Magnetic Resonance Imaging (MRI) plays a crucial role in brain disease diagnosis, but it is not always feasible for certain patients due to physical or clinical constraints. Recent studies attempt to synthesize MRI from Computed Tomography (CT) scans; however, low-dose protocols often result in highly sparse CT volumes with poor throughplane resolution, making accurate reconstruction of the full brain MRI volume particularly challenging. To address this, we propose ReBrain, a retrieval-augmented diffusion framework for brain MRI reconstruction. Given any 3D CT scan with limited slices, we first employ a Brownian Bridge Diffusion Model (BBDM) to synthesize MRI slices along the 2D dimension. Simultaneously, we retrieve structurally and pathologically similar CT slices from a comprehensive prior database via a fine-tuned retrieval model. These retrieved slices are used as references, incorporated through a ControlNet branch to guide the generation of intermediate MRI slices and ensure structural continuity. We further account for rare retrieval failures when the database lacks suitable references and apply spherical linear interpolation to provide supplementary guidance. Extensive experiments on SynthRAD2023 and BraTS demonstrate that ReBrain achieves state-of-the-art performance in cross-modal reconstruction under sparse conditions.

ABSTRACT Atomic subgraphs are inherent and functionally meaningful structures in real‐world graphs, capturing cohesive units such as social communities, molecular functional groups, or neural circuits. Preserving these atomic subgraphs during graph partitioning is crucial for maintaining semantic integrity, improving algorithmic interpretability, and reducing communication overhead in parallel processing. However, traditional partitioning methods often overlook this structural prior, leading to fragmentation of such subgraphs and degradation in downstream analytical quality. In this work, we propose a novel balanced graph partitioning approach that explicitly preserves atomic subgraphs through a coarsen‐partition‐refine framework. In the coarsening phase, smaller subgraphs are merged into a larger one based on the maximum edge‐to‐vertex weight ratio between subgraphs. In the partitioning phase, a spectral k ‐way method divides the coarsened graph into k balanced blocks. In the refinement phase, boundary subgraphs are exchanged between target blocks via designed rules, reducing cut‐edge weights and ultimately yielding higher‐quality balanced partitions. We evaluate our method on real‐world and synthetic datasets by generating graphs with diverse subgraph distributions. The experimental results demonstrate the feasibility and effectiveness of our method.

With the rapid development of mobile Internet in recent years, a large scale of continuous arrival correlative data, namely dynamic streaming graph, are extensively generated in various application fields. Analyzing, mining and making good use of such a streaming graph face great challenges. In dynamic graph analytics and identification, node classification of graph is one of the most important works and has become a hot research filed. It has a wide range of application scenarios, such as malicious users detection in social networks and shopping recommendation in E-commerce. Due to the large scale and variable structure of the streaming graph, node classification become very difficult. To this end, this article proposes a node classification method for a streaming graph based on a lightweight variable graph neural network (GNN), named NC_SGOI. We use the time window mode for processing a streaming graph in batches. In the first time window, a GNN pretraining model is built and trained by contrastive learning. So, the optimal hyperparameters and the seed nodes with labels can be obtained, and the cold start problem can be solved in this way. In subsequent time windows, the optimal hyperparameters and classification results obtained in each previous time window are reused. Then, the reconstructed model is fine-tuned and further optimized, which can avoid a lot of repetitive training. Meanwhile, using the principle of “firefly light intensity variation,” we obtain a small-scale subgraph locally affected by newly added nodes. Treating such subgraph as the input graph for a lightweight reconstructed model, the size of the training GNN can be reduced, and the process of node classification can be accelerated. Extensive experiments indicate that our algorithm NC_SGOI greatly improves the accuracy of node classification compared to two traditional algorithms. Even compared to the state-of-the-art node classification algorithm DynGNN, NC_SGOI shows a better accuracy and faster speed in node classification.

