Mehrdad AhangarCani; Mohammad Reza Malek
Abstract
Extended Abstract
Introduction and Objective
Road traffic accidents impose numerous social, economic, and cultural costs upon various societies, especially developing countries. Identification of accident blackspots is a method proposed to deal with car accident risks. Among various events associated ...
Read More
Extended Abstract
Introduction and Objective
Road traffic accidents impose numerous social, economic, and cultural costs upon various societies, especially developing countries. Identification of accident blackspots is a method proposed to deal with car accident risks. Among various events associated with transportation network, road traffic accidents play a significant role, because of their specific features, including high frequency, high intensity and the chance of direct involvement of all members of the community.This problem is more conspicuous in developing countries such as Iran. The present study aims to identifyaccidentblackspotsand to prepare risk map for road trafficaccidents in Babol city using volunteered geographic information.
Materials and methods
According to the characteristics of the study area, the present study takes advantage of criteria such as distance from population centers, proximity to city squares, distance from footbridges, and proximity to road intersections to identifyaccidentblackspotsand a prepare risk map for roadtraffic accidents in Babol city. Accident blackspots detected by volunteered geographic information, along with the criteria determined by applying analytic hierarchy process (AHP) and analytic network process (ANP) were compared in a pairwise manner, and their respective weight was calculated to showtheir specific level of impact. Ultimately, a risk map was produced for the risk of road traffic accidents obtained from each method. In order to evaluate the accuracy of the identified accident blackspots obtained from volunteered geographic information, as well as the accuracy of susceptibility maps, ROC curve and Kappa Coefficient were applied to police official records.
Results and Discussion
According to the findings, Jame Mosque shopping center, Shahabnia shopping center, intersection of Farhangstreet and Velayat square were identified as the most accident-prone areas in Babol city. Also, among the prespecified criteria, distance from population centers and distance from intersections are considered to be the most important criteria, respectively. Results obtained from the evaluation criteria indicatedhigh accuracy of volunteered geographic information, and thus it is concluded that this kind of information can be effective in determining the accident blackspotsinBabol city. Also, the ANP method works better than AHP method in preparing the risk map of accidents.
Conclusion and Future works
Due to the large number of road accidents, especially in developing countries,the issue of accident blackspotsand providing a risk map for road trafficaccidents are an essential part of roads safety. In the present study, volunteered geographic information was used, along with multivariate decision-making methods of analytic hierarchy process (AHP) and analytic network process (ANP) to identifyaccident blackspots based on number, causes and severity of accidents and to develop a risk map for driving accidents in Babol city. Moreover, the criteria of distance from population centers, proximity to the city squares, distance from the footbridges, and adjacency to intersections were used to determine accident blackspotsand to prepare a risk map for driving accidents in Babol city. According to the results, Jame Mosque shopping center, Shahabnia shopping center, Farhang intersection and Velayat square were identified as the most accident-prone points in Babol city. Also, distance from population centers and distance from intersectionswere identified as the most important criteria, respectively. Evaluation criteria demonstrated that volunteered geographic information can be effective and accurate in determining accident blackspotsinBabol city. Also, the ANP method worked better than AHP method in preparing the risk map of driving accidents. The method proposed in this study to identify accident blackspots and preparedriving accidents risk maps can be generalized to other areas. Basedon the characteristics of specific routes, other criteria such as arc radius, longitudinal slope can alsobe used. It is also suggested that the results of other methods used for investigation ofaccidentblackspotsand production of risk maps based onvolunteered geographic information (VGI) are compared with the results of the present study.
Mehrdad AhangarCani; Seyyed Hossien Khasteh
Abstract
Extended Abstract Introduction and Objective Due to the location of Iran in dry regions of the Middle East, and also because of the rapid increase in its urban population and water consumption, every day the issue of water scarcity becomes more severe in Iran. In recent years, Iran has faced serious ...
