Road-network traffic monitoring on city-scale is critical for a wide range of applications, such as traffic forecasting, congestion identification, traffic safety, and urban planning, etc. Despite the fruitful research outcomes, however, most traffic monitoring models suffered from limited coverage, data sparsity, and data deviation, which leads to a biased and inaccurate result. With the widespread usage of mobile phones, mobile signaling data is of great value for various fields, especially for monitoring urban traffic. Thousands cell towers are distributed in the urban area, which can serve as ubiquitous sensors. Specifically, a mobile phone will passively generate a mobile signaling record that contains users’ spatiotemporal information. When mobile phone users move with their phones, their phones will interact with cell towers and these towers can obtain their mobile signaling records. And these signaling records contain sufficient information for traffic monitoring. However, there also exists excessive noise in signaling records, which makes most monitoring models abandon these data. In this paper, we present the Urban-STM scheme, which utilizes large-scale anonymous and coarse-grained mobile signaling data to infer road-network traffic conditions. We apply our scheme to a real-world signaling dataset in Changchun city and present an extensive validation study based on 2000 taxicabs’ GPS trajectories. Experiment results show that our scheme improves traffic monitoring performance in terms of coverage and accuracy.

The speed and efficiency of overloaded artificial screening bus images are relatively low, which results in a large number of human resources waste problems. Therefore, an overload classification method for bus images based on image processing and support vector machine was proposed to intelligently identify the image overload or not. Based on the consideration we have done the following work. Firstly, the bus images were preprocessed, including image enhancement using histogram equalization method and image segmentation using improved Otsu algorithm; Secondly, the features of the segmented images was extracted by Kirsch edge detection operator to establish the image feature sample library; Finally, the appropriate kernel function and parameters were chosen to establish a classifier model based on support vector machine, which can train the sample library to classify the bus images. Theoretical analysis and experimental results show that the average classification accuracy of the polynomial kernel function is better than those of the Gaussian kernel function and the Sigmoid kernel function in the finite range of parameters selection. When the parameter d of the polynomial kernel function is 4, the classification accuracy is 93.68%, and its classification performance is stable and there is no significant increase or fall. And the conclusion was verified in the actual application.

The 3D reconstruction can facilitate the diagnosis of liver disease by making the target easier to identify and revealing the volume and shape much better than 2D imaging. In this paper, in order to realize 3D reconstruction of liver parenchyma, a series of pretreatments are carried out, including windowing conversion, filtering and liver parenchyma extraction. Furthermore, three kinds of modeling methods were researched to reconstruct the liver parenchyma containing surface rending, volume rendering and point rendering. The MC (marching cubes) algorithm based on 3D region growth is proposed to overcome the existence of a large number of voids and long modeling time for the contours of traditional MC algorithms. Simulation results of the three modeling methods show different advantages and disadvantages. The surface rendering can intuitively image on the liver surface modeling, but it cannot reflect the inside information of the liver. The volume rendering can reflect the internal information of the liver, but it requires a higher computer performance. The point rendering modeling speed is quickly compared to the surface rendering and the volume rendering, whereas the modeling effect is rough. Therefore, we can draw a conclusion that different modeling methods should be selected for different requirements.

We introduced the idea of network connection structure and position matching into the design of the routing protocol of the pocket switched networks (PSN ),and solved the routing problem of message packets from two aspects:global search and local search.Firstly,from exploring the global network connection structure of information transmission effect, we knew the most effective communication node in complex networks should be the most core node located in the network connection structure, instead of nodes with high global society degree. Secondly, we discussed the rationality and feasibility of local search based on position matching degree.Finally,we proposed a routing protocol based on social structure degree and node active network,namely K core. Message is forwarded in the global community initially,and message is forwarded to the node in the center of the network until node to be forwarded the message is located near the destination node of the message.Then the message is forwarded according to the position matching degree of the nodes in the vicinity.Compared with classical protocols,the proposed method can achieve a higher delivery success rate and less cost on the basis of guaranteeing almost the same message delay.

According to the serial correlation characteristics of liver CT images, in this paper, based on the morphology expansion and corrosion method, we put forward a liver CT sequence image segmentation method based on region growing algorithm. First conduct the smoothing denoising pretreatment to the sequence image([1]), and then select an image, and the region growing algorithm was adopted to realize the liver parenchyma area division. We adopt expansion and corrosion to process the segmentation result. Later we take it as the seed point of the next image. Finally we finish all the liver CT sequence image segmentation. Experimental results show that this method can effectively conduct the liver sequence image segmentation, and fill the empty after sequence segmentation, greatly reducing the user interaction.

Specific to the lack of effective domain division method and much first-order fuzzy relationship, this paper proposes a second-order Markov model based fuzzy time series prediction method. It uses fuzzy C-means clustering to obtain the membership of elements in the time series. It introduces the transition matrix in second-order Markov model to represent fuzzy relations. It updates traditional representation and calculation of fuzzy relations. It forecasts the element’s membership in fuzzy clusters and defuzzifies the membership using the center-of-gravity method. It applies the model to the performance predic-tion of China Mobile 3G, and the accuracy is improved when compared to the traditional fuzzy time series prediction method.

For the characteristics of liver images and the shortcomings of the traditional region growing algorithm, a liver segmentation method based on RBF-CI (RBF-Confidence Interval) is proposed. On the basis of the application of window adjusting technology and the anisotropic diffusion method, the RBF neural network learning algorithm is introduced to calculate the coefficient of the confidence interval in order to reduce users' interaction amount and realize adaptive liver image segmentation. Simulation results show that, the proposed RBF-CI region growth segmentation algorithm can achieve effective segmentation results of liver images. For the ten sets of the liver images, while our proposed segmentation algorithm result achieves an average accuracy rate of 90.86%, which indicates the segmentation is accurate.

As a promising procedure of mobile application. So far, lifelogging has already some initial attempts on photos, audios and video records. However, they are just simple information recording tools, in which the receivers cannot feel the senders with empathy in space or time. In this poster, we propose a concept called MemoryRetrospect, which combines Lifelogging with Social Awareness. It considers not only our daily photos and videos, but also the weather, the locations and time. When and how to open the e-records can be set by the senders' willing. Thus the receivers have a chance to feel the true space-time meaning of the e-records. More exactly, every e-record will be packaged in a capsule, which the senders are able to set with kinds of scenes as the activation conditions for recipients. With this, the recipients can experience and understand senders' happiness, beautiful moments and emotions at some certain moment.

An intensity statistics based graph cut segmentation algorithm is proposed in this paper to improve the accuracy and adaptive capacity of liver segmentation. The proposed segmentation method consists of four steps as follows: First, combined with the Otsu algorithm and associated with a cropped liver image, we defined a gray interval as the liver's intensity range. Second, the fuzzy c-means clustering algorithm was applied to compute the average intensity and the variance. Third, we establish the cost function with the statistic results. Finally, we employed the improved graph cut model to extract the liver parenchyma from a large cross-section liver image. Experimental results show that the proposed segmentation method is feasible for different liver images of different intensity statistics.

According to the characteristics of the liver image and the shortcomings of the traditional region growing algorithm, a modified region growing algorithm is proposed based on the adaptive anisotropic filtering. The first, a anisotropic filtering algorithm is proposed based on adaptive anisotropic filtering and we make images noise reduction through it. Second, we studied a method which can select seeds automatically, then the parameters which are in the region growing algorithm will be obtained through Otsu. These innovations and improvements enable segmentation algorithm automatic, fast, accurate. Experiments show that, the algorithm that this article proposed the region growing based on adaptive image segmentation of the liver, the result is better than the traditional region growing algorithm.

A FCM-based segmentation algorithm is proposed in this paper to improve the accuracy and efficiency of liver parenchyma segmentation. The proposed segmentation method consists of four steps as follows:First,we characterized the gray distribution of the unfiltered image. Second, combined with the Otsu algorithm and associated with a cropped liver image, we defined a gray interval as the liver's intersity range. Third, The fuzzy c-means clustering algorithm was applied to define the confidence interval of traditional confidence connectivity method. Finally, we employed the improved confidence connected algorithm to extract the liver parenchyma from a large cross-section liver image. Experimental results show that the proposed segmentation method is feasible even for diseased liver images.

