• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1261-1269
• /
• 1999

다층 퍼셉트론은 다양한 응용 분야에 성공적으로 적용되고 있는 대표적인 신경회로망 모델이다. 그러나 다층 퍼셉트론의 학습에서 나타나는 플라토에 기인한 느린 학습 속도와 지역 극소는 실제 응용문제에 적용함에 있어서 가장 큰 문제로 지적되어왔다. 이 문제를 해결하기 위해 여러 가지 다양한 학습알고리즘들이 개발되어 왔으나, 계산의 비효율성으로 인해 실제 문제에는 적용하기 힘든 예가 많은 등, 현재까지 만족할 만한 해결책은 제시되지 못하고 있다. 본 논문에서는 다층퍼셉트론의 베이시스 함수로 사용되는 시그모이드 함수를 보다 일반화된 형태로 정의하여 사용함으로써 학습에 있어서의 플라토를 완화하고, 지역극소에 빠지는 것을 줄이는 접근방법을 소개한다. 본 방법은 기존의 변형된 가중치 수정식을 사용한 학습 속도 향상의 방법들과는 다른 접근 방법을 택함으로써 기존의 방법들과 함께 사용하는 것이 가능하다는 특징을 갖고 있다. 제안하는 방법의 성능을 확인하기 위하여 간단한 패턴 인식 문제들에의 적용 실험 및 기존의 학습 속도 향상 방법을 함께 사용하여 시계열 예측 문제에 적용한 실험을 수행하였고, 그 결과로부터 제안안 방법의 효율성을 확인할 수 있었다. Abstract A multilayer perceptron is the most well-known neural network model which has been successfully applied to various fields of application. Its slow learning caused by plateau and local minima of gradient descent learning, however, have been pointed as the biggest problems in its practical use. To solve such a problem, a number of researches on learning algorithms have been conducted, but it can be said that none of satisfying solutions have been presented so far because the problems such as computational inefficiency have still been existed in these algorithms. In this paper, we propose a new learning approach to minimize the effect of plateau and reduce the possibility of getting trapped in local minima by generalizing the sigmoidal function which is used as the basis function of a multilayer perceptron. Adapting a new approach that differs from the conventional methods with revised updating equation, the proposed method can be used together with the existing methods to improve the learning performance. We conducted some experiments to test the proposed method on simple problems of pattern recognition and a problem of time series prediction, compared our results with the results of the existing methods, and confirmed that the proposed method is efficient enough to apply to the real problems.

• Design Convergence Study
• /
• v.16 no.6
• /
• pp.169-184
• /
• 2017

There is a lot of needs that are not expressed as much as the expressed needs in familiar products and services that are used in daily life such as a smartphone. Finding the 'Inconveniences in familiar use' make it possible to create opportunities for value expanding in the existing products and service area. There are a lot of related works, which have studied the definition of hidden needs and the methods to find it. But, they are making it difficult to address the hidden needs in the cases of familiar use due to focus on the new product or service developing typically. In this study, we try to redefine the hidden needs in the daily familiarity and approach it in the new way to find out. Because of the users' unability to express what they want and the complexity of needs which can not be explained clearly, we can not approach it as the quantitative issue. For this reason, the basic data type selected as the user behavior data excluding all description is the screen-shot of the smartphone. We try to apply the integrated rules and patterns to the individual data using the qualitative coding techniques to overcome the limitations of qualitative analysis based on unstructured data. From this process, We can not only extract meaningful clues which can make to understand the hidden needs but also identify the possibility as a way to discover hidden needs through the review of relevance to actual market trends. The process of finding hidden needs is not easy to systemize in itself, but we expect the possibility to be conducted a reference frame for finding hidden needs of other further studies.

• Journal of Preventive Medicine and Public Health
• /
• v.11 no.1
• /
• pp.123-127
• /
• 1978

