Quantum-inspired neural networks have demonstrated strong potential in modeling non-classical phenomena in cognitive tasks, particularly in multimodal sentiment analysis, marking a significant advancement over traditional models. However, existing multimodal quantum-inspired neural networks fall short in fully modeling the multimodal density matrix, typically relying on simplistic neural mappings to represent quantum entanglement. This lack of explicit physical constraints, particularly those governing open quantum system dynamics, limits both the interpretability and performance. To address this limitation, we propose a novel framework grounded in quantum stochastic dynamics, introducing two quantum-inspired neural networks, which model the evolution of multimodal data as Markovian and non-Markovian open quantum systems, respectively. This approach enables the simulation of quantum system evolution to capture rich non-classical interactions between modalities. The resulting entangled multimodal density matrix is then measured through quantum projections to extract high-level features for downstream sentiment analysis and sarcasm detection. Extensive experiments on benchmark bimodal and trimodal datasets demonstrate that our models consistently outperform state-of-the-art traditional baselines, large-scale language models and quantum-inspired neural networks. Ablation studies confirm the critical role of quantum stochastic dynamics in performance gains. Furthermore, we enhance the interpretability by tracking the evolution of the density matrix using von-Neumann entanglement entropy as a quantitative metric, providing deeper insight into the internal mechanisms of the model.

Multi-signature is a typical digital signature for signing one message by multiple signers. Its advantage is that the length of the signature is independent of the number of signers, even though multiple users sign the same message. It can therefore serve as a fundamental building block in many secure multiple computation scenarios, e.g., signing a transaction in blockchain applications, signing a routing message in routing discovery protocols, and so on. Nonetheless, most of the existing multi-signature schemes have been still based on traditional signatures over the hardness of number theory problems such as integer factoring or discrete logarithm, which may be insecure in future quantum computing environment. Besides, they impose the cost of public key infrastructure due to the authentication of public keys. Instead, identity-based (ID-based) signature can avoid such overhead due to the management of public keys by using a public identity as a public key. Therefore, in this paper we propose a broadcast multi-signature scheme that is ID-based and lattice-based (i.e., with the hardness assumption on solving lattice problems). Our scheme has the advantages from not only ID-based signatures but also lattice-based signatures. Moreover, the scheme is efficient as the signature length is short, which is suitable for length sensitive applications, e.g., signing transactions in a blockchain.

Money laundering using cryptocurrency poses significant threats to the blockchain ecosystem. Due to the decentralized and anonymous nature of cryptocurrencies, detecting such laundering activities is difficult. Although substantial research has been conducted, almost all existing methods detect cryptocurrency laundering from an individual perspective, ignoring the fact that money laundering is typically a group behavior. Group information should be very helpful in laundering behavior analysis, but such laundering groups are hard to be recognized due to anonymity and diversity of purposes of cryptocurrency transactions. To address this challenge, we design a multi-persona grouping algorithm that can effectively group accounts into persona subgraphs. Then, we extract two subgraph features: cycle basis number and cycle overlapping ratio, and build an unsupervised model to evaluate laundering scores of each subgraph. Extensive experiments on both synthetic and real-world datasets demonstrate that, compared with existing methods, our proposed method can improve detection accuracy by 17.4 percentage points on average. To the best of our knowledge, this is the first work on group-based detection of cryptocurrency laundering.

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach’s security.

In Mobile Edge Computing (MEC) systems, Unmanned Aerial Vehicles (UAVs) facilitate Edge Service Providers (ESPs) offering flexible resource provisioning with broader communication coverage and thus improving the Quality-of-Service (QoS). However, dynamic system states and various traffic patterns seriously hinder efficient cooperation among UAVs. Existing solutions commonly rely on prior system knowledge or complex neural network models, lacking adaptability and causing excessive overheads. To address these critical challenges, we propose the DisOff, a novel profit-aware cooperative offloading framework in UAV-enabled MEC with lightweight Deep Reinforcement Learning (DRL). First, we design an improved DRL with twin critic-networks and delay mechanism, which solves the Q-value overestimation and high variance and thus approximates the optimal UAV cooperative offloading and resource allocation. Next, we develop a new multi-teacher distillation mechanism for the proposed DRL model, where the policies of multiple UAVs are integrated into one DRL agent, compressing the model size while maintaining superior performance. Using the real-world datasets of user traffic, extensive experiments are conducted to validate the effectiveness of the proposed DisOff. Compared to benchmark methods, the DisOff enhances ESP profits while reducing the DRL model size and training costs.

