• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2013

In this paper, we propose a video summarization technique on a smartphone, based on spatiotemporal saliency. The proposed technique detects scene changes by computing the difference of the color histogram, which is robust to camera and object motion. Then the similarity between adjacent frames, face region, and frame saliency are computed to analyze the spatiotemporal saliency in a video clip. Over-segmented hierarchical tree is created using scene changes and is updated iteratively using mergence and maintenance energies computed during the analysis procedure. In the updated hierarchical tree, segmented frames are extracted by applying a greedy algorithm on the node with high saliency when it satisfies the reduction ratio and the minimum interval requested by the user. Experimental result shows that the proposed method summaries a 2 minute-length video in about 10 seconds on a commercial smartphone. The summarization quality is superior to the commercial video editing software, Muvee.

• Korean Journal of Plant Resources
• /
• v.15 no.1
• /
• pp.43-49
• /
• 2002

Effects of BA treatment and cut planting methods on shooting and seedling characteristics were investigated to increase seedling products by cuttings of lacquer tree. Dipping on 1,000mg/L BA solution was better than dripping with same solution at 5 weeks after cut planting. As shooting rate was increased suddenly, it was 85％ at 10 weeks after cut planting. Among 3 dripping treatments, interval was not effective on shooting rate. Dripping per 2 days with 100 ㎕ of 1,000 mg/L BA solution was most effective on seedling height and leaf number and than dipping was more effective than dripping per 5 and 7 days. Branch developed on near part from dripped scion. Shooting of horizontal planting was earlier about a week and rate was increased suddenly from 3 to 6 weeks, it was highest with 96％ than others at 10 weeks after planting. Seedling of horizontal cut planting was tallest about 40cm and branch developed lower than vertical and oblique cut planting. In case of horizontal cut planting, 2-3 shoots were formed on different part of scion and than those were could divided to seedling, so horizontal cut planting was most effective to propagation of seedling than any others.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12B
• /
• pp.1058-1065
• /
• 2008

In the Internet, as computer resource is developed, multimedia data request being increase more and more. It is effective way that process both high capacity-data and real-time data. Overlay Multicast is an effective method for efficient utilization of system resources and network bandwidth without using hardware customization. Overlay Multicast is an effective method for multimedia data service to multi-users. Multicast tree reconstruction is required when a non-leaf host leaves or fails. In this paper, relay-frame interval is selected as revealed network-state with jitter. In our proposal, multi-user service control algorithm gives a delay effect in multimedia request time. The simulation results show that our proposal takes shorter period of time than the other algorithms to reconstruct a similar tree and that it is a more effective way to deal with a lot of nodes that have lost their multi-user nodes.

• Journal of the Korean Society for information Management
• /
• v.36 no.2
• /
• pp.57-77
• /
• 2019

Random Forest (RF), a representative ensemble technique, was applied to automatic classification of journal articles in the field of library and information science. Especially, I performed various experiments on the main factors such as tree number, feature selection, and learning set size in terms of classification performance that automatically assigns class labels to domestic journals. Through this, I explored ways to optimize the performance of random forests (RF) for imbalanced datasets in real environments. Consequently, for the automatic classification of domestic journal articles, Random Forest (RF) can be expected to have the best classification performance when using tree number interval 100~1000(C), small feature set (10%) based on chi-square statistic (CHI), and most learning sets (9-10 years).