In an online search, users often input an ambiguous short query to search engines, which leads to search engines being unable to accurately understand the true users' query intent. Thus, enhancing the users' query intent is necessary. Traditional methods of guessing and inferring user intentions are based on either personal past search data, or the group's search history data. The former faces the cold start problem for new users due to the lack of search history data, while the latter cannot accurately get the intent of new search requests due to different users having different intentions even for the same search query. To solve the above issues and to enhance the representation of search requests by adding some query keywords, we construct a user-query-document search heterogeneous graph with users' search history data of their friend networks, which can express the behavioral features and interrelationships of searches. To facilitate the enhanced representation of a query intent, we present TAHAN, a type-aware heterogeneous graph attention network (GAT) model. Extensive experiments on real-world datasets show that our method not only outperforms the state-of-the-art models, but also achieves superior performance in addressing the data sparsity and cold-start problems.

Large Language Models (LLMs) face challenges due to hallucination issues. Current solutions use retrieval-augmented generation (RAG), integrating LLMs with external knowledge to enhance answer accuracy. However, the misuse of irrelevant external knowledge can be misleading. In this paper, we propose a novel method called Retrieve-and-Discriminate Prompter (RD-P), which leverages knowledge graphs (KGs) for trustworthy RAG by synchronizing knowledge retrieval and discrimination in a unified model. Specifically, we train a prompter based on a pre-trained language model with shared parameters. It has two key modules: the retriever and the discriminator. The retriever identifies relevant reasoning paths in the KG, while the discriminator evaluates their credibility through "logical coverage calculation" and in turn instructs the retrieval process. Prompts are then constructed to guide LLMs in reasoning and answering questions using both retrieved and implicit knowledge. Experiments on knowledge-intensive question answering (QA) tasks demonstrate that our method significantly improves answer coverage rate while reducing the retrieval scale, achieving superior performance in complex KGQA tasks compared with state-of-the-art RAG methods at a low cost.

With the advent of 5G era, Internet-of-Things will become possible, and a large amount of correlative data, namely the streaming graph (SG), is continuously generated in various application fields, which poses a great challenge to analyze and make good use of such graph data. The balanced partition of a big graph, especially a dynamic SG, has always been basic research in graph theory, and there are many classical methods. However, this article explores a novel method, that is, an SG$k$-way partitioning via a multiplayer repeated game so as to realize the equilibrium of the total number of nodes in different partitions and achieve high cohesion or low edge-cut in each partition. We regard the SG partitioning process during each time window as a multiplayer game process, treat$k$target partitions as game players, and use all possible actions that players select new nodes as the strategy set. Some effective constraints are given to reduce the strategy space and accelerate the game process. Moreover, we define equilibrium degree (ED) and modularity degree (MD), which are used to design the utility function of game players. All game players finally reach the Nash equilibrium via multiplayer repeated games. At this time, each player corresponds to a strategy. Under the guidance of these strategies, the new nodes are added to each target partition, and then the goal of optimal partitioning is achieved. The above operations are carried out in each time window. The subsequent time windows can reuse the partitioning results of the previous time window in order to realize dynamic incremental partitioning for an SG. Extensive experiments indicate that while ensuring the partition quality of an SG, our proposed algorithm also greatly improves the speed of online partitioning. Even compared with the state-of-the-art SG partitioning algorithm PLDG, our algorithm still obtains better performance.

Software dynamic evolution is a hot topic in software engineering. Traditional evolution is caused by the change in user requirements and running environments. However, in mobile computing systems, there is a new problem that place change leads to the change in software configuration, deployment, and function, which is called the problem of software evolution triggered by place change. Facing this new problem, traditional evolution methods fail to formally describe their evolution process and analyze their evolution performance. Therefore, a new method needs to be developed to ensure the reliability of software evolution triggered by place change. We first address various situations regarding the change of the software function caused by place change in physical space, which are described by a Bigraph model. Then, the triggering conditions for software evolution are defined, and a reaction system corresponding to software evolution is discussed. A theory about software function change caused by place change is developed, including a novel algorithm for identifying software evolution rules that involve place information and the control process for the whole software evolution (CPSE) in a mobile computing environment. Finally, some real case studies illustrate the effectiveness and correctness of our proposed method. Extensive experiments show that our algorithm CPSE outperforms Quiescence and version consistency (VC)-concurrent versions (CV) algorithms in timeliness and average disruption.