Mobile edge computing (MEC) relieves the latency and energy consumption of mobile applications by offloading computation-intensive tasks to nearby edges. In wireless metropolitan area networks (WMANs), edges can better provide computing services via advanced communication technologies. For improving the Quality-of-Service (QoS), edges need to be collaborated rather than working alone. However, the existing solutions of multiedge collaboration solely adopt a centralized or decentralized decision-making way of load balancing, making it hard to achieve the optimal result because the local and global conditions are not jointly considered. To solve this problem, we propose a novel two-stage decision-making method of load balancing for multiedge collaboration (TDB-EC). First, the centralized decision making is executed with global information, where a deep neural networks (DNNs)-based prediction model is designed to evaluate the range of task scheduling between adjacent edges. Next, considering the global condition of load balancing, the decentralized decision making is executed with local information, where a deep$Q$-networks (DQN)-based$Q$-value prediction model of adjustment operations is developed to evaluate the load balancing plan among edges. Finally, the objective load balancing plan is obtained via feedback control. Extensive simulation experiments demonstrate the adaptability of the TDB-EC to various scenarios of multiedge load balancing, which approximates the optimal result and outperforms three classic methods.

As the workloads and service requests in cloud computing environments change constantly, cloud-based software services need to adaptively allocate resources for ensuring the Quality-of-Service (QoS) while reducing resource costs. However, it is very challenging to achieve adaptive resource allocation for cloud-based software services with complex and variable system states. Most of the existing methods only consider the current condition of workloads, and thus cannot well adapt to real-world cloud environments subject to fluctuating workloads. To address this challenge, we propose a novel Deep Reinforcement learning based resource Allocation method with workload-time Windows (DRAW) for cloud-based software services that considers both the current and future workloads in the resource allocation process. Specifically, an original Deep Q-Network (DQN) based prediction model of management operations is trained based on workload-time windows, which can be used to predict appropriate management operations under different system states. Next, a new feedback-control mechanism is designed to construct the objective resource allocation plan under the current system state through iterative execution of management operations. Extensive simulation results demonstrate that the prediction accuracy of management operations generated by the proposed DRAW method can reach 90.69%. Moreover, the DRAW can achieve the optimal/near-optimal performance and outperform other classic methods by 3$\sim$13% under different scenarios.

In this article, we proposedualtraceabledistributedattributebasedencryption withsubsetkeywordsearch system (DT-DABE-SKS, abbreviated as$\mathcal {DT}$) to simultaneously realize data source trace (secure provenance) and user trace (traitor trace) and flexible subset keyword search from polynomial interpolation. Leveraging non-interactive zero-knowledge proof technology,$\mathcal {DT}$preserves privacy for both data providers and users in normal circumstances, but a trusted authority can disclose their real identities if necessary, such as the providers deceitfully uploading false data or users maliciously leaking secret attribute key. Next, we introduce the new conception of updatable and transferable message-lock encryption (UT-MLE) for block-level dynamic encrypted file update, where the owner does not have to download the whole ciphertext, decrypt, re-encrypt and upload for minor document modifications. In addition, the owner is permitted to transfer file ownership to other system customers with efficient computation in an authenticated manner. A nontrivial integration of$\mathcal {DT}$and UT-MLE lead to the distributed ABSE with ownership transfer system ($\mathcal {DTOT}$) to enjoy the above merits. We formally define$\mathcal {DT}$, UT-MLE, and their security model. Then, the instantiations of$\mathcal {DT}$and UT-MLE, and the formal security proof are presented. Comprehensive comparison and experimental analysis based on real dataset affirm their feasibility.

Many existing searchable encryption schemes are inflexible in retrieval patterns. The data usage authorization is almost permanent valid as long as the user is not revoked. This “all-or-nothing” authorization mode is not compatible with the “pay-as-you-use” commercial billing model. In this article, we propose a new notion called time controlled expressive predicate query with accountable anonymity. It realizes time controlled data query, where a time server issues time token to authorize search privilege in designated time period. The data users can anonymously query on encrypted data and the anonymity is accountable in a way that the trusted authority is able to deanonymize data users if they misbehave in the system. The underlying techniques are anonymous credential, Pederson commitment and non-interactive zero-knowledge proof. We firstly design an efficient expressive predicate query (EPQ) scheme, which is proved secure to protect the privacy of expressive search predicate. Based on EPQ, we present a concrete system instantiation, which realizes key-escrow free and time token nontransferability. The formal definition and security models are given out. The system is formally proved indistinguishable against chosen keyword-set attacks, unforgeable of time tokens and accountable of anonymous users. The comparison and experiment results demonstrate its scalability and efficiency.

Abstract A redactable consortium blockchain (RCB) can build a trust layer for industrial internet of things (IIoT) so as to enable IIoT to resist certain powerful attacks resulting in improper block content. The redactability is particularly important for blockchains applied in IIoT with valuable or sensitive activities such as financial IoT or energy-trading IoT. Huang et al. proposed a threshold chameleon hash (TCH) scheme and then constructed an accountable-and-sanitizable chameleon signature scheme based on TCH. These two primitives are further used as fundamental modules to build an RCB, which empowers IIoT devices to operate the blockchain in a controllable way. However, our paper shows that Huang et al.’s RCB suffers from a security problem that weakens the crucial redactability. Specifically, we find out that if a transaction in a given block is legally redacted by all authorized sensors who collectively hold the private redacting key, anyone (without any private information) can further redact this redacted transaction and delete any transaction within this redacted block and, meanwhile, any sensor user with a private signing (not redacting) key can insert a forged transaction into this redacted block. We further address this threat by replacing the TCH module in Huang et al.’s RCB with our designed TCH.

