Mining Social Groups with Weighted Similarity in Campus Wireless Network

With the popularity of wireless networks and the prevalence of personal mobile computing devices, understanding the characteristic of wireless network users is of great significance to the network performance. In this study, system logs from two universities, Dartmouth College and Shanghai Jiao Tong University(SJTU), were mined and analyzed. Every user's log was represented by a user profile. A novel weighted social similarity was proposed to quantify the resemblance of users considering influence of location visits. Based on the similarity, an unsupervised learning method was applied to cluster users. Though environment parameters are different, two universities both form many social groups with Pareto distribution of similarity and exponential distribution of group sizes. These findings are very important to the research of wireless network and social network .

A weight's agglomerative method for detecting communities in weighted networks based on weight's similarity

This paper proposes the new definition of the community structure of the weighted networks that groups of nodes in which the edge＇s weights distribute uniformly but at random between them. It can describe the steady connections between nodes or some similarity between nodes＇ functions effectively. In order to detect the community structure efficiently, a threshold coefficient t~ to evaluate the equivalence of edges＇ weights and a new weighted modularity based on the weight＇s similarity are proposed. Then, constructing the weighted matrix and using the agglomerative mechanism, it presents a weight＇s agglomerative method based on optimizing the modularity to detect communities. For a network with n nodes, the algorithm can detect the community structure in time O（n2 log~）. Simulations on networks show that the algorithm has higher accuracy and precision than the existing techniques. Furthermore, with the change of t~ the algorithm discovers a special hierarchical organization which can describe the various steady connections between nodes in groups.

Feasibility of similarity coefficient map for improving morphological evaluation of T_2* weighted MRI for renal cancer

The purpose of this paper is to investigate the feasibility of using a similarity coefficient map（SCM） in improving the morphological evaluation of T2＊ weighted（T2＊W） magnatic resonance imaging（MRI） for renal cancer.Simulation studies and in vivo 12-echo T2＊W experiments for renal cancers were performed for this purpose.The results of the first simulation study suggest that an SCM can reveal small structures which are hard to distinguish from the background tissue in T2＊W images and the corresponding T2＊ map.The capability of improving the morphological evaluation is likely due to the improvement in the signal-to-noise ratio（SNR） and the carrier-to-noise ratio（CNR） by using the SCM technique.Compared with T2＊ W images,an SCM can improve the SNR by a factor ranging from 1.87 to 2.47.Compared with T2＊ maps,an SCM can improve the SNR by a factor ranging from 3.85 to 33.31.Compared with T2＊W images,an SCM can improve the CNR by a factor ranging from 2.09 to 2.43.Compared with T2＊ maps,an SCM can improve the CNR by a factor ranging from 1.94 to 8.14.For a given noise level,the improvements of the SNR and the CNR depend mainly on the original SNRs and CNRs in T2＊W images,respectively.In vivo experiments confirmed the results of the first simulation study.The results of the second simulation study suggest that more echoes are used to generate the SCM,and higher SNRs and CNRs can be achieved in SCMs.In conclusion,an SCM can provide improved morphological evaluation of T2＊W MR images for renal cancer by unveiling fine structures which are ambiguous or invisible in the corresponding T2＊W MR images and T2＊ maps.Furthermore,in practical applications,for a fixed total sampling time,one should increase the number of echoes as much as possible to achieve SCMs with better SNRs and CNRs.

A Visual Attention Model for Robot Object Tracking

Inspired by human behaviors, a robot object tracking model is proposed on the basis of visual attention mechanism, which is fit for the theory of topological perception. The model integrates the image-driven, bottom-up attention and the object-driven, top-down attention, whereas the previous attention model has mostly focused on either the bottom-up or top-down attention. By the bottom-up component, the whole scene is segmented into the ground region and the salient regions. Guided by top-down strategy which is achieved by a topological graph, the object regions are separated from the salient regions. The salient regions except the object regions are the barrier regions. In order to estimate the model, a mobile robot platform is developed, on which some experiments are implemented. The experimental results indicate that processing an image with a resolution of 752 × 480 pixels takes less than 200 ms and the object regions are unabridged. The analysis obtained by comparing the proposed model with the existing model demonstrates that the proposed model has some advantages in robot object tracking in terms of speed and efficiency.

Prediction of network public opinion features in urban planning based on geographical case-based reasoning

As a significant part of sustainable urban development proposed by the United Nations,urban planning is related to the ecological environment and transportation,especially affecting quality of life and social well-being. In the process of urban planning,the public express their opinions on open network platforms,resulting in large quantities of network public opinion data,which has important implications for evaluating urban planning. Based on the idea of geographical case-based reasoning (CBR),this paper constructs an expression framework for urban planning cases in the form of a ‘case problem–case attribute–case result’ triad. On this basis,this paper proposes a similarity calculation method of urban planning cases that integrates case attribute. Finally,based on an improvement to the traditional k-nearest neighbors method,the proposed public opinion feature calculation model considers similarity weights,which allow us to predict network public opinion features,including viewpoint-level emotional tendency and concerned groups of urban planning cases. The experimental result shows similarity weights (SWs) model could effectively improve the prediction accuracy,where the average MIC-F1 score reached more than 74%. Based on CBR,the proposed method can predict the development trends of public opinion in future planning cases,and provide scientific and reasonable decision support for urban planning.

Consistent Depth Maps Estimation from Binocular Stereo Video Sequence

In the paper, an approach is proposed for the problem of consistency in depth maps estimation from binocular stereo video sequence. The consistent method includes temporal consistency and spatial consistency to eliminate the flickering artifacts and smooth inaccuracy in depth recovery. So the improved global stereo matching based on graph cut and energy optimization is implemented. In temporal domain, the penalty function with coherence factor is introduced for temporal consistency, and the factor is determined by Lucas-Kanade optical flow weighted histogram similarity constraint(LKWHSC). In spatial domain, the joint bilateral truncated absolute difference(JBTAD) is proposed for segmentation smoothing. The method can smooth naturally and uniformly in low-gradient region and avoid over-smoothing as well as keep edge sharpness in high-gradient discontinuities to realize spatial consistency. The experimental results show that the algorithm can obtain better spatial and temporal consistent depth maps compared with the existing algorithms.