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.2
• /
• pp.68-81
• /
• 2023

This study aims to establish a scenario based on the spacing and arrangement of the roadside trees to reduce heat waves and fine dust in cities that occurred during the urbanization process and to quantitatively analyze the degree of reduction. The ENVI-met 5.0.2v model, a micro-climate simulation program, was used to analyze the degree of improvement in the thermal environment and fine dust according to the roadside tree scenario. As a result of temperature analysis according to street tree spacing, the narrower the distance between roadside trees, the lower the temperature during the day as the number of planted trees increased, and a similar pattern was shown regardless of the distance between roadside trees in the morning and evening. In the case of fine dust emitted from the road, the concentration of fine dust increased slightly due to the increase in roadside trees, but the concentration of sidewalks where people walk increased slightly or there was no difference because of blocking fine dust on trees. The temperature according to the arrangement of street trees tended to decrease as the number of planted trees increased as the arrangement increased. However, not only the amount of trees but also the crown projected area was judged to have a significant impact on the temperature reduction because the temperature reduction was greater in the scenario of planting the same amount of trees and widening the interval of arrangement. In terms of the arrangement, the fine dust concentration showed a difference from the results according to the interval, suggesting that the fine dust concentration may change depending on the relationship between the main wind direction and the tree planting direction. By quantitatively analyzing the degree of thermal environment and fine dust improvement caused by roadside trees, this study is expected to promote policies and projects to improve the roadside environment efficiently, such as a basic plan for roadside trees and a project for wind corridor forests.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.40 no.4
• /
• pp.18-27
• /
• 2012

This paper proposes a management method for a coastal black pine forest landscape considering the parallax effect. For the study, 10 coastal black pine forests in Gangneung were investigated about the average width of the coastal forests, the average diameters, and the intervals of the pines. Categorizations were realized for the 3 types of scene(sea, field, mountain, residential area, commercial area), diameter(16cm, 22cm, 28cm) and interval(5m, 7m, 10m) to produce a total of 45 scenic simulations. An investigation was made on the scenic preferences using 45 simulation images with S.D, and Likert Scales. The results were as follows: According the comparison of scenic preferences, natural landscapes(sea, field, and mountain) ranked high among preferences, with fabricated landscapes(residential area, commercial area) ranked low. The highest scenic preferences were shown with the seascape and an interval of 7m between the trees. On the contrary, the interrelationship was very low between the visual quantity of the scenic's elements(green, sky, building, road etc.) and the scenic preferences. As the results of the factor analysis, the 3 sense factors of "Depth(78.0%)" "Diversity(l5.6%)" and "Spatiality(6.4%)" explained coastal scenic preferences. "Spatiality" showed significant differences at intervals of 5~7m, and 10m between trees. This shows coastal forest management based on the interval of 10m standard affecting scenic preference.

• Korean Journal of Environment and Ecology
• /
• v.6 no.2
• /
• pp.162-167
• /
• 1993

A mixed deciduous forest community in Mt. Sobaek was studied to determine the adequate number of plots of tree stratum for investigating forest community structure. Twenty l0m $\times$ l0m plots were set up iii the studied forest community, and species area curve. performance curve and statistical method were carried out. According to species-area curve, the minimal number of plots where a given percentage increase in number of plots produced less than the same percentage increase in number of species was eight. The minimal number of plots where a given percentage increase in number of plots produced less than the half of the percentage increase in number of plots was eleven. According to performance curve by importance value of the major species, the minimal number of plots where the dominant species was distinguished from the subdominant species was five. The minimal number of plots where the subdominant species was distinguished from each other was ten. Therefore, ten l0m $\times$ l0m plots seems to give an adequate sample for investigating structure of the studied forest community. Similarity index between the ten plots and total twenty plots was above 90%, and 95% confidence interval of species diversity of the ten plots was $\pm$ 0.073.

• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.83-101
• /
• 2005

Customer retention is one of the major issues in life insurance industry, in which competition is increasingly fierce. There are many things for the life insurers to do many things to retain the customers. One of those things is to make sure to keep in touch with all customers. When an insurance-planner resigned, his/her customers must be taken care of by some planner-assistants. This article outlines the design of Contact Scheduling System (CSS) that supports planner-assistants for contacting the customers. Planner-assistants are unable to share the resigned insurance-planner's experience and knowledge regarding the customer relationship management. The CSS developed by employing both Classification And Regression Tree (CART) technique and Sequential Pattern Mining (SPM) technique has a two-stage process. In the first stage, it segments the customers into eight groups by CART model. Then it generates contact scheduling information consisting of contact-purpose, contact-interval and contact-channel, according to the segment's typical contact pattern. Contact-purpose is derived by schedule-driven, event-driven, or business-rule-driven. Schedule-driven contact is determined by SPM model. In the operation of CSS in a realistic situation, it shows a practicality in supporting planner-assistants to keep in touch with the customers efficiently and effectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.83-97
• /
• 2021

