Search

In real applications, the label information on many data is inaccurate, or a completely reliable label needs to be obtained at a high cost. The previous supervised hashing algorithms consider only the label information in the mapping process from Euclidean space to Hamming space when learning hash codes. However, there is no doubt that these algorithms are suboptimal in maintaining the relationships between high-dimensional data spaces. To overcome this problem, this paper advances a new weakly supervised discrete discriminant hashing (WDDH) to ensure a more effective representation of data and better retrieval of information. First, we consider the nearest neighbour relationship between samples, and new neighbourhood graphs are constructed to describe the geometric relationship between samples. Second, the algorithm embeds the learning of the hash function into the model and optimises the hash codes by a one-step iterative updating algorithm. Finally, it is compared with the existing classical unsupervised hashing algorithm and supervised hashing algorithm on different databases. The results and discussion of the experiments clearly show that the proposed WDDH algorithm in this paper is more robust for data representation in learning low-quality label data, coarse-grained label data and noisy data. [ABSTRACT FROM AUTHOR]

Many applications in cognitive science and artificial intelligence utilize semantic similarity and relatedness to solve difficult tasks such as information retrieval, word sense disambiguation, and text classification. Previously, several approaches for evaluating concept similarity and relatedness based on WordNet or Wikipedia have been proposed. WordNet-based methods rely on highly precise knowledge but have limited lexical coverage. In contrast, Wikipedia-based models achieve more coverage but sacrifice knowledge quality. Therefore, in this paper, we focus on developing a comprehensive semantic similarity and relatedness method based on WordNet and Wikipedia. To improve the accuracy of existing measures, we combine various taxonomic and non-taxonomic features of WordNet, including gloss, lemmas, examples, sister-terms, derivations, holonyms/meronyms, and hypernyms/hyponyms, with Wikipedia gloss and hyperlinks, to describe concepts. We present a novel technique for extracting ' is-a ' and ' part-whole ' relationships between concepts using the Wikipedia link structure. The suggested technique identifies taxonomic and non-taxonomic relationships between concepts and offers dense vector representations of concepts. To fully exploit WordNet and Wikipedia's semantic attributes, the proposed method integrates their semantic knowledge at feature-level, combining semantic similarity and relatedness into a single comprehensive measure. The experimental results demonstrate the effectiveness of the proposed method over state-of-the-art measures on various gold standard benchmarks. [ABSTRACT FROM AUTHOR]

Ranking is one of the central machine learning tasks arising from supervised learning and has many important applications in information retrieval. Many ranking approaches have been designed and extensively studied. In this paper we study two kernel ranking algorithms, the regularized least square ranking and its bias corrected version, which learn scoring functions from reproducing kernel Hilbert spaces (RKHSs). We say a kernel is perfect for ranking if an optimal scoring function lies in the associated RKHS. It is imperfect if an optimal scoring function can be approximated by the RKHS. The two regularized kernel ranking algorithms have been shown theoretically justified and empirically effective when the kernel is perfectly chosen. In practice, however, kernels are usually selected via cross validation process. It is more common than not that the kernel is imperfectly chosen. We develop a novel leave-two-out analysis technique to evaluate the generalization performance of the two regularized ranking algorithms in this situation. We show that they are still effective and can achieve the capacity independent optimal convergence rates. [ABSTRACT FROM AUTHOR]

K-nearest neighbors search (K-NNS) is a fundamental problem in many areas of machine learning and data mining. In an attempt to solve NNS problems by locality-sensitive hashing (LSH)-based algorithms and avoid the F1-trap, in this paper, we theoretically prove the necessity of maintaining close edges of each dimension, the independence of the partition location and the precision of retrieval. Based on the theories, a new method is proposed for constructing the hash function family. Then, a volume-balancing locality-sensitive hashing (VBLSH) algorithm is implemented. In this algorithm, the problem of constructing the hash function family is transformed into an optimization problem under a fixed number of hypercubes. By solving the optimization problem, different hyperplane intervals are set for each dimension to ensure that the hash functions can evenly segment the data space, where each segmented hypercube has a close volume and close side lengths. Finally, the analysis of the algorithm shows that the VBLSH algorithm has a high index coding efficiency and hash code calculation efficiency. The experimental results show that the VBLSH algorithm can simultaneously take into account the efficiency, precision and recall rate, and avoid the F1-trap; it shows excellent effectiveness on 4 datasets. [ABSTRACT FROM AUTHOR]

