K-Means Clustering 알고리즘과 헤도닉 모형을 활용한 서울시 연립·다세대 군집분류 방법에 관한 연구 (A Study on the Clustering Method of Row and Multiplex Housing in Seoul Using K-Means Clustering Algorithm and Hedonic Model)
-
- 지능정보연구
- /
- 제23권3호
- /
- pp.95-118
- /
- 2017
최근 도심을 중심으로 연립 다세대의 거래가 활성화되고 직방, 다방등과 같은 플랫폼 서비스가 성장하고 있다. 연립 다세대는 수요 변화에 따른 시장 규모 확대와 함께 정보 비대칭으로 인해 사회적 문제가 발생 되는 등 부동산 정보의 사각지대이다. 또한, 서울특별시 또는 한국감정원에서 사용하는 5개 또는 25개의 권역 구분은 행정구역 내부를 중심으로 설정되었으며, 기존의 부동산 연구에서 사용되어 왔다. 이는 도시계획에 의한 권역구분이기 때문에 부동산 연구를 위한 권역 구분이 아니다. 이에 본 연구에서는 기존 연구를 토대로 향후 주택가 격추정에 있어 서울특별시의 공간구조를 재설정할 필요가 있다고 보았다. 이에 본 연구에서는 연립 다세대 실거래가 데이터를 기초로 하여 헤도닉 모형에 적용하였으며, 이를 K-Means Clustering 알고리즘을 사용해 서울특별시의 공간구조를 다시 군집하였다. 본 연구에서는 2014년 1월부터 2016년 12월까지 3년간 국토교통부의 서울시 연립 다세대 실거래가 데이터와 2016년 공시지가를 활용하였다. 실거래가 데이터에서 본 연구에서는 지하거래 제거, 면적당 가격 표준화 및 5이상 -5이하의 실거래 사례 제거와 같이 데이터 제거를 통한 데이터 전처리 작업을 수행하였다. 데이터전처리 후 고정된 초기값 설정으로 결정된 중심점이 매번 같은 결과로 나오게 K-means Clustering을 수행한 후 군집 별로 헤도닉 모형을 활용한 회귀분석을 하였으며, 코사인 유사도를 계산하여 유사성 분석을 진행하였다. 이에 본 연구의 결과는 모형 적합도가 평균 75% 이상으로, 헤도닉 모형에 사용된 변수는 유의미하였다. 즉, 기존 서울을 행정구역 25개 또는 5개의 권역으로 나뉘어 실거래가지수 등 부동산 가격 관련 통계지표를 작성하던 방식을 속성의 영향력이 유사한 영역을 묶어 16개의 구역으로 나누었다. 따라서 본 연구에서는 K-Means Clustering 알고리즘에 실거래가 데이터로 헤도닉 모형을 활용하여 연립 다세대 실거래가를 기반으로 한 군집분류방법을 도출하였다. 또한, 학문적 실무적 시사점을 제시하였고, 본 연구의 한계점과 향후 연구 방향에 대해 제시하였다.
