Search

Crowdsourcing is a hotspot research field which can facilitate machine learning by collecting labels to train models. Consequently, the state-of-the-art research efforts in crowdsourcing focus on truth inference or label integration, to remove inconsistent labels or to alleviate biased labeling. In turn, the integrated labels will be used to fine-tune machine learning models. Particularly, in this paper, we change the target of truth inference in crowdsourcing from discrete labels to multiple comments given by online participants, that is, the integration of the crowdsourced comments. For such a goal, we propose a Self-play and Sentiment-Emphasized Comment Integration Framework (SSECIF), based on deep Q-learning, with three unique features. First, our framework SSECIF can generate the comment integration in a totally self-play way, without relying on the ground truth generated by human effort. Second, the integrated comment generated by SSECIF can include salient content with low redundancy. Third, the proposed framework SSECIF has emphasized, with a higher intensity, the sentiment in the integrated comment, in order to reflect the attitude or opinion more obviously. Extensive evaluation on real-world datasets demonstrates that SSECIF has achieved the best overall performance in terms of both effectiveness and efficiency, compared with the state-of-the-art methods. Index Terms: Crowdsourcing; Comment Integration; Reinforcement Learning; Deep Q-Learning; Sentiment Analysis.

Nowadays, mining opinion or sentiment from the online user-generated texts has become a research hot-spot. Although, a large amount of lexicon-based Chinese polarity detection works have been done, yet the existing methods have one common flaw that even the same word can have opposite polarities among different seed-lexicons, or polarity fuzziness. Therefore, in order to further enhance the performance of Chinese sentiment polarity detection, in this paper, we start from a two-aspect lexicon expansion, specifically, detecting sentiment polarity for new words and revising sentiment polarity for words already defined in seed-lexicons, so that the polarity fuzziness can be avoided. Then, we formulate a novel sentiment polarity detection framework for Chinese (SPDFC) with more effort to fine-grained sentiment processing, involved in symmetrical mapping, sentiment feature pruning and text representation. In this way, the word polarity can be directly taken as features, further penetrating into polarity detection phase. According to the experimental results, compared to other classical and state-of-the-art methods, the proposed the framework SPDFC can achieve the best overall performance from the perspective of Chinese polarity detection, sentiment feature pruning as well as text representation.

Nowadays, user’s privacy is a critical matter in multimedia social networks. However, traditional machine learning anomaly detection techniques that rely on user’s log files and behavioral patterns are not sufficient to preserve it. Hence, the social network security should have multiple security measures to take into account additional information to protect user’s data. More precisely, access control models could complement machine learning algorithms in the process of privacy preservation. The models could use further information derived from the user’s profiles to detect anomalous users. In this paper, we implement a privacy preservation algorithm that incorporates supervised and unsupervised machine learning anomaly detection techniques with access control models. Due to the rich and fine-grained policies, our control model continuously updates the list of attributes used to classify users. It has been successfully tested on real datasets, with over 95% accuracy using Bayesian classifier, and 95.53% on receiver operating characteristic curve using deep neural networks and long short-term memory recurrent neural network classifiers. Experimental results show that this approach outperforms other detection techniques such as support vector machine, isolation forest, principal component analysis, and Kolmogorov–Smirnov test.

Community detection is one of the hot topics in the complex networks. It aims to find subgraphs that are internally dense but externally sparsely connected. In this paper, a new method is proposed to identify the most influential nodes which are considered as cores of communities and achieve the initial communities. Then, by an expansion strategy, unassigned nodes are added to initial communities to expand communities. Finally, merging overlapping communities to get the final community structure. To evaluate the performance of the proposed node influence method (LGI), the susceptible–infected–removed (SIR) diffusion model are used. Testing with the synthetic networks and real-world networks, LGI can identify best nodes with high influence and is better than other centrality methods. Finally, experiments show that our proposed community detection algorithm based on influential nodes (LGIEM) is able to detect communities efficiently, and achieves better performance compared to other recent methods.