• Based on type-2 fuzzy theory, a distributionally robust optimization method for the sustainable development problems is developed. • The robust counterpart of original distributionally robust fuzzy sustainable development model is established. • A domain decomposition method is designed to find the robust optimal solution that can immunize against the distribution uncertainty. The existing literature on sustainable development problems mainly focuses on multicriteria decision analyses, and ignores the impact of uncertain information on optimal labor allocation decisions. It is necessary for sustainable development to implement suitable policies under uncertainty that integrate several competing aspects including economic, environmental, energy and social criteria. Based on type-2 fuzzy theory, this paper develops a distributionally robust optimization method for sustainable development problems. In our new model, the uncertain per capita gross domestic product (GDP), per capita electricity consumption and per capita greenhouse gas (GHG) emissions are characterized by parametric interval-valued (PIV) possibility distributions and their associated uncertainty distribution sets. Under two assumptions on the underlining decision-making environment, the robust counterpart of the original distributionally robust fuzzy sustainable development model is formally established. To solve the proposed robust sustainable development model, this paper discusses the computational issue concerning the infinitely many integral objective functions and credibilistic constraints, and turns the robust counterpart model into its computationally tractable equivalent deterministic submodels. Taking advantage of the structural characteristics of the equivalent submodels, a domain decomposition method is designed to find the robust optimal solution that can protect against distribution uncertainty. Finally, this paper applies the proposed optimization method for the key economic sectors of the United Arab Emirates (UAE) to provide quantitative justification in planning future labor and resource allocation. [ABSTRACT FROM AUTHOR]

Since Torra introduced the concept of hesitant fuzzy sets, it has seen wide applications in decision-making problems, cluster analysis, medical diagnosis, personnel appraisal, information retrieval and so on. And, nowadays, there arise many discussions related to hesitant fuzzy sets. In particular, recently, Hu extends the truth values set of hesitant fuzzy sets and hesitant fuzzy relations from the family of subsets of unit interval to the family of nonempty subsets of any linearly ordered set with an involutive negator and calls them hesitant sets and hesitant relations, respectively. This paper continues to consider this topic and mainly intends to give a systematical discussion to hesitant relations on their properties and potential applications in three-way decisions. First, this paper shows some novel properties of the operations on linearly ordered set with an involutive negator. Second, this paper investigates some vital properties of hesitant relations, especially for the compositions, projections, reflexivity, symmetry, *-transitivity and so on. Third, this paper proposes various types of ordered hesitant relations. Finally, this paper discusses some applications of hesitant relations in the constructions of decision evaluation functions in three-way decision spaces. [ABSTRACT FROM AUTHOR]

Data engineers invest significant effort in the early stages of data analysis, including identifying relevant datasets in large and complex data lakes. Data retrieval efficiency becomes an urgent concern as data volumes continue to increase with structures that vary in size and complexity. This paper presents a novel strategy for accelerating data discovery in data lakes. Our approach integrates self-supervised techniques and weighted similarity estimation for efficient dataset classification, facilitating faster search and retrieval. By extracting meta-feature characteristics, our approach improves data traceability in data lakes through clustering, resulting in significant improvements in modularity, showing an efficiency gain of 69.8%. Regarding dataset search through classification, it consistently achieves AUC-ROC scores exceeding 0.85, indicating strong performance in class differentiation. Finally, our method reduces the overall execution time more than twofold and shows promising applications for addressing real-world challenges in various data lake domains. [ABSTRACT FROM AUTHOR]

Text similarity measures have become increasingly pivotal in text-related research and applications, encompassing tasks such as information retrieval, text classification, document clustering. Unveiling the equality relationship between encrypted words is fundamental for ensuring privacy-preserving text similarity. Identity-based encryption with equality test (IBEET) emerges as a promising solution for computing similarity over encrypted data in cloud environment. However, prevalent IBEET schemes often lack control over the lifespan of trapdoors, potentially leading to misuse and unauthorized disclosure of users' privacy. In this paper, we introduce a novel primitive known as controllable forward secure identity-based encryption with equality test (CFS-IBEET), designed to support both permanent trapdoor and temporary trapdoor. We present a concrete CFS-IBEET scheme based on bilinear pairing and conduct a comprehensive security analysis against two types of adversaries in random oracle model. The comprehensive performance evaluation shows that our CFS-IBEET scheme offers significant advantages of high efficiency of encryption, decryption, trapdoor generation and test algorithms as well as the guarantee of controllable forward security, showcasing its applicability for collaborative filtering recommendation system in E-commerce age. • Propose a stronger IBEET for privacy-preserving text similarity. • Flexibly control the granularity of time-based authorization for forward security. • Formally prove its security against two adversaries in random oracle model. • Show its practical application in collaborative filtering recommendation system thanks to its significant high efficiency. [ABSTRACT FROM AUTHOR]

Abstract A certificateless aggregate signature (CLAS) scheme employing a reduced signature size eliminates the complexity of certificate management in a traditional public key cryptosystem. A compact aggregate signature, where the size does not depend on the aggregate number, is desirable when the objective is to reduce storage cost and bandwidth. However, in conventional compact CLAS schemes, aggregation of signatures is restricted. The state information is meant to be used only once for security; it is generally used to restrict aggregation to signatures generated with the same state information. This paper proposes the first unrestricted and compact CLAS scheme where the signature size is constant and any combination of signatures can be aggregated. Aside from convenient storage and communication costs, our scheme is also equipped with a secure system against realistic adversaries. Moreover, we evaluate the performance of our CLAS scheme and demonstrate its effectiveness. Finally, this paper reveals that it is not possible to construct an unrestricted and compact CLAS scheme for a widely used structure with constant pairing computation. [ABSTRACT FROM AUTHOR]

Abstract A Top-k retrieval algorithm returns the k best answers of a query according to a given ranking. From a theoretical point of view, the solution of this query is straightforward if we do not take into consideration execution time. However, in many practical situations, execution time is a substantial issue. In such a case, the process of getting the top k in an optimal time becomes an interesting and non-trivial task. This paper presents an algorithm to retrieve the top-k associated to an arbitrary ranking function. The idea is to decompose the ranking function as a supremum of a certain set of functions where an efficient top-k retrieval procedure can be easily applied. Besides the theoretical presentation of the algorithm, the paper provides a set of experiments to validate the approach. [ABSTRACT FROM AUTHOR]

Personalized information retrieval has become more crucial and challenging in today's time, as every user is demanding information according to their own perspectives. To achieve personalization, this paper proposes a methodology with a focus on the selection of an effective composition corresponding to various supporting modules of a personalization methodology. Collaborative tagging can be quite helpful in constructing User Interest Profile (UIP) and Resource Illustration Profile (RIP). The proposed methodology also focuses on UIP augmentation using multiple strategies; and a novel approach has also been designed to handle outlier tags which caused ambiguity in collective RIP. Even a good UIP and RIP alone cannot create an efficient personalization methodology; they also require a suitable mapping with user's query requirement. Therefore, in the proposed methodology, the fuzzy satisfaction requirement-based novel mapping functions have been designed to measure query relevance score and user interest relevance score for a web resource. These scores have been further used to calculate the post-relevance score of a web resource after a suitable trade-off. Experiments using the del.icio.us dataset show that the proposed methodology has outperformed each and every baseline by a considerable margin. [ABSTRACT FROM AUTHOR]

Private Information Retrieval (PIR) allows a client to privately retrieve some data from a public database. There exist two types of PIR: (computational) Single-server PIR (SPIR) and (information-theoretic) multi-server PIR. In this paper, we focus on exploring SPIR. We first propose a simple and efficient additively-homomorphic encryption scheme of which privacy is based on the learning with binary errors assumption that is known as an interesting candidate for practical lattice-based cryptography. Then, according to our proposed homomorphic encryption scheme, we give a Verifiable (single/multi-bit) SPIR (VSPIR) scheme for the single-query case under the malicious server model. To the best of our knowledge, our proposal is the first practical non-interactive VSPIR scheme employing an efficient probabilistic proof that can discover the forged result with overwhelming probability. The corresponding communication complexity and computational complexity are comparable with those of some typical SPIR schemes. Moreover, we extend our single-query VSPIR scheme to construct a non-interactive multi-query solution. In particular, the corresponding communication complexity and computational complexity are the same as those of the single-query scheme. Finally, we provide detailed implementation results to confirm efficiency of our proposals. [ABSTRACT FROM AUTHOR]

• A new fuzzy squareness measure for evaluating how much a given shape is a fuzzy square is introduced. • Such a measure ranges through (0, 1], and reaches maximal value 1 iff for a fuzzy square. • The new fuzzy squareness measure is invariant w.r.t. similarity transformations. • The new measure is naturally defined and theoretically well-founded. • Effectiveness of the new measure is illustrated through classification tasks performed on three large well-known image datasets. In this paper, we define a new fuzzy squareness measure to quantify how much a given fuzzy shape matches a fuzzy square. The new fuzzy shape-based measure is naturally defined and theoretically well-founded, resulted in that its behavior can be understood and predicted in advance. It runs through the interval (0 , 1 and takes the maximum value equals 1 if and only if the shape measured is a fuzzy square. The new fuzzy squareness measure is also invariant to similarity transformations. Several various experiments to illustrate the behavior of the new measure, and to verify all the theoretically proven results are also shown. Effectiveness and usefulness of the new fuzzy squareness measure are demonstrated in the tasks of object classification performed on three large well-known modern image datasets such as MPEG-7 CE-1, Swedish Leaf, and Portuguese Leaves datasets. [ABSTRACT FROM AUTHOR]

A classic t -private PIR (private information retrieval) scheme allows a user to retrieve one out of n values from k communicating replicated databases while any t of the k databases cannot identify the value being retrieved. However, in reality, the user may be more interested in retrieving multiple values simultaneously. This paper is devoted to the PIR problem with m retrieved values and k databases against t colluding databases (t -private MPIR) in the context of information-theoretic security. The relationship m ⩽ w (k - t) is derived, where w is the largest average amount of information got by the user from each of the k databases. When w = 1 , via trace functions in finite fields, a t -private MPIR scheme retrieving m = k - t values is presented with the complexity O (log n). Our scheme provides a lower complexity than those in the literature (the best known complexity for general t and k is a fractional power function of n). [ABSTRACT FROM AUTHOR]