Abstract The combination of unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) technology breaks through the limitations of traditional terrestrial communications. The effective line-of-sight channel provided by UAVs can greatly improve the communication quality between edge servers and mobile devices (MDs). To further enhance the Quality-of-Service (QoS) of MEC systems, a multi-UAV-enabled MEC system model is designed. In the proposed model, UAVs are regarded as edge servers to offer computing services for MDs, aiming to minimize the average task response time by jointly optimizing UAV deployment and computation offloading. Based on the problem definition, a two-layer joint optimization method (PSO-GA-G) is proposed. First, the outer layer utilizes a Particle Swarm Optimization algorithm combined with Genetic Algorithm operators (PSO-GA) to optimize UAV deployment. Next, the inner layer adopts a greedy algorithm to optimize computation offloading. The extensive simulation experiments verify the feasibility and effectiveness of the proposed PSO-GA-G. The results show that the PSO-GA-G can achieve a lower average task response time than the other three baselines.

With time-varying workloads and service requests, cloud-based software services necessitate adaptive resource allocation for guaranteeing Quality-of-Service (QoS) and reducing resource costs. However, due to the ever-changing system states, resource allocation for cloud-based software services faces huge challenges in dynamics and complexity. The traditional approaches mostly rely on expert knowledge or numerous iterations, which might lead to weak adaptiveness and extra costs. Moreover, existing RL-based methods target the environment with the fixed workload, and thus they are unable to effectively fit in the real-world scenarios with variable workloads. To address these important challenges, we propose a Prediction-enabled feedback Control with Reinforcement learning based resource Allocation (PCRA) method. First, a novel Q-value prediction model is designed to predict the values of management operations (by Q-values) at different system states. The model uses multiple prediction learners for making accurate Q-value prediction by integrating the Q-learning algorithm. Next, the objective resource allocation plans can be found by using a new feedback-control based decision-making algorithm. Using the RUBiS benchmark, simulation results demonstrate that the PCRA chooses the management operations of resource allocation with 93.7 percent correctness. Moreover, the PCRA achieves optimal/near-optimal performance, and it outperforms the classic ML-based and rule-based methods by 5$\sim$∼7% and 10$\sim$∼13%, respectively.

In this article, we propose a privacy-preserving medical treatment system using nondeterministic finite automata (NFA), hereafter referred to as P-Med, designed for remote medical environment. P-Med makes use of the nondeterministic transition characteristic of NFA to flexibly represent medical model, which includes illness states, treatment methods and state transitions caused by exerting different treatment methods. A medical model is encrypted and outsourced to cloud to deliver telemedicine service. Using P-Med, patient-centric diagnosis and treatment can be made on-the-fly while protecting the confidentiality of patient’s illness states and treatment recommendation results. Moreover, a new privacy-preserving NFA evaluation method is given in P-Med to get a confidential match result for the evaluation of an encrypted NFA and an encrypted data set, which avoids the cumbersome inner state transition determination. We demonstrate that P-Med realizes treatment procedure recommendation without privacy leakage to unauthorized parties. We conduct extensive experiments and analysis to evaluate the efficiency.

Secure search over encrypted remote data is crucial in cloud computing to guarantee the data privacy and usability. To prevent unauthorized data usage, fine-grained access control is necessary in multi-user system. However, authorized user may intentionally leak the secret key for financial benefit. Thus, tracing and revoking the malicious user who abuses secret key needs to be solved imminently. In this paper, we propose an escrow free traceable attribute based multiple keywords subset search system with verifiable outsourced decryption (EF-TAMKS-VOD). The key escrow free mechanism could effectively prevent the key generation centre (KGC) from unscrupulously searching and decrypting all encrypted files of users. Also, the decryption process only requires ultra lightweight computation, which is a desirable feature for energy-limited devices. In addition, efficient user revocation is enabled after the malicious user is figured out. Moreover, the proposed system is able to support flexible number of attributes rather than polynomial bounded. Flexible multiple keyword subset search pattern is realized, and the change of the query keywords order does not affect the search result. Security analysis indicates that EF-TAMKS-VOD is provably secure. Efficiency analysis and experimental results show that EF-TAMKS-VOD improves the efficiency and greatly reduces the computation overhead of users' terminals.

