• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.652-662
• /
• 2023

Identifying highly discriminating genes is a critical step in tumor recognition tasks based on microarray gene expression profile data and machine learning. Gene selection based on tree models has been the subject of several studies. However, these methods are based on a single-tree model, often not robust to ultra-highdimensional microarray datasets, resulting in the loss of useful information and unsatisfactory classification accuracy. Motivated by the limitations of single-tree-based gene selection, in this study, ensemble gene selection methods based on multiple-tree models were studied to improve the classification performance of tumor identification. Specifically, we selected the three most representative tree models: ID3, random forest, and gradient boosting decision tree. Each tree model selects top-n genes from the microarray dataset based on its intrinsic mechanism. Subsequently, three ensemble gene selection methods were investigated, namely multipletree model intersection, multiple-tree module union, and multiple-tree module cross-union, were investigated. Experimental results on five benchmark public microarray gene expression datasets proved that the multiple tree module union is significantly superior to gene selection based on a single tree model and other competitive gene selection methods in classification accuracy.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.500-509
• /
• 2022

With the rapid development of educational informatization, teaching methods become diversified characteristics, but a large number of information data restrict the evaluation on teaching subject and object in terms of the effect of English education. Therefore, this study adopts the concept of incremental learning and eigenvalue interval algorithm to improve the weighted decision tree, and builds an English education effect evaluation model based on association rules. According to the results, the average accuracy of information classification of the improved decision tree algorithm is 96.18%, the classification error rate can be as low as 0.02%, and the anti-fitting performance is good. The classification error rate between the improved decision tree algorithm and the original decision tree does not exceed 1%. The proposed educational evaluation method can effectively provide early warning of academic situation analysis, and improve the teachers' professional skills in an accelerated manner and perfect the education system.

• 한국환경복원기술학회지
• /
• 제12권6호
• /
• pp.51-62
• /
• 2009

The purpose of this study is to analyze the profitability by selecting Pinus densiflora S. et Z. worthy of ornamental tree from among the cutting timber in the urban development project, and then presents the improvements. The study site is the whole area of Oedong-eup Gyeongju city Gyeongsangbuk-do and subject trees numbers are 2,180 trees. Analysis method is cost analysis because it is used generously pubic land development. In results, at first, in case of forest development currently cutting tree costs 7.3 million Won/ha. and no profit is occurred at all. Secondly, the forward direction order of tree treatments expenses are in sawdust production, selling lumber, selling ornamental tree, and selling ornamental tree, sawdust production, selling lumbered on the aspect of profits by the selling stumpage. Especially, selling trees as ornamental tree costs 127 million Won/ha. which shows the highest profits. Third, the management of ornamental tree pine tree after transplantation from development site costs 5 times less than purchasing the same quality trees. Hence, it is recommended to re-utilize the trees from the development sites to produce a high standard gardens and it also provides the basis for the low carbon green growth society.

• 한국환경과학회지
• /
• 제32권1호
• /
• pp.11-24
• /
• 2023

This study aimed to provide preliminary data for the improvement of the tree doctor qualification test (first written test), which was newly created by enforcing the Forest Protection Act on June 28, 2018., The high demand for system improvement accelerated this study. The results were analyzeds through literature and questionnaire surveys. Writing test questions and the license of the tree doctor qualification exam are currently managed by the Korea Forestry Research Institute, and it is deemed that the test should be entrusted to Human Resources Development Service of Korea for fair and transparent management. Additionally, the plan for the improvement of the subject-wise scope of examination questions writing, difficulty of test questions, and acceptance rate of the first test should be prepared after public hearings or seminars related to the examination questions.

• 한국산업융합학회 논문집
• /
• 제27권2_2호
• /
• pp.333-341
• /
• 2024

The current public survey performance review extracts samples according to the set screening ratio, and examines the extracted samples to determine the suitability or inadequacy of the survey performance. The examiner directly judges the survey performance submitted by the performer, and extracts it in consideration of various field conditions and topography for each subject. However, it is necessary to secure fairness in the examination as it is extracted with different extraction methods for each subject and the judgment of the examiner. Accordingly, in order to automate sampling for public survey performance review, the detailed sampling criteria of the reviewer were investigated to prepare a volume calculation table, and the automation of sampling using Python was studied. In addition, by reviewing items that can and cannot be automated, the application of the automated decision tree algorithm of sampling was reviewed.