Mining a big data stream with continuous, unbounded, and time-varying data items is a great challenge. In the situation where computational resources for real-time processing are limited, it is especially hard to select high-value data items from a big data stream. This article studies on selection policies based on the multiarmed bandit. We cache the online arriving data items in different buffers according to the characteristics of data items. These buffers are regarded as the arms of a multiarmed bandit. We pay attention to several key factors in selecting data items including the data item value, processing time, resource consumption, and loss value caused by some discarded items. Thus, a comprehensive reward mechanism for each data item is given as the foundation for the selection of data items, that is, gambling decision-making. We design three selection policies: the improved$\varepsilon $-greedy, the improved upper confidence bound (UCB), and a data item selection policy named dynamic high-reward incentive (DHRI) with active, dynamic, and incentive reward. They are all trying to balance “exploitation and exploration” in a multiarmed bandit. Experimental results show that our proposed approach is effective and outperforms the traditional methods.

With the gradual maturity of component oriented software development method, component-based software evolution technology has become hot research in academia and industry. Although many evolution rules are designed, they rarely consider component type-mismatched problem in evolution rules. This has led to evolution rules that often run error in software evolution execution. Hence, focusing on the mismatch problem of component type in software evolution, this paper addresses various evolution rules with condition constrains to support component type matching. First, we use the bigraph theory to model the software architecture and employ bigraph term language to describe the basic component evolution operations. Second, we join type system into the term language and use the type term language to express the condition constraints on position and connection for component evolution rules. These condition constraints can guarantee the type-matched among components that participate in software evolution. Furthermore, we show that the component type-matched still kept during a number of different evolution rules are used in the whole software evolution reaction system. Finally, two cases study of evolution progress of ATM system and tourism information system are presented. Two cases illustrate the effectiveness of our approach.

The rise of cloud computing and the Internet not only bring change on the data center, but also lead to transformation in software development, deployment, operation and maintenance. With the continuous improvement of the current cloud computing and the internet environment, how to make better use of cloud computing platform, and how to serve the users is a popular field of computer software is a big challenge. In recent years, with the further development of concepts like micro-services and containers, software will further step forward to the Cloudware. This paper discusses how to deploy Cloudware in cloud environment, and proposes a new method to construct the PaaS platform which can directly deploy software on the cloud without any modification, while achieving a new model by the browser services. By using micro-service architecture, we achieving good performance of extension, scalable deployment, faults tolerance and flexible configuration. Finally, we evaluate this method by constructing a complete framework and carrying out an interactive delay experiment that directly focuses on users' experience, which also shows the effectiveness of this method.

As software systems become more and more complex, there is need to consider not only data structures and algorithms but also the general structure or architecture of the system. Many researchers have presently focused on dynamic evolution of software architectures. Most of them usually emphasized on describing and analyzing the dynamic evolution process of software architectures, while lacking formally modeling and verifying composite dynamic evolution of software architectures. In this paper, we propose a formal method of modeling and verifying composite dynamic evolution of software architectures using hypergraph grammars. We represent software architectures with hypergraphs, give out corresponding composite evolution rules of software architectures, and then model composite dynamic evolution of software architectures according to those rules. At last we verify the liveness property of composite dynamic evolution of software architectures using model checking, and give out corresponding verification algorithms. Our approach provides a graphical representation for composite dynamic evolution of software architectures, and displays a formal theoretical basis on grammars.

