was used in this paper which was one of typical interest point extraction algorithms. Generally, the interest points extracted from human faces are less distinctive than the interest points extracted from objects due to the similar shapes of human faces. Thus, the accuracy of the face recognition using SURF tends to be low. In order to improve it, we propose a face recognition algorithm which performs interest point extraction by SURF and the Gabor wavelet transform to extract descriptors from the interest points. In the result, the proposed method shows around 23% better recognition accuracy than SURF-based conventional methods.