نشریه علوم و فنون نقشه برداری
سال دوازدهم شماره 1 (پیاپی 45، تابستان 1401)

The occurrence of crime in society causes insecurity and chaos in people's lives, imposes extensive material and spiritual costs on society, and diverts a lot of time, money, and energy from the country's security agents. Spatial investigation of a crime in the past and predicting the likelihood of its occurrence in the future, or in other words, determining the spatial centers of crime, can help manage crime prevention better or deal with it effectively. Unfortunately, measuring a crisis center is a complex issue. In this regard, many statistical methods can be used to identify crisis hotspots, including cluster analysis. In the present study, for the proper efficiency of such analyzes, with a combined approach of spatial information systems and K-means clustering, the spatial distribution of crime in Qazvin (as a case study) is investigated. Assist in locating crime centers more accurately. The results showed that this combined approach could model the local centers of crime in Qazvin.

The combination of 2D laser rangefinder(LRF) and camera has many application in robotics, mapping,self-driving vehicles to map and capture  color and texture information of objects. to fuse LRF and camera’s data, these  sensors must be carefully calibrated related to each other. Extrinsic calibration between a LRF and camera is often performed by common features. Therefore extrinsic calibration between LRF and camera is necessary process.  Extrinsic calibration between a Camera and a LRF  is often performed by common features in data captred by two sensors. In this research, three difrent methods for extrinsic calibration between a LRF and a camera using photogrammetric control field and ping pong balls are presented. In calibration process using 3D and 2D point clouds,ping pong balls are used as common targets that can be identified in the camera and LRF data. In calibration using the 3D point clouds, the calibration parameters are calculated using the point clouds generated from the test field at the main station and performing the bundel adjusment using a set of images taken from the control field. In this method, a 3D point cloud is obtained from combination of 2D LRF and servo motor data. The 2D LRF  is connected to the servo motor by a gimbal so that the extension of the servo motor shaft pass through the center of the LRF. The LRF rotation is measured by the encoder in the servo motor, and by rotating the LRF, all 2D scans at a station can be registered relative to each other. On the other hand, through images taken from the control field and bundel adjusment technoque, the position of the balls in the photogrammetric model is obtained. The second method is similar to the first method,except that a 2D point cloud is used instead of a 3D point cloud. In the first and second methods, the coordinates of the centers of ping pong balls are available in two different coordinate systems, so the relationship between the two coordinate systems with the 3D conformal equation is obtained. In the third method, through the pyramid created in the corner of the room and solving the perspective-three-point problem,  the 2D LRF calibration parameters at the main station relative to the control field are calculated with just one scan. The calibration parameters of camera in the main station relative to the control field are calculated using bundel adjusment and 3D conformal equations. Finally, the calibration parameters of the LRF relative to the camera are obtained. According to the RMSE calculated for checkpoints, calibration using 3D point cloud,calibaration using room corner and calibration using 2D point cloud were the most accurate, respectively.

In the recent three decades, building damage map production after an earthquake has been one of the most important challenges in disaster management. For decades, researchers have utilized different kinds of sensors, including airborne LiDAR, RADAR, and optical satellite imagery, in order to create earthquake-induced damage maps. LiDAR and RADAR sensors are disadvantageous due to their high cost and difficulty of acquisition. Additionally, optical satellite images are limited by the lack of timely availability of high-resolution imagery, a low signal-to-noise ratio, and the inability to reconstruct 3D data. On the other hand, the recent development of low-cost and flexible-resolution UAVs along with high accessibility has opened up a great opportunity in this area. Furthermore, UAV data make detecting damage levels possible according to the well-known EMS-98 damage standard. However, there are still a few researchers that have considered international damage standards. When developing a strategy for detecting damage, three important factors should be considered: accuracy, efficiency, and cost. Recently, a lot of attention has been paid to deep-learning models in the field of damage detection. These algorithms require enormous amounts of data, which takes a lot of time and energy. Moreover, such models are unlikely to be general enough due to the sophisticated and numerous types of damage that can occur to a building. So, these issues pose a serious limitation for their practical application in a disaster situation. Since this research put forward a novel and rapid method for detecting the damage to buildings on four levels using a designed removal decision tree. For testing the proposed method, orthophoto and DSM were derived from raw and post-event UAV images of two regions of Sarpol-e-Zahab. An overview of the presented framework for generating the damage map of buildings is depicted in figure1. In summary, our original contributions are described as follows:Taking into account three crucial parameters of crisis management including accuracy, cost, and time efficiency.Presenting a height anomaly index that distinguishes minor damage from major damage. In short, this index represents the percent of negative values in clustered DMS based on DBSCAN.Damage level detection according to EMS-98 standard in four levels, including, “no visible damage to slight damaged”, “Minor damaged”, ”major damaged”, and “collapsed”.Fig.1. The proposed method for detecting damage to buildings in 4 levelsThe results for two study areas of "Sarpol-e Zahab" reveals achieving an accuracy of 86% and a kappa coefficient of 81% for processing 142 buildings within just 15 seconds which indicates the efficiency and time efficiency of the proposed method. In addition, Because of being fully automatic (being unsupervised), the cost of this method is very low. As a consequence, our findings in this research revealed the high potential of UAV data for timely damage detection and rescue after an earthquake. However, the negative effects of shadows and trees are some of the challenges that should be considered in future research.