Nowadays, the amount of user-generated contents (UGCs) or texts has surged exponentially. Therefore, recognizing emotions from these texts can bring about lots of advantages. In this paper, we have proposed a novel model named Deep Rolling to predict emotion for target participant in a multi-participant communication context. First, the proposed method converts a text collection into a set of n -dimension vectors for emotion representation and re-organizes texts into a sequence in time order. Then, Deep Rolling can predict the emotion of target participant corresponding to a future time point . Second, apart from simply taking in texts posted by target participant via LSTM , the proposed method has also incorporated texts posted by other participants at every time step by CNN . In this way, Deep Rolling can predict target participant’s emotion by processing emotions from both the target and all the other participants in an ensemble way. Finally, data factorization has also been introduced into Deep Rolling to enhance the overall prediction efficiency. According to experimental results, compared with the state-of-art methods, our proposed model has achieved the best prediction precision on different target participants. At the same time, Deep Rolling has also maintained the prediction efficiency at an acceptable level.

A new k-anonymous method which is different from traditional k-anonymous was proposed to solve the problem of privacy protection. Specifically, numerical data achieves k-anonymous by adding noises, and categorical data achieves k-anonymous by using randomization. Using the above two methods, the drawback that at least k elements must have the same quasi identifier in the k-anonymous data set has been solved. Since the process of finding anonymous equivalence is very time consuming, a two-step clustering method is used to divide the original data set into equivalence classes. First, the original data set is divided into several different sub-datasets, and then the equivalence classes are formed in the sub-datasets, thus greatly reducing the computational cost of finding anonymous equivalence classes. The experiments are conducted on three different data sets, and the results show that the proposed method is more efficient and the information loss of anonymous dataset is much smaller.

In this paper, we will propose a novel approach based on graph analysis which will use community structure detection algorithm to detect topics in the keywords graph of micro-blogging data. Furthermore, considering the specificity of the Sina microblogging, we propose novel keywords filtering model and graph generation algorithm to meet the dual requirements of topic detection and community detection. We validate our approach on a big natural disaster dataset from Sina micro-blog, in which about 103 micro-blogging posts with about 104 distinct feature tags. The experimental results definitely revealed the relationship between the keywords and the natural disaster topics. Our methodology is a scalable method which can adapt to the changes in the amount of data. Especially, we can get abundant information about natural disasters in the topic detection and help the government guide the rescue of disasters.

Fog computing has been introduced for extending cloud computing to the edge of the network, which brings features and services closer to end-users. Despite all the benefits provided, fog computing still suffers from security and privacy issues. Location privacy has a critical issue since fog nodes collect sensitive data. The users continuously send queries to the Location-based service (LBS) server, which may cause vulnerabilities where an attacker may track users. Subsequently, location privacy is not adequate to preserve privacy and attackers can still deduce the movement pattern of the user. Therefore, trajectory privacy has been used to provide better protection for the whole trajectory of the user. Meanwhile, most of the existing researches did not protect the future location of the user, while attackers may predict or estimate the users’ next position if the geographical environment constraints are not considered and the historical data of the user not protected. To resolve the addressed issues and provide better privacy, we developed an approach for preserving the user’s future trajectory privacy by predicting the future location of the user using Extended Mobility Markov Chain (n-MMC) and then generating dummy trajectories by Dummy Rotation Algorithm. The results show that the system can achieve privacy preservation of the future trajectory of the user with an average accuracy of 60%.

With the rapid growth of social network, the cost of computation is increasing. Many existing algorithms are not suitable for the large-scale data. Apache Spark is an open-source cluster computing framework that empowers us to solve the problem of community detection in a cluster of computer. In this paper, we propose a novel label propagation algorithm on Spark, called PSPLPA (Probability and similarity based Parallel label propagation algorithm). PSPLPA employs a new label updating strategy using probability in the label propagation procedure during each iteration. First, weight calculation, which is based on k-shell, is integrated into the label initialization process. Second, parallel propagation steps are comprehensively proposed to utilize label probability efficiently. Third, randomness in label updating is significantly reduced via automatic label selection and similarity computation. Experiments conducted on artificial and real social networks demonstrate that the proposed algorithm exhibits high scalability and high accuracy.

With the development of mobile Internet technology, location-based services (LBS) has been widely used in social networks, such as WeChat. A user of WeChat can discover people nearby with the help of LBS. However, users need to send their current locations to get the service, which may lead to the leakage of their location privacy. An effective way to protect the user's location privacy is using an imprecise location, such as a region to replace his real location. When processing continuous queries, the user need to transmit the region to the server continuously and an attacker is able to infer the real location from the overlapping regions. In this paper, we use circle as the query region and describe how to form a circle region. Then we study the overlapping circle attack and design a method to avoid this attack by changing the confidence level to a fixed value. We also propose an algorithm E PPINQ for the server to process a k NN query while protecting user's location against the attack. Experimental results show that our algorithm is more effective and efficient than the existing algorithm.