본 연구의 목적은 용인시에 대한 생태발자국 지수 산정 및 변화분석을 통해 용인시의 환경용량 추이를 분석하고, 이를 바탕으로 용인시의 도시개발 및 계획의 방향을 제언하는 것이다. 이를 위하여 용인시를 대상으로 1993년, 2003년, 2013년에 걸친 생태발자국 지수 분석을 실시하였으며, 지수분석 결과를 바탕으로 용인시의 토지이용 변화와 개발패턴의 문제점에 대하여 분석하였다. 또한 GIS(Geographic Information System)를 기반으로 한 토지피복도와 생태발자국 지수의 비교를 통해 용인시 토지이용의 변화를 환경적 측면에서 분석하였다. 본 연구 결과는 다음의 세 가지로 요약될 수 있다. 첫째, 용인시의 총 생태발자국 지수는 1993년 3.20(gha), 2003년 6.50(gha), 2013년 11.15(gha)로 산정되었으며, 이는 용인시의 생태발자국이 세계적으로 요구되는 1인당 생태발자국 1.8(gha)는 물론, 한국 전체의 1인당 평균 생태발자국인 3.56(gha)을 훨씬 상회하는 수준으로, 지역 환경용량에 비해 과도한 자원소비가 이루어지고 있다는 것을 보여주고 있다. 둘째, 1993년부터 20여 년간 용인시의 생태발자국을 부문별로 분석한 결과, 산림부문의 생태발자국이 가장 크게 증가하였으며, 다음으로 에너지 부문, 음식 부문, 건조환경부문으로 순으로 나타났다. 특히, 산림 생태발자국의 경우 1993년에는 가장 낮은 0.002(gha)였으나, 2013년에는 7.32(gha)로 급증했으며, 에너지의 경우도 0.87(gha)에서 2.38(gha)로 비교적 높은 증가율을 보였다. 이는 급격한 도시개발로 인한 목재수요와 목재생산력의 지나친 불균형 및 주거와 상업용지 개발에 따른 에너지 수요의 급격한 증가에 기인하는 것으로 분석된다. 셋째, 지난 10여 년간 생태발자국과 산림 및 건조환경 토지피복의 변화를 관찰한 결과, 산림부문의 생태발자국이 가장 크게 확대되었으며, 실제 훼손된 산림면적 또한 증가된 건조환경 면적에 집중되어 있음을 알 수 있었다. 에너지 부문의 생태발자국 또한 급격한 증가를 보여주고 있는데, 이는 토지피복도 분석에서 알 수 있듯 건조환경부문, 특히 상업시설과 도로 및 철도용지의 급증에 크게 기인하는 것으로 분석되었다. 이는 향후 용인시가 개발 시 산림의 훼손을 최소화하고, 녹지면적을 확대해야 할 필요성을 제기하고 있으며, LPG 등 화석연료의 소비를 줄이는 대신 신재생에너지의 확대를 적극적으로 추진해야 한다는 근거를 제공할 수 있다.
Today most developed countries provide modern medical care for most of the population. The rural area is the more neglected area in the medical and health field. In public health, the philosophy is that medical care for in maintenance of health is a basic right of man; it should not be discriminated against racial, environmental or financial situations. The deficiency of the medical care system, cultural bias, economic development, and ignorance of the residents about health care brought about the shortage of medical personnel and facilities on the rural areas. Moreover, medical students and physicians have been taught less about rural health care than about urban health care. Medical care, therefore, is insufficient in terms of health care personnel/and facilities in rural areas. Under such a situation, there is growing concern about the health problems among the rural population. The findings presented in this report are useful measures of the major health problems and even more important, as a guide to planning for improved medical care systems. It is hoped that findings from this study will be useful to those responsible for improving the delivery of health service for the rural population. Objectives: -to determine the health status of the residents in the rural areas. -to assess the rural population's needs in terms of health and medical care. -to make recommendations concerning improvement in the delivery of health and medical care for the rural population. Procedures: For the sampling design, the ideal would be to sample according to the proportion of the composition age-groups. As the health problems would be different by group, the sample was divided into 10 different age-groups. If the sample were allocated by proportion of composition of each age group, some age groups would be too small to estimate the health problem. The sample size of each age-group population was 100 people/age-groups. Personal interviews were conducted by specially trained medical students. The interviews dealt at length with current health status, medical care problems, utilization of medical services, medical cost paid for medical care and attitudes toward health. In addition, more information was gained from the public health field, including environmental sanitation, maternal and child health, family planning, tuberculosis control, and dental health. The sample Sample size was one fourth of total population: 1,438 The aged 10-14 years showed the largest number of 254 and the aged under one year was the smallest number of 81. Participation in examination Examination sessions usually were held in the morning every Tuesday, Wenesday, and Thursday for 3 hours at each session at the Namchun Health station. In general, the rate of participation in medical examination was low especially in ages between 10-19 years old. The highest rate of participation among are groups was the under one year age-group by 100 percent. The lowest use rate as low as 3% of those in the age-groups 10-19 years who are attending junior and senior high school in Taegu city so the time was not convenient for them to recieve examinations. Among the over 20 years old group, the rate of participation of female was higher than that of males. The results are as follows: A. Publie health problems Population: The number of pre-school age group who required child health was 724, among them infants numbered 96. Number of eligible women aged 15-44 years was 1,279, and women with husband who need maternal health numbered 700. The age-group of 65 years or older was 201 needed