• 전자공학회논문지C
• /
• 제35C권10호
• /
• pp.59-68
• /
• 1998

데이터 마이닝의 목적은 유용한 패턴을 찾음으로써 데이터를 이해하는데 있으므로, 찾아진 패턴은 정확할뿐 아니라 이해하기 쉬워야한다. 따라서 정확하고 이해하기 쉬운 패턴을 추출하는 데이터 마이닝에 대한 연구가 필요하다. 본 논문에서는 퍼지 결정 트리를 이용한 효과적인 데이터 마이닝 알고리즘을 제안한다. 제안된 알고리즘은 ID3, C4.5와 같은 결정 트리 알고리즘의 이해하기 쉬운 장점과 퍼지의 표현력을 결합하여 간결하고 이해하기 쉬운 규칙을 생성한다. 제안된 알고리즘은 히스토그램에 기반하여 퍼지 소속함수를 생성하는 단계와 생성된 소속 함수를 이용하여 퍼지 결정 트리를 구성하는 두 단계로 이루어진다. 또한 제안된 방법의 타당성을 검증하기 위하여 표준적인 패턴 분류 벤치마크 데이터인 Iris 데이터와 Wisconsin Breast Cancer 데이터에 대한 실험 결과를 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4908-4928
• /
• 2017

Recent research into wireless sensor network (WSN)-related technology that senses various data has recognized the need for spatio-temporal queries for searching necessary data from wireless sensor nodes. Answers to the queries are transmitted from sensor nodes, and for the efficient transmission of the sensed data to the application server, research on index processing methods that increase accuracy while reducing the energy consumption in the node and minimizing query delays has been conducted extensively. Previous research has emphasized the importance of accuracy and energy efficiency of the sensor node's routing process. In this study, we propose an itinerary-based R-tree (IR-tree) to solve the existing problems of spatial query processing methods such as efficient processing and expansion of the query to the spatio-temporal domain.

• 한국경영과학회지
• /
• 제18권2호
• /
• pp.183-203
• /
• 1993

One of the most difficult and time-consuming stages in the development of the knowledge-based system is a knowledge acquisition. A splitting algorithm is developed to infer a rule-tree which can be converted to a rule-typed knowledge. A market segmentation may be performed in order to establish market strategy suitable to each market segment. As the sales data of a product market is probabilistic and noisy, it becomes necessary to prune the rule-tree-at an acceptable level while generating a rule-tree. A splitting algorithm is developed using the pruning measure based on a total amount of information gain and the measure of existing algorithms. A user can easily adjust the size of the resulting rule-tree according to his(her) preferences and problem domains. The algorithm is applied to a market segmentation problem of a medium-large computer market. The algorithm is illustrated step by step with a sales data of a computer market and is analyzed.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.642-645
• /
• 2007

Mounted in aircraft, LiDAR (Light Detection And Ranging) technology uses pulses of light to collect data about the terrain below. The main objective of this study was to extract reliable the individual tree and analysis techniques to facilitate the used LiDAR data for estimating tree crown diameter by measuring individual trees identifiable on the three dimensional LiDAR surface. In addition, this study can be quantitative analysis of individual tree through the canopy parameter.

• Bulletin of the Korean Chemical Society
• /
• 제30권11호
• /
• pp.2717-2722
• /
• 2009

The use of the classification and regression tree (CART) methodology was studied in a quantitative structure-activity relationship (QSAR) context on a data set consisting of the binding affinities of 39 imidazobenzodiazepines for the α1 benzodiazepine receptor. The 3-D structures of these compounds were optimized using HyperChem software with semiempirical AM1 optimization method. After optimization a set of 1481 zero-to three-dimentional descriptors was calculated for each molecule in the data set. The response (dependent variable) in the tree model consisted of the binding affinities of drugs. Three descriptors (two topological and one 3D-Morse descriptors) were applied in the final tree structure to describe the binding affinities. The mean relative error percent for the data set is 3.20%, compared with a previous model with mean relative error percent of 6.63%. To evaluate the predictive power of CART cross validation method was also performed.

• Journal of the Korean Data and Information Science Society
• /
• 제25권5호
• /
• pp.1137-1149
• /
• 2014

Since the bifurcating autoregressive (BAR) model was developed by Cowan and Staudte (1986) to analyze cell lineage data, a lot of research has been directed to BAR and its generalizations. Based mainly on the author's works, this paper is concerned with a contemporary review on the BAR in terms of an overview and perspectives. Specifically, bifurcating structure is extended to multi-cast tree and to branching tree structure. The AR(1) time series model of Cowan and Staudte (1986) is generalized to tree structured random processes. Branching correlations between individuals sharing the same parent are introduced and discussed. Various methods for estimating parameters and related asymptotics are also reviewed. Consequently, the paper aims to give a contemporary overview on the BAR model, providing some perspectives to the future works in this area.

• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.83-88
• /
• 2024

In this paper we used classification algorithms on social networking. We are proposing, a new classification algorithm called the improved Decision Tree (IDT). Our model provides better classification accuracy than the existing systems for classifying the social network data. Here we examined the performance of some familiar classification algorithms regarding their accuracy with our proposed algorithm. We used Support Vector Machines, Naïve Bayes, k-Nearest Neighbors, decision tree in our research and performed analyses on social media dataset. Matlab is used for performing experiments. The result shows that the proposed algorithm achieves the best results with an accuracy of 84.66%.

• 한국공간정보시스템학회 논문지
• /
• 제11권3호
• /
• pp.55-62
• /
• 2009

유비쿼터스 컴퓨팅 환경에서의 LBS, 즉 u-LBS는 실세계의 수많은 객체가 위치정보와 밀접히 연관된 대용량 데이타를 대상으로 한다. 특히, 사용자의 위치 정보와 관련하여 검색하려고 하는 객체인 POI에 대한 빠른 검색이 중요하다. 따라서 u-LBS에서 POI의 효율적인 검색을 위한 인덱스 구조에 대한 연구가 필요하다. 본 논문에서는 u-LBS에서 정적 POI를 대상으로 이를 효율적으로 검색하기 위한 DGR-Tree를 제시한다. DGR-Tree는 변형된 R-Tree를 기본 인덱스로 하고 동적 레벨 그리드를 보조 인덱스로 사용하는 구조이다. DGR-Tree는 점 데이타에 적합하도록 최적화하고 있으며 리프 노드 간 겹침 문제를 해결한다. DGR-Tree에서 동적 레벨 그리드는 점 데이타의 밀집도에 따라 동적으로 구성되며, 각 셀은 DGR-Tree의 리프 노드와 연계를 위한 포인터를 저장하여 리프 노드를 직접 접근하도록 함으로써 인덱스 접근 성능을 향상시킨다. 또한, 본 논문에서는 DGR-Tree를 위한 KNN 검색 알고리즘을 제시한다. 이 알고리즘에서는 KNN 검색 시 후보 셀에 빠르게 접근하기 위하여 동적 레벨 그 리드를 활용하며, 후보를 노드별로 구분하여 저장함으로써 후보 리스트 내에서의 정렬 비용을 감소시킨다. 마지막으로 실험을 통해 DGR-Tree의 우수성을 입증하였다.

• 한국환경복원기술학회지
• /
• 제22권5호
• /
• pp.1-12
• /
• 2019

It is important to measure the height of trees as an essential element for assessing the forest health in urban areas. Therefore, an automated method that can measure the height of individual tree as a three-dimensional forest information is needed in an extensive and dense forest. Since airborne LiDAR dataset is easy to analyze the tree height(z-coordinate) of forests, studies on individual tree height measurement could be performed as an assessment forest health. Especially in urban forests, that adversely affected by habitat fragmentation and isolation. So this study was analyzed to measure the height of individual trees for assessing the urban forests health, Furthermore to identify environmental factors that affect forest growth. The survey was conducted in the Mt. Bongseo located in Seobuk-gu. Cheonan-si(Middle Chungcheong Province). We segment the individual trees on coniferous by automatic method using the airborne LiDAR dataset of the two periods (year of 2016 and 2017) and to find out individual tree growth. Segmentation of individual trees was performed by using the watershed algorithm and the local maximum, and the tree growth was determined by the difference of the tree height according to the two periods. After we clarify the relationship between the environmental factors affecting the tree growth. The tree growth of Mt. Bongseo was about 20cm for a year, and it was analyzed to be lower than 23.9cm/year of the growth of the dominant species, Pinus rigida. This may have an adverse effect on the growth of isolated urban forests. It also determined different trees growth according to age, diameter and density class in the stock map, effective soil depth and drainage grade in the soil map. There was a statistically significant positive correlation between the distance to the road and the solar radiation as an environmental factor affecting the tree growth. Since there is less correlation, it is necessary to determine other influencing factors affecting tree growth in urban forests besides anthropogenic influences. This study is the first data for the analysis of segmentation and the growth of the individual tree, and it can be used as a scientific data of the urban forest health assessment and management.

• Journal of the Korean Statistical Society
• /
• 제25권1호
• /
• pp.1-24
• /
• 1996

In selecting a final tree, Breiman, Friedman, Olshen, and Stone(1984) compare the prediction risks of a pair of tree, where one contains the other, using the standard error of the prediction risk of the larger one. This paper proposes an approach to selection of a final tree by using the standard error of the difference of the prediction risks between a pair of trees rather than the standard error of the larger one. This approach is compared with CART's for simulated data from a simple regression model. Asymptotic results of the approaches are also derived and compared to each other. Both the asymptotic and the simulation results indicate that final trees by CART tend to be smaller than desired.