Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Jun Feng is active.

Publication


Featured researches published by Jun Feng.


Smart Innovation, Systems and Technologies | 2014

Index and Query Methods in Road Networks

Jun Feng; Toyohide Watanabe

This book presents the index and query techniques on road network and moving objects which are limited to road network. Here, the road network of non-Euclidean space has its unique characteristics such that two moving objects may be very close in a straight line distance. The index used in two-dimensional Euclidean space is not always appropriate for moving objects on road network. Therefore, the index structure needs to be improved in order to obtain suitable indexing methods, explore the shortest path and acquire nearest neighbor query and aggregation query methods under the new index structures.Chapter 1 of this book introduces the present situation of intelligent traffic and index in road network, Chapter 2 introduces the relevant existing spatial indexing methods. Chapter 3-5 focus on several issues of road network and query, they involves: traffic road network models (see Chapter 3), index structures (see Chapter 4) and aggregate query methods (see Chapter 5). Finally, in Chapter 6, the book briefly describes the applications and the development of intelligent transportation in the future.


industrial and engineering applications of artificial intelligence and expert systems | 2004

Heuristic approach based on lambda-interchange for VRTPR-tree on specific vehicle routing problem with time windows

Naoto Mukai; Jun Feng; Toyohide Watanabe

One of the difficulties of using Artificial Neural Networks (ANNs) to estimate atmospheric temperature is the large number of potential input variables available. In this study, four different feature extraction methods were used to reduce the input vector to train four networks to estimate temperature at different atmospheric levels. The four techniques used were: genetic algorithms (GA), coefficient of determination (CoD), mutual information (MI) and simple neural analysis (SNA). The results demonstrate that of the four methods used for this data set, mutual information and simple neural analysis can generate networks that have a smaller input parameter set, while still maintaining a high degree of accuracy.


industrial and engineering applications of artificial intelligence and expert systems | 2004

Incremental maintenance of all-nearest neighbors based on road network

Jun Feng; Naoto Mukai; Toyohide Watanabe

One of the difficulties of using Artificial Neural Networks (ANNs) to estimate atmospheric temperature is the large number of potential input variables available. In this study, four different feature extraction methods were used to reduce the input vector to train four networks to estimate temperature at different atmospheric levels. The four techniques used were: genetic algorithms (GA), coefficient of determination (CoD), mutual information (MI) and simple neural analysis (SNA). The results demonstrate that of the four methods used for this data set, mutual information and simple neural analysis can generate networks that have a smaller input parameter set, while still maintaining a high degree of accuracy.


international conference on tools with artificial intelligence | 2005

Behavioral decision based on abstraction of pheromone distribution for transport vehicles

Naoto Mukai; Toyohide Watanabe; Jun Feng

In this paper, we focus on behavioral decisions for empty transport vehicles e.g., they should wait on their place or go to other places. Effective behaviors of empty vehicles enable to decrease waiting times of customers. Our algorithm to acquire such effective behaviors is based on transport experiences of vehicles (i.e., history). It means that vehicles adjust to their city environment by learning trends of transport demands (e.g., amounts and directions). Our algorithm consists of learning and abstraction stages. In the learning stage, vehicles acquire low-level rules of actions at an intersection. In the abstraction stage, vehicles acquire high-level rules of actions in a region. Finally, we report simulation results and show the effectiveness of our algorithm


pacific rim international conference on artificial intelligence | 2004

Indexing approach for delivery demands with time constraints

Naoto Mukai; Jun Feng; Toyohide Watanabe

Demand-bus system is focused as a new transportation system. Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) we address is a simple environment model for demand-bus system. In the problem, delivery demands with time constraints occur enduringly. Share-ride vehicles transport customers to their destination. In order to solve this problem, we propose CRTPR-Tree which indexes moving vehicles on a road network. A node of the tree consists of a pointer to vehicle (in leaf nodes) or pointers to child nodes (in intermediate nodes), a bounding rectangle, and a time constraint. Moreover, we propose two scheduling algorithms based on time traveling measure (TTM) or time constraint measure (TCM) for delivery orders of customers. We performed experiments with the profitability and the usability on an ideal environment. The experimental results show that our approach produces good effects.


international conference on information technology coding and computing | 2003

Index structure for managing multi-levels of road networks on distributed environment

Jun Feng; Toyohide Watanabe

With a view to attaining the shareability and consistency of map information under a distributed environment, we propose a multi-level/multi-theme map information model to maintain maps in consistency with original source datasets. However, the distributed management of spatial datasets results in a complex maintenance processing, especially when the modification refers to several datasets. To solve this problem effectually, in this paper we propose an index structure, the MOR-tree (multi-levels-object-relation tree), for organizing the integrated maintenance procedure. The MOR-tree is an extension of the R-tree index structure with the ability of indexing spatial objects of multi-levels in one hierarchy and recording relations among objects at different levels. The performance of MOR-tree is also evaluated with a prototype system in this paper.


Archive | 2003

Search of Continuous Nearest Target Objects along Route on Large Hierarchical Road Network

Jun Feng; Toyohide Watanabe


Transactions of the Institute of Systems, Control and Information Engineers | 2003

A Fast Search Method of Nearest Target Object in Road Networks

Jun Feng; Toyohide Watanabe


Ieej Transactions on Electronics, Information and Systems | 2002

Effective Representation of Road Network on concept of Object Orientation

Jun Feng; Toyohide Watanabe


日本データベース学会letters | 2003

Representation of Transportation Network and Continuous Nearest Neighbor Search

Jun Feng; Naoto Mukai; Toyohide Watanabe

Collaboration


Dive into the Jun Feng's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge