• Title/Summary/Keyword: input factors

Search Result 1,589, Processing Time 0.03 seconds

Estimation of Fractional Urban Tree Canopy Cover through Machine Learning Using Optical Satellite Images (기계학습을 이용한 광학 위성 영상 기반의 도시 내 수목 피복률 추정)

  • Sejeong Bae ;Bokyung Son ;Taejun Sung ;Yeonsu Lee ;Jungho Im ;Yoojin Kang
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.5_3
    • /
    • pp.1009-1029
    • /
    • 2023
  • Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R2 of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R2 of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

A Study on Measuring the Efficiency of Global Ocean Carriers by Using Data Envelopment Analysis (DEA를 활용한 글로벌해운선사의 효율성측정)

  • Bang, Hee-Seok;Kang, Hyo-Won
    • Journal of Korea Port Economic Association
    • /
    • v.27 no.1
    • /
    • pp.213-234
    • /
    • 2011
  • The literature on efficiency of the maritime and shipping industry has typically focused on container ports and terminals. The study presented in this paper uses data envelopment analysis to evaluate ocean carriers based on financial and operational data from 2004 to 2007. A comparison is made up of the efficiency of global ocean carriers in efficiency of financial and operational performance respectively. A positive correlation is shown between the input and output data. In the static-efficiency analysis, we describe CCR, BCC and scale efficiency of Global Ocean Carriers in 2007. And we also provide about the stability and trend of their efficiency for four years (2004-2007) in the dynamic-efficiency analysis. The empirical results validate the necessity of restoring freight rates to facilitate the efficiency of the global ocean carriers supported by adjust of the supply of containership space. The study provides a basis for estimating the competitiveness of international shipping companies, for benchmarking best practice and for identifying the specific factors and causes of inefficiency.

Fuzzy Optimal Reservoir Operation Considering Abnormal Flood (이상홍수를 고려한 퍼지 최적 저수지 운영)

  • Choi, Changwon;Yu, Myung Su;Yi, Jaeeung
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.32 no.4B
    • /
    • pp.221-232
    • /
    • 2012
  • In this study, the model enhancing the safety of reservoirs and reducing the downstream flood damage by reservoirs system operation during abnormal flood was developed. Linear programming was used for the optimal reservoirs system operation during an abnormal flood and fuzzy inference system was introduced to solve the uncertainty problem which is included in hydrological factors like inflow, water level and inflow variation of reservoir operation. The linear programming model determined the optimal reservoir system operation rules and could be used in situation where water demands varies rapidly during the abnormal flood events using fuzzy control technique. In this study, the optimal reservoirs system operation for Andong and Imha reservoirs located in the upper basin of Nakdong river was performed in order that the design flood discharge at Andong city would not be exceeded for the design flood of 100 year and PMF(Probable Maximum Flood). And the model that determines the release according to the downstream flow discharge, the reservoir storage, the inflow and the inflow variation of each reservoir was developed using the optimal system operation result and fuzzy control technique. The developed model consisted of 224 fuzzy rules according to the conditions of Andong reservoir, Imha reservoir and Andong city. And the release from each reservoir could be determined when the current data are used as input data through the developed GUI.

A Study on the Fire Reconstruction of Exterior on High-rise Building (Focus on Fire Case Including the Woosin Golden Suite in Haeundae) (고층 건축물 외장재의 화재 재현에 관한 연구 (해운대 우신골든스위트의 화재사례를 중심으로))

  • Min, Se-Hong;Lee, Jae-Moon
    • Fire Science and Engineering
    • /
    • v.27 no.2
    • /
    • pp.25-30
    • /
    • 2013
  • 'Heaundae Woosin Building' fire was the case that a fire breaking out on the $4^{th}$ floor spread out the $38^{th}$ floor which is a top story and the penthouse was destroyed by fire. After this fire, the fire safety for high rise buildings has been on the rise and several new laws and regulations related in the buildings were created. The study is to analyze Heaundae officetel building case using FDS which is one of the CFD programs for fire. The methodology of this study is to analyze the case comparing with fire spread and route from a virtual fire simulation and related articles and a video clip of actual scene fire. This study shows that a fire spreading on top of levels spent approximately 30 minutes and, which is similar to the actual fire case. Also the pattern of spread has similarity with the case. However, even if the actual fire case shows the fire pattern was "V shape", the smoke-view presents the fire dose not spread horizontally as much as the real fire case. The result shows uncertainty of the modeling based on many grids and a limitation of putting interior finish input sources and the direction of the wind might cause the difference. Also, to analyze factors influencing on a vertical fire, another fire modeling is performed by in condition of modeling environment considering concrete interior finish between buildings and no wind. The result presents the fire spread in smoke-view does not spread vertically as much as the actual case.