more health care and 65 of them had disabilities. (Table 2). Environmental sanitation: Seventy-nine percent of the residents relied upon well water as a primary source of dringking water. Ninety-three percent of the drinking water supply was rated as unfited quality for drinking. More than 90% of latrines were unhygienic, in structure design and sanitation (Table 15). Maternal and child health: Maternal health Average number of pregnancies of eligible women was 4 times. There was almost no pre- and post-natal care. Pregnancy wastage Still births was 33 per 1,000 live births. Spontaneous abortion was 156 per 1,000 live births. Induced abortion was 137 per 1,000 live births. Delivery condition More than 90 percent of deliveries were conducted at home. Attendants at last delivery were laymen by 76% and delivery without attendants was 14%. The rate of non-sterilized scissors as an instrument used to cut the umbilical cord was as high as 54% and of sickles was 14%. The rate of difficult delivery counted for 3%. Maternal death rate estimates about 35 per 10,000 live births. Child health Consultation rate for child health was almost non existant. In general, vaccination rate of children was low; vaccination rates for children aged 0-5 years with BCG and small pox were 34 and 28 percent respectively. The rate of vaccination with DPT and Polio were 23 and 25% respectively but the rate of the complete three injections were as low as 5 and 3% respectively. The number of dead children was 280 per 1,000 living children. Infants death rate was 45 per 1,000 live births (Table 16), Family planning: Approval rate of married women for family planning was as high as 86%. The rate of experiences of contraception in the past was 51%. The current rate of contraception was 37%. Willingness to use contraception in the future was as high as 86% (Table 17). Tuberculosis control: Number of registration patients at the health center currently was 25. The number indicates one eighth of estimate number of tuberculosis in the area. Number of discharged cases in the past accounted for 79 which showed 50% of active cases when discharged time. Rate of complete treatment among reasons of discharge in the past as low as 28%. There needs to be a follow up observation of the discharged cases (Table 18). Dental problems: More than 50% of the total population have at least one or more dental problems. (Table 19) B. Medical care problems Incidence rate: 1. In one month Incidence rate of medical care problems during one month was 19.6 percent. Among these health problems which required rest at home were 11.8 percent. The estimated number of patients in the total population is 1,206. The health problems reported most frequently in interviews during one month are: GI trouble, respiratory disease, neuralgia, skin disease, and communicable disease-in that order, The rate of health problems by age groups was highest in the 1-4 age group and in the 60 years or over age group, the lowest rate was the 10-14 year age group. In general, 0-29 year age group except the 1-4 year age group was low incidence rate. After 30 years old the rate of health problems increases gradually with aging. Eighty-three percent of health problems that occured during one month were solved by primary medical care procedures. Seventeen percent of health problems needed secondary care. Days rested at home because of illness during one month were 0.7 days per interviewee and 8days per patient and it accounts for 2,161 days for the total productive population in the area. (Table 20) 2. In a year The incidence rate of medical care problems during a year was 74.8%, among them health problems which required rest at home was 37 percent. Estimated number of patients in the total population during a year was 4,600. The health problems that occured most frequently among the interviewees during a year were: Cold (30%), GI trouble (18), respiratory disease (11), anemia (10), diarrhea (10), neuralgia (10), parasite disease (9), ENT (7), skin (7), headache (7), trauma (4), communicable disease (3), and circulatory disease (3) -in that order. The rate of health problems by age groups was highest in the infants group, thereafter the rate decreased gradually until the age 15-19 year age group which showed the lowest, and then the rate increased gradually with aging. Eighty-seven percent of health problems during a year were solved by primary medical care. Thirteen percent of them needed secondary medical care procedures. Days rested at home because of illness during a year were 16 days per interviewee and 44 days per patient and it accounted for 57,335 days lost among productive age group in the area (Table 21). Among those given medical examination, the conditions observed most frequently were respiratory disease, GI