Power management of application programs is a hot research in the area of green computing and high-productivity computing. Because of the complexity of application programs, heterogeneity of processors and uncertainty of the running environment, it is difficult to propose an accurate method to predict energy consumption for application program directly. So, we present a power analysis paradigm for application program based on artificial neural network. First, we build a power analysis model based on back propagation neural network (BPNN). The three factors of software, hardware and environment are taken as the inputs of BPNN, and energy consumption and finish time as the outputs of BPNN. Next, we choose lot of classic application programs from different fields as training samples. After learning and training, an expected BPNN is obtained which can be used to predict energy consumption for other new programs. Repeated experiments show that this power analysis paradigm is rational and feasible.

Service management is becoming more and more important within the area of IT management. How to efficiently manage and organize service in complicated IT service environments with frequent changes is a challenging issue. IT service and the related information from different sources are characterized as diverse, incomplete, heterogeneous, and geographically distributed. It is hard to consume these complicated services without knowledge assistant. To address this problem, a systematic way (with proposed toolsets and process) is proposed to tackle the challenges of acquisition, structuring, and refinement of structured knowledge. An integrated knowledge process is developed to guarantee the whole engineering procedure which utilizes Bayesian networks (BNs) as the knowledge model. This framework can be successfully applied on key tasks in service management, such as problem determination and change impact analysis, and a real example of Cisco VoIP system is introduced to show the usefulness of this method.

ABSTRACT Cloud computing has become a scalable services consumption and delivery platform in the field of computer science. As more and more consumers delegate their tasks to cloud providers, service level agreements (SLAs) between consumers and providers emerge as a key aspect. Because of the dynamic nature of the cloud, continuous monitoring on quality‐of‐service attributes is necessary to enforce SLAs. In this paper, we propose a trust mechanism‐based task scheduling model for cloud computing. Referring to the trust relationship models of social persons, trust relationship is built among computing nodes, and the trustworthiness of nodes is evaluated by utilizing the Bayesian cognitive method. Integrating the trustworthiness of nodes into a dynamic level scheduling algorithm, the trust dynamic level scheduling algorithm for cloud computing is proposed. Theoretical analysis and simulations prove that the proposed algorithm can efficiently meet the requirement of cloud computing workloads in trust, sacrificing fewer time costs, and assuring the execution of tasks in a secure way in cloud environment. Copyright © 2011 John Wiley & Sons, Ltd.

Peer-to-Peer (P2P) reputation management system based on social network often relies on the nodes' feedbacks and is needed to evaluate the trustworthiness of participating peers to combat malicious peer behaviors. Some peers collude and organize a collusive group in P2P file sharing system. The collusive group is harmful and easy to be confused with union that is composed by peers with same partial. We proposed a novel approach to evaluate a suspected group as a whole to distinguish clique from union. Besides this, in each estimation process, peers download a subset of trust ratings of feedbacks instead of all and make up difference caused by feedbacks reducing through repeated transaction accumulation. Simulation experiments demonstrate the system is accurate and decreases downloading data of estimation trust process. The results show the approach is proper for networks with moderate ratio of malicious peers.

Abstract A common perception is that there are two competing visions for the future evolution of the Web: the Semantic Web and Web 2.0. In fact, Semantic Web technologies must integrate with Web 2.0 services for both to leverage each other's strengths. This paper illustrates how Semantic Web technologies can support information integration and make it easy to create semantic mashups. An intelligent recommendation system for tourism is presented to show the efficiency of our method. Through the ontology of tourism, the system allows the integration of heterogeneous online travel information. An integrated knowledge process is developed to guarantee the whole engineering procedure. Based on the Bayesian network technique, the system recommends tourist attractions to a user by taking into account the travel behavior both of the user and of other users. Copyright © 2010 John Wiley & Sons, Ltd.