The major objective of this research is to identify those hospital characteristics that best explain cost variation among hospitals and to formulate linear models that can predict hospital costs. Specific emphasis is placed on hospital output, that is, the identification of diagnosis related patient groups (DRGs) which are medically meaningful and demonstrate similar patterns of hospital resource consumption. A casemix index is developed based on the DRGs identified. Considering the common problems encountered in previous hospital cost research, the following study requirements are estab-lished for fulfilling the objectives of this research: 1. Selection of hospitals that exercise similar medical and fiscal practices. 2. Identification of an appropriate data collection mechanism in which demographic and medical characteristics of individual patients as well as accurate and comparable cost information can be derived. 3. Development of a patient classification system in which all the patients treated in hospitals are able to be split into mutually exclusive categories with consistent and stable patterns of resource consumption. 4. Development of a cost finding mechanism through which patient groups' costs can be made comparable across hospitals. A data set of Medicare patients prepared by the Social Security Administration was selected for the study analysis. The data set contained 27,229 record abstracts of Medicare patients discharged from all but one short-term general hospital in Connecticut during the period from January 1, 1971, to December 31, 1972. Each record abstract contained demographic and diagnostic information, as well as charges for specific medical services received. The 'AUT-OGRP System' was used to generate 198 DRGs in which the entire range of Medicare patients were split into mutually exclusive categories, each of which shows a consistent and stable pattern of resource consumption. The 'Departmental Method' was used to generate cost information for the groups of Medicare patients that would be comparable across hospitals. To fulfill the study objectives, an extensive analysis was conducted in the following areas: 1. Analysis of DRGs: in which the level of resource use of each DRG was determined, the length of stay or death rate of each DRG in relation to resource use was characterized, and underlying patterns of the relationships among DRG costs were explained. 2. Exploration of resource use profiles of hospitals; in which the magnitude of differences in the resource uses or death rates incurred in the treatment of Medicare patients among the study hospitals was explored. 3. Casemix analysis; in which four types of casemix-related indices were generated, and the significance of these indices in the explanation of hospital costs was examined. 4. Formulation of linear models to predict hospital costs of Medicare patients; in which nine independent variables (i. e., casemix index, hospital size, complexity of service, teaching activity, location, casemix-adjusted death. rate index, occupancy rate, and casemix-adjusted length of stay index) were used for determining factors in hospital costs. Results from the study analysis indicated that: 1. The system of 198 DRGs for Medicare patient classification was demonstrated not only as a strong tool for determining the pattern of hospital resource utilization of Medicare patients, but also for categorizing patients by their severity of illness. 2. The wei틴fed mean total case cost (TOTC) of the study hospitals for Medicare patients during the study years was $11,27.02 with a standard deviation of $117.20. The hospital with the highest average TOTC ($1538.15) was 2.08 times more expensive than the hospital with the lowest average TOTC ($743.45). The weighted mean per diem total cost (DTOC) of the study hospitals for Medicare patients during the sutdy years was $107.98 with a standard deviation of $15.18. The hospital with the highest average DTOC ($147.23) was 1.87 times more expensive than the hospital with the lowest average DTOC ($78.49). 3. The linear models for each of the six types of hospital costs were formulated using the casemix index and the eight other hospital variables as the determinants. These models explained variance to the extent of 68.7 percent of total case cost (TOTC), 63.5 percent of room and board cost (RMC), 66.2 percent of total ancillary service cost (TANC), 66.3 percent of per diem total cost (DTOC), 56.9 percent of per diem room and board cost (DRMC), and 65.5 percent of per diem ancillary service cost (DTANC). The casemix index alone explained approximately one half of interhospital cost variation: 59.1 percent for TOTC and 44.3 percent for DTOC. Thsee results demonstrate that the casemix index is the most importand determinant of interhospital cost variation Future research and policy implications in regard to the results of this study is envisioned in the following three areas: 1. Utilization of casemix related indices in the Medicare data systems. 2. Refinement of data for hospital cost evaluation. 3. Development of a system for reimbursement and cost control in hospitals.

• Journal of Korean Society of Forest Science
• /
• v.70 no.1
• /
• pp.1-6
• /
• 1985

The purpose of this experiment lies in finding the most appropriate cutting condition of Taxus cuspidata Sieb. et Zucc. which has been considered valuable tree species in gardening. Statistical analysis was focused on the comparison of the average ratios of rooting between greenhouses and fields, based on the observation rooted autogenis. To conduct this survey, hardwood cutting of Taxus cuspidata Sieb. et Zucc. were performed at both places of experiment above on April 20, 1982 with rooting results calculated on October 31, 1982. After formation of cuttings, it was soaked in IBA 200 ppm for 12 hours and than put in a bed. A summary of the result is presented as follows; 1) Cutting at the greenhouse showed higher average rate of rooting than at fields. Same tendency was found regardless of the differences in treatment. 2) It was clear that IBA-treatment contributed remarkably to causing higher average rooting rate. As an evidence, when twenty centimeter cuttings were inserted sandy media, IBA-treated area resulted in eighty six percent of average rooting rate, as compared with only twenty three percent in nontreatment case. In case of field cutting, IBA-treatment brought about fifty three percent of rooting in comparison with eleven percent nontreatment. 3) When sandy soil, loam and brown soil were separately used as cutting media, the highest rooting rate was found in case of sandy soil, without any difference between the two experimental places above. 4) As a result of the analysis to seek the impact of the length of cuttings on rooting, the range of length form fifteen to twenty centimeter was apparently most appropriate. It was also found that the rate of rooting declined beyond twenty five centimeter. 5) Two kinds of rooting pattern were observed. One was the case that callus cell lump was created on the lower cut side of cuttings. Importantly, root radical were formed inside the lump to influence the germination of root system. The other relates to the case that adventitious root which look like lateral roots appeared at the stem region. In abstract, first, sandy soil was effectively recommended in case of hardwood cutting in April. Second, the most appropriate length of cuttings ranged between fifteen and twenty centimeters. Third, high density IBA treatment was clearly effective. Forth, for proper environmental management, both pre-disinfection of sail by sterilizer and maintenance of high relative humidity were essentially required.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.4
• /
• pp.101-110
• /
• 2020