trouble, parasite disease, neuralgia, skin disease, trauma, tuberculosis, anemia, chronic obstructive lung disease, eye disorders-in that order (Table 22). The main health problems required secondary medical care are as fellows: (previous page). Utilization of medical care (treatment) The rate of treatment by various medical facilities for all health problems during one month was 73 percent. The rate of receiving of medical care of those who have health problems which required rest at home was 52% while the rate of those who have health problems which did not required rest was 61 percent (Table 23). The rate of receiving of medical care for all health problems during a year was 67 percent. The rate of receiving of medical care of those who have health problems which required rest at home was 82 percent while the rate of those who have health problems which did not required rest was as low as 53 percent (Table 24). Types of medical facilitied used were as follows: Hospital and clinics: 32-35% Herb clinics: 9-10% Drugstore: 53-58% Hospitalization Rate of hospitalization was 1.7% and the estimate number of hospitalizations among the total population during a year will be 107 persons (Table 25). Medical cost: Average medical cost per person during one month and a year were 171 and 2,800 won respectively. Average medical cost per patient during one month and a year were 1,109 and 3,740 won respectively. Average cost per household during a year was 15,800 won (Table 26, 27). Solution measures for health and medical care problems in rural area: A. Health problems which could be solved by paramedical workers such as nurses, midwives and aid nurses etc. are as follows: 1. Improvement of environmental sanitation 2. MCH except medical care problems 3. Family planning except surgical intervention 4. Tuberculosis control except diagnosis and prescription 5. Dental care except operational intervention 6. Health education for residents for improvement of utilization of medical facilities and early diagnosis etc. B. Medical care problems 1. Eighty-five percent of health problems could be solved by primary care procedures by general practitioners. 2. Fifteen percent of health problems need secondary medical procedures by a specialist. C. Medical cost Concidering the economic situation in rural area the amount of 2,062 won per residents during a year will be burdensome, so financial assistance is needed gorvernment to solve health and medical care problems for rural people.
The objective of this research is to test the feasibility of developing a statewide truck traffic forecasting methodology for Wisconsin by using Origin-Destination surveys, traffic counts, classification counts, and other data that are routinely collected by the Wisconsin Department of Transportation (WisDOT). Development of a feasible model will permit estimation of future truck traffic for every major link in the network. This will provide the basis for improved estimation of future pavement deterioration. Pavement damage rises exponentially as axle weight increases, and trucks are responsible for most of the traffic-induced damage to pavement. Consequently, forecasts of truck traffic are critical to pavement management systems. The pavement Management Decision Supporting System (PMDSS) prepared by WisDOT in May 1990 combines pavement inventory and performance data with a knowledge base consisting of rules for evaluation, problem identification and rehabilitation recommendation. Without a r.easonable truck traffic forecasting methodology, PMDSS is not able to project pavement performance trends in order to make assessment and recommendations in the future years. However, none of WisDOT's existing forecasting methodologies has been designed specifically for predicting truck movements on a statewide highway network. For this research, the Origin-Destination survey data avaiiable from WisDOT, including two stateline areas, one county, and five cities, are analyzed and the zone-to'||'&'||'not;zone truck trip tables are developed. The resulting Origin-Destination Trip Length Frequency (00 TLF) distributions by trip type are applied to the Gravity Model (GM) for comparison with comparable TLFs from the GM. The gravity model is calibrated to obtain friction factor curves for the three trip types, Internal-Internal (I-I), Internal-External (I-E), and External-External (E-E). ~oth "macro-scale" calibration and "micro-scale" calibration are performed. The comparison of the statewide GM TLF with the 00 TLF for the macro-scale calibration does not provide suitable results because the available 00 survey data do not represent an unbiased sample of statewide truck trips. For the "micro-scale" calibration, "partial" GM trip tables that correspond to the 00 survey trip tables are extracted