National Engineering Research Center for Geographic Information System

Wuhan, China

National Engineering Research Center for Geographic Information System

Wuhan, China
Time filter
Source Type

Lee J.,Henan University | Lee J.,Kent State University | Gong J.,Wuhan University | Li S.,Wuhan University | Li S.,National Engineering Research Center for Geographic Information System
International Journal of Geographical Information Science | Year: 2017

We examined three different ways to integrate spatial and temporal data in kernel density estimation methods (KDE) to identify space–time clusters of geographic events. Spatial data and time data are typically measured in different units along respective dimensions. Therefore, spatial KDE methods require special extensions when incorporating temporal data to detect spatiotemporal clusters of geographical event. In addition to a real-world data set, we applied the proposed methods to simulated data that were generated through random and normal processes to compare results of different kernel functions. The comparison is based on hit rates and values of a compactness index with considerations of both spatial and temporal attributes of the data. The results show that the spatiotemporal KDE (STKDE) can reach higher hit rates while keeping identified hotspots compact. The implementation of these STKDE methods is tested using the 2012 crime event data in Akron, Ohio, as an example. The results show that STKDE methods reveal new perspectives from the data that go beyond what can be extracted by using the conventional spatial KDE. © 2017 Informa UK Limited, trading as Taylor & Francis Group

Zhou Z.,Wuhan University | Zhou Z.,National Engineering Research Center for Geographic Information System | Yu F.,Wuhan University | Yu F.,National Engineering Research Center for Geographic Information System | And 2 more authors.
4th International Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services - Proceedings of IEEE UPINLBS 2016 | Year: 2016

The emergence of geofences makes it easy to push geo-notifications. It is important for pedestrians in indoor environments to receive notifications in certain rooms as well as different floors. The existing methods only use the characteristics of the wireless signal to distinguish geofences. However, wireless signals are unstable in some areas and often limited to a single floor. This may poses problems to deliver geo-notifications in multi-floor indoor environments. In this paper, we propose iGeoNoti, a fine-grained indoor geo-notification system. It adopts indoor pedestrian reachable distance (PRD) to define an indoor geofence represented by the graph. The isolated rooms and floors can be thus represented as the whole one graph-based indoor geofence. As a proof of concept, the system provides a web user interface to describe indoor geofence scenarios according to the understandable semantic rules. We evaluate iGeoNoti in real world. The experimental results show that it is easy to define indoor geofence in our proposed system by using the PRD-based rule and geo-notifications can be triggered in fine-grained locations. © 2016 IEEE.

Wang D.,University of Florida | Shang J.,Wuhan University | Shang J.,National Engineering Research Center for Geographic Information System | Cheng W.,Wuhan University | Li X.,University of Florida
4th International Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services - Proceedings of IEEE UPINLBS 2016 | Year: 2016

Sub-room-level location-based services are poised to impact people's daily lives in the near future. Sub-room-level semantic location history (SLH) construction is an essential component of such services. However, little in-depth research on constructing SLH in sub-room-level scenarios has been conducted. In this paper, we propose iMiner, an automatic sub-room-level SLH construction system. iMiner consists of an improved Kalman filter-based approach to obtain accurate location and heading estimation from inertial sensor readings of smartphones. The collected users' location and heading histories arc further mined to estimate areas of interaction (AOIs). AOT is a novel idea and a powerful tool for accurately embedding points of interest into geographic trajectories. A series of experiments were conducted in two large-scale sites. The results have demonstrated the effectiveness of the proposed system. © 2016 IEEE.

Yu W.,Wuhan University | Yu W.,National Engineering Research Center for Geographic Information System
PLoS ONE | Year: 2017

Regional co-location scoping intends to identify local regions where spatial features of interest are frequently located together. Most of the previous researches in this domain are conducted on a global scale and they assume that spatial objects are embedded in a 2-D space, but the movement in urban space is actually constrained by the street network. In this paper we refine the scope of co-location patterns to 1-D paths consisting of nodes and segments. Furthermore, since the relations between spatial events are usually inversely proportional to their separation distance, the proposed method introduces the “Distance Decay Effects” to improve the result. Specifically, our approach first subdivides the street edges into continuous small linear segments. Then a value representing the local distribution intensity of events is estimated for each linear segment using the distance-decay function. Each kind of geographic feature can lead to a tessellated network with density attribute, and the generated multiple networks for the pattern of interest will be finally combined into a composite network by calculating the co-location prevalence measure values, which are based on the density variation between different features. Our experiments verify that the proposed approach is effective in urban analysis. © 2017 Wenhao Yu. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Yanmei L.,Design Science | Yuda C.,National Engineering Research Center for Geographic Information System
Proceedings - 2015 8th International Symposium on Computational Intelligence and Design, ISCID 2015 | Year: 2016

Micro-blog sentiment analysis aims to find user's attitude and opinion of hot events. Most of studies have used SVM, CRF and other traditional algorithms, which based on manual tagging of a lot of emotional characteristics, but paid a high price. To improve this situation, further studied deep learning and Micro-blog sentiment analysis, and proposed a new technical solution. It firstly crawled some data from Micro-blog through crawler, then after corpus pretreatment, as the input sample of Convolutional Neural Network, and built the classifier based on SVM/RNN, finally judged the emotional orientation of each sentence in a given test set. Verified by examples, experimental results show that this solution can effectively improve the accuracy of emotional orientation, validation result is ideal. © 2015 IEEE.