This study was conducted through the analysis of literature and on-site research as a case study of 14 artists' gardens with traditional themes presented at the garden fair. With Focusing on the design process for determining traditional reproduction, the following characteristics and implications were derived by analyzing the design goals, selection of subjects for traditional reenactment, determination of methods for reproduction, and design stages of landscape components. First, the pattern of selecting traditional structures as subjects for reproduction in many artist gardens can be understood as an advantage of being suitable for narrow sites and having remarkable topic communicability. They directly delivered the design intent by adding the names of traditional structures such as Madang, Wool, Buttumak, Jangdokdae, Chuibyeong and Seokgasan. Works expressed indirectly, such as Wall, Korean Garden, Suwon, and Seoul craftsmen, have relatively weak topic communicability. There were also symbolic representations of objects to be reproduced, such as Seonbi, marginal spaces, and Pung-lyu. Second, while reproducing Hanok Madang, separate the gardens paved with grass and stone, the fortress wall of Suwon Hwaseong and the northwest Gongsimdon of the watchtower. Also the garden with a miniature version of the extraneous Yong-yeon and the garden, which was reproduced as a low decorative wall in the rest area based on Nakan-Eupseong Fortress, shows the need for a deep understanding of tradition. On the other hand, the reproducting works of choosing the location of the traditional garden, the Korean Garden showed the importance of systematic arrangement with the surrounding environment, the beauty of the space in the courtyard of Hanok, the beauty of the slowness enjoyed by the scholars and the reenactments of the Pung-lyu culture of Moonlight boating are not only imitating traditional structures but also spreading understanding of tradition to garden culture and sentiment. Third, there were many works that reconstructed the real-size traditional structure in a straightforward way in relation to design. The garden was divided into Chuibyeong and the living space was decorated with Buttumak, chimneys, and gardens, and facilities representing Gyeongbokgung Palace, Soswaewon, and Seoseokji were systemically arranged. However it recognized the importance of selecting the key design elements, constructing the elevation of the structure, and the sense of scale of the space from works that reproduced the large Suwon Hwaseong and Nakan-Eupseong in an abstract way. While there are examples gardens of Hanok yards and Bazawul, which are far from the original image among the gardens that chose the dismantling method, the Blank-space garden expressed only by a frame composed of cubes, and Seonbi's Sarangbang garden, that permeated the moonlight with many traditional structures are the positive examples. The Seoul Artisan Garden, Jikji Simche Garden and Pung-lyu Garden, which display modernly designed landscape components, need an explanation to understand the author's intention.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.19-31
• /
• 2023

The importance of barrier free is being highlighted worldwide. This study attempted to identify barrier-free research trends using text mining. Through this, it was intended to help with research and policies to create a barrier free environment. The analysis data is 227 papers published in domestic academic journals from 1996 when barrier free research began to 2022. The researcher converted the title, keywords, and abstract of an academic thesis into text, and then analyzed the pattern of the thesis and the meaning of the data. The summary of the research results is as follows. First, barrier-free research began to increase after 2009, with an annual average of 17.1 papers being published. This is related to the implementation guidelines for the barrier-free certification system that took effect on July 15, 2008. Second, results of barrier-free text mining i) As a result of word frequency analysis of top keywords, important keywords such as barrier free, disabled, design, universal design, access, elderly, certification, improvement, evaluation, and space, facility, and environment were searched. ii) As a result of TD-IDF analysis, the main keywords were universal design, design, certification, house, access, elderly, installation, disabled, park, evaluation, architecture, and space. iii) As a result of N-Ggam analysis, barrier free+certification, barrier free+design, barrier free+barrier free, elderly+disabled, disabled+elderly, disabled+convenience facilities, the disabled+the elderly, society+the elderly, convenience facilities+installation, certification+evaluation index, physical+environment, life+quality, etc. appeared in a related language. Third, as a result of the CONCOR analysis, cluster 1 was barrier-free issues and challenges, cluster 2 was universal design and space utilization, cluster 3 was Improving Accessibility for the Disabled, and cluster 4 was barrier free certification and evaluation. Based on the analysis results, this study presented policy implications for vitalizing barrier-free research and establishing a desirable barrier free environment.