Cloud computing provides flexible data management and ubiquitous data access. However, the storage service provided by cloud server is not fully trusted by customers. Searchable encryption could simultaneously provide the functions of confidentiality protection and privacy-preserving data retrieval, which is a vital tool for secure storage. In this paper, we propose an efficient large universe regular language searchable encryption scheme for the cloud, which is privacy-preserving and secure against the off-line keyword guessing attack (KGA). A notable highlight of the proposal over other existing schemes is that it supports the regular language encryption and deterministic finite automata (DFA) based data retrieval. The large universe construction ensures the extendability of the system, in which the symbol set does not need to be predefined. Multiple users are supported in the system, and the user could generate a DFA token using his own private key without interacting with the key generation center. Furthermore, the concrete scheme is efficient and formally proved secure in standard model. Extensive comparison and simulation show that this scheme has function and performance superior than other schemes.

The purpose of this special issue is to collate a selection of representative research articles that were primarily presented at the Ninth “Green Cloud Computing: Methodology and Practice,” held in conjunction with SC'14. This annual conference brings together practitioners, researchers, students, and scholars interested in updating their knowledge about or active in green cloud computing, in order to foster state-of-the-art research in the area of green cloud computing including the topics of modeling, algorithm development, implementation, and execution. Although cloud computing has been widely adopted by the industry, it still suffers from different challenging issues, one of which is efficient energy management. The cloud may comprise thousands of servers, network devices, and disks and typically serve millions of users globally. Such a large-scale data center will consume considerable amount of energy. Therefore, optimizing the efficiency of the application's use of cloud resources and improving the energy efficiency in cloud, without sacrificing Service Level Agreements (SLA), cannot only save significant budget for cloud users and owners but also make a significant contribution to greater environmental sustainability. This special issue will serve as a landmark source for education, information, and reference to practitioners, researchers, students, and scholars. This issue would be incomplete without in-VM management and it is very useful in green cloud computing because it provides the abilities of in-VM monitoring, VM reconfiguration, and performance measurement. Zhan et al3 propose a secure automated in-VM management approach, a hypervisor-based shell managing the VMs in an out-of-box way. In addition, it presents a dummy process selection and a system call injection method to further enhance the system security and transparency. Large-scale data processing is a problem that must be faced in green cloud computing. Ding et al4 consider the data structure of the graph and propose an index structure named Closure+-tree to process the subgraph query efficiently. Wang et al5 consider the shortcoming of collaborative filtering in processing large-scale data and propose a new method for training autoencoder-based CF. We encourage the reader to review the works of Ye et al,6 Chen et al,7 and He et al8 to get more information about the topics of modeling, algorithm development, implementation, and execution.

Nowadays, Internet of things (IoT) become more and more popular. At the same time, the requirements of security mechanism for multimedia in IoT received a huge concern. Multimedia data is easily shared by devises, applications and social networks set by IoT. Therefore, it is indispensable to guarantee the privacy and security of shared multimedia data. In this paper, we address the secure multimedia data sharing problem in cloud computing by designing proxy re-encryption (PRE) scheme. Our schemes cope with the issues of data validity, data confidentiality and authentication during encrypted multimedia data sharing. Unlike as usually done in the literature, we present a CCA-secure PRE scheme which removes pairings firstly. Then we design a refined CCA-secure PRE scheme called publicly verifiable PRE without parings. It is demonstrated that our schemes meet not only the security and high efficiency requirements of multimedia data sharing, but also the public verifiability. The validity of ciphertext, both the original and re-encrypted ciphertext, can be publicly verified which brings additional efficiency due to offloading the validity check of ciphertexts from the power-limited clients to any semi-honest public cloud.

Summary With the advent of cloud computing, more and more consumers prefer to use the cloud services with the pay‐as‐you‐consume mode. The cloud storage brings about great convenience to users, who store data in cloud and access to it using the smart devices anytime and anywhere. Consumers' information should be encrypted to guarantee the data privacy. Flexible searching on ciphertext is a critical challenge to be solved for effective data utilization. In this paper, we propose a novel semantic keyword searchable proxy re‐encryption scheme for secure cloud storage. A highlight of this work is that the scheme is quantum attack resistant, while most of the available searchable encryption schemes are not. It supports not only exact keyword search but also synonym keyword search. Moreover, the data owner is capable to delegate his search right to another user using the proxy re‐encryption mechanism. In the generation process of re‐encryption key, the delegator and delegatee do not need to be interactive with each other. The scheme is also collusion resistant. Under the learning with errors hardness problem, this scheme is proved secure in standard model.

With the completion of the Human Genome Project, proteomics research has become one of the most important topics in the fields of life science and natural science. The project determined that proteins participate in life activities mainly in the form of complexes. At present, research on protein-protein interaction networks (PPINs) have mainly focused on detecting protein complexes or function modules. This problem has been transformed into a recognizable dense subgraph problem in a PPIN diagram.The situation in PPIN research in recent years is introduced in this study, including commonly used databases, traditional detection algorithms, recent solutions, and the application of the swarm intelligence algorithms in this field. We then propose a detection scheme based on particle swarm optimization (PSO) and gene ontology knowledge. This scheme combines PSO and biological gene ontology knowledge to identify complexes from PPINs. Simultaneously, network topology knowledge improves the detection accuracy of the protein module.

