• Journal of Korean Society of Rural Planning
• /
• v.17 no.3
• /
• pp.15-25
• /
• 2011

This paper is to contribute for management and restoration as a basic study of vegetation structure in Aemirang Hill, Nakdongjeongmaek. To verify the characteristics of vegetation structure, we set up 25 plots($100m^2$). The result of community analysis was used by TWINSPAN classification. The communities were classified 7 types i.e. Quercus variabilis community, Quercus mongolica community, Pinus densiflora community, Pinus densiflora-Quercus mongolica community, Q. mongolica-Quercus variabilis community, Quercus mongolica-Betula davurica community, Larix leptolepis community. Pinus densiflora community and Pinus densiflora-Quercus mongolica community are progressively transforming a Quercus mongolica community that is called Pinus densiflora next succession stage. Whereas the communities that has dominant Quercus variabilis and Quercus mongolica did not appear a next generation succession tree such as Carpinus laxiflora, Carpinus cordata in the under story and shrub layer. Therefore, Aemirang Hill's ecological succession was to maintain the status condition. Aemirang Hill's diversity index is 0.5738 to 0.8906. It were analyzed that diversity index was lower than other places.

• Journal of Korean Society of Rural Planning
• /
• v.19 no.2
• /
• pp.121-128
• /
• 2013

The greenhouse gas emission according to the energy consumption is the cause of global warming. With various climates, it is occurs the direct problems to ecosystem. The various studies are being to reduce the carbon dioxide, which accounts for more than 80% of the total greenhouse gas emissions. In this study, estimate the carbon usage using potential biomass extracted from forest type map according to land-use by satellite image, and estimate the amount of carbon dioxide, according to the energy consumption of urban area. The $CO_2$ adsorption is extracted by the amount of forest based on the direct absorption of tree, the other used investigated value. The $CO_2$ emission in Jecheon was 3,985,900 $TCO_2$ by energy consumption. At the land cover classification, the forest is analyzed as 624,085ha and the farmland is 148,700ha. The carbon dioxide absorption was estimated at 1,834,850 Tons from analyzed forest. In case of farmland, it was also estimated at 706,658 Tons.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.2
• /
• pp.151-156
• /
• 2001

We describe a new representation for learning concepts that differs from the traditional decision tree and rule induction algorithms. Our algorithm PROLEARN learns one or more prototype per class and follows instance based classification with them. Prototype here differs from psychological term in that we can have more than one prototype per concept and also differs from other instance based algorithms since the prototype is a "ficticious ideal example". We show that PROLEARN is as good as the traditional machine learning algorithms but much move stable than them in an environment that has noise or changing training set, what we call 'stability’.tability’.

• Journal of the Korean Institute of Rural Architecture
• /
• v.7 no.2
• /
• pp.56-63
• /
• 2005

This study is to provide basic research data of village composition and housing types of Central Java in Indonesia. So, I needed both field survey and research for 3 villages. I surveyed several houses cased on three village which located in two Desa of Salatica and one Desa of Purbowangi in rural area. The analysis of this research is divided into main categories as follow; The first is characteristics of village composition. And the second is classification of exterior form types and spatial composition of housing. Through this survey, the results of study are as follows. 1. The main elements of village compositions are public facilities, cross street including in naturalism, and shadow within high-rise tree. But it is not important to planning for orientation. 2. The types of house are 16 in all Indonesia land. But in this study 3 village are followed to Java style which has traditional roof style and clay tile material 지붕, 처마, conservation 3. Spatial composition of inner side is focused of living room-Ruang Tamu, and others are organized in small size. But recently new type of improved village house has rest room into living space.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2E
• /
• pp.17-24
• /
• 2001

In this paper, we propose the bootstrap and aggregating (bagging) vector quantization (VQ) classifier to improve the performance of the text-independent speaker recognition system. This method generates multiple training data sets by resampling the original training data set, constructs the corresponding VQ classifiers, and then integrates the multiple VQ classifiers into a single classifier by voting. The bagging method has been proven to greatly improve the performance of unstable classifiers. Through two different experiments, this paper shows that the VQ classifier is unstable. In one of these experiments, the bias and variance of a VQ classifier are computed with a waveform database. The variance of the VQ classifier is compared with that of the classification and regression tree (CART) classifier[1]. The variance of the VQ classifier is shown to be as large as that of the CART classifier. The other experiment involves speaker recognition. The speaker recognition rates vary significantly by the minor changes in the training data set. The speaker recognition experiments involving a closed set, text-independent and speaker identification are performed with the TIMIT database to compare the performance of the bagging VQ classifier with that of the conventional VQ classifier. The bagging VQ classifier yields improved performance over the conventional VQ classifier. It also outperforms the conventional VQ classifier in small training data set problems.

• ALGAE
• /
• v.24 no.4
• /
• pp.231-238
• /
• 2009

The genus Grateloupia is the largest with more than 96 currently recognized species in the family Halymeniaceae, but morphological features of the genus are highly homoplasious making species identification difficult. In this study, we analyzed rbcL gene from 34 samples collected in Korea and compared the haplotypes of Korean species with those already published. The rbcL tree confirmed the occurrence of eight species in Korea: G. asiatica, G. catenata, G. divaricata, G. elliptica, G. imbricata, G. lanceolata, G. subpectina, and G. turuturu. All, except G. asiatica and G.catenata, been introduced from their native northeastern Asian waters to Australasian, European, and North American waters. The introduced haplotypes of G. lanceolata in Europe and North America were absent in Korea, while haplotype sharing of G. turuturu in Korea and Europe was common. Further sampling will show a source population of each introduced species and also provide a correct list of Grateloupia from Korea, including the other remaining 11 species of the genus.

• Biomedical Science Letters
• /
• v.10 no.4
• /
• pp.485-493
• /
• 2004

In the current field of Medical Informatics, the information increases, and changes fast, so we can access the various data types which are ranged from text to image type. A small number of technician digitizes these data to establish database, but it is needed a lot of money and time. Therefore digitization by many end-users confronting data and establishment of searching database is needed to manage increasing information effectively. New data and information are taken fast to provide the quality of care, diagnosis which is the basic work in the medicine. And also It is needed the medical database for purpose of private study and novice education, which is tool to make various data become knowledge. However, current medical database is used and developed only for the purpose of hospital work management. In this study, using text input, file import and object images are digitized to establish database by people who are worked at the medicine field but can not expertise to program. Data are hierarchically constructed and then knowledge is established using a tree type database establishment method. Consequently, we can get data fast and exactly through search, apply it to study as subject-oriented classification, apply it to diagnosis as time-depended reflection of data, and apply it to education and precaution through function of publishing questions and reusability of data.

• Journal of Information Technology Application
• /
• v.3 no.2
• /
• pp.1-24
• /
• 2001

This purpose of this study is to drive important criteria for improving customer relationship of R institute using data mining techniques. The focus of this research is to consider patterns and interactions of research variables from research management database of R institute, and to classify the outside organizations and the inside organizations for research contract organizations, and to decide the directions of customer relationship management through analyzing the research type and research cost of research topics. In order to drive criteria variables through pattern analysis of the research database, decision tree algorithm is employed. The results show that determinant variables of 17 input variables are research period, overhead cost, R ＆ D cost as variables to classify the outside and inside contract organization.

• Korean Journal of Adult Nursing
• /
• v.16 no.2
• /
• pp.316-326
• /
• 2004

Purpose: The purpose of this study was to identify effects of a self-management program on self-efficacy and compliance in patients with CHF. Hypothesis: 1) Patients with CHF who are provided with a self-management program will show higher self-efficacy scores than a control group. 2) Patients who are provided with a self-management program will show higher compliance scores than a control group. Method: This study was designed as a nonequivalent non-synchronized pre-posttest control group. There were eight patients in the experimental group, and twelve in the control group. According to NYHA classification, all patients belonged under the classesII to IV. Data were collected using the instruments developed by the researchers. Data were analyzed using descriptive statistics and Mann Whitney U test. Result: There were significant differences in self-efficacy scores and compliance scores between the experimental and control group. Conclusion: By utilizing the program, patients were able to monitor their symptoms routinely, comply with therapeutic regimen, and feel better able to positively influence their disease. Therefore, better compliance means fewer readmissions of patients with CHF.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.209-212
• /
• 2001

본 논문에서는 text-to-speech 시스템에서 사용할 억양 모델을 위해 벡터 양자화(vector quantization) 방식을 이용한다. 어절 경계강도(break index)는 세단계로 분류하였고, CART(Classification And Regression Tree)를 사용하여 어절 경계강도의 예측 규칙을 생성하였다. 예측된 어절 경계강도를 바탕으로 운율구를 예측하였으며 운율구는 다섯 개의 억양 패턴으로 분류하였다. 하나의 운율구는 정점(peak)의 시간축, 주파수축 값과 이를 기준으로 한 앞, 뒤 기울기를 추출하여 네 개의 파라미터로 단순화하였다. 운율구에 대해서 먼저 운율구가 문장의 끝일 경우와 아닐 경우로 분류하고, 억양 패턴 다섯 개로 분류하여. 모두 10개의 운율구 set으로 나누었다. 그리고 네 개의 파라미터를 가지고 있는 운율구의 억양 패턴을 벡터 양자화 방식을 이용하여 분류(clusteing)하였다 운율의 변화가 두드러지는 조사와 어미는 12 point의 기본주파수 값을 추출하고 벡터 양자화하였다. 운율구와 조사 어미의 codebook index는 문장에 대한 특징 변수 값을 추출하고 CART를 사용하여 예측하였다. 합성할 때에는 입력 tort에 대해서 운율구의 억양 파라미터를 추정한 다음, 조사와 어미의 12 point 기본주파수 값을 추정하여 전체 억양 곡선을 생성하였고 본 연구실에서 제작한 음성합성기를 통해 합성하였다.