Caches are used to improve the performance of the internet, and to reduce the latency of data access time and the low speed of repeated computing processes. Cache replacement is one of the most important issues in a caching system; therefore, it must be coordinated with the caching system to minimize the access latency and maximize the hit rate or byte hit rate. In this paper, we presented a novel caching replacement algorithm named Weighted Greedy Dual Size Frequency (WGDSF) algorithm, which is an improvement on the Greedy Dual Size Frequency (GDSF) algorithm. The WGDSF algorithm mainly adds weighted frequency-based time and weighted document type to GDSF. By increasing the above two weighted parameters, WGDSF performs fairly well at keeping popular objects in the cache and replacing rarely used ones. Our experiment shows that this algorithm has a better hit rate, byte hit rate and access latency than state-of-the-art algorithms, such least Recently Used, least Frequently Used, and GDSF.

Cache memory plays an important role in improving the performance of web servers, especially for big data transmission, which response time is constrained. It is necessary to use an effective method, such as web cache. Because an outstanding cache replacement algorithm can not only reduce the users access time but also improve the performance of the system. The traditional used weighting replacement policy does not consider the size parameter, hence, it may perform poorly while the datasets are larger. In this paper, we propose a novel, high-performance cache replacement algorithm for the web cache, named weighting size and cost replacement policy (WSCRP) bases on the weighting replacement policy. The algorithm recalculates the objects weight with adding the cost attribute in the cache, then orders the weight. Additionally the influence of various factors on the Web object as frequency, time, and cost value are considered. When the cache space cannot satisfy the new request object, the replacement policy WSCRP replaces the largest weighting and cost object. The experiments show that proposed algorithm has higher hit rate and byte rate for different datasets, and can effectively improve the performance of web cache.

In the healthcare domain, protecting the electronic health record (EHR) is crucial for preserving the privacy of the patient. To help protect the sensitive data, access control mechanisms can be utilized to restrict access to only legitimate users. However, an issue arises when the authorized users abuse their access privileges and violate privacy preferences of the patients. While traditional access control schemes fall short of defending against the misbehavior of authorized users, risk-aware access control models can provide adaptable access to the system resources based on assessing the risk of an access request. When an access request is deemed risky, but within acceptable thresholds, risk mitigation strategies can be exploited to minimize the risk calculated. This paper proposes a risk-aware, privacy-preserving risk mitigation approach that can be utilized in the healthcare domain. The risk mitigation approach controls the patient’s medical data that can be exposed to healthcare professionals, according to their trust level as well as the risk incurred of such data exposure, by developing a novel Risk Measure formula. The developed Risk Measure is proven to manage the risk effectively. Furthermore, Risk Mitigation Data Disclosure algorithms, RIMIDI0 and RIMIDI1, which utilize the developed risk measures, are proposed. Experimental results show the feasibility and effectiveness of the proposed method in preserving the privacy preferences of the patient. Since the proposed approach exposes the patient’s data that are relevant to the undergoing medical procedure while preserving the privacy preferences, positive outcomes can be realized, which will ultimately bring forth quality healthcare services.

With the fast development of social networks, more and more data has been generated. Finding useful information among these data is important. Subgraph matching is the method that can be used in social networks for social search, recommender systems, and so on. In this paper, we choose five typical graph matching methods which are VF2, SPath, TurboISO, BoostIso, and RI to value their performance and scalability in social networks. These methods are verified by three social network data sets whose node’s number vary from thousands to millions. According to the experiments, we can find that VF2 and RI is applicable for rather small graphs while SPath performs better in large graph when average degree of graph is small. When graph with high average degree, TurboISO and BoostIso performs better. What is more, we also compare the efficiency of different matching order when searching. The order choosing strategy proposed by RI is better.