Sentiment analysis is a technology with great practical value, it can solve the phenomenon of network comment information disorderly to a certain extent, and accurate positioning of user information required. Currently for Chinese sentiment analysis research is relatively small, including a variety of supervised learning method of classification result and the text feature representation methods and feature selection mechanism and other factors impact on the classification performance is an urgent problem. In this paper, we taken the verb, adjectives and adverbs as text features, used TF-IDF to calculate weight of words. Then we adopted the SVM and ELM with kernels to analyze the text emotion tendentiousness. The experimental results show that ELM with kernels can be obtained a better classification result in a relatively short period of time than SVM.

The purpose of this special issue is to collate a selection of representative research articles that were primarily presented at the 2015 International Conference on Cloud Computing and Big Data 1. This conference brings together researchers and industry practitioners in order to exchange information regarding advancements in the state-of-the-art and practice of cloud computing, big data, and social network, as well as to identify emerging research topics and define the future directions of cloud computing, big data, and social network. Nowadays, various social applications such as blogs, e-mail, instant messaging, social networking (Facebook, Twitter, LinkedIn, etc.), wikis, and social bookmarking have been widely popularized by providing digital platforms for social interaction. Today's online social network or mobile social network pervades all aspects of our daily lives and contains vast amount of data. From this vast amount of data, ability is needed to extract and analyze the social networks of a new era that can be consisted of millions of nodes and connections. Meanwhile, various critical issues such as clustering and evolution mining of social networks, modeling and understanding of social behaviors via computational means, information spread and modeling, social influence analysis, social recommendations, etc., provide significant challenges. This special issue is devoted to analysis of these large-scale social structures and what is more important to identify the areas where social network analysis can be applied and provide the knowledge that is not accessible for other types of analysis. This special issue contains research papers addressing the state-of-the-art in social network analysis and its application. A set of carefully selected works was invited based on the original presentations at the 2015 International Conference on Cloud Computing and Big Data 1, which was held in Huangshan, China, 17–19 June 2015. The extended works have been thoroughly reviewed by an international technical reviewing committee, and only nine papers covering a wide range of relevant challenges in social network were selected for this special issue. The manuscripts tackle research on different topics, including networking, infrastructures, algorithms, applications, and miscellaneous. The set of accepted papers can be organized under the following key subjects and subsections and are briefly described in the remaining parts of this section. Data center is the most important infrastructure for many key applications, such as social network analysis, web service, etc. Data center networks usually mix with a large amount of latency-agnostic background flows and a large number of latency-sensitive application flows. Directly using the traditional TCP in data center networks, which is deadline agnostic, may suffer from performance and efficiency problem. The recent works that improve TCP focus on the latency-sensitive flows themselves but cannot effectively ensure deadline for the latency-sensitive flows. In the first paper, ‘Make-way: transporting latency-sensitive flows nonblockingly in oversubscription data center networks’ 2, by Deng Gang, Gong Zhenghu, and Wang Hong, a new data center network transport protocol, called Make-way, is proposed for satisfying the deadlines of latency-sensitive flows. In Make-way, once a latency-sensitive flow encounters congestion, the latency-agnostic background flows will make way for it. Especially, Make-way does not need any special support of hardware modification. Because the latency-agnostic flows in data center networks usually contribute the majority of traffic, by doing so, the latency-sensitive flows may be transported nonblockingly in data center networks and thus can meet their deadlines. Extensive simulation results show that Make-way can meet the deadlines of latency-sensitive flows with a probability of more than 97%. MapReduce has been widely regarded as a flexible, scalable, and easy-to-use distributed programming paradigm for big data processing such as social network data analysis. The second paper, ‘MEMoMR: accelerate MapReduce via reuse of intermediate results’ 3, by Hong Yao, Jinlai Xu, Zhongwen Luo, and Deze Zeng, tries to accelerate the MapReduce performance from the intermediate result-reusing aspect. The authors observe that existing intermediate result-reusing mechanism is not efficient enough, as many input/output operations are wasted. Efficient reusing of the intermediate results could potentially improve the MapReduce performance. Inspired by such fact, they propose a framework, named more efficient intermediate result reusing for MapReduce (MEMoMR), by introducing a novel reusing mechanism that can substantially reduce the input/output overhead. To this end, they invent a new metadata description method and apply it in the reusing phase. They practically realize MEMoMR and evaluate its performance by implementing it in a real cluster. The experiment results show that MEMoMR can improve the system performance as high as 23.4%, comparing against Dache. Stream processing is one of the key technologies for data processing in social networks. In order to speed up processing in stream processing systems, a data analysis operator could be partitioned into n parallel tasks, which are usually deployed on m nodes coexisting with other application operators. Because the node performance can vary in unpredictable ways, the tasks should be redistributed at runtime for stream applications to meet their strict latency requirements. In order to redistribute the tasks to the best node and dynamically adapt to resource or load fluctuations, the third paper, ‘Runtime-aware adaptive scheduling in stream processing’ 4, by Yuan Liu, Xuanhua Shi, and Hai Jin, presents a runtime-aware adaptive schedule mechanism that aims at minimizing the operator processing latency and minimizing the latency difference between different nodes' tasks. A new abstraction called performance cost ratio (PCR) is proposed, which evaluates the node performance. The higher the node's PCR is, the less cost the node will pay for processing one tuple and the more tasks should be deployed on it. The PCR-based quantitative algorithm applies itself to make task loads quantized to the processing capacity of nodes, move the minimum amount of operator's tasks, and keep the tasks locally at the same time. A runtime-aware adaptive scheduler is implemented as an extension to stream processing system, Storm. Matrix factorization is one of leading techniques for many applications, including social network-based recommendation systems. Many parallel stochastic gradient descent (SGD) methods have been proposed to address the matrix factorization issue on shared-memory (multi-core) systems and distributed systems. However, these methods cannot be accelerated significantly on graphics processing unit (GPU) systems because the serious over-writing problem and thread divergence may occur. The fourth paper, ‘GPUSGD: a GPU-accelerated stochastic gradient descent algorithm for matrix factorization’ 5, by Jing Jin, Siyan Lai, Su Hu, Jing Lin, and Xiaola Lin, proposes an efficient GPU