Su G.,National Engineering Research Center for Geographic Information System | Su G.,CAS Qingdao Institute of Oceanology | Lin F.,CAS Qingdao Institute of Oceanology | He S.,CAS Qingdao Institute of Oceanology | Sun J.,CAS Qingdao Institute of Oceanology
International Conference on Geoinformatics | Year: 2016

In order to improve display effect and analysis and decision ability of marine geology information, the Marine Geology 3D Geographic Information System is established based on Skyline software and Visual studio.NET development platform. It is a WebGIS application platform, builds submarine 3D scene by using the satellite image and marine geology survey data, provides 3D scene roaming, attribute query, submarine terrain browsing, sea level rise simulation, coastline change simulation, mineral resources evaluation and other functions, provides service for marine geology survey, development, management, and decision making. This paper mainly introduces the design of system framework, data preparation, and function realization for the purpose of discussing the design and realization of 3D WebGIS based on Skyline. © 2015 IEEE.

Hu X.,Wuhan University | Hu X.,National Engineering Research Center for Geographic Information System | Shang J.,Wuhan University | Shang J.,National Engineering Research Center for Geographic Information System | And 3 more authors.
International Journal of Distributed Sensor Networks | Year: 2015

Indoor localization techniques using Wi-Fi fingerprints have become prevalent in recent years because of their cost-effectiveness and high accuracy. The most common algorithm adopted for Wi-Fi fingerprinting is weighted K-nearest neighbors (WKNN), which calculates K-nearest neighboring points to a mobile user. However, existing WKNN cannot effectively address the problems that there is a difference in observed AP sets during offline and online stages and also not all the K neighbors are physically close to the user. In this paper, similarity coefficient is used to measure the similarity of AP sets, which is then combined with radio signal strength values to calculate the fingerprint distance. In addition, isolated points are identified and removed before clustering based on semi-supervised affinity propagation. Real-world experiments are conducted on a university campus and results show the proposed approach does outperform existing approaches. © 2015 Xuke Hu et al.

Shang J.,Wuhan University | Shang J.,National Engineering Research Center for Geographic Information System | Gu F.,University of Melbourne | Hu X.,Wuhan University | And 2 more authors.
Sensors (Switzerland) | Year: 2015

The utility and adoption of indoor localization applications have been limited due to the complex nature of the physical environment combined with an increasing requirement for more robust localization performance. Existing solutions to this problem are either too expensive or too dependent on infrastructure such as Wi-Fi access points. To address this problem, we propose APFiLoc—a low cost, smartphone-based framework for indoor localization. The key idea behind this framework is to obtain landmarks within the environment and to use the augmented particle filter to fuse them with measurements from smartphone sensors and map information. A clustering method based on distance constraints is developed to detect organic landmarks in an unsupervised way, and the least square support vector machine is used to classify seed landmarks. A series of real-world experiments were conducted in complex environments including multiple floors and the results show APFiLoc can achieve 80% accuracy (phone in the hand) and around 70% accuracy (phone in the pocket) of the error less than 2 m error without the assistance of infrastructure like Wi-Fi access points. © 2015 by the authors; licensee MDPI, Basel, Switzerland.

He X.-Z.,National Engineering Research Center for Geographic Information System | He X.-Z.,Wuhan University
International Conference on Geoinformatics | Year: 2016

After analog and digital mapping, it is now heading towards information-based map production era. How to provide high-quality, real time Geo-information products and diversified services has become the highlight in the information-based mapping stage. This paper elaborates on database-driven map production technical, a delta-based map products dynamic update solution, in order to provide new guidelines and new methods for product updating under the information-based mapping system. These technical guidelines have already been successfully applied to the national 1 50 000 topographical map production. © 2015 IEEE.

Chen G.,Wuhan University | Chen G.,National Engineering Research Center for Geographic Information System | Zeng A.,Zhengzhou University | Zeng A.,State Key Laboratory of Geographic Information Engineering | And 4 more authors.
Solid Earth | Year: 2016

To establish the horizontal crustal movement velocity field of the Chinese mainland, a Hardy multi-quadric fitting model and collocation are usually used. However, the kernel function, nodes, and smoothing factor are difficult to determine in the Hardy function interpolation. Furthermore, the covariance function of the stochastic signal must be carefully constructed in the collocation model, which is not trivial. In this paper, a new combined estimation method for establishing the velocity field, based on collocation and multi-quadric equation interpolation, is presented. The crustal movement estimation simultaneously takes into consideration an Euler vector as the crustal movement trend and the local distortions as the stochastic signals, and a kernel function of the multi-quadric fitting model substitutes for the covariance function of collocation. The velocities of a set of 1070 reference stations were obtained from the Crustal Movement Observation Network of China, and the corresponding velocity field was established using the new combined estimation method. A total of 85 reference stations were used as checkpoints, and the precision in the north and east component was 1.25 and 0.80mmyr-1, respectively. The result obtained by the new method corresponds with the collocation method and multi-quadric interpolation without requiring the covariance equation for the signals. © Author(s) 2016.

Loading National Engineering Research Center for Geographic Information System collaborators
Loading National Engineering Research Center for Geographic Information System collaborators