Fengjing Shao

Detecting Community Structure in Networks by Propagating Labels of Nodes

Community structure is a common property of many networks. Automatically finding communities in networks can provide invaluable help in understanding the structure and the functionality of networks. Many algorithms to find communities have been developed in recent years. Here we devise a new algorithm to detect communities in networks--propagation algorithm. By propagating the labels of nodes in networks, detecting communities are transformed into analyzing the labels of nodes in networks in this algorithm. Real-world and computer-generated networks are used to verify this algorithm. The results of our experiments indicate that it is sensitive to community structure and effective at discovering communities in networks.

Water quality assessment with hierarchical cluster analysis based on Mahalanobis distance

Water quality assessment is crucial for assessment of marine eutrophication, prediction of harmful algal blooms, and environment protection. Previous studies have developed many numeric modeling methods and data driven approaches for water quality assessment. The cluster analysis, an approach widely used for grouping data, has also been employed. However, there are complex correlations between water quality variables, which play important roles in water quality assessment but have always been overlooked. In this paper, we analyze correlations between water quality variables and propose an alternative method for water quality assessment with hierarchical cluster analysis based on Mahalanobis distance. Further, we cluster water quality data collected form coastal water of Bohai Sea and North Yellow Sea of China, and apply clustering results to evaluate its water quality. To evaluate the validity, we also cluster the water quality data with cluster analysis based on Euclidean distance, which are widely adopted by previous studies. The results show that our method is more suitable for water quality assessment with many correlated water quality variables. To our knowledge, it is the first attempt to apply Mahalanobis distance for coastal water quality assessment.

A Sequential Pattern Mining Algorithm Based on Improved FP-tree

Sequential pattern mining is an important data mining problem with broad application. Most of the previously developed sequential pattern mining methods need to scan the database many times. In this study, STMFP algorithm based on improved FP-tree is presented for sequential pattern mining. By improving the FP-tree structure, every node of the tree can store a set of items instead of one item. After scanning the sequential database once time, the tree can store all the sequences. In addition, a novel mining method, combining nodes from leaf to root which helps mining sequential patterns, is proposed. The cost of mining pattern sequence is divided into two parts. One is to construct STMFP Tree. The cost of this part associates with the size of sequential database. Another one is to find random assembled nodes from leaf to root in every path of STMFP tree. Because the maximal length of path is bounded by the maximal length of one transaction, and there are exiting common nodes which help reduce the number of leaf nodes, so the cost of this part must be much less than the size of the database. Compared with other methods which need to scan the sequential database many times, the cost of our method must be less than two passes of the database. Through the whole mining process, it only needs scan the database once time.

Complex network model of the Treatise on Cold Damage Disorders

Abstract Investigating the underlying principles of the Treatise on Cold Damage Disorder is meaningful and interesting. In this study, we investigated the symptoms, herbal formulae, herbal drugs, and their relationships in this treatise based on a multi-subnet composited complex network model (MCCN). Syndrome subnets were constructed for the symptoms and a formula subnet for herbal drugs. By subnet compounding using MCCN, a composited network was obtained that described the treatment relationships between syndromes and formulae. The results obtained by topological analysis suggested some prescription laws that could be validated in clinics. After subnet reduction using the MCCN, six channel (Tai-yang, Yang-ming, Shao-yang, Tai-yin, Shao-yin, and Jue-yin) subnets were obtained. By analyzing the strengths of the relationships among these six channel subnets, we found that the Tai-yang channel and Yang-ming channel were related most strongly with each other, and we found symptoms that implied pathogen movements and transformations among the six channels. This study could help therapists to obtain a deeper understanding of this ancient treatise.

Network Propagation with Dual Flow for Gene Prioritization

Based on the hypothesis that the neighbors of disease genes trend to cause similar diseases, network-based methods for disease prediction have received increasing attention. Taking full advantage of network structure, the performance of global distance measurements is generally superior to local distance measurements. However, some problems exist in the global distance measurements. For example, global distance measurements may mistake non-disease hub proteins that have dense interactions with known disease proteins for potential disease proteins. To find a new method to avoid the aforementioned problem, we analyzed the differences between disease proteins and other proteins by using essential proteins (proteins encoded by essential genes) as references. We find that disease proteins are not well connected with essential proteins in the protein interaction networks. Based on this new finding, we proposed a novel strategy for gene prioritization based on protein interaction networks. We allocated positive flow to disease genes and negative flow to essential genes, and adopted network propagation for gene prioritization. Experimental results on 110 diseases verified the effectiveness and potential of the proposed method.

