Change point detection is crucial for identifying state transitions and anomalies in dynamic systems, with applications in network security, health care, and social network analysis. Dynamic systems are represented by dynamic graphs with spatial and temporal dimensions. As objects and their relations in a dynamic graph change over time, detecting these changes is essential. Numerous methods for change point detection in dynamic graphs have been developed, but no systematic review exists. This paper addresses this gap by introducing change point detection tasks in dynamic graphs, discussing two tasks based on input data types: detection in graph snapshot series (focusing on graph topology changes) and time series on graphs (focusing on changes in graph entities with temporal dynamics). We then present related challenges and applications, provide a comprehensive taxonomy of surveyed methods, including datasets and evaluation metrics, and discuss promising research directions.

Federated Learning (FL) has been extensively applied in urban environmental prediction tasks of mobile edge computing by training a global machine learning model without data sharing. However, the training of FL faces the challenges such as the poor generalization capability of a single global model over heterogeneous data and hefty communication overhead caused by the frequent model exchange between massive edge servers and remote cloud servers. To address such issues, we propose HPFL-CN, a novel communication-efficient Hierarchical Personalized Federated edge Learning framework with Complex Network clustering. HPFL-CN introduces Privacy-preserving Feature Clustering (PFC) to extract privacy-preserving low-dimensional feature representations of each edge server via mapping the environmental data to different complex network domains for clustering similar edge servers accurately. Based on the clustering results of PFC, anedge-mediator-cloudhierarchical architecture is proposed to realize personalization at the cluster level by Effective Hierarchical Scheduling (EHS). Furthermore, to adapt to dynamic scenarios of new edge servers joining and streaming data generation, we further extend HPFL-CN to Adaptive personalized federated learning with dynamic grouping (Ada-HPFL-CN), which can flexibly re-group edge servers and adjust mixed model weights and the model aggregation frequency adaptively. Our extensive experiments on real-world datasets demonstrate the efficacy of our framework, which outperforms state-of-the-art FL methods regarding personalization and communication efficiency performance.

Sparse mobile crowdsensing (Sparse MCS) is an emerging paradigm for urban-scale sensing applications, which recruits suitable participants to complete sensing tasks in only a few selected cells and then infers data of unsensed cells for saving sensing costs and obtaining high-quality sensing maps. In Sparse MCS, one crucial issue is task assignment, in which the platform selects cells whose sensing data can reduce inferred sensing maps errors (i.e., cell selection) and recruits the participant set with the maximum contribution for performing tasks (i.e., participant recruitment). The research on participant recruitment mainly focuses on single participatory-based or single opportunistic-based sensing mode. Due to the complementarity of two sensing modes, recruiting participants by only one sensing mode would result in wasting sensing resources and compromising the quality of task completion. Thus, combining the advantages of two sensing modes, we propose a task assignment framework based on hybrid sensing modes in Sparse MCS (HSM-SMCS) for achieving a good tradeoff between sensing quality and cost. Specifically, we propose a heuristic two-stage search strategy that simultaneously recruits opportunistic and participatory participants to perform tasks in significant cells within the constraint of total costs, considering their contributions to sensing map inference. Thereinto, for opportunistic participants, mobility prediction greatly affects task assignment effectiveness. However, existing prediction algorithms lead to unsatisfactory outcomes when the historical trajectory data of opportunistic participants are scarce. To effectively improve the predictive accuracy, we design a mobility prediction model based on transfer learning. The experimental evaluation on real trajectory data sets and sensor data sets of corresponding areas demonstrates that our framework outperforms state-of-the-art methods with higher quality reconstructed sensing maps.

Federated Learning (FL), a promising privacy-preserving distributed learning paradigm, has been extensively applied in urban environmental prediction tasks of Mobile Edge Computing (MEC) by training a global machine learning model without data sharing. However, it is hard for the shared global model to be well generalized among local edge servers, due to the statistical data heterogeneity, especially in real-world urban environmental data. Besides, the existing FL approaches may result in excessive communication and computation overhead due to the frequent transmission and aggregation of model parameters between massive edge servers and remote cloud servers. To address the above issues, we propose HPFL-CN, a novel communication-efficient Hierarchical Personalized Federated edge Learning framework via Complex Network feature clustering, aiming to cluster edge servers with similar environmental data distributions and then high-efficiently train personalized models for each cluster via hierarchical architecture. Specifically, HPFL-CN introduces Privacy-preserving Feature Clustering (PFC) to extract privacy-preserving low-dimensional feature representations of each edge server via mapping the environmental data to different complex network domains for clustering similar edge servers accurately. According to the clustering results of PFC, HPFL-CN further introduces an edge-mediator-cloud architecture for hierarchical model aggregation by Effective Hierarchical Scheduling (EHS), in which every mediator coordinates the training of edge servers within each cluster and periodically uploads model to cloud server for global model aggregation. Meanwhile, each mediator server would find a trade-off between cloud and edge models to realize personalization within clusters. Our extensive experiments on real-world datasets demonstrate the effectiveness and generalization of HPFL-CN, which outperforms other state-of-the-art FL methods regarding personalization performance and communication efficiency.