from the full statewide GM trip table. These "partial" GM trip tables are then merged and a partial GM TLF is created. The GM friction factor curves are adjusted until the partial GM TLF matches the 00 TLF. Three friction factor curves, one for each trip type, resulting from the micro-scale calibration produce a reasonable GM truck trip model. A key methodological issue for GM. calibration involves the use of multiple friction factor curves versus a single friction factor curve for each trip type in order to estimate truck trips with reasonable accuracy. A single friction factor curve for each of the three trip types was found to reproduce the 00 TLFs from the calibration data base. Given the very limited trip generation data available for this research, additional refinement of the gravity model using multiple mction factor curves for each trip type was not warranted. In the traditional urban transportation planning studies, the zonal trip productions and attractions and region-wide OD TLFs are available. However, for this research, the information available for the development .of the GM model is limited to Ground Counts (GC) and a limited set ofOD TLFs. The GM is calibrated using the limited OD data, but the OD data are not adequate to obtain good estimates of truck trip productions and attractions .. Consequently, zonal productions and attractions are estimated using zonal population as a first approximation. Then, Selected Link based (SELINK) analyses are used to adjust the productions and attractions and possibly recalibrate the GM. The SELINK adjustment process involves identifying the origins and destinations of all truck trips that are assigned to a specified "selected link" as the result of a standard traffic assignment. A link adjustment factor is computed as the ratio of the actual volume for the link (ground count) to the total assigned volume. This link adjustment factor is then applied to all of the origin and destination zones of the trips using that "selected link". Selected link based analyses are conducted by using both 16 selected links and 32 selected links. The result of SELINK analysis by u~ing 32 selected links provides the least %RMSE in the screenline volume analysis. In addition, the stability of the GM truck estimating model is preserved by using 32 selected links with three SELINK adjustments, that is, the GM remains calibrated despite substantial changes in the input productions and attractions. The coverage of zones provided by 32 selected links is satisfactory. Increasing the number of repetitions beyond four is not reasonable because the stability of GM model in reproducing the OD TLF reaches its limits. The total volume of truck traffic captured by 32 selected links is 107% of total trip productions. But more importantly, ~ELINK adjustment factors for all of the zones can be computed. Evaluation of the travel demand model resulting from the SELINK adjustments is conducted by using screenline volume analysis, functional class and route specific volume analysis, area specific volume analysis, production and attraction analysis, and Vehicle Miles of Travel (VMT) analysis. Screenline volume analysis by using four screenlines with 28 check points are used for evaluation of the adequacy of the overall model. The total trucks crossing the screenlines are compared to the ground count totals. L V/GC ratios of 0.958 by using 32 selected links and 1.001 by using 16 selected links are obtained. The %RM:SE for the four screenlines is inversely proportional to the average ground count totals by screenline .. The magnitude of %RM:SE for the four screenlines resulting from the fourth and last GM run by using 32 and 16 selected links is 22% and 31 % respectively. These results are similar to the overall %RMSE achieved for the 32 and 16 selected links themselves of 19% and 33% respectively. This implies that the SELINICanalysis results are reasonable for all sections of the state.Functional class and route specific volume analysis is possible by using the available 154 classification count check points. The truck traffic crossing the Interstate highways (ISH) with 37 check points, the US highways (USH) with 50 check points, and the State highways (STH) with 67 check points is compared to the actual ground count totals. The magnitude of the overall link volume to ground count ratio by route does not provide any specific pattern of over or underestimate. However, the %R11SE for the ISH shows the least value while that for the STH shows the largest value. This pattern is consistent with the screenline analysis and the overall relationship between %RMSE and ground count volume groups. Area specific volume analysis provides another broad statewide measure of the performance of the overall model. The truck traffic in the North area with 26 check points, the West area with 36 check points, the East area with 29 check points, and the South area with 64 check points are compared to the actual ground count totals. The four areas show similar results. No specific patterns in the L V/GC ratio by area are found. In addition, the %RMSE is computed for each of the four areas. The %RMSEs for the North, West, East, and South areas are 92%, 49%, 27%, and 35% respectively, whereas, the average ground counts are 481, 1383, 1532, and 3154 respectively. As for the screenline and volume range analyses, the %RMSE is inversely related to average link volume. 