The MagicARPhone: An AR-Based Game on Phone Offering Personalized Enjoyment

Mobile phone is an ideal platform for Augmented Reality. However, there is no related application supplying users with changeable and optional experience of three-dimension models. MagicARPhone, a new type of Augmented Reality game allowing users to see their favorite three-dimension models coexisting with the real world on their smart phone, is proposed in this paper. The phone undertakes the whole AR processing. Various 3-D models are available on MagicARPhone wap site, which allows users to download their fond ones by wireless network. Besides, users could upload their models to share their enjoyment. A Model Parser on the server is created to export the useful model data for reconstructing the visual scene on smart phone.

Boarding Stations Inferring Based on Bus GPS and IC Data

Understanding bus passengers’ flow patterns is an important guide for optimization of public transport system. In most cities buses have been equipped with GPS devices and Smart IC card fare devices, which leads to amount of real-time geocoded data of buses and passengers. Usually these two kinds of data could be combined for inferring passengers’ boarding stations. However, in some cases there is no straightforward relation between them, such that boarding station of passengers are unknown. In this paper, an inferring method for finding the correspondence between these two types of data is proposed. This method was validated by Qingdao data. Based on that, we analyze the spatio-temporal distribution of passengers’ flow.

Construction and Analysis of Meteorological Elements Correlation Network

Analysis of the correlation between meteorological elements could help find climate changing patterns. In this paper, the time series of meteorological elements, such as pressure, temperature and humidity, are converted to a correlation network, in which nodes represent the correlation relation (state) between the two meteorological elements and edges represent the transformation between different states. By analyzing the topological properties of the correlation network (degree, strength, path, etc.), the correlation patterns between meteorological elements could be found. Empirical studies of Weifang with 9 years climate observation data show that the correlation network has a power-law distribution and sub-seasonal characteristics. The correlation between temperature and pressure are more strongly negative and it did not change significantly with the year went. The correlation shows a seasonal variation that more negative correlation in summer and the spring as follows.

An automatic detection of green tide using multi-windows with their adaptive threshold from Landsat TM/ETM plus image

Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of green tide is presented from Landsat TM/ETM plus image which needs not the atmospheric correction. In order to achieve an automatic detection of green tide, a linear relationship (y =0.723x+0.504) between detection threshold y and subtraction x (x=λnir–λred) is found from the comparing Landsat TM/ETM plus image with the field surveys. Using this relationship, green tide patches can be detected automatically from Landsat TM/ETM plus image. Considering there is brightness difference between different regions in an image, the image will be divided into a plurality of windows (sub-images) with a same size firstly, and then each window will be detected using an adaptive detection threshold determined according to the discovered linear relationship. It is found that big errors will appear in some windows, such as those covered by clouds seriously. To solve this problem, the moving step k of windows is proposed to be less than the window width n. Using this mechanism, most pixels will be detected [n/k]×[n/k] times except the boundary pixels, then every pixel will be assigned the final class (green tide or sea water) according to majority rule voting strategy. It can be seen from the experiments, the proposed detection method using multi-windows and their adaptive thresholds can detect green tide from Landsat TM/ETM plus image automatically. Meanwhile, it avoids the reliance on the accurate atmospheric correction.

Weighted Bipartite Network Projection for Personalized Recommendations

Abstract—To reduce the difficulty of personalized recommendations, the traditional network-based method constructed bipartite networks with stronger links (higher ratings). However, weaker links and link weights were almost ignored. Although the existing method effectively mined users’ preferences, it was impossible to catch users’ disgusts. Therefore, this paper proposed a novel method to effectively discover users’ preferences and disgusts. Experimental results on the MovieLens dataset demonstrated that the proposed method was much more superior to the baseline method under the diversity index.