In the Distributed Parallel Stream Processing Systems (DPSPS), elastic resource allocation allows applications to dynamically response to workload fluctuations. However, resource provisioning can be particularly challenging, due to the unpredictability of the workload. In addition, unlike CPU resources, bandwidth resources are often ignored in resource allocation. Moreover, resource allocation and resource placement are considered separately. In this paper, we investigate the proactive elastic resource scheduling problem for computation-intensive and communication-intensive applications, which aims at meeting the latency requirement with the minimal energy cost, and propose a dynamic collaborative strategy from the systemic perspective. Specifically, we first model a collaborative workload prediction pattern to accurately predict the upcoming workload, and construct a latency estimation model to estimate the latency of the application. Then, we design an energy-efficient resource pre-allocation method, in which the CPU frequency adjustment and the stability of resource reconfigurations are both considered. Finally, we present a communication-aware resource placement approach. Simulation results show that, compared with the reactive strategies, our strategy achieves an obviously better latency performance, and effectively avoids unnecessary resource adjustments. Meanwhile, the energy consumption is about saved by 50 percent on average, and the communication cost is maintained at a very low level of 4 percent.

With increasing real-time and resource-intensive requirements, approximate computing is widely adopted to improve the performance of query processing over data streams. However, existing works concentrate on simple queries with single-step operations, such as point or join queries. There are a large number of nested queries with selection or filtering operations before aggregation. In this poster, we focus on approximate nested stream queries. We first propose a novel approximate model, SCM-sketches, that makes two-stage approximation for nested query answering with guaranteed errors. In the first stage for nested filtering operations, we use the sampling method to compress the arriving data. Then in the second stage, a sketch is used for further aggregation or join operations. We also theoretically analyze the effect of error propagation on approximate errors. Compared with existing sketch-based methods, experiment results with real-life datasets verify the effectiveness of SCM-sketches.

In online approximate stream processing, customers generally submit their requests with some specific quality requirements (e.g. maximum error). This raises a critical problem that online quality control is necessary to meet customized requirements. Since continuous arriving data needs to be processed immediately, it brings the difficulty of acquiring knowledge which significantly affects the efficiency of sampling. Hence, it's more challenging to ensure a prescribed level of quality without knowledge about data. In this paper, we present an adaptive approximate processing framework for online stream applications to address the challenges mentioned above. Specially, we first design a new data knowledge learning scheme to stratify the arriving stream data. Then, based on the online learning results, we propose a dynamic sampling strategy with the consideration of the stream rate. Finally, we further present a double-check error control mechanism to manage the output quality. Experiments with real world datasets show that the proposed approximate framework is not only applicable to different data distributions, but also provides a customized error control.

Satisfying spatial-temporal coverage requirement in the interested regions while considering the quality of the sensing data with budget limitation is a major research challenge in mobile crowdsensing. Most existing research in this field focus on the number of sensor readings collected in each covered subarea and do not consider individual differences of participants for contributing to data quality improvement. In this paper, we propose a novel coverage metric, quality coverage, which considers both the spatial coverage and the quality of sensing data and then use task allocation approaches to achieve highly diverse and spatial quality coverage level within a limited budget for different application scenarios.

In China, the rapid development of medical informatization and the increasing public health awareness greatly stimulate the growth of Electronic Physical Records (EPR). This paper focuses on analyzing and mining electronic physical records to provide constructive suggestions for people's lifestyles using data of thirty thousand individual records in 2009 within the nine-month period from April to December, at China-Japan Union Hospital of Jilin University. During the analyzing process, numerous challenges were faced such as data storage, data noise and data incompletion etc. Thus we designed a framework as the resolution to these problems, and utilized data mining methods including association rules to find the characteristics of all ages in Changchun and gained some satisfactory results such as the abnormal BMI increasing with age. We also utilized the community discovery algorithm to explore the relationship between abnormal physical indicators. However, the result is not satisfactory and the module cant even reach 0.1. To solve the problem of information isolation in China, we also implement a data platform.

