Title: Enhanced Rubber Yield Prediction in High-Density Plantation Areas Using a GIS and Machine Learning-Based Forest Classification and Regression Model
<br>Cover Date: 2024-09-01
<br>Cover Display Date: September 2024
<br>DOI: 10.3390/f15091535
<br>Description: Rubber is a perennial plant grown for natural rubber production, which is used in various global products. Ensuring the sustainability of rubber cultivation is crucial for smallholder farmers and economic development. Accurately predicting rubber yields is necessary to maintain price stability. Remote sensing technology is a valuable tool for collecting spatial data on a large scale. However, for smaller plots of land owned by smallholder farmers, it is necessary to process productivity estimates from high-resolution satellite data that are accurate and reliable. This study examines the impact of spatial factors on rubber yield and evaluates the technical suitability of using grouping analysis with the forest classification and regression (FCR) method. We developed a high-density variable using spatial data from rubber plots in close proximity to each other. Our approach incorporates eight environmental variables (proximity to streamlines, proximity to main river, soil drainage, slope, aspect, NDWI, NDVI, and precipitation) using an FCR model and GIS. We obtained a dataset of 1951 rubber yield locations, which we split into a training set (60%) for model development and a validation set (40%) for assessment using area under the curve (AUC) analysis. The results of the alternative FCR models indicate that Model 1 performs the best. It achieved the lowest root mean square error (RMSE) value of 19.15 kg/ha, the highest R-squared (R<sup>2</sup>) value (FCR) of 0.787, and also the highest R<sup>2</sup> (OLS) value of 0.642. The AUC scores for Model 1, Model 2, and Model 3 were 0.792, 0.764, and 0.732, respectively. Overall, Model 4 exhibited the highest performance according to the AUC scores, while Model 3 performed the poorest with the lowest AUC score. Based on these findings, it can be concluded that Model 1 is the most effective in predicting FCR compared to the other alternative models.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial Predictive Modeling of Liver Fluke Opisthorchis viverrine (OV) Infection under the Mathematical Models in Hexagonal Symmetrical Shapes Using Machine Learning-Based Forest Classification Regression
<br>Cover Date: 2024-08-01
<br>Cover Display Date: August 2024
<br>DOI: 10.3390/sym16081067
<br>Description: Infection with liver flukes (Opisthorchis viverrini) is partly due to their ability to thrive in habitats in sub-basin areas, causing the intermediate host to remain in the watershed system throughout the year. Spatial modeling is used to predict water source infections, which involves designing appropriate area units with hexagonal grids. This allows for the creation of a set of independent variables, which are then covered using machine learning techniques such as forest-based classification regression methods. The independent variable set was obtained from the local public health agency and used to establish a relationship with a mathematical model. The ordinary least (OLS) model approach was used to screen the variables, and the most consistent set was selected to create a new set of variables using the principal of component analysis (PCA) method. The results showed that the forest classification and regression (FCR) model was able to accurately predict the infection rates, with the PCA factor yielding a reliability value of 0.915. This was followed by values of 0.794, 0.741, and 0.632, respectively. This article provides detailed information on the factors related to water body infection, including the length and density of water flow lines in hexagonal form, and traces the depth of each process.