algorithm, named GPUSGD, to solve the matrix factorization problem based on SGD method. The proposed GPUSGD not only can handle the over-writing problem but also can avoid the performance loss caused by the thread divergence. The experimental results show that, compared with the existing state-of-the-art parallel methods, GPUSGD performs much better in accelerating the matrix factorization. The authors also claim that the proposed algorithm is the first work of developing a parallel SGD method to improve the matrix factorization on the GPU. Correlation analysis is both popular and useful in a number of social networking research, particularly in the exploratory data analysis. In the fifth paper, ‘Using Spearman's correlation coefficients for exploratory data analysis on big dataset’ 6, by Chengwei Xiao, Jiaqi Ye, Rui Máximo Esteves, and Chunming Rong, three well-known and often-used correlation coefficients – Pearson product-moment correlation coefficient and Spearman and Kendall rank correlation coefficients – are compared from definition to application domain. Based on the characteristics of the pump's vibration dataset, the nonparametric and distribution-free Spearman rank correlation coefficient is introduced to analyze the relationship between the pump's state and each of the 207 880 variables. The percentage of variables and exact variables' tables with high Spearman's correlation coefficients for state 1 and state 2, state 1 and state 3, state 2 and state 3, and 3 states in different files are obtained respectively, which has important valuation for the future research of the unsupervised machine learning system. Alongside the rapid development of e-commerce, purchase prediction has become an increasingly important consideration for a wide variety of retail platforms. Along with the development of social networks, much attention has been given to the influence of the social networks on users' purchase. The sixth paper, ‘Purchase prediction using tmall-specific features’ 7, by Yang Zhao, Liang Yao, and Yin Zhang, proposes a framework which combines machine learning methods with a threshold-moving approach to predict sets of pairs (user ID and brand ID) in terms of whether a certain brand is purchased by a specified user according to his or her historical activity records. Three specific feature groups are extracted: click features, purchase features, and collect-and-cart features using a dataset from Tmall, a Chinese business-to-consumer online retail platform. Next, seven user purchase prediction experiments with different combinations of the three feature groups are conducted, and the purchase prediction performance is observed. The results show that a combination of all three feature groups, with 27 features in total, provides valuable purchase prediction contributions. It is identified that the last-day shopping cart count, from the collect-and-cart feature group, is a valuable feature capable of markedly affecting prediction performance. In addition, the purchase feature group is also shown to have a greater impact on purchase prediction. Social network has become a very popular way by which Internet users communicate and interact online. Effective user interest prediction is significant for service providers in a set of application scenarios such as user behavior analysis, resource recommendation, etc. In the seventh paper, ‘Interest prediction in social networks based on Markov chain modeling on clustered users’ 8, submitted by Xianghan Zheng, Dongyun An, and Wenzhong Guo, user interest prediction method based on the Markov chain modeling on clustered users is proposed with the following procedure: collecting dataset from 4613 users and more than 16 million messages from Sina Weibo, obtaining each user's interest eigenvalue sequence and establishing single-Markov chain model, and implementing user clustering algorithm for the multi-Markov chain construction in order to divide users into a set of predefined interest categories. The proposed solution is capable of predicting both long-term and short-term user interests based on a suitable selection of the initial state distribution, λ. The proposed solution also proves that short-term interests are consistent with long-term interests if the influences of social or user-related events that cause interruptions (e.g., earthquake, birthday, etc.) are not considered. Furthermore, the experiments show that the proposed solution is feasible and efficient and can achieve a higher accuracy of prediction than that of the other approaches such as support vector machine and K-means. The flourishing social networks have greatly enriched the ways of communications and thus brought people in the world much closer than ever. However, critical contexts of the traditional face-to-face communications, for example, body gestures, could be missing during the online communication, hampering the user experiences. The eighth paper, ‘AAH: accurate activity recognition of human beings using WiFi signals’ 9, by Yu Gu, Lianghu Quan, and Fuji Ren, tries to fill in the blank by presenting a passive and device-free activity recognition system through harvesting fingerprints of different activities from ubiquitous WiFi signals. The proposed system can be integrated into any existing wireless local area networks without additional hardware supports. Also, it does not need the subjects to be cooperative during the recognition process. A prototype system is built and evaluated via extensive real-world experiments. By comparing with three state-of-the art solutions, that is, K-nearest neighbor, naive Bayes, and bagging, the superiority of the proposed method is shown in terms of accuracy and complexity. For analyzing the social network, it is important to classify the network traffic and identify the applications running in the network. With the rapid development of smart phones, recent years have witnessed an exponential growth of the number of mobile apps. Considering the security and management issues, network operators need to have a clear visibility into the apps running in the network. The ninth paper, ‘Automatically identifying apps in mobile traffic’ 10, by Lingjun She, Jianhua Sun, Hao Chen, Wenyong Zhong, Cheng Chang, Zhiwen Chen, Wentao Li, and Shuna Yao, presents a novel approach to generating the fingerprints for mobile apps from network traffic. The fingerprints that characterize the unique behaviors of specific mobile apps can be used to identify mobile apps from the real network traffic. In order to handle the large volume of traffic efficiently, the authors use non-negative matrix factorization to perform traffic analysis to cluster similar network traffic into groups. Then, access patterns of individual apps that are extracted from each group can be used as fingerprints, distinguishing apps from others uniquely. The experimental evaluations show that the proposed approach can identify the mobile apps from random and mixed network traffic with high precision. The articles presented in this special issue provide recent advances in some fields related to social network analysis and applications. In particular, the manuscripts undertake research on different topics, including networking, infrastructures, algorithms, applications, and miscellaneous. We hope that the readers can benefit from the perspectives presented in this special issue and will contribute to these strategically important, exciting, and fast-growing research areas. In closing, we would like to thank all the authors who have submitted their research work to this special issue. We would also like to acknowledge the contribution of many experts in the field who have participated in the review process and provided helpful suggestions to the authors on improving the content and presentation of the papers. We would also like to express our gratitude to the editor-in-chief, Prof. Geoffrey C. Fox, for his support and help in bringing forward this special issue. We hope you will enjoy the papers in this collection.

