The Analysis of Spatial-Temporal Evolution of City Accessibility Based on Highway Network in Henan Province in China

Accessibility is an important tool to evaluate the maturity of a regional traffic network structure which describes the traffic convenience in the traffic network. The paper defines a new accessibility index by using the resident population weighted average value of the sum of inverse of the traveling time distance and time threshold coming from ordinary traffic network, and then uses this accessibility index to analyze the spatial-temporal characteristics of Henan highway network, as well as its evolution patterns from 2005 to 2020. The results show that with the expansion and improvement of Henan highway network, city accessibility level has been significantly improved, spatial convergence is obvious, the cities in the north central are always High-High aggregation area, the cities in the south are always Low-Low aggregation area, gradually forming the characteristics of Northwest high and Southeast low, relative balance between East and West. There is some non-conforming phenomenon in highway mileage growth and improvement of the city accessibility levels, but this situation is being weakened, the highway network layout is gradually rationalized, the spatial distribution of city accessibility and that of population are beginning to converge.

Geohazards and risk assessment along highway in Sichuan Province, China

Geohazards along highways are the main natural hazards that could affect the safety and operation of highway systems.Understanding the risks faced by highways in areas affected by geohazards is an urgent problem to be solved.This study used historical geohazard events from Sichuan Province and highway network data to propose a geohazard risk index that reflects the risk geohazards along highways.Furthermore,this work applied the entropy method and expert scoring to calculate the weight of the index.The spatial distributions of landslides,debris flows,collapses,and unstable slopes along the highways were analysed based on ArcGIS spatial statistics,and the highway geohazard intensity index were obtained.The relationships between slope,rainfall,vegetation coverage,rock type,land use,and incision depth with geohazards were analysed,and the highway geohazard susceptibility index was calculated by the weighted information method.Based on the intensity and susceptibility index,we obtained a geohazard risk index which can better evaluate the risk of highways,and made a highway geohazard risk map to aid the prevention and mitigation of geohazards along highways and assist with highway network planning.

Economic Assessment of Planned Projects in Highway Network Planning

This paper presents a method of economic assessment for planned projects in the process of highway network planning. Economic assessment method is being done on the basis of cost benefit analysis, and the cost and benefit calculation methods are discussed respectively.

HAM:a deep collaborative ranking method incorporating textual information

The recommendation task with a textual corpus aims to model customer preferences from both user feedback and item textual descriptions.It is highly desirable to explore a very deep neural network to capture the complicated nonlinear preferences.However,training a deeper recommender is not as effortless as simply adding layers.A deeper recommender suffers from the gradient vanishing/exploding issue and cannot be easily trained by gradient-based methods.Moreover,textual descriptions probably contain noisy word sequences.Directly extracting feature vectors from them can harm the recommender’s performance.To overcome these difficulties,we propose a new recommendation method named the HighwAy reco Mmender(HAM).HAM explores a highway mechanism to make gradient-based training methods stable.A multi-head attention mechanism is devised to automatically denoise textual information.Moreover,a block coordinate descent method is devised to train a deep neural recommender.Empirical studies show that the proposed method outperforms state-of-the-art methods significantly in terms of accuracy.

Towards better entity linking

As one of the most important components in knowledge graph construction,entity linking has been drawing more and more attention in the last decade.In this paper,we propose two improvements towards better entity linking.On one hand,we propose a simple but effective coarse-to-fine unsupervised knowledge base(KB)extraction approach to improve the quality of KB,through which we can conduct entity linking more efficiently.On the other hand,we propose a highway network framework to bridge key words and sequential information captured with a self-attention mechanism to better represent both local and global information.Detailed experimentation on six public entity linking datasets verifies the great effectiveness of both our approaches.