Predictability performance enhancement for suspended sediment in rivers:Inspection of newly developed hybrid adaptive neuro-fuzzy system model

Reliable modeling of river sediments transport is important as it is a defining factor of the economic viability of dams, the durability of hydroelectric-equipment, river susceptibility to pollution, suitability for navigation, and potential for aesthetics and fish habitat. The capability of a new machine learning model, fuzzy c-means based neuro-fuzzy system calibrated using the hybrid particle swarm optimization-gravitational search algorithm（ANFIS-FCM-PSOGSA） in improving the estimation accur...     

An efficient approach for historical storage and retrieval of segmented road data in Geographic Information System for Transportation

One of the most powerful functions of Geographic Information System for Transportation(GIS-T)is Dynamic Segmentation(DS),which is used to increase the efficiency and precision of road management by generating segments based on attributes.The road segments describing transportation data are both spatially and temporally referenced.For a variety of transportation applications,historical road segments must be preserved.This study presents an appropriate approach to preserve and retrieve the historical road segments efficiently.In the proposed method,only the portions of segments of a time stamp that have been changed into new segments rather than storing the entire segments for every old time stamp are recorded.The storage of these portions is based on the type of changes.A recursive algorithm is developed to retrieve all segments for every old time stamp.Experimental results using real data of Tehran City,Iran justify the strength of the proposed approach in many aspects.An important achievement of the results is that database volume for 2006,2007 and 2008 within the Historical Line Event Table(HLET)is reduced by 70%,80%and 78%,respectively.The proposed method has the potential to prevent from vast data redundancy and the unnecessary storage of entire segments for each time stamp.Since the present technique is performed on ordinary plain tables that are readable by all GIS software,special software platforms to manage the storage and retrieval of historical segments are not needed.In addition,this method simplifies spatio-temporal queries.