Summary Effective user interest prediction is significant for service providers in a set of application scenarios such as user behavior analysis and resource recommendation. However, existing approaches are either incomplete or proprietary. In this paper, user interest prediction based on the Markov chain modeling on clustered users is proposed with the following procedure: collect dataset from 4613 users and more than 16 million messages from Sina Weibo; obtain each user's interest eigenvalue sequence and establish single‐Markov chain model; and implement user clustering algorithm for the multi‐Markov chain construction in order to divide users into a set of predefined interest categories. The proposed solution is capable of predicting both long‐term and short‐term user interests based on a suitable selection of the initial state distribution, λ. The proposed solution also proves that short‐term interests are consistent with long‐term interests if the influences of social or user‐related events that cause interruptions (e.g., earthquake and birthday) are not considered. Furthermore, experiments show that the proposed solution is feasible and efficient and can achieve a higher accuracy of prediction than that of the other approaches such as Support Vector Machine (SVM) and K‐means. Copyright © 2015 John Wiley & Sons, Ltd.

In this paper, we investigate a typical clustering technology, namely, Gaussian mixture model (GMM)-based approach, for user interest prediction in social networks. The establishment of the model follows the following process: collect dataset from 4613 users and more than 16 million messages from Sina Weibo, obtain each user's interest eigenvalue sequence and establish GMM model to clustering users. In theory and experiment, this approach is feasible. The GMM-based approach considers the prediction accuracy and consuming time. A series of experiments are conducted to validate the feasibility and efficiency of the proposed solution and whether it can achieve a higher accuracy of prediction compared with other approaches, such as SVM and K-means. Further experiments show that GMM-based approach could produce higher prediction accuracy of 93.9%, thus leveraging computation complexity.

Adding to societal changes today, are the miscellaneous big data produced in different fields. Coupled with these data is the appearance of risk management. Admittedly, to predict future trend by using these data is conducive to make everything more efficient and easy. Now, no matter companies or individuals, they increasingly focus on identifying risks and managing them before risks. Effective risk management will lead them to deal with potential problems. This thesis focuses on risk management of flight delay area using big real time data. It proposes two different prediction models, one is called General Long Term Departure Prediction Model and the other is named as Improved Real Time Arrival Prediction Model. By studying the main factors lead to flight delay, this thesis takes weather, carrier, National Aviation System, security and previous late aircraft as analysis factors. By utilizing our models can do not only long time but also short term flight delay predictions. The results demonstrate goodness of fit. Besides the theory part, it also presents a practical and beautiful web application for real time flight arrival prediction based on our second model.