Source selection is the problem of identifying a subset of available data sources that best meet a user’s needs. In this paper we propose a user-driven approach to source selection that seeks to identify sources that are most fit for purpose. The approach employs a decision support methodology to take account of a user’s context, to allow end users to tune their preferences by specifying the relative importance between different criteria, looking to find a trade-off solution aligned with his/her preferences. The approach is extensible to incorporate diverse criteria, not drawn from a fixed set, and solutions can use a subset of the data from each selected source, rather than require that sources are used in their entirety or not at all. The paper describes and motivates the approach, presenting a methodology for modelling a user’s context, and its collection of optimisation algorithms for exploring the space of solutions, and compares and evaluates the resulting algorithms using multiple real world data sets. The experiments show how source selection results are produced that are attuned to each user’s preferences, both with respect to overall weighted utility and through faithful representation of a user’s preferences within a result, while scaling to potentially thousands of sources. [ABSTRACT FROM AUTHOR]

Question Answering (QA) systems based on Information Retrieval return precise answers to natural language questions, extracting relevant sentences from document collections. However, questions and sentences cannot be aligned terminologically, generating errors in the sentence retrieval. In order to augment the effectiveness in retrieving relevant sentences from documents, this paper proposes a hybrid Query Expansion (QE) approach, based on lexical resources and word embeddings, for QA systems. In detail, synonyms and hypernyms of relevant terms occurring in the question are first extracted from MultiWordNet and, then, contextualized to the document collection used in the QA system. Finally, the resulting set is ranked and filtered on the basis of wording and sense of the question, by employing a semantic similarity metric built on the top of a Word2Vec model. This latter is locally trained on an extended corpus pertaining the same topic of the documents used in the QA system. This QE approach is implemented into an existing QA system and experimentally evaluated, with respect to different possible configurations and selected baselines, for the Italian language and in the Cultural Heritage domain, assessing its effectiveness in retrieving sentences containing proper answers to questions belonging to four different categories. [ABSTRACT FROM AUTHOR]

Chameleon hash functions are collision resistant when only the hashing keys of the functions are known. In particular, without the knowledge of the secret information, the chameleon hash function is merely like a regular cryptographic hash function, where it is hard to find collisions. However anyone who has trapdoor keys can efficiently generate pre-images for the chameleon hash function. In some applications, such as redactable blockchains, unfortunately the existing properties do not suffice and we need more features. Actually, it is required that without knowing the trapdoor keys, nobody can compute collisions, even if he can see collisions for arbitrary hash functions. In 2017, Ateniese et al. introduced the notion of chameleon hash functions in the enhanced collision resistant model and proposed a construction in the standard model satifying the features. To date, efficient constructions of this kind of chameleon hash functions remain as an open research problem. In this paper, we answer this problem affirmatively by presenting efficient constructions of the chameleon hash function satisfying the enhanced collision resistance. The contributions of this work are twofold. First, we show the weakness of previous work. Then, we proceed with proposing new schemes with more efficiency. Technically, we present a new chameleon hash function in the basic model and based on simple assumptions. This chameleon hash function is well compatible with Groth-Sahai proof systems and the Cramer-Shoup encryption schemes, and can be used as a stepping stone to construct an efficient chameleon hash function in the enhanced collision resistant model. Moreover, we show our basic chameleon hash can be combined with optimal ZK-SNARKs of Groth and Maller that leads to shorter sizes for chameleon hash function in the enhanced collision resistant model. [ABSTRACT FROM AUTHOR]

• The sequential and tree-structured LSTM with attention is proposed. • Word-based features can enhance the relation extraction performance. • The proposed method is used for the relation extraction. • The relation extraction performance is demonstrated on public datasets. Semantic relation extraction is crucial to automatically constructing a knowledge graph (KG), and it supports a variety of downstream natural language processing (NLP) tasks such as query answering (QA), semantic search and textual entailment. In addition, the semantic relation extraction task is mainly responsible for identifying entity pairs from raw texts and extracting the semantic relations between the extracted entity pairs. Existing methods consider only lexical-level features and often ignore syntactic features, resulting in poor relation extraction performance. By analyzing the necessity of the syntactic dependency and the contributions of words in a sentence to relation extraction, this paper proposes an end-to-end method that uses bidirectional tree-structured long short-term memory (LSTM) to extract structural features based on the dependency tree of a sentence. To enhance the performance of the relation extraction, the bidirectional sequential LSTM with attention is used to identify word-based features including the positional information of entity pairs and the contribution of words. Then, structural features and word-based features are concatenated to optimize the relation extraction performance. Finally, the proposed method is used on the SemEval 2010 task 8 and the CoNLL04 datasets to validate its performance. The experimental results show that the proposed method achieves state-of-the-art results on the SemEval 2010 task 8 and the CoNLL04 datasets. [ABSTRACT FROM AUTHOR]

When optimizing many-objective problems (MaOP), the same strategy might behave differently when facing problems with different features. Therefore, obtaining problem features helps to obtain high-quality solutions. However, in practice, the problem features are unknown during the optimization process. In this case, learning to adjust strategies to match the problem features is a challenging work. In this paper, a learning-based algorithm is proposed, aimed to enhance the generalization ability. On the basis of a decomposition-based many-objective optimization framework, a learning automaton (LA) is included in the algorithm. The LA adjusts the evolutionary strategies of the algorithm to adapt to the problem characteristics, according to the feedback information during the optimizing procedure. An external archive is employed to store the Pareto non-dominant solutions. Based on the external archive, a reference vector adjustment strategy is designed to enhance the capability of solving problems with a degenerate or discrete Pareto front (PF). To validate the performance of the proposed algorithm, a comparison experiment is conducted on a novel authority test suite. Five state-of-the-art algorithms are selected as peer algorithms. The results of the experiment indicate that the proposed algorithm obtains satisfactory performance in determining the convergence and the approximation of the PF. [ABSTRACT FROM AUTHOR]

• A new multi-layer interaction preference based multi-objective optimization algorithm through decomposition (MLIP-MOEA/D) is proposed. • A fast way to get preference region is established, during the selection process, the preference weight vector is redefined using the angle-based method. • A novel multi-layer interaction strategy for searching the accurate solutions is proposed. During evolution, the preferred region is reduced gradually, making it easier for user to get the final preferred solution(s). • Besides ZDT problems with two objectives, the proposed algorithm shows its potentiality for solving many-objective problems, i.e., DTLZ problems with 3, 5, 8, 10 objectives. Many problems in real world have not only one objective to be met. In the majority of cases, a set of trade-off solutions which spread evenly along the entire Pareto optimal front are generated by multi-objective evolutionary algorithms (MOEAs). Taking the preference of decision maker (DM) into consideration, some specified solutions can be obtained, which is of great interest in practical applications. In this paper, a novel multi-layer interaction preference based multi-objective evolutionary algorithm through decomposition (denoted as MLIP-MOEA/D) is proposed. In MLIP-MOEA/D, a multi-layer interactive strategy is developed during evolution, in the first-layer interaction, the DM will provide a reference vector and an initial radius to determine a preference range, then all solutions in this range will be updated. The algorithm will stop if the DM is satisfied with the first output result, otherwise it will go on to the second-layer interaction. In this step, the most preferred solution generated from the first-layer interaction will be chosen as the new preference direction, and the weight vector is redefined by the angle-based method, and the range of preferred region is reduced gradually, until the closest solution that meet the DM's need is found. The algorithm is tested on a set of benchmark problems including DTLZ problems with more than three objectives, the experimental studies show that the proposed algorithm can effectively search the preferred solutions with the preference information and successfully deal with many-objective optimization problems. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of constructing aggregation functions which support the concept of partial agreement when only one or more sub-group(s) of decision makers and criteria, not necessarily all of them, is (are) involved to take the final action. The proposed method is started with computing all different α -combinations from an n -element set of inputs, according to the binomial coefficient, and then completed by combining their aggregations. This approach, so-called combination operator-based aggregation function, guarantees to consider various agreement scenarios at different consensus levels in contrary with the traditional composition-based construction methods that act as a full agreement. The attention is then given to the weighted case specially the conditions of weighting vectors for ensuring the well-defined property of the proposed method. As an application, the combination operator-based aggregation function is generalized over the Cartesian product of unit intervals [0,1] to deal with multi-polar information. The proposed aggregating methodology is then used to reach consensus in a group decision-making problem. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) approaches are widely applied in recommender systems. Traditional CF approaches have high costs to train the models and cannot capture changes in user interests and item popularity. Most CF approaches assume that user interests remain unchanged throughout the whole process. However, user preferences are always evolving and the popularity of items is always changing. Additionally, in a sparse matrix, the amount of known rating data is very small. In this paper, we propose a method of online collaborative filtering with dynamic regularization (OCF-DR), that considers dynamic information and uses the neighborhood factor to track the dynamic change in online collaborative filtering (OCF). The results from experiments on the MovieLens100K, MovieLens1M, and HetRec2011 datasets show that the proposed methods are significant improvements over several baseline approaches. [ABSTRACT FROM AUTHOR]

A new rough neural network (RNN)-based model is proposed in this paper. The radial basis function network with dynamic decay adjustment (RBFNDDA) is applied to learn information directly from a data set and group it in terms of prototypes. Then, a neighborhood rough set-based procedure is applied to detect prototype outliers. This hybrid model is named rough RBFNDDA1. However, the removal of all outliers may cause information loss because some outliers may represent rare yet useful information in a classification task. As such, the parameters of a prototype outlier, i.e., its radius and weight, are exploited to gauge whether the information encoded by the prototype is meaningful. This hybrid model is named rough RBFNDDA2. The results from a benchmark experimental study show that rough RBFNDDA2 can retain meaningful prototype outliers and, at the same time, significantly reduce the number of prototypes from the original RBFNDDA model while maintaining classification accuracy. A real-world application in a power generation plant is used to evaluate and demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Source retrieval for plagiarism detection retrieves documents that may be the sources of plagiarism for a suspicious document while minimizing the retrieval costs. Compared with traditional information retrieval, queries from the same suspicious document retain their contextual relations and are no longer isolated from each other. The correlation of queries leads to the aggregation of search results; the documents retrieved by different queries may be relevant or the same. However, previous studies have failed to devote sufficient attention to the aggregation of search results in source retrieval. In this paper, the task of source retrieval is formalized into a framework of learning to rank, and a Ranking Logistical Regression Model is utilized to implement the framework. Furthermore, addressing the aggregation of search results, we propose the Source Retrieval Model Focused on Aggregation for plagiarism detection. We evaluate various aspects of the proposed model on the PAN 2013 and the PAN 2014 Plagiarism Source Retrieval Corpus. With respect to established baselines, the experimental results indicate that the Source Retrieval Model Focused on Aggregation yields statistically significantly improved performance of source retrieval with equal or lower cost effectiveness. [ABSTRACT FROM AUTHOR]

The notion of uncertainty measure is one of the most important topics in rough set theory and has been studied in different kinds of information tables. However, few studies have focused on the interval set information table, which is regarded as one of the generalized models of single-valued information tables. This paper aims at studying the uncertainty measurements for interval set information tables. Firstly, an interval δ -similarity relation is induced based on the similarity degree. The similarity relation induces the granules, which form a covering in interval set information tables. Secondly, four types of granularity measures are defined to measure the granularity of a covering. Thirdly, the concepts of accuracy and roughness in rough set theory are respectively extended to δ -accuracy and δ -roughness for interval set information tables. Furthermore, four new combinations ofuncertainty measures by considering proposed granularity measures and δ -accuracy and δ -roughness are defined and analyzed. Theoretical analyses and experimental results illustrate that the proposed measures are effective and accurate for interval set information tables. [ABSTRACT FROM AUTHOR]

Link prediction is an important task in complex network analysis and can be found in many real-world applications such as recommendation systems, information retrieval, and marketing analysis of social networks. This paper focuses on studying the evolution mechanism of real-world temporal networks. Specifically, given a set of temporal links during a fixed time window, how to predict the existence of links at any point in the future. To address this problem, we propose a novel semi-supervised learning framework, which integrates both survival analysis and game theory. First, we carefully define the ϵ-adjacent network sequence, and make use of time stamp on each link to generate the baseline network evolution sequence. Next, to capture the law of network evolution, we employ the Cox Proportional Hazard Model (Cox PHM) to study the relative hazard associated with each temporal link, so as to estimate the coefficients of covariates, which are defined as a set of neighborhood based proximity features. To narrow the area of inquiry, we further propose a game theory based two-way selection mechanism to predict the future network topology. We finally encapsulate these two new technologies in a robust Autonomy-Oriented-Computing (AOC) multi-agent system, and propose a paralleled algorithm to conduct the temporal link prediction task. Extensive experiments were applied to real-world temporal networks to demonstrate both effectiveness and scalability of the proposed approach. [ABSTRACT FROM AUTHOR]

• An optimized ranking algorithm for manycore systems. • Different shared-memory parallelization strategies are investigated. • A thorough evaluation of the proposed optimizations using a 72-core machine. Multimedia data, such as images and videos, has become very popular in people's daily life as a result of the widespread use of mobile devices. The ever-increasing amount of such data, along with the necessity for real-time retrieval, has lead to the development of new methods that can process them in a timely fashion with acceptable accuracy. In this paper, we study the performance of ReckNN, an unsupervised manifold learning algorithm based on the reciprocal neighbourhood and the authority of ranked lists. Most of the related work in this field do not fully investigate optimization strategies, an aspect that is becoming more important with the high availability of manycore machines. In order to address that issue, we fully investigate optimization opportunities in this article and make the following three main contributions. Firstly, we develop an efficient and scalable method for storing and accessing the distances between objects (e.g., video or image) based on dictionaries. Secondly, we employ memoization to speed up the computation of authority scores, leading to a significant performance gain even on single-core architectures. Lastly, we devise and implement several parallelization strategies and show that they are scalable on a 72-core Intel machine. The experimental results with MPEG-7, Corel5k and MediaEval benchmarks show that the optimized ReckNN delivers both efficiency and scalability, highlighting the importance of the proposed optimizations for manycore machines. [ABSTRACT FROM AUTHOR]