In recent decades, due to the various facilities in big cities that have caused the expansion of cities and urbanization and the increasing desire of citizens to live with a machine, this change in life pattern has also caused an increase in environmental pollution, difficult conditions for the livability of human life space, such as (The destruction of urban and suburban vegetation and the loss of ecological balance. The expansion of the population of cities and excessive population density in cities has caused the destruction of the natural environment and the construction of artificial structures that require physical and It has made the human spirit more visible to the environment. Considering that Iran is one of the countries located in the dry belt of the world, the cities to deal with noise and air pollution, as well as reduce environmental stress more than any other point to the space They need green. Considering the many problems that we see in changing the urban structure today, the heterogeneous quantification of the environment has been considered as a goal in landscape ecology, so that recently there have been efforts to develop methods In order to quantify the spatial heterogeneity (complexity and variability of the system characteristics, including the mosaic spatial layout of the land surface) (time and space) the features of the land have been done. Terrain metrics are a useful tool for expressing the mosaic pattern of urban green spaces and its changes in connection with urban development processes, which, in addition to interpreting the effect of the aforementioned processes on the ecological characteristics of the environment, can be used in decision making related to the growth of the city, distribution of uses and urban green space development planning. Therefore, according to the existing problems in defining and determining the urban green space, the application of remote sensing science, which is considered a powerful tool in the management of urban resources, and by providing the facilities of this science in order to provide up-to-date information, digital processing of images and the possibility of comparison Sometimes the data has helped experts to monitor the changes of the green space over time. Also, by using remote sensing in combination with terrain measurements, it can improve the understanding of urban spatial structure and change processes. Today, the high speed and extent of changes, both structural and process, in the face of the land, which are caused by destructive human activities, have made planners face many issues and problems. The present study was conducted in order to evaluate map production using Sentinel-1 and Landsat-8 radar images using local climate method and vector machine in Tehran metropolis. Using the proposed method, it was determined that the central and southern parts of Tehran have a very concentrated residential structure, so that urban green spaces are rarely seen in the urban context, while the green spaces in the north of Tehran are scattered among the contexts. It is residential, which indicates the existence of private green spaces in this part of the city. Also, in the south of the city, due to the presence of fine-grained texture in this area, due to the presence of residential centers in these areas, compared to the residential texture of the northern parts of the city, in the central and southern areas, private green spaces do not exist or rarely exist, and this warning increases. Heat islands and higher temperature are in the south of the city. Maps produced using remote sensing can be an alarm for municipal managers who can prevent future problems with planning and management. Also, considering the important role of green space in the morale of citizens and crime reduction, it is necessary for city managers to pay enough attention to the issue of reducing green space and the lack of proper distribution of use in Tehran, because neglecting this issue can lead to other problems. It created compensable for the citizens.

Analyzing natural hazards due to economic, environmental, and social effects is necessary for crisis management. However, good analysis comes from good data. In this case, natural hazard databases or inventories that contain all spatial, temporal, and other relevant information for each event are required. To realize that, news and social media, which provide detailed information about the hazards, are two precious resources. Nevertheless, most works manually extracted events from these text resources in the inventory development process. This paper presents a framework for extracting natural hazard events automatically from news stories by leveraging text mining techniques. By implementing the framework for the study region of Iran, we analyzed the spatial-temporal distribution of natural hazards.