Social network has become a very popular way for internet users to communicate and interact online. Users spend plenty of time on famous social networks (e.g., Facebook, Twitter, Sina Weibo, etc.), reading news, discussing events and posting messages. Unfortunately, this popularity also attracts a significant amount of spammers who continuously expose malicious behavior (e.g., post messages containing commercial URLs, following a larger amount of users, etc.), leading to great misunderstanding and inconvenience on users׳ social activities. In this paper, a supervised machine learning based solution is proposed for an effective spammer detection. The main procedure of the work is: first, collect a dataset from Sina Weibo including 30,116 users and more than 16 million messages. Then, construct a labeled dataset of users and manually classify users into spammers and non-spammers. Afterwards, extract a set of feature from message content and users׳ social behavior, and apply into SVM (Support Vector Machines) based spammer detection algorithm. The experiment shows that the proposed solution is capable to provide excellent performance with true positive rate of spammers and non-spammers reaching 99.1% and 99.9% respectively.

With the wide adoption of cloud computing, the scientific applications are migrated to cloud for execution. The complex structure of scientific applications bring challenges to optimization scheduling scientific applications across multiple heterogeneous clouds. In this paper, the directed acyclic graphs (DAGs) are adopted to represent scientific applications, which have different priorities in the process of scheduling. We propose a dynamic multi-cloud priority list scheduling algorithm (DMPLS), combining with workloads preemptive strategy and feedback mechanism to schedule scientific applications in time. Our algorithm regulates the workloads scheduling dynamically based on the updated information about the actual workloads execution time. The experimental results show that the proposed algorithm reduces the average time to complete the applications compared with First-Come-First-Service and Round-Robin algorithm. Moreover, the advantage of the DMPLS algorithm is more significant under the severe resources confliction situations.

Social network has become a very popular way for internet users to communicate and interact online. Users spend a great deal of time on famous social networks (e.g. Facebook, Twitter, Sina Weibo, etc.), reading news, discussing events and posting their messages. Unfortunately, this popularity also attracts a significant amount of spammers who continuously expose malicious behaviors (e.g. Post messages containing commercial topics or URLs, following a larger amount of users, etc.), leading to great inconvenience on normal users' social activities. In this paper, a supervised machine learning based spammer filtering method is proposed. We first collected a dataset from Sina Weibo that includes 30,116 users and more than 16 million messages, then, construct a labeled dataset of users and manually classify users into spammers and non-spammers, after that, abstract a set of novel features from message content and users' social behavior, and apply into SVM based spammer classifier. Our experiments show that true positive rate of spammers and non-spammers could reach 99.1% and 99.9%.

Today, Smart Home monitoring services have attracted much attention from both academia and industry. However, in the conventional monitoring mechanism the remote camera can not be accessed for remote monitoring anywhere and anytime. Besides, traditional approaches might have the limitation in local storage due to lack of device elasticity. In this paper, we proposed a Cloud-based monitoring framework to implement the remote monitoring services of Smart Home. The main technical issues considered include Data-Cloud storage, Local-Cache mechanism, Media device control, NAT traversal, etc. The implementation shows three use scenarios: (a) operating and controlling video cameras for remote monitoring through mobile devices or sound sensors; (b) streaming live video from cameras and sending captured image to mobile devices; (c) recording videos and images on a cloud computing platform for future playback. This system framework could be extended to other applications of Smart Home.

Due to a few realistic challenges (e.g. lack of protocol support, limitation of NAT and firewall, etc), it is difficult to access residential multimedia services from heterogeneous network environment. In this paper, we propose a system architecture for accessing residential multimedia services from either local or remote networks. The proposed solution includes UPnP-based local multimedia access, Cloud-based remote multimedia access, and a few corresponding technical approaches (for instance, security, NAT traversal, etc) are also considered. The prototype implementation and evaluation shows feasibility and efficiency of proposed solution.

Today, Peer-to-Peer SIP based communication systems have attracted much attention from both academia and industry. The decentralized nature of P2P might provide the distributed peer-to-peer communication system without help of the traditional SIP server. However, it comes to the cost of reduced manageability and therefore causes security problems, e.g. distrust, privacy leaks, unpredictable availability, etc. In this paper, we investigate on P2PSIP security issues and propose a proxy-based system architecture that improves security during P2PSIP session initiation. The main issues considered in this architecture include Source inter-working, Encryption & Decryption, Policy Management, Destination inter-working, etc. We also implement a prototype with 16 Chord Secure Proxys (CSPs) and 496 P2PSIP peers. After that we analyze this system architecture in several aspects: number of hops and delay, trust upgrading, and the protection of security breaches (e.g. malicious or compromised intermediate peer). We take Chord as the P2PSIP overlay as example. However, this system architecture is independent of Chord overlay and could be extended to the other DHT (Distributed Hash Table) technologies.