• 한국통신학회논문지
• /
• 제21권11호
• /
• pp.2886-2896
• /
• 1996

본 논문에서는 ATM망의 VP계층 망 상에서의 VC 연결에 대한 멀티캐스트 라우팅 알고리즘인 CMTVD(Constrained Multicast Tree with Virtual Destination) 알고리즘을 제안한다. CMTVD 멀티캐스트 라우팅 알고리즘은 서비스 유형에 따라 달라지는 제한사항을 반영하여 경로를 할당하되, 여러 목적 노드 그룹들간에 경로가 최대한 공유될 수 있도록 하여 총 링크 사용을 최소화할 수 있도록 한 휴리스틱 알고리즘이다. 소스노드와 목적노드들 및 가상목적 노드들로 구성되는 최소 비용 스타이너 트리를 구하는데, 연결가지를 추가시킬 때마다 서비스 유형에 따른 제한사항을 가중치로 반영한다. 지연에 민감한 실시간 서비스에 대해서는 최대 허용 지연을 초과하지 않도록 가급적 지연이 작은 연결가지를 선택하고, 비실시간 서비스에 대해서는 망에 부하가 분산되도록 하는 연결가지를 선택한다. 시뮬레이션 결과에 의하면 CMTVD 알고리즘은 망의 노드수가 증가하고 목적노드 그룹 수가 크며 그들이 집중화되어 있을수록 CMT(Constrained Multicast Tree) 알고리즘에 비해 더 나은 경로를 찾는데, 경로 비용 성능이 약 10% ~ 15% 정도 개선되었다. 본 논문에서는 ATM 망을 VP 계층에서 가상 멀티캐스트망으로 재구성하고 연결가지의 비용함수를 선택 가능한 경로들간의 상대적 비용요소만을 고려하여 단순화함으로써 복잡도를 줄여 실제 환경에 사용할 수 있도록 고려하였다.

• 한국언어정보학회지:언어와정보
• /
• 제5권1호
• /
• pp.55-71
• /
• 2001

One of the controversial issues in English locative inversion (LI) construction( e. g. Under the tree sat a woman) has been the functional status of preverbal PP and postverbal NP, i.e. whether they are a subject, a complement, or filer (topic) Based on the distributional parallelisms between the PP and NP on the one hand and an ordinary subject and filler on the other this paper proposes that the PP has a dual function as a subject and filler, while the NP also has some subject properties that the PP does not have These mixed functional properties are analyzed in the theory of HPSG expecially with the versions recently developed by Sag(1997) Manning and Sag(1999) and Ginzburg and Sag(to appear). This analysis claims that the LI construction needs to satisfy two general, independent constraints head-subject- phrase and head-filler-phrase. This position suggests that the English LI construction is an instance of the peripheral phenomena whose construction specific constraint is inherited from more general core constraints. (Dongseo University)

• 한국지리정보학회지
• /
• 제7권4호
• /
• pp.1-14
• /
• 2004

본 연구에서는 GIS 응용에서 이동객체의 궤적을 인덱싱하기 위해 기존에 제안되었던 TB(Trajectory-Bundle)-트리의 성능을 개선시킬 수 있는 연결테이블(LinkTable:L-Table) 기반의 확장된 TB-트리(L-Table TB-Tree:LTB-Tree)를 제안하고 아울러 제안하는 색인기법의 성능평가를 위해 다음과 같은 사항을 고려한다. 첫째, 기존의 R*-트리, TB-트리, 그리고 제안하는 LTB-트리를 성능평가 대상으로 선정한다. 둘째, 실험 데이타 집합으로는 랜덤 데이타 집합 및 실제 데이타 집합을 이용한다. 셋째, 시스템의 가용 메모리의 제약을 고려해 메모리 버퍼 크기에 따른 성능평가를 수행한다. 넷째, 다양한 데이타 분포도를 가지고 있는 실험 데이타를 이용하여 성능평가를 수행한다. 마지막으로 삽입성능 및 검색성능(궤적질의 및 영역질의)을 평가한다. 성능평가를 분석한 결과, 제안하는 색인기법이 기존의 색인기법들에 비해 삽입과 궤적질의의 검색 측면에서 더 우수함을 보인다.

• 한국조경학회지
• /
• 제17권2호
• /
• pp.1-14
• /
• 1989

The purpose of this study was to develop the principle of space composition in Jungja of a category of korean traditional space. The results which analyzed outside space, prospect angle and preference factors for landscape with making, Jungja which has artificially constructed pond within Gyeongbug province, the subject of study were as fellows ; Size of pond was quite different in each Jungja, and its form was retangular. There was built circle island or figured ten-long life within pond. These pursued harmony of the cosmic dual force or eternal youth. Average angle of depression and horizontal angle from floor of Jungja to pond were respectively 16$^{\circ}$ 23', 48$^{\circ}$ 26'. Average angle of depression to island in pond was 13$^{\circ}$28'. Average angle of depression from floor of Jungia to wall was 2$^{\circ}$58'. With controlling height of wall, there was maintained privacy and used borrowed landscape. Tree within garden was mainly planted a deciduous tall tree, the important species of tree were bamboo, pomegranate tree, crape myrtle, etc. Variables that gave influence on landscape preference degree were things about tree and pond. On prospecting pond, these variables-feeling for shore protection, impression for water, visual depth to pond feeling for shore protection, impression for water, visual depth to pond-gave Largely influences.

• 한국산림과학회지
• /
• 제97권5호
• /
• pp.501-507
• /
• 2008

The data of crown width with 4 directions, DBH, tree height, and coordinate for sample trees were collected from 30 permanent sample plots in secondary fore st of the Maoershan Experimental Forestry Farm, Northeast China. In this paper, the competition of individual trees in stand were discussed for secondary forest by using iterative Hegyi competition index and crown overlap index that represented the competitive and cooperative interactions among neighboring trees. Active competitors of subject tree in the competition zone were selected to calculate the iterative competition index. Using the results of crown classification based on the equal crown projection area, a new distance dependent competition index called crown overlap index (COI) was developed for secondary forest. The COI performed well in describing the crown competition rather than crown competition factor (CCF). The individual-based competition index discussed in this paper will provide more precise for developing individual tree growth models for secondary forest and it can also use to adjust the stand structure for spatial optimal management.