<br>Citations: 4
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial prediction of the probability of liver fluke infection in water resource within sub-basin using an optimized geographically-weighted regression model
<br>Cover Date: 2024-01-01
<br>Cover Display Date: 2024
<br>DOI: 10.3389/fvets.2024.1487222
<br>Description: Introduction: Infection with liver flukes (Opisthorchis viverrini) is partly attributed to their ability to thrive in sub-basin habitats, causing the intermediate host to remain within the watershed system throughout the year. It is crucial to conduct spatial monitoring of fluke infection at a small basin analysis scale as it helps in studying the spatial factors influencing these infections. The number of infected individuals was obtained from local authorities, converted into a percentage, and visually represented as raster data through a heat map. This approach generates continuous data with dependent variables. Methods: The independent set comprises nine variables, including both vector and raster data, that establish a connection between the location of an infected person and their village. Design spatial units optimized for geo-weighted modeling by utilizing a clustering and overlay approach, thereby facilitating the optimal prediction of alternative models for infection. Results and discussion: The Model-3 demonstrated the strongest correlation between the variables X5 (stream) and X7 (ndmi), which are associated with the percentage of infected individuals. The statistical analysis showed t-statistics values of −2.045 and 0.784, with corresponding p-values of 0.016 and 0.085. The RMSE was determined to be 2.571%, and the AUC was 0.659, providing support for these findings. Several alternative models were tested, and a generalized mathematical model was developed to incorporate the independent variables. This new model improved the accuracy of the GWR model by 5.75% and increased the R<sup>2</sup> value from 0.754 to 0.800. Additionally, spatial autocorrelation confirmed the difference in predictions between the modeled and actual infection values. This study demonstrates that when using GWR to create spatial models at the sub-basin level, it is possible to identify variables that are associated with liver fluke infection.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Cohesion Analysis of Rubber Stand Ages Using Object-Based Image Analysis and Spatial Autocorrelation
<br>Cover Date: 2024-01-01
<br>Cover Display Date: 2024
<br>DOI: 10.3844/JCSSP.2024.1723.1733
<br>Description: Latex and rubber wood are crucial raw materials used in various industries and play a significant role in the economies of many countries, particularly in tropical regions. Mapping the areas where these materials are planted and classifying the age of rubber stands is important for managing growth assessment, yield assessment, and estimating the number of mature rubber trees that will be harvested. In this study, we conducted a visual interpretation of high-resolution satellite imagery from Google Earth in Mueang Loei District, Loei Province, Thailand. We discovered a total of 443.78 square kilometers of rubber plantations on the west side of the research area. The rubber stands were categorized into four age groups: Under seven years old, seven to fifteen years old, fifteen to twenty-five years old, and over twenty-five years old. To analyze the age classification accuracy, we employed Object-Based Image Analysis (OBIA) using the Hierarchical classification technique with Sentinel-2A images. We compared the results with the overall accuracy and Kappa coefficient of agreement between the ground-truth data and Google Earth satellite imagery. As the planting zones were not ordered within the research area, all four age groups were combined inside the rubber plantation area. The Kappa coefficient is 68.55 and the overall accuracy is 77.23%. This can be attributed to the fact that rubber farming is still in its early stages in the region. The area occupied by rubber plantations in the 15–25-year-old and 7–15-year-old age groups is 99.40 (22.40%) and 169.23 (38.13%) square kilometers, respectively. The area occupied by rubber plantations in less than 7 years is 96.85 (21.82%) square kilometers. The results are reliable as they validate the spatial relevance of each age group’s rubber plantation size to the outcomes of the image analysis with clustered spatial correlation. The findings of this study demonstrate that OBIA can be used to categorize rubber age ranges, particularly for middle-aged (7–15 years old and 15–25 years old) and mature (>25 years old) rubber with similar canopy features. The information obtained from this study can be utilized to analyze the issue of declining rubber prices due to the surplus production from numerous rubber plantations, which may lead some farmers to convert their land to other cash crops.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke Opisthorchis viverrini (OV) Infection in Small Sub-Watersheds
<br>Cover Date: 2023-12-01
<br>Cover Display Date: December 2023
<br>DOI: 10.3390/ijgi12120503
<br>Description: Infection of liver flukes (Opisthorchis viverrini) is partly due to their suitability for habitats in sub-basin areas, which causes the intermediate host to remain in the watershed system in all seasons. The spatial monitoring of fluke at the small basin scale is important because this can enable analysis at the level of the factors involved that influence infections. A spatial mathematical model was weighted by the nine spatial factors X<inf>1</inf> (index of land-use types), X<inf>2</inf> (index of soil drainage properties), X<inf>3</inf> (distance index from the road network, X<inf>4</inf> (distance index from surface water resources), X<inf>5</inf> (distance index from the flow accumulation lines), X<inf>6</inf> (index of average surface temperature), X<inf>7</inf> (average surface moisture index), X<inf>8</inf> (average normalized difference vegetation index), and X<inf>9</inf> (average soil-adjusted vegetation index) by dividing the analysis into two steps: (1) the sub-basin boundary level was analyzed with an ordinary least square (OLS) model used to select the spatial criteria of liver flukes aimed at analyzing the factors related to human liver fluke infection according to sub-watersheds, and (2) we used the infection risk positional analysis level through machine-learning-based forest classification and regression (FCR) to display the predictive results of infection risk locations along stream lines. The analysis results show four prototype models that import different independent variable factors. The results show that Model 1 and Model 2 gave the most AUC (0.964), and the variables that influenced infection risk the most were the distance to stream lines and the distance to water bodies; the NDMI and NDVI factors rarely affected the accuracy. This FCR machine-learning application approach can be applied to the analysis of infection risk areas at the sub-basin level, but independent variables must be screened with a preliminary mathematical model weighted to the spatial units in order to obtain the most accurate predictions.