Healthcare centers always aim to deliver the best quality healthcare services to patients and earn their satisfaction. Technology has played a major role in achieving these goals, such as clinical decision-support systems and mobile health social networks. These systems have improved the quality of care services by speeding-up the diagnosis process with accuracy, and allowing caregivers to monitor patients remotely through the use of WBS, respectively. However, these systems’ accuracy and efficiency are dependent on patients’ health information, which must be inevitably shared over the network, thus exposing them to cyber-attacks. Therefore, privacy-preserving services are ought to be employed to protect patients’ privacy. In this work, we proposed a privacy-preserving healthcare system, which is composed of two subsystems. The first is a privacy-preserving clinical decision-support system. The second subsystem is a privacy-preserving Mobile Health Social Network (MHSN). The former was based on decision tree classifier that is used to diagnose patients with new symptoms without disclosing patients’ records. Whereas the latter would allow physicians to monitor patients’ current condition remotely through WBS; thus sending help immediately in case of a distress situation detected. The social network, which connects patients of similar symptoms together, would also provide the service of seeking help of near-by passing people while the patient is waiting for an ambulance to arrive. Our model is expected to improve healthcare services while protecting patients’ privacy.

Due to advancements in the development of wireless medical sensing devices and wireless communication technologies, the wireless body area network (WBAN) has become an eminent part of e-healthcare systems. WBAN uses medical sensors to continuously monitor and collect the physiological parameters of a patient’s health and send them to a remote medical server through a portable digital assistance (PDA)/mobile. Due to limitations in communication, such as power, storage, and the computational capabilities of sensors, data aggregation techniques are used to reduce the communication overhead in real-time data transmission in WBAN. However, since the WBAN transmits sensitive health data, data security and data privacy are a major concern. In this paper, we propose a secure privacy-preserving data aggregation (SPPDA) scheme based on bilinear pairing for remote health monitoring systems to improve data aggregation efficiency and data privacy. Our proposed SPPDA scheme utilizes the homomorphic property of the bilinear ElGamal cryptosystem to perform privacy-preserving secure computation and combines it with the aggregate signature scheme, enabling data authenticity/integrity in the WBAN. The proposed SPPDA scheme is proved to be semantically secure under the decisional bilinear Diffie–Hellman assumption. Security analysis demonstrates that our proposed scheme preserves data confidentiality, data authenticity, and data privacy; it also resists passive eavesdropping and replay attacks. A performance evaluation based on simulation results and a comparison of computational cost with related schemes show that data aggregation and batch verification at the PDA significantly reduce communication and transmission overhead and support efficient computation at the remote server.

The increase in the number of devices with a massive revolution in mobile technology leads to increase the capacity of the wireless communications net-works. Multi-user Multiple-Input Multiple-Output is an advanced procedure of Multiple-Input Multiple-Output, which improves the performance of Wireless Local Area Networks. Moreover, Multi-user Multiple-Input Multiple-Output leads the Wireless Local Area Networks toward covering more areas. Due to the growth of the number of clients and requirements, researchers try to improve the performance of the Medium Access Control protocol of Multi-user Multiple-Input Multiple-Output technology to serve the user better, by supporting different data sizes, and reducing the waiting time to be able to transmit data quickly. In this paper, we propose a Clustering Multi-user Multiple-Input Multiple-Output protocol, which is an improved Medium Access Control protocol for Multi-user Multiple-Input Multiple-Out-put based on MIMOMate clustering technique and Padovan Backoff Algorithm. Utilizing MIMOMMate focuses on the signal power which only serves the user in that cluster, minimizes the energy consumption and increases the capacity. The implementation of Clustering Multi-user Multiple-Input Multiple-Output performs on the Network Simulator (NS2.34) platform. The results show that Clustering Multi-user Multiple-Input Multiple-Output protocol improves the throughput by 89.8%, and reduces the latency of wireless communication by 43.9% in scenarios with contention. As a result, the overall performances of the network are improved.

The massive reach of social networks (SNs) has hidden their potential concerns, primarily those related to information privacy. Users increasingly rely on social networks for more than merely interactions and self-representation. However, social networking environments are not free of risks. Users are often threatened by privacy breaches, unauthorized access to personal information, and leakage of sensitive data. In this paper, we propose a privacy-preserving model that sanitizes the collection of user information from a social network utilizing restricted local differential privacy (LDP) to save synthetic copies of collected data. This model further uses reconstructed data to classify user activity and detect abnormal network behavior. Our experimental results demonstrate that the proposed method achieves high data utility on the basis of improved privacy preservation. Moreover, LDP sanitized data are suitable for use in subsequent analyses, such as anomaly detection. Anomaly detection on the proposed method’s reconstructed data achieves a detection accuracy similar to that on the original data.