Read More
Extended Abstract Introduction and Objective Due to the location of Iran in dry regions of the Middle East, and also because of the rapid increase in its urban population and water consumption, every day the issue of water scarcity becomes more severe in Iran. In recent years, Iran has faced serious water scarcity and excessive consumption of water resources. Therefore, patterns of urban water consumption, different geographic, spatial, demographic, social, and economic parameters, and the relation between these parameter and water consumption are considered to be among important issues affecting management of water resources. The present study seeks to investigate and analyze the spatial pattern of domestic water consumption in Babol County, and also to identify parameters affecting the pattern of water use. This is achieved by extracting association rules from some spatial and socio-economic parameters and based on the water use level in this County. The study also aims to determine regions with high/low level of water use, investigate spatial distribution of water consumption and finally, identify and categorize parameters affecting domestic water consumption at neighborhood level in this County using Decision Tree model. Materials and methods Data: Domestic water consumption data, census data, spatial and socio-economic parameters such as distance from main roads, distance from Babolrood, total area of garden and green space in each building, building site and standing property (total area of house yard), population density, total number of houses vs. apartments, number of housing units, average number of people per household, percentage of young/old people per household were extracted from the Statistical Center of Iran for the time period of 2011 to 2016. Then, these data were used to analyze urban water consumption in Babol County. Methods: Apriori algorithm - a data mining algorithm used to extract association rules- has been used to discover and extract relationships between different spatial socio-economic parameters and domestic water consumption patterns. Moreover, a decision tree has been developed which takes advantage of these parameters to predict domestic water use. Results and Discussion Results indicated that number of houses, number of household members, green space in each house, total area of house yard and distance from main roads are directly related with the household water consumption. On the other hand, population density, percentage of youth population, number of residential units and distance from Babolrood River are inversely related to domestic water consumption. Among all parameters considered in the present study, total area of house yard, distance from Babolrood River, number of residential units and number of household members exhibited a stronger relationship with water consumption. Thus, they were located on higher branches of the final decision tree. Additionally, results of global Moran’s I index indicated that there exists a spatial autocorrelation among household water consumption data. Moreover, this index indicated the clustered nature of residential water consumption distribution in Babol County. Also, spatial distribution of domestic water consumption in this County demonstrated that western and coastal areas with minimum distance from Babolrood River have the highest level of domestic water consumption. Therefore, it can be concluded that with an increase in distance from Babolrood River, domestic water consumption decreases. Only terraced and semi-detached houses exist in these neighborhoods. Thus compared to other neighborhoods, they have a lower population density, larger green space and larger yard. Conclusion and Future Works The present study applies Apriori algorithm to extract association rules and discover the relationship between spatial and socio-economic parameters and domestic water consumption. Results indicated that spatial and socio-economic parameters affect the spatial distribution of domestic water consumption in Babol County. Developing a decision tree, parameters associated with domestic water consumption were categorized and amount of water consumption was predicted. Extracted rules predicted domestic water consumption of test data with an accuracy of 75%. In this study, global Moran’s I index indicated the existence of a spatial autocorrelation among water consumption data. It also proves the clustered nature of domestic water consumption distribution in the study area. Additionally, spatial distribution of domestic water consumption in Babol County indicated that western and coastal neighborhoods have the highest level of domestic water consumption, while southern neighborhoods of Babol County have the lowest level of domestic water consumption. Model developed in the present study provides an opportunity for analyzing and predicting the level of water consumption. This will make planning for the reduction of water consumption and management of water resources possible. We suggest that future works evaluate the effect of other spatial and socio-economic parameters such as water cost and educational status of household members in a longer period (more than 5 years) to improve the accuracy of the model.
Mehrdad AhangarCani; Mahdi Farnaghi
Abstract
Introduction
Introduction and Objectives: Cutaneous Leishmaniasis (CL) is a vector-borne disease, endemic of the Middle East. The spread of CL is highly associated with the socio-ecological interactions of vectors, hosts and environmental conditions. CL is the most frequent vector-borne disease in Iran ...