<br>Citations: 5
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial Predictive Modeling of the Burning of Sugarcane Plots in Northeast Thailand with Selection of Factor Sets Using a GWR Model and Machine Learning Based on an ANN-CA
<br>Cover Date: 2022-10-01
<br>Cover Display Date: October 2022
<br>DOI: 10.3390/sym14101989
<br>Description: The main purpose of the study is to apply symmetry principles to general mathematical modelling based on multi-criteria decision making (MCDM) approach for use in development in conjunction with geographic weighted regression (GWR) model and optimize the artificial neural network-cellular automaton (ANN-CA) model for forecasting the sugarcane plot burning area of Northeast Thailand. First, to calculate the service area boundaries of sugarcane transport that caused the burning of sugarcane with a fire radiative power (FRP) values using spatial correlation analysis approach. Second, the analysis of the spatial factors influencing sugarcane burning. The study uses the approach of symmetry in the design of algorithm for finding the optimal service boundary distance (called as cut-off) in the analysis of hot-spot clustering and uses calculations with the geographic information system (GIS) approach, and the final stage is the use of screened independent variable factors to predict the plots of burned sugarcane in 2031. The results showed that the positively related factors for the percentage of cane plot sintering in the sub-area units of each sugar plant’s service were the distance to transport sugarcane plots index and percentage of sugarcane plantations in service areas, while the negative coefficients were FRP differences and density of sugarcane yield factors, according to the analysis with a total of seven spatial variables. The best GWR models display local R<sup>2</sup> values at levels of 0.902 to 0.961 in the service zones of Khonburi and Saikaw. An influential set of independent variables can increase the accuracy of the ANN-CA model in forecasting with kappa statistical estimates in the range of 0.81 to 0.85 The results of the study can be applied to other regions of Thailand, including countries with similar sugarcane harvesting industries, to formulate policies to reduce the exposure of sugarcane harvested by burning methods and to support the transportation of sugarcane within the appropriate scope of service so that particulate matter less than 2.5 microns ((Formula presented.)) can be reduced.
<br>Citations: 11
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial environmental modeling for wildfire progression accelerating extent analysis using geo-informatics
<br>Cover Date: 2020-01-01
<br>Cover Display Date: 2020
<br>DOI: 10.15244/pjoes/115175
<br>Description: The fire situation during the dry season of Thailand, in the last 10 years, has become more severe. The Tad Sung Forest Park area has reported the intensity of wildfires for the past 7 years. This research has applied the geographic weighted regression (GWR) model to generate a spatial relationship analysis model for wildfires. This research aims to create a spatial model to analyze the risk of hazardous areas against wildfire and to analyze the factors that affect forest fire risks in order to protect against wildfires. The service area (SA<inf>LY</inf>) model was obtained through the first approach. The wildfire-GWR results of the study showed that the model can predict at the R<sup>2</sup> level greater than 82% and varies according to the sub-area boundaries. Factors affecting the acceleration of wildfires are (positive coefficient) the digital elevation model (DEM), normalized burn ratio (NBR), land surface temperature (LST) and (negative coefficient) normalized difference vegetation index (NDVI), slope and aspect. In addition, the distance from the road factor has little effect on wildfire intensity in most areas. The results of the research are used to create a risk-sensitive map of wildfires through surveillance by importing the independent variable factors in the model and using it as a prototype of the same kind of space.
