• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.1-3
• /
• 2015

In this paper, we propose a sparse signal reconstruction method referred to as the matching pursuit with a pruning-based tree search (PTS-MP). Two key ingredients of PTS-MP are the pre-selection to put a restriction on columns of the sensing matrix to be investigated and the tree pruning to eliminate unpromising paths from the search tree. In our simulations, we confirm that PTS-MP is effective in recovering sparse signals and outperforms conventional sparse recovery algorithms.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.427-430
• /
• 2018

본 논문에서는 오목을 두는 지능적 프로그램을 설계하고 구현하였다. 규칙은 렌주 룰(renju rule)을 기준으로 하였으며, $15{\times}15$ 게임 판에서 오목을 둔다. 초기에는 문제 분석을 통하여 분석된 가중치로 판단을 하여 판단을 하여 게임을 진행하도록 하였으나, 반복된 수행의 경험적 판단을 통하여 얻은 정보로 여러 차례 수정하며 고정된 가중치를 구성하고, 이 가중치를 게임에서 돌을 놓을 때 평가 기준으로 삼도록 하였으며, 최소-최대 게임 트리(min-max game tree)를 이용하여 상대가 있는 게임을 수행할 수 있도록 하였다. 또한 프로그램 자신에게 유리한 수를 찾기 위한 탐색에서 무의미한 노드들의 전개를 줄여 제한된 시간안에 좋은 수를 찾을 수 있도록 알파 베타 가지치기(alpha-beta pruning)를 사용하도록 프로그램을 구현하였다. 이렇게 구현된 오목 프로그램은 게임을 본 프로그램과 게임 하기 원하는 주변의 일반인들에게 90% 이상의 승률을 보이고 있었다.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.449-466
• /
• 2006

We propose to use variable selection methods based on penalized regression for pruning decision tree ensembles. Pruning methods based on LASSO and SCAD are compared with the cluster pruning method. Comparative studies are performed on some artificial datasets and real datasets. According to the results of comparative studies, the proposed methods based on penalized regression reduce the size of boosting ensembles without decreasing accuracy significantly and have better performance than the cluster pruning method. In terms of classification noise, the proposed pruning methods can mitigate the weakness of AdaBoost to some degree.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.4
• /
• pp.20-36
• /
• 2022

This study aims to provide basic data for high-quality street tree management by setting reasonable management items and appropriate unit prices by reviewing the adequacy of current street tree management. Currently, street tree management items, except for street tree pruning, use general landscape tree quantity per unit for the street tree management quantity per unit. KEPCO (Korea Electric Power Corporation) applied pruning items from standard electric production infrastructure and carried out the activities at an average unit price of 51% lower for heavy pruning and 39% lower for light pruning than the standard estimate. This was judged to be a level that could not maintain or increase the quality of street tree management. It was determined that an appropriate standard unit price for street tree management was necessary. To improve the quantity per unit for the proper management of street trees, it was necessary to review costs in the field. However, due to the absence of data on actual construction costs in the domestic landscape field, detailed items of the US RSMeans Building Construction Cost Data (RSMeans) were reviewed, and the actual construction costs were calculated by applying personal domestic expenses. As a result, the standard of the estimated unit showed a good ratio of 107% for heavy pruning of street tree pruning compared to the actual construction cost, but light pruning was underestimated with a 59% ratio. Shrub pruning was 82%, weeding was 92%, tree fertilization was 87%, and windbreak wall installation was 91% under-engineered. In addition, it was also confirmed that the watering by sprinkler trucks and chemical spraying were over-designed compared to the actual construction cost at the rates of 118% and 124%, respectively. Due to the specificity of the street trees, the increase in personal expenses and the input cost of equipment, such as road safety controls, were judged to be the main cause of the underestimation of items. Therefore, it is necessary to add items related to street trees and general landscape trees to the landscape maintenance items of the standard of the estimated unit.

• Korean Journal of Environmental Agriculture
• /
• v.40 no.2
• /
• pp.73-82
• /
• 2021

BACKGROUND: The successful management of jujube trees depends on maintaining a balance between reproductive and vegetative growth. In general, heading cuts of trunk stimulate rather vegetative growth, but could decrease flower initiation. This study was conducted to establish a heading-back pruning severities at planting in the one year old 'Daeneung' jujube whip nursery tree by investigating vegetative growth and fruit yield. METHODS AND RESULTS: The heading back pruning severity was assigned as 5 different ranges as follow: one bud (TR-10, heading back pruning was 10 cm above the ground), three buds (TR-30), five buds (TR-50), seven buds (TR-70), and nine buds (TR-90) were left of scion. The number of buds on whip trunk was correlated to the central leader length and increment of trunk cross-sectional area, negatively, and to the tree height and canopy volume, positively. The yields in the TR-50 treatment were higher about 2 times than other treatments. The fruit diameter was not significantly different among the treatments. CONCLUSION: These results indicated that the optimum location of heading-back pruning in one year old 'Daeneung' jujube tree was 50 cm above the ground as evaluated by the balance of reproductive and vegetative growth.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.26 no.2
• /
• pp.38-53
• /
• 1998