According to spatial and temporal coverage of Mehr news agency, we selected this website as the main resource, and for training machine-learning-based models, we used ISNA's news articles. The process starts by mining web pages. All irrelevant records such as the news stories about maneuvers, conferences, and contradicts are removed automatically. Then, standardizing the texts of news articles should be accomplished. In the next stage, the text classification technique determines whether a news story is about a newly occurred event or a current event, in which context about the event the news story is published, and which natural hazards are pointed out in the text. For the first and the second text classification task, we used machine-learning-based models which achieved 0.875 and 0.716 for F-score, respectively. For the third task, we developed leveraged a rule-based model. The results of text classifications are used in the proceeding steps, including toponym recognition and resolution, information extraction, and topic detection and tracking.

The results show that although most natural hazards have a specific temporal distribution, the highest total frequency is for a Solar Hijri year's initial and final months. Spatially, the storm occurs more in eastern than western provinces. The diversity of other meteorological hazards, except dust, in northern provinces, is more than in southern ones. Regardless of the fatalities, the highest frequency of reported earthquake events is for southern provinces.

This paper presents a framework for automatically extracting natural hazard events from news stories. The framework leverages several text mining techniques such as text classification and information extraction to develop an inventory of the hazards. We implemented the framework to analyze the natural hazards of Iran from 1390 to 1400 Solar Hijri. Comparing the number of extracted events with the thematic maps published by the National Disaster Management Organization shows that the differences vary with the province. Based on that, the frequency of extracted events for some provinces equals the official statistics; hence the analysis for mined events is generalizable to real-world situations.

The earth and land surface have always changed over time. By identifying and modeling of types of these changes, accurate and up-to-date information will be available from the LULC. It is even possible to predict future land cover changes by considering geographical rules and patterns of change behavior. Satellite sensors are one of the most important remote sensing tools that provide images with different resolutions and regular and extensive data from land surfaces. On the other hand, the combination of these images, especially radar and optical images, according to the specific characteristics of each of them, has had an important impact on the development of methods for detecting and modeling changes. In this research, by using satellite images time series, the pattern of the spatial and temporal behavior of LULC changes in a specific time period was monitored and changes in land surface were modeled. Then LULC changes in the future time are predicted using the spatial-temporal model. The presented model used a spatial autoregressive relationship based on the seasonal and time series trend components. Phenological and temporal changes were modeled by determining the spatial correlation of changes in land cover by the remaining component. Using regression relationships, phenological and temporal changes were modeled according to the spatial correlation of changes in land cover by the component. Finally, considering all changes (gradual, seasonal, and abrupt) according to the designed regression function, a cubic spatial neighborhood window was defined. Array cubes (spatial-temporal) moved on the whole image. In each move, on the one hand, regression parameters were estimated, and by applying these estimates to known data, on the other hand, land cover at the next time was predicted by the spatio-temporal model. The main focus of this research is to recognize and predict the behavior of land cover changes over time by considering the spatial correlation of changes in neighboring pixels within a spatial-temporal model. In this regard, a combination of radar and optical images is used to simultaneously use the capabilities of these images in order to detect the types of land cover and identify their changes. Radar and Optical images are combined with an innovative approach based on a combination of feature-level and decision-level fusion. In the proposed method, the integration is performed based on the definition of a linear relationship between the feature extracted from radar images and optical images in a time series. In the process of combining images, thresholds have been used, which have been determined based on the features extracted from radar and optical images. The threshold for all land cover was determined experimentally by analyzing features extracted during the seasons (rainy and dry). To evaluate the accuracy of the predicted results with the approach presented in this study, the predicted results of land cover changes were compared with the results of land cover classification from the RF algorithm. According to this evaluation, the accuracy of forecasting changes for water bodies, vegetation, barren lands, and salt marsh was estimated to be 82.5, 94.9, 86.8, and 94.7%, respectively.