'The SELINK adjustments of productions and attractions resulted in a very substantial reduction in the total in-state zonal productions and attractions. The initial in-state zonal trip generation model can now be revised with a new trip production's trip rate (total adjusted productions/total population) and a new trip attraction's trip rate. Revised zonal production and attraction adjustment factors can then be developed that only reflect the impact of the SELINK adjustments that cause mcreases or , decreases from the revised zonal estimate of productions and attractions. Analysis of the revised production adjustment factors is conducted by plotting the factors on the state map. The east area of the state including the counties of Brown, Outagamie, Shawano, Wmnebago, Fond du Lac, Marathon shows comparatively large values of the revised adjustment factors. Overall, both small and large values of the revised adjustment factors are scattered around Wisconsin. This suggests that more independent variables beyond just 226; population are needed for the development of the heavy truck trip generation model. More independent variables including zonal employment data (office employees and manufacturing employees) by industry type, zonal private trucks 226; owned and zonal income data which are not available currently should be considered. A plot of frequency distribution of the in-state zones as a function of the revised production and attraction adjustment factors shows the overall " adjustment resulting from the SELINK analysis process. Overall, the revised SELINK adjustments show that the productions for many zones are reduced by, a factor of 0.5 to 0.8 while the productions for ~ relatively few zones are increased by factors from 1.1 to 4 with most of the factors in the 3.0 range. No obvious explanation for the frequency distribution could be found. The revised SELINK adjustments overall appear to be reasonable. The heavy truck VMT analysis is conducted by comparing the 1990 heavy truck VMT that is forecasted by the GM truck forecasting model, 2.975 billions, with the WisDOT computed data. This gives an estimate that is 18.3% less than the WisDOT computation of 3.642 billions of VMT. The WisDOT estimates are based on the sampling the link volumes for USH, 8TH, and CTH. This implies potential error in sampling the average link volume. The WisDOT estimate of heavy truck VMT cannot be tabulated by the three trip types, I-I, I-E ('||'&'||'pound;-I), and E-E. In contrast, the GM forecasting model shows that the proportion ofE-E VMT out of total VMT is 21.24%. In addition, tabulation of heavy truck VMT by route functional class shows that the proportion of truck traffic traversing the freeways and expressways is 76.5%. Only 14.1% of total freeway truck traffic is I-I trips, while 80% of total collector truck traffic is I-I trips. This implies that freeways are traversed mainly by I-E and E-E truck traffic while collectors are used mainly by I-I truck traffic. Other tabulations such as average heavy truck speed by trip type, average travel distance by trip type and the VMT distribution by trip type, route functional class and travel speed are useful information for highway planners to understand the characteristics of statewide heavy truck trip patternS. Heavy truck volumes for the target year 2010 are forecasted by using the GM truck forecasting model. Four scenarios are used. Fo~ better forecasting, ground count- based segment adjustment factors are developed and applied. ISH 90 '||'&'||' 94 and USH 41 are used as example routes. The forecasting results by using the ground count-based segment adjustment factors are satisfactory for long range planning purposes, but additional ground counts would be useful for USH 41. Sensitivity analysis provides estimates of the impacts of the alternative growth rates including information about changes in the trip types using key routes. The network'||'&'||'not;based GMcan easily model scenarios with different rates of growth in rural versus . . urban areas, small versus large cities, and in-state zones versus external stations. cities, and in-state zones versus external stations.