<br>Citations: 11
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Built-up growth impacts on digital elevation model and flood risk susceptibility prediction in Muaeng District, Nakhon Ratchasima (Thailand)
<br>Cover Date: 2019-07-01
<br>Cover Display Date: 1 July 2019
<br>DOI: 10.3390/w11071496
<br>Description: The transformation of land-use and land cover in Nakhon Ratchasima province, Thailand has rapidly changed over the last few years. The major factors affecting the growth in the province arise from the huge expansion of developing areas, according to the government's development plans that aim to promote the province as a central business-hub in the region. This development expansion has eventually intruded upon and interfered with sub-basin areas, which has led to environmental problems in the region. The scope of this study comprises three objectives, i.e., (i) to optimize the Cellular Automata (CA) model for predicting the expansion of built-up sites by 2022; (ii) to model a linear regression method for deriving the transition of the digital elevation model (DEM); and (iii) to apply Geographic Weighted Regression (GWR) for analyzing the risk of the stativity of flood areas in the province. The results of this study show that the optimized CA demonstrates accurate prediction of the expansion of built-up areas in 2022 using Land use (LU) data of 2-year intervals. In addition, the predicting model is generalized and converged at the iteration no. 4. The prediction outcomes, including spatial locations and ground-water touch points of the construction, are used to estimate and model the DEM to extract independent hydrology variables that are used in the determination of Flood Risk Susceptibility (FRS). In GWR in the research called FRS-GWR, this integration of quantitative GIS and the spatial model is anticipated to produce promising results in predicting the growth and expansion of built-up areas and land-use change that lead to an effective analysis of the impacts on spatial change in water sub-basin areas. This research may be beneficial in the process of urban planning with respect to the study of environmental impacts. In addition, it can indicate and impose important directions for development plans in cities to avoid and minimize flood area problems.
<br>Citations: 13
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial linear programming model to reduce a pollution emissions of sugarcane transportation in northeastern Thailand
<br>Cover Date: 2017-01-01
<br>Cover Display Date: 2017
<br>DOI: N/A
<br>Description: Currently, the sugarcane transportation management in Thailand relies only on arbitrary and unsystematic decisions. The increase of truck trip for sugarcane transportation in Northeast, Thailand is proportionate to the increase of emission level and has caused traffic congestion and delay in transportation. This can lead to low efficiency and great loss in transportation cost unnecessary. The purpose of the study is to apply Network Analysis (NA) and Spatial Linear Programming (SLP) to perform transportation management of sugarcane produced in the northeast region of Thailand. The sugarcane cropping area in this region of Thailand is the biggest compared to others. The sugarcane areas distribute in 228 districts out of 321. There are 16 sugar factories to serve the region out of total 47 nationwide. The purpose of the study was to apply Network Analysis and Linear Programming to perform transportation management of sugarcane produced in the Northeast region of Thailand. The main objective of the study was minimizing the total emission by proper allotting sugarcane from plots to certain sets of factories. To deal with a very large number of plots in the region, the methodology comprised 2 steps. The first step was to allot total sugarcane product from districts to certain sets of factories. The second step used the results from the first step as input to allot sugarcane from each plot to a certain set of factories specific for each district. As a result for the first objective of the study, the minimum total emission level in district and plot levels were 1,466,641,682.33 units and 1,551,454,082.19 units, respectively. The results from both steps of both objectives were consistent with the research hypotheses.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Simulation of air pollution violence to potential area selection of the air quality monitoring station in Nakhon Ratchasima municipality, Thailand
<br>Cover Date: 2013-08-26
<br>Cover Display Date: 2013
<br>DOI: N/A
<br>Description: The purpose of the study is to generate traffic air pollution map using mathematical model and GIS (geographic information system) to determine a proper zone of AQMS(air quality monitoring station) in municipality area. The pollutants analyzed were carbon monoxide (CO), and nitrogen oxides (NO <inf>x</inf>) which can be harmful to people living in the area. The three steps of mapping process were performed under the GIS environment using the existing vehicle emission rates and pollutant dispersion model. First, traffic volume, road network, and the emission rates of road segments varying with types of vehicle were collected from existing data. Second, the pollutant concentrations were calculated by use of CALINE4, a tool with Gaussian dispersion model. The model parameters include emission rate, wind directions and speeds, ambient temperature and observed pollutant concentration, and atmospheric stability during all seasons from the January 1, 2010 to May 31, 2011 with regardless the rainy season.This resulted in concentrations at many receptor points along links of the road network. Third, distributions of pollution concentrations were generated by means of the spatial interpolation of those from receptors. The results of pollution raster-based maps are used for determining frequency of violence map. The resulting frequency of violence will be further integrated to determine a potential area of AQMS.Finally, achieving pollution potential area of AQMS can be located as helpful basic data for efficient traffic and transportation planning.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Sugarcane transportation allocation using Multi-Objective Decision Analysis, Northeast region of Thailand
<br>Cover Date: 2013-01-01
<br>Cover Display Date: 2013
<br>DOI: N/A
<br>Description: The sugarcane transportation management in Thailand currently relies only on arbitrary and unsystematic decisions. This can lead to great loss in transportation cost (TC) unnecessary. The objective of this research is to apply Network Analysis (NA) and Linear Programming (LP) to performing transportation management of sugarcane in the Northeast region of Thailand. The optimization of the Multi-Objectives Decision Analysis (MODA) through the LP is minimization of TC and environmental impact (EI) by proper allotting sugarcane from plots to certain sets of factories using shortest routes resulted from the NA. To deal with a very big number of plots in the region, the analysis comprises 2 steps:first, toprovide which factory(s) and how much the sugarcane from each district should be allot to; second, to allot and transport sugarcane from plots in district to factories usingpatternof the first step.This study was successful in providing proper methods and techniques to optimize sugarcane transportation management so as to meet objectives requirement.