In recent years, rapidly accumulating genomic data have posed a challenge to integrate multiple data sources and to analyze the integrated networks globally. In this paper we present a method to reverse engineer integrative gene networks. The main advantage of our method is the integration of different quantitative and qualitative data sets in order to reconstruct a multiplex network, without necessarily imposing data constraints, such as each genomic datum needs to have the same number of entities. The computation boils down to solving small quadratic programs based on local neighborhood of nodes. We applied the method to DREAM5 dataset, and compared the results with the community networks from the challenge. We further demonstrated our method through a case study using breast cancer data, integrating metastasis gene expression data with interactome data. Overall, our method can be applied in many settings of network system biology.

Information technology is advancing faster than anticipated. The amount of data captured and stored in electronic form by far exceeds the capabilities available for comprehensive analysis and effective knowledge discovery. There is always a need for new sophisticated techniques that could extract more of the knowledge hidden in the raw data collected continuously in huge repositories. Biomedicine and computational biology is one of the domains overwhelmed with huge amounts of data that should be carefully analyzed for valuable knowledge that may help uncovering many of the still unknown information related to various diseases threatening the human body. Biomarker detection is one of the areas which have received considerable attention in the research community. There are two sources of data that could be analyzed for biomarker detection, namely gene expression data and the rich literature related to the domain. Our research group has reported achievements analyzing both domains. In this paper, we concentrate on the latter domain by describing a powerful tool which is capable of extracting from the content of a repository (like PubMed) the parts related to a given specific domain like cancer, analyze the retrieved text to extract the key terms with high frequency, present the extracted terms to domain experts for selecting those most relevant to the investigated domain, retrieve from the analyzed text molecules related to the domain by considering the relevant terms, derive the network which will be analyzed to identify potential biomarkers. For the work described in this paper, we considered PubMed and extracted abstracts related to prostate and breast cancer. The reported results are promising; they demonstrate the effectiveness and applicability of the proposed approach.

Genes are encoding regions that form essential building block within the cell and lead to proteins which are achieving various functions. However, some genes may be mutated due to internal or external factors and this is a main cause for various diseases. The latter case could be discovered by closely examining samples taken from patients to identify faulty genes. In other words, it is important to identify mutated genes as disease biomarkers. Then consider certain normal and infected samples to build a classifier model capable of successfully classifying new samples as infected or normal. The work described in this paper addresses this problem by introducing a comprehensive framework that incorporates the two stages of the process, namely feature selection and sample classification. In fact, high dimensionality in terms of the number of genes and small number of samples distinguishes gene expression data as an ideal application for the proposed framework. Reducing the dimensionality is essential to efficiently analysis the samples for effective knowledge discovery. Actually, there is a tradeoff between feature selection and maintaining acceptable accuracy. The target is to find the reduction level or compact set of features which once used for knowledge discovery will lead to improved performance and acceptable accuracy. For the first stage, we concentrate on four feature selection techniques, namely chi-square from statistics, frequent pattern mining and clustering from data mining, and community detection from network analysis. The effectiveness of the feature reduction techniques is demonstrated in the second stage by coupling them with classification techniques, namely associative classification, support vector machine and naive Bayesian classifier. Majority voting is applied for both stages. The results reported for four cancer datasets demonstrate the applicability and effectiveness of the proposed framework.

Mining sequential patterns is an important activity in computerized data analysis, and further analysis of discovered patterns can lead to more important findings in a post mining stage. Methods that integrate the traditional mining tasks with a know

In parallel to rapid growth of internet technologies, security becomes more critical in various real life applications such as e-finance, e-health, and e-government. These applications strictly require data authentication mechanisms. To address this essential issue, we grasp the idea of client based authenticity for interactive web technologies. We proposed a novel client based web form signing and checking with XML data structure method. Our method specifically uses XML structure for the involvement of data exchange between web applications. Our method curbs the DoS (Denial of Service) attacks for protection of the server. In order to illustrate our ideas, we adapted our digital signature mechanism on health related forms with two commonly used web browsers.

Automated text summarization is important to for humans to better manage the massive information explosion. Several machine learning approaches could be successfully used to handle the problem. This paper reports the results of our study to compare the performance between neural networks and support vector machines for text summarization. Both models have the ability to discover non-linear data and are effective model when dealing with large datasets.