In the Internet age, Software security and piracy becomes a more and more important issue. In order to prevent software from piracy and unauthorized modification, various techniques have been developed. Among them is software watermarking which protects software through embedding some secret information into software as an identifier of the ownership of copyright for this software. This paper gives an new algorithm based on stack-state transition graph, watermarks is embed by adding additional code in the executable file, and extracted by recognizing the relationship of stack-state which processed in runtime. Analysis proves that our algorithm is more reliable.

Abstract People encounter more information than they can possibly use every day. But all information is not necessarily of equal value. In many cases, certain information appears to be better, or more trustworthy, than other information. And the challenge that most people then face is to judge which information is more credible. In this paper we propose a new problem calledCorroboration Trust, which studies how to find credible news events by seeking more than one source to verify information on a given topic. We design an evidence‐based corroboration trust algorithm calledTrustNewsFinder, which utilizes the relationships between news articles and related evidence information (person, location, time and keywords about the news). A news article is trustworthy if it provides many pieces of trustworthy evidence, and a piece of evidence is likely to be true if it is provided by many trustworthy news articles. Our experiments show thatTrustNewsFindersuccessfully finds true events among conflicting information and identifies trustworthy news better than the popular search engines. Copyright © 2009 John Wiley & Sons, Ltd.

Service management is becoming more and more important within the area of IT service management. How to efficiently manage and organize service in complicated IT environments with frequent changes is a challenging issue. Service and the related information from different sources are characterized as diverse, incomplete, heterogeneous, and geographically distributed. It is hard to consume these complicated data without knowledge assistant. To address this problem, a knowledge engineering framework is proposed to tackle the challenges of acquisition, structuring and refinement of structured knowledge regarding existing different unstructured information resource, and the Bayesian network is utilized as the knowledge model. This framework can be successfully applied on key tasks in service management, such as problem determination and change impact analysis. And a real example of Cisco VoIP system is introduced to show the usefulness of this method.

Grid service is composed of elementary services and the execution procedure is characterized by dynamical evolvement and exceptional no-determinism. The existing service description language, BPEL4WS (abbreviated to BPEL), only provides static service description, which cannot guarantee the correct composition of elementary services and dynamically monitor the occurrence of the exceptional events. According to the problems mentioned above, a verification approach to check the validity of the behavior partial order sequence of a grid service is proposed in this paper, which converts the grid service script based on BPEL into the behavior sequence described in Cpi-calculus automatically, and extracts the partial order constraint rules on the behavior of elementary services in a grid service, based on which to check the reachability of elementary services and validity of the behavior sequence during the execution of a grid service. A validity check algorithm is proposed finally.

Many dependence tests have been proposed for loop parallelization in the case of arrays with linear subscripts, but little work has been done on the arrays with non-linear subscripts, which sometimes occur in parallel benchmarks and scientific and engineering applications. This paper focuses on array subscripts coupled integer power index variables. We attempt to use the integer interval theory to solve the above difficult dependence test problem. Some "interval solution" rules for polynomial equations have been proposed in this paper. Furthermore, based on the proposed rules, we present a novel approach to loop dependence analysis, which is termed the polynomial variable interval test or PVI-test, and also develop a related algorithm. Some case studies show that the PVI-test is effective and efficient. Compared to the VI test, the PVI-test makes significant improvement, and is therefore a more general scheme of dependence test

Traditional overlay network simulators provide accurate low-level models of the network hardware and protocols but are but none of them deal with the problem of trust in the large scale overlay networks. We tackle this problem by employing a trust overlay simulator, which offer a viable solution to simulate trustworthy behavior in overlay networks. With this simulator, we can exam varies kinds of the trust and reputation mechanisms in the overlay environment. We hope that this simulator will help move the overlay network closer to fulfilling its promise by developing and testing trust and reputation-based protocols on it

By leveraging economic principles, we present the conception about the supply and demand balance of Grid resources, and propose a price-adjusting mechanism. The mechanism focuses on adjusting the unreasonable prices of both isolated resources and dependent resources, so as to achieve equilibrium prices and promote the global balance of the supply and demand.