Biomass is a crucial component of the carbon cycle; thus, accurate evaluation is essential to manage the forest and understand its role in climate change. Biomass estimation also supports the international reduced emission from deforestation and forest degradation (REDD), including cases such as deforestation reduction, sustainable management of forests, protection and enhancement of forest carbon reserves). Today, using remote sensing techniques with the help of field data has revolutionized the estimation of forest biomass. Forest biomass estimation can be based on the processing of remote sensing data obtained from active sensors (for example, lidar and radar) and passive sensors (for example, optical sensors). In most previous studies, mainly vegetation indices (such as Normalized Difference Vegetation Index (NDVI), Ratio Vegetation Index (RVI), and Soil-Adjusted Vegetation Index (SAVI)) have been used to estimate biomass. Using terrain data, the amount of biomass is estimated using allometric equations, and the required pre-processing is done on optical and radar images. The attributes obtained from the scattering matrix and the ratios of the components of the scattering matrix and the attributes obtained from H/α decomposition are extracted from the radar image and the attributes of vegetation, soil and water are extracted from the optical image. Results and discussion  In this study, in order to improve the accuracy of estimating the biomass of forest areas, the features extracted from the optical images of Sentinel-2 sensor and Sentinel-1 radar data as well as field data of Noor forest areas, Mazandaran province, whose forest cover type, Carpinus betulus and Quercus Castaneifolia and also includes rare species such as Populus Caspica Bornm trees. In this study, we used the genetic optimization method in four classes of mixed vegetation, natural forest, degraded forest, and forest reserves were studied. In this regard, multivariate linear regression and support vector regression have been used to model between ground data and radar and optical features. Genetic algorithm (GA) is one of the most common evolutionary algorithms. This method finds potential solutions to optimize problems at the right time, especially when the search space is very wide. Also, a genetic algorithm has been used during the modeling process using multivariate linear regression to select the optimal features extracted from radar and optical images. Evaluation of the results showed that the use of the multivariate regression method led to more accurate results than the support vector regression method in the study area. Also, evaluation of the results showed that using features selected by a genetic algorithm led to an accurate R2 of 0.78, 0.87, 0.68, and 0.79 for first to fourth vegetation classes, respectively. Therefore, the results showed that the efficiency of the genetic algorithm in feature selection for biomass estimation from satellite images using the multivariate regression method.

Landslide is a geological phenomenon that occurs in the unstable slopes of mountainous areas and in some cases causes very severe human and economic losses.  Research shows that by using the classification of landslide prone areas, possible future damage can be prevented.  The purpose of this study is to produce a landslide sensitivity map for Ardabil province using two machine learning methods ANFIS and SVM and combining them with PSO and GWO metaheuristic algorithms.  For this purpose, first a landslide map of 253 points was prepared.  Among the slip points, 70% were considered for Training and the remaining 30% were used for validation.  Continuing and according to previous studies and available data, fourteen effective factors including height, slope, slope direction,profile curvature and plan curvature of the slope, land use, lithology, rainfall, distance from the road, distance from the river, distance from the fault, road density , river density and fault density were selected.  After preparing the database using MATLAB software, the combined models SVR - PSO , SVR - GWO , ANFIS - GWO and ANFIS - PSO were implemented and then the landslide sensitivity index was obtained for each model.  During the modeling process, the performance of each method was evaluated using the RMSE statistical index.  Finally, landslide sensitivity maps were generated for each model using ArcMap 10.5 software and then the accuracy of each map was estimated using the ROC curve.  The results show that the ANFIS - psd model is more efficient than the other three models. The results of ROC curve obtained by applying ANFIS - PSO  , ANFIS - GWO , SVR - PSO , SVR - GWO were 89.4, 85.7, 88.1, 88.7,respectively.

 One of the main public needs of people in all societies is public health. Identifying pathogenic agents and how they are transmitted and distributed in the environment is one of the management methods in providing the health needs of communities [1]. Studying the distribution of diseases is important for two reasons. First, these studies can be a way to find the causes of diseases, and second, the geographical distribution of diseases can be an indicator of how people and human groups interact with the environment [6]. Therefore, it is necessary to design a system for data management in order to control and care for infectious diseases. The spatial information system with the possibility of using satellite information is a new and cost-effective method in line with this need, which in the long run will compensate the initial investment by reducing the costs of data collection and disease control, and in addition, the way to use these facilities in information management systems. and provides care for other diseases. Because health and illness always have a spatial dimension [8]. Identifying and displaying spatial patterns plays an important role in establishing health policies. For many, spatial data analysis is the same as map production. The use of disease distribution maps for epidemiological purposes has a long history. The first step in the design of spatial information systems in Hamadan city is to examine the human location and the potential and actual information sources of the infectious disease care system. The main purpose of using the spatial information system is to strengthen and support the care and management system of infectious diseases and create the ability to analyze the spatial information and then make timely decisions [9].