False or unverified information spreads just like accurate information on the web, thus possibly going viral and influencing the public opinion and its decisions. Fake news and rumours represent the most popular forms of false and unverified information, respectively, and should be detected as soon as possible for avoiding their dramatic effects. The interest in effective detection techniques has been therefore growing very fast in the last years. In this paper we survey the different approaches to automatic detection of fake news and rumours proposed in the recent literature. In particular, we focus on five main aspects. First, we report and discuss the various definitions of fake news and rumours that have been considered in the literature. Second, we highlight how the collection of relevant data for performing fake news and rumours detection is problematic and we present the various approaches, which have been adopted to gather these data, as well as the publicly available datasets. Third, we describe the features that have been considered in fake news and rumour detection approaches. Fourth, we provide a comprehensive analysis on the various techniques used to perform rumour and fake news detection. Finally, we identify and discuss future directions. [ABSTRACT FROM AUTHOR]

Inductive learning from multi-class and imbalanced datasets is one of the main challenges for machine learning. Most machine learning algorithms have their predictive performance negatively affected by imbalanced data. Although several techniques have been proposed to deal with this difficulty, they are usually restricted to binary classification datasets. Thus, one of the research challenges in this area is how to deal with imbalanced multiclass classification datasets. This challenge become more difficult when classes containing fewer instances are located in overlapping regions of the data attribute space. In fact, several studies have indicated that the degree of class overlapping has a higher effect on predictive performance than the global class imbalance ratio. This paper proposes a novel evolutionary ensemble-based method for multi-class imbalanced learning called the evolutionary inversion of class distribution in overlapping areas for multi-class imbalanced learning (EVINCI). EVINCI uses a multiobjective evolutionary algorithm (MOEA) to evolve a set of samples taken from an imbalanced dataset. It selectively reduces the concentration of less representative instances of the majority classes in the overlapping areas while selecting samples that produce more accurate models. In experiments performed to evaluate its predictive accuracy, EVINCI was superior to state-of-the-art ensemble-based methods for imbalanced learning. [ABSTRACT FROM AUTHOR]

Abstract Clustering is one of the most commonly used techniques in data mining. Its main goal is to group objects into clusters so that each group contains objects that are more similar to each other than to objects in other clusters. The evaluation of a clustering solution is a task carried out through the application of validity indices. These indices measure the quality of the solution and can be classified as either internal that calculate the quality of the solution through the data of the clusters, or as external indices that measure the quality by means of external information such as the class. Generally, indices from the literature determine their optimal result through graphical representation, whose results could be imprecisely interpreted. The aim of this paper is to present a new external validity index based on the chi-squared statistical test named Chi Index, which presents accurate results that require no further interpretation. Chi Index was analyzed using the clustering results of 3 clustering methods in 47 public datasets. Results indicate a better hit rate and a lower percentage of error against 15 external validity indices from the literature. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a novel approach for classifying and retrieving 3D shapes. We first propose a new polar view based strategy that, by using 360-degree projection, effectively reflects the internal structure and key features of a 3D shape. Specifically, the point cloud of the 3D shape is mapped to a two-dimensional (2D) plane, and the polar view representation is obtained by the maximum depth of the point cloud. Projecting 3D point clouds into a 2D plane enables us to use sufficient image data for training, and the process also takes advantage of both image-based and 3D shape-based methods. We propose a convolutional neural network (CNN) that is trained by using only a single polar view of a 3D shape to obtain the polar view representation (PVR) and realize the classification and retrieval of 3D shapes. Experiments on standard datasets, such as ModelNet10 and ModelNet40, show that our method outperforms state-of-the-art methods on 3D shape classification and retrieval. [ABSTRACT FROM AUTHOR]

Vast amounts of trajectory data have been collected due to the popularity of GPS devices. Analyzing this wealth of data is important, thus highlighting the need to efficiently index and store this large amount of data on secondary storage to allow for efficient retrieval. Existing approaches index trajectories based on data partitioning index structures such as R-trees or space partitioning index structures such as quad-trees. R-tree like data structures, when used for indexing trajectories, result in large overlapping minimum bounding boxes and are therefore inefficient for the indexing and storage of large trajectory data sets. Existing approaches based on space partitioning do not allow the tradeoff of time versus space constraints in a way that is sensitive to query patterns. This paper proposes a new indexing and storage approach called GCOTraj, which partitions a large spatio-temporal data space into multi-dimensional grid cells and orders these grid cells in two different ways, first via traditional space filling curves which are not sensitive to query patterns; and second, via the Graph-Based Ordering approach (GBO) which is a state-of-the-art workload-based ordering technique for multidimensional data. GCOTraj clusters and stores trajectories to secondary storage based on the ordering produced by ordering algorithms. A good ordering will result in less disk seeks when retrieving disk blocks to answer a query. In addition, GCOTraj uses an index to spot the targeted data on disk and reduce the redundant data retrieved therefore reducing disk IO. Extensive experiments suggest that GCOTraj outperforms the state-of-the-art trajectory storage scheme TrajStore by a factor of up to 16.07 in IO time to answer range queries. [ABSTRACT FROM AUTHOR]