Read More
Introduction
Introduction and Objectives: Cutaneous Leishmaniasis (CL) is a vector-borne disease, endemic of the Middle East. The spread of CL is highly associated with the socio-ecological interactions of vectors, hosts and environmental conditions. CL is the most frequent vector-borne disease in Iran and especially in the north-eastern province, Golestan, which has long been known as one of the most important endemic areas for CL dispersion. Therefore, Golestan province was selected as the study area of this research. The main objectives of the study are to analyze annual spatial distribution of CL, investigate the relations between environmental/climate factors and incidence rate of CL and also provide a model to predict CL distribution at rural district level in Golestan province.
Materials and methods
Data: CL incidences, census data, environmental and climate factors have been used in this study to provide a model and produce a map to predict the CL distribution. The CL incidences are continuously recorded by the Center for Disease Control and Prevention (CDC) of Golestan province. The population and census data for 2013-2015 period were obtained from Iranian Statistical Center. Environmental and climate data such as vegetation, average humidity, average temperature, precipitation, number of rainy days, number of freezing days, maximum wind speed and evaporation rate were used as parameters affecting the model.
Methodology
The statistical and geo-statistical analyses were used to investigate the relation between environmental/climate factors and CL incidence rate, and to investigate the existence of spatial autocorrelation between CL cases, respectively. Additionally, Multilayer perceptron (MLP) neural network was used to model the relation between the distribution of CL incidences with environmental/climate factors, and also to generate the risk maps of CL. MLP is a type of neural network which consists of multiple layers of neurons or processing elements connected in a feed forward fashion. It encompasses three types of layers: input, hidden, and output. It has a unidirectional flow of information. Generally, information flow starts from input layer, goes through hidden layer, and then to output layer, which provides the response of the network to the input stimuli. In this type of network, there are generally three distinct types of neurons in layers. The input layer contains some neurons as the input variables. The hidden neurons, which are contained in one or more hidden layers, process and encode information within the network. The hidden layer receives, processes, and passes the input data to the output layer. Number of hidden layers and number of neurons within each layer affect the accuracy and functionality of the network. The output layer contains target output vector. In this study, effective parameters along with CL incidence rate of 2013-2014 were fed to the MLP as training data. The trained MLP was used afterward to generate the risk map of 2015 and test accuracy of the model. In order to determine the optimal parameters of the MLP, the grid-search and cross-validation techniques were used on 25% of the training dataset in the training phase. The performance of MLP was investigated using the root mean square error (RMSE), mean absolute percentage error (MAPE) and area under curve (AUC) of receiver operating characteristic (ROC) measures. Sensitivity analysis was also used to determine most effective variables regarding predictive mapping of CL distribution
Results and Discussion
Results of global Moran’s I index indicated that there is spatial autocorrelation among CL cases, and also distribution of CL cases in Golestan province in each 3 years is clustered. Moreover, statistical analyses showed that majority of the incidences belonged to rural districts of Gonbad-Kavos and Maraveh-Tappeh. Based on the results of statistical analyses (including Pearson correlation and Spearman rank correlation), positive correlations were observed between the CL incidence rate and average temperature, maximum wind speed and evaporation. In addition, negative correlation was found between the CL incidence rate and average humidity, precipitation, number of rainy days, number of freezing days and vegetation. According to the results of evaluation criteria including RMSE, MAPE and AUC, the trained MLP model was able to generate risk maps of CL in 2013-2015 for each rural district with acceptable accuracy. Additionally, results of sensitivity analysis indicate that vegetation and average humidity are the most influencing variables in the incidence of CL and in predictive mapping of CL distribution in Golestan province.
Conclusion and Future works
In this study, the global Moran’s I index indicated the presence of spatial autocorrelation among CL cases, and clustered distribution of disease in the study area. The statistical analyses showed that environmental and climate factors greatly affect the spatial distribution of CL. The MLP method, used to generate CL distribution risk maps, was able to generate the study area risk maps with acceptable accuracy. Results highlight the potential high risk areas requiring special plans and resources for monitoring and control of the disease. As a future work, we suggest that the effects of other environmental and socio-economic parameters should be evaluated to improve the accuracy of the model. It is also recommended that other methods such as regression and other neural network techniques be used to generate CL risk maps.