Ray casting algorithm is a kind of widely used volume rendering algorithm in the field of medical 3D reconstruction. One of the greatest advantages of it is the high rendering quality, while the rendering speed is rather low. In order to accelerate the rendering speed, in this paper, it proposed an accelerated ray casting algorithm which is based on the proximate cloud algorithm, combined with empty voxel leaping and fast interpolation. Meanwhile, it also analyzed the complexity of computing to significantly enhance the speed of the algorithm on volume rendering.

Aiming to the need of proactive monitoring and performance prediction in 3G networks,it proposes a prediction method of the Gaussian regression model based on the median filter,integrates the Gaussian regression model with the median filtering method,pretreats the sample data with median filtering,and then the processed data is done to the Gaussian regression prediction,the prediction results are as the prediction curve of the active alarm mechanism.Simulation results show that compared to other prediction algorithms,the Gaussian process based on median filtering predicts more effectively and generates more accurate prediction curves.It provides a theoretical basis for proactive monitoring in 3G and above network to determine an effective threshold.

Specific to the need of performance prediction in communication networks,a connection rate prediction method based on fuzzy Auto-Regressive(AR) model was proposed and improved,and the fuzzy AR model based on adaptive fitting degree threshold was studied.The median filtering method was applied to pre-process the data of fuzzy AR model.On this basis,for the uncertain thresholds of some applications,the fitting degree threshold formula was added to the prediction model to make it adaptive.The simulation results show that the predistion method based on fuzzy AR model can be used to predict the connection rate with a higher fitting degree.

The current researches about the Internet of Things pay less attention to the service model,especially to the method on the mapping between resources and users′ needs for active service.In order to solve this issue,service resource selection strategy by three-tier structure under the Internet of Things,including priority selection based on the grade of service resources was proposed,followed by the selection mechanism based on the user terminal needs and user preference.A estimation method of service resource level based on fuzzy logic was also proposed.Not only solved the problem of blindness of services resource selection under the Internet of Things,but also made the granularity of service resources selection be more detailed to meet the individual needs of user.

针对TD-SCDMA网络的故障告警信息量大,且具有衍生性和相似性的特点,采用属性相似度的关联分析方法,对故障告警信息压缩、过滤、归一化处理,可有效提高告警数据的质量,结合TD-SCDMA网络故障的特点,讨论了总体属性、网元、时间、告警等级属性的相似度计算方法。

In the Quadtree Partition, Images need to be encoded. IFS provides this issue a unique way. According to it, we construct the IFS model based on quadtree segmentation and find the model's Hutchinson operator and IFS attractor. Based on the above, we re-establish WEMSDNM, during which traits of the field of business domain stand out. Comparing with the traditional algorithms by experiment, the result indicates that its performance has been improved to a certain extent.

For fair shortcomings of current existing algorithms of the Proportional Delay Differentiated(PDD) services model in the relative differentiated,the enhanced algorithm for differentiated service based on probability(WPPLQ) for the mobile location services platform is proposed.This algorithm in calculating the waiting time is optimized to make it more accurate,and by calculating the packet size to determine the service response time,so that the scheduling algorithm is more fair.By the NS-2 simulation platform,the algorithm is simulated and tested.It is verified that the PLQ algorithm and the WPPLQ algorithm are in line with performance requirements which grading the quality of service and feasibilities of differentiated service in PDD model.And it show that WPPLQ algorithm has higher fairness.

The primitive in the different formats needs to be associated by the primary key.According Heinz,Hartmut and Dietmars weighted information theory,we use a different way to deal with it.Based on the idea,we construct WEMFBCDNM(Weighted Entropy Model Based on Fractal Box Counting Dimension and Natural Measure),which is more suitable for the vector diagram format.Comparing with the traditional algorithms,this method has improved its performance to a certain extent.