 The studied area:

This research was implemented in Hamadan city. Demographic information was prepared from the demographic information related to the census of 2015 in Hamedan city, and to obtain information on infectious diseases, it was extracted from the classified information set of patients in Bo Ali Sina University of Medical Sciences, Hamedan city. Specific results of this research are presented in several sections.

 The information needed in this research is collected by using library studies, checking similar domestic and foreign research records, collecting descriptive information by questioning and studying the documents available in libraries, as well as field research. In this research, in order to develop the methodology and processes for investigating the distribution of diseases, as well as the effect of interactive GIS systems on the control and management of diseases, two series of analysis and evaluation are carried out. descriptive test and inferential test; Therefore, in order to implement the stage of identifying the distribution of diseases during a 5-year period in Hamedan city, first all the necessary data of the health centers and Boali University of Medical Sciences of Hamedan are prepared and collected, after verifying the information based on statistical methods and performing the Smirnov test. Kolmogorov, data distribution is examined. After that, the distribution of the obtained data is checked with the T-statistics test. Finally, after performing the descriptive test, this information is categorized and then analyzed based on the characteristics of the diseases and their time period, the results of these analyzes are shown in the form of tables and evaluation charts. In the spatial statistics test, in order to evaluate spatial systems on the control and management of diseases in a 5-year period, first, spatial information based on the location of the residence of each case, longitude and latitude related to the residence of each patient for the spatial analysis of the disease was obtained and in a database stored and then classified based on the main diseases. In this regard, after checking the accuracy of the entered data, secondary analysis is defined based on the main charts and tables. By examining the location of sick people in the geographic information system (GIS) and entering the information and characteristics of patients in this system, important information such as the distribution of the disease, examination of the produced clusters, geographical effects on the disease, the speed of spread and transmission of the disease can be obtained. For spatial analysis, Moran's spatial autocorrelation method and Pearson's statistical test are used to estimate the correlation of diseases with spatial characteristics in the GIS environment. It is also possible to implement a suitable system process framework in order to model the distribution of different diseases outside of the current research based on the mechanism of the spatial information system and satellite images in the control and management of diseases in any region. This framework includes types of diseases and time-spatial distribution patterns that cause and effect relationships between entities will be presented in the form of a block diagram.

Implementation:

 The purpose of this study is to prepare a map of the spatial and temporal clusters of infectious diseases, to investigate the factors affecting the disease and their impact, and finally to find a method to model the prevalence of the disease, this model can help disease management and control programs. All information and documents related to the causes of the disease were extracted by study and evaluation. In this regard, it is necessary to perform processing related to the model on descriptive items with the same spatial unit; Therefore, the required spatial unit was considered for all factors. In order to model the diseases using the moving average model, first the zoning map of Hamedan city was prepared using the number of infected patients in each region. Then, using the moving average model and using the Raster Calculator computing space in ArcGIS software, the final disease distribution model was produced.

Today, drones have received much attention due to their many benefits and wide range of applications such as mapping, agriculture, and crisis management, and have replaced many of the existing traditional methods. However, the expansion of drones and their unauthorized entry into important infrastructure such as government buildings can pose potential threats to public safety. Therefore, small drone detection, localization, and tracking systems are critical. In recent years, neural network-based diagnostic methods and deep learning approaches have shown considerable ability in the field of drone detection. Therefore, in this research, a detection method based on deep convolutional learning networks has been used to detect drones. On the other hand, the use of visible images faces problems such as the presence of hidden areas, crowded backgrounds, and the impossibility of separating the background and light problems inside the image. Also, thermal image-based systems, despite having night vision power, have less spatial resolution than the visible image, which makes the drone detection process difficult. Recently, the use of depth images, which do not have the challenges associated with visible images and show the distance and proximity of the object to the camera, has become very popular. In this research, drone detection has been performed using a collection of simulation and real depth images and using YOLO (You Only Look Once) deep learning network. The real depth images in this study were obtained through a Semi Global Matching algorithm (SGM), and finally, the validation of the trained model was examined with a variety of real-time and simulation depth images with three types of drones inside and outside the environment. Finally, the results of drone detection with the desired deep learning network in the simulation depth images reached an average precision of 84%, an average time of 125 ms, and in real depth images an average precision of 74%, an average time of 133 ms.