This study quantified annual net carbon uptake by urban landscape trees and provided equations to estimate it for Ginkgo biloba, platanus occidentalis, Zelkova serrata and Acer palmatum, based on measurement of exchange rate for two years growing seasons from Sep., 1995 to Aug., 1997. The carbon uptake was significantly influenced by photosynthetic capacity, photon flux density and pruning. Ginkgo biloba showed the highest rate of net CO\sub 2\ uptake per unit leaf area and Acer palmatum did the lowest rate among those species. A tree shaded by adjacent building over the growing seasons showed net CO\sub2\ uptake per unit leaf area much lower than another tree of the same species less shaded. Annual net carbon uptake per tree was 19kg for Zelkova serrata, but only 1 kg for Ginkgo biloba and Platanus occidentalis with crown volume dwarfed from pruning. One Zekoval serrata tree annually offset carbon emission from consumption of about 32 liter of gasoline or 83 kWh of electricity. Strategies to improve CO\sub 2\ uptake by urban landscape trees include planting of species with high potosynthetic capacity, sunlight-guaranteed road and building layout for street trees, planting of shade-tolerant species in the north of buildings, and relocation of utility lines to underground and minimized pruning.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.4
• /
• pp.264-273
• /
• 2016

This study was conducted to find out the influence of water stress from May to June on photosynthesis, shoot growth and fruit quality of apple trees. Fuji'/M.9 apple trees were root pruned at full bloom (30th April), parallel to the row of 30 cm or 60 cm from the trunk, to one side or both sides of trunk. The average value of afternoon leaf water potential from May to June of the no root pruning was maintained over -1.80 MPa, but that of root-pruning treatments was maintained under -1.80 MPa. In the comparison of average value of leaf water potential from May to June by root-pruning degree, the root pruning both sides at 30 cm from trunk was lowest (-2.06 MPa), followed by the root pruning both sides at 60 cm (-2.02 MPa) and the root pruning one side at 30 cm (-1.91 MPa). Root pruning one side at 30 cm or both sides at 60 cm reduced photosynthetic rate from May to June by 80% or 65%, respectively, compared with no root pruning. So, the degree of decreasing total shoot length or average fruit weight compare to the no root pruning of the root pruning one side at 30 cm was 25% or 11%, respectively, and those of the root pruning both sides at 30 cm was 45% or 15%, respectively. However, the soluble solid content and fruit color of the root pruning was higher than those of the no root pruning, and those of the root pruning both sides was higher than root pruning one side. These results indicate that the fruit enlargement was decreased when the average value of average leaf water potential from May to June was under -1.80 MPa, and the shoot growth was decreased when that was under -2.00 MPa.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.54-60
• /
• 2021

Monte-Carlo GO is a computer GO program that is sufficiently competent without using knowledge expressions of IGO. Although it is computationally intensive, the computational complexity can be reduced by properly pruning the IGO game tree. Here, I achieve this by using a potential model based on the knowledge expressions of IGO. The potential model treats GO stones as potentials. A specific potential distribution on the GO board results from a unique arrangement of stones on the board. Pruning using the potential model categorizes legal moves into effective and ineffective moves in accordance with the potential threshold. Here, certain pruning strategies based on potentials and potential gradients are experimentally evaluated. For different-sized boards, including an official-sized board, the effects of pruning strategies are evaluated in terms of their robustness. I successfully demonstrate pruning using a potential model to reduce the computational complexity of GO as well as the robustness of this effect across different-sized boards.

• Journal of Korean Society of Forest Science
• /
• v.105 no.1
• /
• pp.73-77
• /
• 2016

In this study, we examined the changes of fruit number and fruit weight according to the length of bearing branch of Actinidia arguta and identified the correlation the length of bearing branch and fruit characteristics. The fruit weight and the fruit number of A. arguta bearing branch which length are below 15 cm and over 30 cm were 11.7 g, 4.3 and 12.3 g, 13.8, respectively. From the results, the bearing brach which length was below 15 cm must be removed in winter season pruning. The pruning experiment was conducted to examine the effects on fruit quality and yield of A. arguta. Total fruit yield of heavy-pruning was $14.3{\pm}1.5kg/tree$. The production of fruits over 15 g wight was $8.2{\pm}0.9kg/tree$, that of fruits between 10 g to 15 g was $4.0{\pm}0.7kg/tree$, and that of fruit below 10 g was $2.1{\pm}0.3kg/tree$, respectively. Average fruit yield of nonpruning was $26.7{\pm}2.1kg/tree$, fruit yield over 15 g, between 10 g and 15 g, and below 10 g were $2.5{\pm}0.5kg/tree$, $19.2{\pm}1.4kg/tree$, and $5.0{\pm}0.6kg/tree$, respectively. Distribution of high quality fruit (over 15 g) showed that non-pruning was almost 15~16 g but pruning was evenly distributed between 15 g and 20 g. According to the survey, The high quality fruit (over 15 g) would not be harvested if the winter pruning is not applied in the A. arguta cultivation.