Medical service providers offer their patients high quality services in return for their trust and satisfaction. The Internet of Things (IoT) in healthcare provides different solutions to enhance the patient-physician experience. Clinical Decision-Support Systems are used to improve the quality of health services by increasing the diagnosis pace and accuracy. Based on data mining techniques and historical medical records, a classification model is built to classify patients&rsquo, symptoms. In this paper, we propose a privacy-preserving clinical decision-support system based on our novel privacy-preserving single decision tree algorithm for diagnosing new symptoms without exposing patients&rsquo, data to different network attacks. A homomorphic encryption cipher is used to protect users&rsquo, data. In addition, the algorithm uses nonces to avoid one party from decrypting other parties&rsquo, data since they all will be using the same key pair. Our simulation results have shown that our novel algorithm have outperformed the Na&iuml, ve Bayes algorithm by 46.46%, in addition to the effects of the key value and size on the run time. Furthermore, our model is validated by proves, which meet the privacy requirements of the hospitals&rsquo, datasets, frequency of attribute values, and diagnosed symptoms.

Recommender systems play an important role in our daily life and are becoming popular tools for users to find what they are really interested in. Matrix factorization methods, which are popular recommendation methods, have gained high attention these years. With the rapid growth of the Internet, lots of information has been created, like social network information, tags and so on. Along with these, a few matrix factorization approaches have been proposed which incorporate the personalized information of users or items. However, except for ratings, most of the matrix factorization models have utilized only one kind of information to understand users’ interests. Considering the sparsity of information, in this paper, we try to investigate the combination of different information, like tags and genres, to reveal users’ interests accurately. With regard to the generalization of genres, a constraint is added when genres are utilized to find users’ similar “soulmates”. In addition, item regularizer is also considered based on latent semantic indexing (LSI) method with the item tags. Our experiments are conducted on two real datasets: Movielens dataset and Douban dataset. The experimental results demonstrate that the combination of tags and genres is really helpful to reveal users’ interests.

Community detection in social networks is a fundamental task of complex network analysis. Community is usually regarded as a functional unit. Networks in real world more or less have overlapping community structure while traditional community detection algorithms assume that one vertex can only belong to one community. This paper proposes an efficient overlapping community detection algorithm named LED (Loop Edges Delete). LED algorithm is based on Structural Clustering, which converts structural similarity between vertices to weights of network. The evaluations of the LED algorithm are conducted both from classical networks from literature and C-DBLP, which is a huge and real-life co-author social network in China. The results show that LED is superior to other methods in accuracy, efficiency, comparing with FastModurity and GN algorithm.

As a research branch of data mining, clustering, as an unsupervised learning scheme, focuses on assigning objects in the dataset into several groups, called clusters, without any prior knowledge. Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is one of the most widely used clustering algorithms for spatial datasets, which can detect any shapes of clusters and can automatically identify noise points. However, there are several troublesome limitations of DBSCAN: (1) the performance of the algorithm depends on two specified parameters, e and MinPts in which e represents the maximum radius of a neighborhood from the observing point and MinPts means the minimum number of data points contained in such a neighborhood. (2) The time consumption for searching the nearest neighbors of each object is intolerable in the cluster expansion. (3) Selecting different starting points results in quite different consequences. (4) DBSCAN is unable to identify adjacent clusters of various densities. In addition to these restrictions about DBSCAN mentioned above, the identification of border points is often ignored. In our paper, we successfully solve the above problems. Firstly, we improve the traditional locality sensitive hashing method to implement fast query of nearest neighbors. Secondly, several definitions are redefined on the basis of the influence space of each object, which takes the nearest neighbors and the reverse nearest neighbors into account. The influence space is proved to be sensitive to local density changes to successfully reduce the amount of parameters and identify adjacent clusters of different densities. Moreover, this new relationship based on the influence space makes the insensitivity to the ordering of inputting points possible. Finally, a new concept-core density reachable based on the influence space is put forward which aims to distinguish between border objects and noisy objects. Several experiments are performed which demonstrate that the performance of our proposed algorithm is better than the traditional DBSCAN algorithm and the improved algorithm IS-DBSCAN.