Chronic obstructive pulmonary disease restricts airflow in the respiratory system. After the age of 40 or 50, the symptoms of this disease become more apparent. According to studies, there were 251 million cases of COPD worldwide in 2016, which is expected to become the third leading cause of death in 2030. The symptoms of this disease include shortness of breath, chronic coughing, and phlegm over several days. While COPD cannot be cured, it can be identified by its symptoms, which will help to improve quality of life and reduce mortality risks. The fundamental principle in this type of disease is early diagnosis and timely access to medical care (including hospitalization). With the advancement of smart and remote technologies in many fields, especially health and treatment, humans have been able to improve and solve problems more efficiently. In recent years, context awareness has become one of the new and practical concepts in the area of health diagnosis and treatment, due to its combination with fuzzy expert systems. Based on this, a system can be context-aware, which includes information to describe the activities of users of a program, so the information is the context. Because the diagnosis process is patient-centered, this information provides them with the possibility of quick notification of abnormalities, which in turn prevents wasted time and money. As a result, this information provides a suitable background for accurate and early prediction of abnormalities for efficient treatment. It seems necessary to design a system that compensates for the previous shortcomings and uses modern concepts of context and context awareness since no study has been conducted regarding the diagnosis of COPD disease by tissue-awareness method and direct communication with the user has not been used in their treatment methods.

The purpose of this model is to create high-level context information based on low-level data. To achieve this goal, low-level context data are converted into different fuzzy sets that form inputs for the fuzzy inference engine, and then they are converted into high-level meaningful information, and based on this knowledge base, conclusions are drawn about the risk level of the disease. There are several factors that can be used to diagnose the level of COPD, including: 1) Air pollution level 2) Disease symptoms 3) Age 4) Cold and hot environmental conditions (temperature). In order to investigate the effective tissues in determining the severity of the disease, 60 patients with chronic obstructive pulmonary disease during one year (2018) in 25 medical centers of Ilam city were asked to provide their medical history and personal characteristics, as well as they completed their questionnaire under the supervision of a doctor. The slope of belonging to a set slowly changes into "not belonging to it" in fuzzy sets, unlike classical sets. There are four basic steps in a fuzzy inference system: fuzzification, knowledge base, decision making unit, and defuzzification. Using the existing rule base, the decision-making unit obtains the diagnostic levels of COPD disease (normal, moderate, severe), which can then be used with the de-fuzzification of the outputs. All the data received from the patients were entered into the fuzzy system and the output was compared with the recorded diagnosis of the specialist doctor to evaluate the system. In order to evaluate and perform the fuzzy system in the diagnosis of COPD, the Kappa test, accuracy, sensitivity, and F1 scores were used.

The determination of effective individual and environmental contects for diagnosing chronic obstructive pulmonary disease was first prepared using library research and risk assessments of determining factors, and then based on a lung disease specialist's opinion. As a result, the fuzzy expert system was designed based on the parameters of the symptoms (such as coughing, chest phlegm, feelings of heaviness in the chest, breathing, sleeping, energy level, range of physical activity, relief from leaving the house - despite the physical condition), air pollution level, age, cold and hot environmental conditions (temperature), etc. After determining the membership functions, it is necessary to create the rule base. According to four system inputs, 183 "if-then" rules were performed. By using the Kappa statistical test, we compared the fuzzy expert system's diagnosis with that of the relevant doctor's final diagnosis. The Kappa statistical test had a value of 0.77, which indicated a very strong relationship between the variables. In the confusion matrix, which is used to evaluate the model's performance, the accuracy value was equal to 0.8167, the sensitivity value was equal to 0.8182, and the F1 score was equal to 0.8791.