<br>Citations: 1
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Frequency of violencemapping of air pollution using mathematical model and geographic information system
<br>Cover Date: 2013-01-01
<br>Cover Display Date: 2013
<br>DOI: N/A
<br>Description: Protection of human health from traffic pollutants is the primary goal of all air pollution control programs. The source of air pollution caused by traffic is considered as line-source emission. The frequency of violence of air pollution reflects environmental impact to people as exposure assessment. The purpose of the study was to generate traffic air pollution severity map in term of frequency of violence using mathematical model and geographic information system (GIS). The pollutants analyzed were CO, PM10 and NOx which can be harmful to people who live in the study area which is NakhonRatchasima municipality. The 3 steps of mapping process were performed in GIS environment using the vehicle emission and pollutant dispersion models. First, pollutant concentrations were calculated using Caline4, a tool with Gaussian dispersion model. The model parameters include emission rate, wind directions and speeds, ambient concentrations and temperatures, and atmospheric stability. This resulted in pollution concentrations of 504 receptors located along links of the road network. Second, the distribution of pollution concentrations was generated by means of the spatial interpolation of concentrations at those receptors. The results were raster-based maps of pollutions distribution varied with wind directions and time periods. Third, they were then used to determine the cell based severity defined by counting the frequency of pollution intensity that was higher than its own mean plus the standard deviation of every time period in each cell. The frequency of violence map of each pollutant achieved could be used as helpful basic data for efficient traffic and transportation planning. Copyright© (2013) by the Asian Association on Remote Sensing.
<br>Citations: 1
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Application of GIS to simulation of the air traffic pollution in Nakhon Ratchasima, Thailand
<br>Cover Date: 2011-12-01
<br>Cover Display Date: 2011
<br>DOI: N/A
<br>Description: The purpose of the study is to generate traffic air pollution map using mathematical model and geographic information system (GIS). The pollutants analyzed were CO, and NOx which can be harmful to people living in the area. The 3 steps of mapping process were performed under the GIS environment using the existing vehicle emission rates and pollutant dispersion model. First, traffic volume, road network, and the emission rates of road segments varying with types of vehicle were collected from existing data. Second, the pollutant concentrations were calculated by use of Caline4, a tool with Gaussian dispersion model. The model parameters include emission rate, wind directions and speeds, ambient temperature and observed pollutant concentration, and atmospheric stability during all seasons from the 1 <sup>st</sup> January 2010 to 31 <sup>st</sup> May 2011. This resulted in concentrations at many receptor points along links of the road network. Third, distributions of pollution concentrations were generated by means of the spatial interpolation of those from receptors. The results can be used as helpful basic data for efficient traffic and transportation planning.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Comparison on different clustering of origins for sugarcane transportation using Network Analysis and Linear Programming
<br>Cover Date: 2011-12-01
<br>Cover Display Date: 2011
<br>DOI: N/A
<br>Description: Currently, the sugarcane transportation management in Thailand has been relied only on arbitrary and unsystematic decisions. This can lead to low efficiency and great loss in transportation cost unnecessary. The purpose of the study is to apply Network Analysis (NA) and Linear Programming (LP) to perform transportation management of sugarcane produced in the Khon Kaen province of Thailand. The NA is for selecting the shortest routes from the origins to factories. The single objective decision analysis is optimization function through the LP in order that total transportation cost of sugarcane product from origins to sets of factories is minimized. Analyses cannot be performed by plots due to their huge amount which are over the limitation of any software. To avoid this limitation, the conventional method always used centers of provinces or districts as the origins. Instead, this study sets up clustering by representative points of districts, sub-districts, and sugarcane plots in sub-districts as the origins. Results from the different clustering of origins for transportation were compared in terms of sugarcane allotment to factories. The study revealed that, with different clustering of origins, the performance by lower clustering level showed more number of factories as destinations and more details of allotments.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Application of GIS and optimization model to potential area selection for air quality monitoring station
<br>Cover Date: 2010-12-01
<br>Cover Display Date: 2010
<br>DOI: N/A