Wireless sensors that make up the Wireless Sensor Network generally have extremely limited power and resources. The wireless sensor enters the sleep state at a certain interval to conserve power. The Sleep deflation attack is a deadly attack that consumes power by preventing wireless sensors from entering the sleep state, but there is no clear countermeasure. Thus, in this paper, using clustering-based binary search tree structure, the Sleep deprivation attack detection model is proposed. The model proposed in this paper utilizes one of the characteristics of both attack sensor nodes and normal sensor nodes which were classified using machine learning. The characteristics used for detection were determined using Long Short-Term Memory, Decision Tree, Support Vector Machine, and K-Nearest Neighbor. Thresholds for judging attack sensor nodes were then learned by applying the SVM. The determined features were used in the proposed algorithm to calculate the values for attack detection, and the threshold for determining the calculated values was derived by applying SVM.Through experiments, the detection model proposed showed a detection rate of 94% when 35% of the total sensor nodes were attack sensor nodes and improvement of up to 26% in power retention.

• Korean Journal of Radiology
• /
• v.23 no.4
• /
• pp.466-478
• /
• 2022

Objective: ¹⁸F-fluorodeoxyglucose (FDG) PET/CT is often used for detecting malignancy in patients with newly diagnosed hemophagocytic lymphohistiocytosis (HLH), with acceptable sensitivity but relatively low specificity. The aim of this study was to improve the diagnostic ability of ¹⁸F-FDG PET/CT in identifying malignancy in patients with HLH by combining ¹⁸F-FDG PET/CT and clinical parameters. Materials and Methods: Ninety-seven patients (age ≥ 14 years) with secondary HLH were retrospectively reviewed and divided into the derivation (n = 71) and validation (n = 26) cohorts according to admission time. In the derivation cohort, 22 patients had malignancy-associated HLH (M-HLH) and 49 patients had non-malignancy-associated HLH (NM-HLH). Data on pretreatment ¹⁸F-FDG PET/CT and laboratory results were collected. The variables were analyzed using the Mann-Whitney U test or Pearson's chi-square test, and a nomogram for predicting M-HLH was constructed using multivariable binary logistic regression. The predictors were also ranked using decision-tree analysis. The nomogram and decision tree were validated in the validation cohort (10 patients with M-HLH and 16 patients with NM-HLH). Results: The ratio of the maximal standardized uptake value (SUVmax) of the lymph nodes to that of the mediastinum, the ratio of the SUVmax of bone lesions or bone marrow to that of the mediastinum, and age were selected for constructing the model. The nomogram showed good performance in predicting M-HLH in the validation cohort, with an area under the receiver operating characteristic curve of 0.875 (95% confidence interval, 0.686-0.971). At an appropriate cutoff value, the sensitivity and specificity for identifying M-HLH were 90% (9/10) and 68.8% (11/16), respectively. The decision tree integrating the same variables showed 70% (7/10) sensitivity and 93.8% (15/16) specificity for identifying M-HLH. In comparison, visual analysis of ¹⁸F-FDG PET/CT images demonstrated 100% (10/10) sensitivity and 12.5% (2/16) specificity. Conclusion: ¹⁸F-FDG PET/CT may be a practical technique for identifying M-HLH. The model constructed using ¹⁸F-FDG PET/CT features and age was able to detect malignancy with better accuracy than visual analysis of ¹⁸F-FDG PET/CT images.