A fuzzy context-based expert system is a new approach that provides accurate and quick information to patients by inferring individual and environmental contexts. The purpose of this study is to gain a deeper understanding of the user's current condition and to determine the level of their illness with the addition of the user's participation in receiving personal and environmental contexts, as well as his participation in decision-making. The approach presented in this article can be repeated and implemented in other situations. This method can be applied in different regions and cities or different division levels such as districts or provinces.

Traffic and its problems have become a big social issue in all societies today. Knowing essential factors that affect traffic, and the factors that aggravate traffic can be useful for managing the traffic. Nowadays, the problem of traffic forecasting has become a goal among different countries. If one can predict the traffic, he can prevent the waste of energy and time. Predicting the traffic situation and its behavior, especially in big cities, requires managing, planning, and spending time. Geographic Information System (GIS) is an important technology and science for spatial analysis. Since traffic is a spatial and temporal problem, this science can well manage the problem of traffic. In the field of traffic, people often look for a route that meets the criteria of being short, low cost, and consuming the least amount of energy. For this reason, traffic is one of the most influential factors in choosing the route to reach the destination. It can be said that people prefer a long route with little traffic to a short route with heavy one. Thus, traffic affects many optimal route equations. Therefore, it is clear that the main criterion for choosing a route is the traffic situation on the relevant route. In this research, the collection of traffic data of Tehran province has been done using the proposed platform. Traffic data exists in real time, but the problem is that there is no platform for data collection. The lack of a suitable platform for storing traffic data has always been a problem that has challenged researchers in this field. Therefore, in this research, a method for collecting and storing traffic data on the web platform has been proposed. In this research, traffic images are first captured from web platforms. Then the intensity of the traffic is identified based on the color scheme. According to the position of the pixels in the image and the existing control points, the ground coordinates of all the pixels are calculated. Finally, the collected coordinates are stored in the database based on the standard spatial format. Finally traffic data is stored in the database instantly based on the current system. During this research, it was found that the point that has heavy traffic has heavy traffic in most hours of the day. It was also found that places with heavy traffic have a uniform behavior during different days of the week. In other words, it is rarely seen that points with different traffic loads have a significant difference in the traffic situation. In terms of accuracy, it can be stated that the collection of traffic data points has been done with acceptable accuracy in terms of location. The collected points are also the most compatible with other data in the database.

Today, location recommender systems have made it possible to analyze and recommend location services for different users. The ability to personalize the provision of services to various system users has increased the applicability and efficiency of such systems. The personalization of recommendations in the field of sports venues is one of the urban services that can be very effective in increasing the level of health of citizens and society. The purpose of the current research is to design a personalized knowledge-based recommender system so that people can receive the most suitable and optimal positions for receiving sports services based on their needs and conditions. In order to implement the proposed plan, different people were clustered based on their characteristics and personal conditions with the help of the self-organizing neural network algorithm, and in order to model the uncertainty, the preferences of the elderly were entered into the intuitive fuzzy inference engine and a clear and accurate output was obtained and given to the user. In this research, the knowledge recommender system has been designed as a personalized basis for providing sports recommendation services so that citizens can receive the most appropriate and optimal services based on their needs and conditions. In order to implement the proposed plan, the characteristics and personal conditions of people were obtained based on various online questionnaires and based on the unsupervised neural network of self-organizer mapping, people with similar characteristics were placed in specific groups, and in this way, and the basic knowledge base for the recommender system was created. Finally, through the descriptive combination of the obtained outputs from the information of the users, optimal positions have been extracted for recommending and displaying the output of the system on the map, Django library, which is a web-based programming platform, has been used. From the Open-Layer location library and J-Query library, the desired location should be shown on the OSM map as a map under mobile. After that, through the designed user interface, the personal characteristics of the people are received, then, the individual cluster is determined, and in order to model the uncertainty, the information received from the citizens is entered into the fuzzy inference engine of the second type. The outputs obtained from the designed algorithm will be displayed as a set of positions and the user can see its position on the map by selecting any of these positions. Then, an explicit and accurate output of the user's preferences has been achieved and a recommendation is made from the inflectional combination of the outputs obtained from the two designed sections, and suitable outputs are recommended to the user. Finally, the system was evaluated based on three parameters: accuracy (0.74), sensitivity (0.81), and F-Score (0.77), and the results indicate a good and acceptable performance of the system.