Abolghasem Sadeghi-Niaraki

Designing Road Maintenance Data Model Using Dynamic Segmentation Technique

Road maintenance management covers a wide spectrum of activities including road construction, rehabilitation and maintenance programs, etc. Geospatial Information Systems (GIS) can immensely assist the decision makers in these applications. Arc-node data models represent roads as linear features with associated attributes. The attributes are linked to arcs with similar length and location without attention to the applications at hand. In addition, these models do not provide the efficient way to present more detailed information of roads. Because Arc-node structure defines the linear feature as an arc and it is not possible to present road data varying in different parts of arc. Therefore, road maintenance data models which are only on the basis of Arc-node structure result in inefficient analysis and even the results which are not consistent with reality. In order to improve the flexibility of such Arc-node presentation in GIS-T, this paper scientifically examines Dynamic Segmentation (DS), that it is an efficient means to manage the heterogeneous attributes along the arcs. Moreover, this research proposed the road maintenance data model using DS technique. The data model in this work was successfully implemented in the Iranian road network. The result on real data illustrated the merits of the present approach.

GIS-based ride-sharing and DRT in Tehran city

In this paper, due to the inefficiency of implemented ride-sharing (RS) and demand responsive transport (DRT) systems in recent decades, these two systems are integrated in order to design a spatial system to manage numbers of single-passenger vehicles and, also, efficiently use public fleet capacity. In the designed system, after preparing and pre-processing on data, in the RS stage, the proposed system searches for fellow travellers for private vehicle users with priority given firstly to the applicants owning a private vehicle. And then, in the DRT stage, the remaining applicants are formed into DRT fellow traveller groups in which each DRT fellow traveller group is assigned an appropriate public vehicle and a parking lot. The proposed system is implemented based on real commuting trips taken in Tehran. The effectiveness of the system is mainly evaluated by comparing the decrease of mileage, gas consumption, and total travel time per vehicle.

A semantic-based classification and regression tree approach for modelling complex spatial rules in motor vehicle crashes domain

Innovative data mining and knowledge discovery approaches that take advantage of geospatial analysis can be useful for analysis of motor vehicle crashes on regional highway corridors. This study presents an Ontology‐based Classification and Regression Tree (OCART) approach to induct crash rules on regional highway corridors by adding ontological reasoning to Classification and Regression Tree (CART) decision rules. It develops an ontology‐driven geospatial framework to predict the motor vehicles crash severity through the proposed OCART approach. A system prototype has been developed and implemented on a regional highway corridor in order to illustrate and evaluate the proposed method. The results demonstrate the application of ontological reasoning and spatial computation significantly improves the performance of CART crash rules. The proposed method reveals new relationships among crash severities and contributing factors that have been kept implicit in CART decision rules. WIREs Data Mining Knowl Discov 2015, 5:181–194. doi: 10.1002/widm.1152

Ontology driven road network analysis based on analytical network process technique

During the past several years, Geographic information system (GIS) has allowed storage, editing, maintenance, dissemination, display and access of geospatial data. Ontologies are a level of description of the knowledge of an application that is independent of internal structure. Existing techniques related to the impedance model for each road segment which is utilized in a route finding algorithm is inadequate. The most impedance models are based on one-dimensional criterion such as distance or time which does not give proper results. Hence, this research investigates how impedance criteria of road segment can represent the real world in GIS using ontology driven architecture. To address this, first several criteria including quantitative as well as qualitative criteria such as traffic and climate are taken into account. Second, to weight these criteria, the Analytical Network Process (ANP) method is proposed. Finally, the impedance model is implemented and verified with real road network data.