<br>Description: The purpose of the study is to select the optimum potential area for location strategy of urban air quality monitoring station with respect to the multi-objectiveand spatial relationshipdesign criteria. The potential area selection comprises 3 steps First, concentration maps were created from the interpolation method based on pollution emissions data from traffic model, which regardless of the meteorology data such as wind directions, wind speed Second, the selection of monitoring stations can be made in the designed grid system. The objective function and constraints prepared to achieve such planning goals can be stated as maximization of highest number of coverage areas and maximization of detection capability of highest pollution concentrations. Third, the constraint set defined in this analysis may cover two design criteria, including the spatial coverage pattern which calculated from sphere of influence which is calculated through network analysis under function service area. The effectiveness can be defined by the coverage effectiveness constraint for illustrating the detection capability of the area covered by existing monitoring station. The budget constraint is limits the number of monitoring stations that can be selected in the optimization process. Finally, the optimal station locations are binary solutions from linearprogramming. The expansion of air quality monitoring station of NakhonRatchasima province in Thailand is used as a case study to demonstratethe proposed methodology.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Application of MODA and GIS to potential area selection for construction material distribution center in the municipality area of Nakhon Ratchasima, Thailand
<br>Cover Date: 2009-12-01
<br>Cover Display Date: 2009
<br>DOI: N/A
<br>Description: The purpose of the study is to select the optimum potential areas for a construction material distribution centers (DCs) of which delivery destinations include 15 retailers (Rs) within the municipality area of Nakhon Ratchasima, Thailand, using Multi- Objective Decision Analysis (MODA) and GIS. The potential area selection comprises 4 steps. First, a set of potential areas was selected off the whole area using binary model applied to certain conditions which are distances from village center, road, railway, and stream, including being idle land use. Second, the best routes with shortest distance condition from each potential area to all retailers were determined through GIS network analyses. Third, total distances of the best routes were input into transportation cost calculation of the minimizing objective function. Minimizing land price was another objective included in this function. The function working under the linear programming provided the smaller set of potential areas which is the subset of the first one. Fourth, the constraint set up on proper area size which is related to its carrying capacity was used to filter the potential areas off the subset. In this study all areas in the subset were above the constraint.
<br>Citations: 1
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Risk ranking of road sections on highways using ordered weight averaging (OWA) decision rule
<br>Cover Date: 2009-12-01
<br>Cover Display Date: 2009
<br>DOI: N/A
<br>Description: Ranked road sections in terms of risk together with ranked weights of factors considered to cause accident for each section are highly effectual information for road safety implementing planning. To achieve this goal, 36 road sections from 5 highways in Nakhon Ratchasima, Thailand with varying slopes, surface widths, and a number of connection routes, initially selected from 166 sections by using 3-year accident data, are ranked into order from the highest risk to the lowest risk using ordered weight averaging (OWA) decision rule. OWA is a multi-criteria evaluation procedure using combination operators. Apart from risk ranking of road sections, the result shows that slope is considered to be the highest rank among risk factors for 16 sections, while 15 and 5 sections are for the number of connection routes and surface width respectively. In addition, a number of ranking sections within each certain highway can be obtained i.e. 17, 12, 3, 2, and 2 sections for highway no. 205, 207, 208, 2150, and 2160, respectively. Then, the priority of road safety programs to reduce accident rate can be set effectively.
<br>Citations: 0
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: A minimizing cost of transport gabage in Nonsung District Nakhon Ratchasima River, Thailand
<br>Cover Date: 2009-01-01
<br>Cover Display Date: 2009
<br>DOI: 10.3844/ajas.2009.285.289
<br>Description: The objective this research for estimate minimum cost of gabage from its sources to disposal sites in Nonsung District Nakhon Ratchasima Province, Thailand. By using genetic algorithms run in microsoft excel add-ins find the minimum cost and appropriate waste allocation.The distance applied in the simulation was displacement between two points not the true distance along the route. It was found from the study that the factors affecting the pattern of the hauling system and waste allocation were number of sources and waste quantities produced, number and capacity of transfer stations and disposal sites and hauling cost from different points. © 2009 Science Publications.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>