Development of the Decision-Making System for National Highway Pavement Management (국도 포장관리를 위한 의사결정시스템 개발)

  • Do, Myungsik;Kwon, Sooahn;Lee, Sang Hyuk;Kim, Yongjoo
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.34 no.2
    • /
    • pp.645-654
    • /
    • 2014
  • PMS (Pavement Management System) of National highways in Korea has used HDM (Highway Development and Management)-4 developed by World Bank for decision-making for maintenance and rehabilitation of pavements. However using HDM-4 is not appropriate in Korea because HDM-4 requires excessive input factors for analysis and economic analysis models loaded in HDM-4 are not suitable for Korean circumstances. Thus this study aims development of decision-making system for effective pavement management with reflecting Korean circumstances. Moreover this study proposed to define component of system, deterioration models, and basic units for component, and to analyze characteristics of component of system, and also to develop optimal decision-making system. The decision-making system for PMS mainly consists of 1) DB of highways, traffics, and socio-economic index, 2) pavement deterioration model, 3) speed prediction models by pavement conditions, 4) economic evaluation models, and 5) decision-making supporting system. Also this study provided analysis results in case studies for system verifications. However pavement deterioration models considering future probabilistic characteristic and index of decision-making are needed to develop for a further study.

An Investigation of the Effect of Government Subsidy Scheme to Bus Industry on the Efficiency of Inner-City Bus Route System (버스 재정지원체계 변화가 버스노선 효율성에 미치는 영향 분석)

  • Jung, Byung Doo;Kim, Kyoung Sik;Kim, Ki Hyuk
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.33 no.6
    • /
    • pp.2455-2464
    • /
    • 2013
  • This study is focused on the effect of reformation of public transportation system on the efficiency of bus route system as a result of change of government subsidy scheme. Two types of government subsidy scheme has been considered and before and after analysis by Data Envelopment Analysis technique has been carried out for bus routes in Ulsan Metropolitan City. The analysis output has shown that there is no clear evidence to clarify the relationship between the change of government subsidy scheme and the efficiency of bus route system. There are two types of backgrounds may be suggested for this situation such as more longer period necessary to identify the policy effect and limitation to increase the number of passenger in a provincial city. Tobit regression analysis has also been conducted to discover the most effective variables for maximum efficiency and three variables including route length, frequency per vehicle per day, and headway are found to be influential. It is also seen that strategy to minimising input factors and service upgrade plan such as shortened route length and headway, increasing frequency per vehicle are necessary to develop the efficiency of bus routes operated in Ulsan city.

The impact of service composition factor on organizational performance of long term care facilities for the elderly people (노인장기요양시설의 서비스 구성요인이 조직성과에 미치는 영향에 관한 연구)

  • Juang, Han Chea;Lim, Hyun Sung;Go, Dae Young;Kang, Sung Ok
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.9 no.1
    • /
    • pp.133-140
    • /
    • 2014
  • The purpose of this research was to identify how service composition factor impact organizational performance of long-term care facilities for elderly people. The target population was the staffs who were working at long-term care facilities for elderly people in urban areas of Seoul, Inchon and cities in Kyonggi-do as of September 2012. Independent variables, main factors for organizational performances, are leadership, educational training, compensation, initiative, and service quality. Dependent variables are selected as duty satisfaction, job performance, financial aptitude and beneficiary-oriented policy. SPSS ver18.0 statistical computer program was conducted in order to analyze the multivariate statistical data. The results are examined in detail in terms of the influence of two managing systems in the senior-care service on the organizational performance and the evaluations of the relation and difference caused by the input variables in two managing systems. In one case of the influence of two managing systems in the senior-care service on the organizational performance, the findings show 1) the influence of the service managing factor is clearly related to duty satisfaction with the result of 0.001 (F=37.429) regression data, 2) the influence of the service managing factor is clearly related to job performance with the result of 0.001 (F=55.099) regression data, 3) the influence of the service managing factor is closely related to financial aptitude with the result of 0.001 (F=56.904) regression data, and 4) the influence of the service managing factor is also clearly related to beneficiary-oriented policy with the result of 0.001 (F=61.367) regression data.

  • PDF

Optimum Packaging Design of Packaging Tray and Cushion Pad of Korean Pears for Exporting using FEA Simulation (FEA 시뮬레이션 기법을 이용한 수출용 한국 배 포장 트레이 및 완충패드 최적 포장설계)

  • Choi, Dong-Soo;Son, Jae-Yong;Kim, Jin-Se;Kim, Yong-Hoon;Park, Chun-Wan;Jung, Hyun-Mo;Hwang, Sung-Wook
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.23 no.5
    • /
    • pp.843-852
    • /
    • 2020
  • Among the many packaging materials used in cushion packaging, there is a lack of optimum design for packaging trays and cushion pads used in pear packaging for export and domestic distribution. It causes over-packaging due to excessive material input, and can be solved by applying various parameters needed to optimize the design of the packaging tray and cushion pad considering the packaging material and the number of pears in the box. In the case of a cushion pad for pears, the economic efficiency of material and thickness should be considered. Therefore, it is possible to design a packaging tray and cushion pad depending on eco-friendly packaging materials (PLA, PET) used by applying appropriate design parameters. The static characteristics of the materials used for the packaging of pears were analyzed using FEA (finite element analysis) simulation technique to derive the optimal design parameters. In this study, we analyzed the contact stress and deformation of PET, PLA tray (0.1, 0.5 1.0, 1.5 and 2 mm) and PET foam (2.0, 3 .0 and 4.0 mm) with pears to derive appropriate cushion packaging design factors. The contact stress between the pear and PET foam pad placed on PLA, PET trays were simulated by FEA considering the bioyield strength (192.54±28 kPa) of the pears and safety factor (5) of packaging design, which is the criterion of damage to the pears. For the combination of PET tray and PET foam buffer pad, the thickness of the PET foam is at least 3 mm, the thickness of the PET foam is at least 1.0 mm, the thickness of the foam is at least 2 mm, and if the thickness of the PET tray is at least 1.5 mm, the thickness of the foam is at least 1 mm, suitable for the packaging design. In addition, for the combination of PLA tray and PET foam pad, the thickness of the PET foam was not less than 2 mm if the thickness of the PLA tray was 0.5 mm, and 1 mm or more if the thickness of the PLA tray was not less than 1.0 mm, the thickness of the PET foam was suitable for the packaging design.

Estimation of Potential Evapotranspiration using LAI (LAI를 고려한 잠재증발산량 추정)

  • Kim, Joo-Hun;Kim, Kyung-Tak
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.8 no.4
    • /
    • pp.1-13
    • /
    • 2005
  • In the process of a hydrology circulation, evapotranspiration is considered a very important factor to build a plan for the development of water resources and to operate water resources system. This study purposes to estimate daily potential evapotranspiration quantity in consideration of energy factors of the surface by using spatial information such as Landsat TM (ETM+) data, DEM and Landcover. Kyounan-cheon, Han River is selected as a target area, and landcover is divided by vegetation and non-vegetation covered area. Penman-Monteith equation which considers leaf-area index is used to estimate potential evapotranspiration quantity of vegetation covered area. The combination method (energy burget and aerodynamic method) is used in non-vegetation covered area. Among the input data for estimating potential evapotranspiration, NDVI, SR and Albedo is formed by Landsat, TM and ETM+ from 1986 through 2002. ground heat flux is estimated by using NDVI distribution map, LAI distribution map is drawn by using SR distribution map. The result of estimation shows that the average potential evapotranspiration in the whole basin is about 1.8-3.2mm/day per each cell. THe results of estimating potential evapotranspiration quantity by each landcover are as follows; water surface 3.6-4.9mm/day, city 1.4-3.1mm/day, bareland 1.4-3.5mm/day, grassland 1.7-3.7mm/day, forest 1.7-3.0mm/day and farmland 1.8-3.6mm/day. The potential evapotranspiration quantity is underestimated in comparison with observed evaporation data by evaporation pan, but it is considered that it has physical propriety.

  • PDF

Aerodynamic noise reduction of fan motor unit of cordless vacuum cleaner by optimal designing of splitter blades for impeller (임펠라 스플리터 날개 최적 설계를 통한 무선진공청소기 팬 모터 단품의 공력 소음 저감)

  • Kim, Kunwoo;Ryu, Seo-Yoon;Cheong, Cheolung;Seo, Seongjin;Jang, Cheolmin;Seol, Hanshin
    • The Journal of the Acoustical Society of Korea
    • /
    • v.39 no.6
    • /
    • pp.524-532
    • /
    • 2020
  • In this study, noise radiated from a high-speed fan-motor unit for a cordless vacuum cleaner is reduced by designing splitter blades on the existing impeller. First of all, in order to investigate the flow field through a fan-motor unit, especially impeller, the unsteady incompressible Reynolds-Averaged Navier-Stokes (RANS) equations are numerically solved by using computational fluid dynamic technique. With predicted flow field results as input, the Ffowcs Williams-Hawkings (FW-H) integral equation is solved to predict aerodynamic noise radiated from the impeller. The validity of the numerical methods is confirmed by comparing the predicted sound pressure spectrum with the measured one. Further analysis of the predicted flow field shows that the strong vortex is formed between the impeller blades. As the vortex induces the loss of the flow field and acts as an aerodynamic noise source, supplementary splitter blades are designed to the existing impeller to suppress the identified vortex. The length and position of splitter are selected as design factors and the effect of each design factor on aerodynamic noise is numerically analyzed by using the Taguchi method. From this results, the optimum location and length of splitter for minimum radiated noise is determined. The finally selected design shows lower noise than the existing one.