The reverse top- k search problem is a variant of the top- k search problem. Suppose that there are a set of objects O and a set of weight vectors W in the d -dimensional space. Then, given a query object, the reverse top- k ( RTOPk ) search is to find a subset W ′ of W such that, when the query object is inserted into O (or already included in O ), the query object is one of the top- k objects for each weight vector in W ′. Many studies on the RTOPk search have been conducted in the last few years. However, the existing methods for the RTOPk search only focus on how to efficiently process evaluations of the weight vectors, which check whether the weight vectors are included in the result without efficient pruning methods. In this paper, we propose an efficient method for the RTOPk search, that overcomes drawbacks of existing methods. In contrast to existing methods, the proposed method prunes each unnecessary weight vector without traversing objects, and filters out each unnecessary object without considering the weight vectors. In addition, the proposed method evaluates weight vectors by preserving search contexts for multiple traversals to tree-based indexes of weight vectors and objects. The experimental results based on synthetic datasets and a real dataset show that the proposed method is significantly more efficient than existing methods. [ABSTRACT FROM AUTHOR]

The recent growth of open data initiatives has led to a tremendous increase in publicly available data resources. This amount of data, together with a rising interest in people to analyze it, poses severe challenges regarding data storage. Data suppliers often compress their resources with standard compressors. The choice of a compression technique, however, has significant impacts on the compression ratio, the compression speed, and the decompression speed. In this paper, we provide an empirical analysis on the compression of open data provided in a relational format, such as comma-separated value files. We consider several compression tools and parameter settings. Furthermore, we propose using a novel column-wise compression strategy, where items that have similar properties, are compressed together. We perform a comprehensive analysis on 24 datasets from different domains, such as life sciences, governmental data, finance sector, and public transportation, which cover a wide range of file sizes (from a few MB to several GB). Our results show that the traversal strategy is of paramount importance for achieving high compression ratios; with improvements of up to one order of magnitude. This study further highlights a set of issues for future work on compressing open data. [ABSTRACT FROM AUTHOR]

As the number of people who use scientific literature databases has grown, the demand for literature retrieval services has steadily increased. One of the most popular retrieval service methods is to find a set of papers similar to the paper under consideration, which requires a measure that computes the similarities between the papers. Scientific literature databases exhibit two interesting characteristics that are not found in general databases. First, the papers cited by older papers are often not included in the database due to technical and economic reasons. Second, since a paper references previously published papers, few papers cite recently published papers. These two characteristics cause all existing similarity measures to fail in at least one of the following cases: (1) measuring the similarity between old, but similar papers, (2) measuring the similarity between recent, but similar papers, and (3) measuring the similarity between two similar papers: one old, the other recent. In this paper, we propose a new link-based similarity measure called C-Rank, which uses both in-link and out-link references, disregarding the direction of the references. In addition, we discuss the most suitable normalization method for scientific literature databases and we propose an evaluation method for measuring the accuracy of similarity measures. For the experiments, we used real-world papers from DBLP's database with reference information crawled from Libra. We then compared the performance of C-Rank with that of existing similarity measures. Experimental results showed that C-Rank achieved a higher accuracy than existing similarity measures. [ABSTRACT FROM AUTHOR]

This paper studies the problem of k-optimal-location-selection ( k OLS) retrieval in metric spaces. Given a set D A of customers, a set D B of locations, a constrained region R , and a critical distance d c , a metric k OLS (M k OLS) query retrieves k locations in D B that are outside R but have the maximal optimality scores . Here, the optimality score of a location l ∈ D B located outside R is defined as the number of the customers in D A that are inside R and meanwhile have their distances to l bounded by d c according to a certain similarity metric (e.g., L 1 -norm, L 2 -norm, etc.). The existing k OLS methods are not sufficient because they are applicable only to the Euclidean space, and are not sensitive to k . In this paper, for the first time, we present an efficient algorithm for k OLS query processing in metric spaces. Our solution employs metric index structures (i.e., M-trees) on the datasets, enables several pruning rules , utilizes the advantages of reuse technique and optimality score estimation , to support a wide range of data types and similarity metrics. In addition, we extend our techniques to tackle two interesting and useful variants, namely, M k OLS queries with multiple or no constrained regions. Extensive experimental evaluation using both real and synthetic data sets demonstrates the effectiveness of the presented pruning rules and the performance of the proposed algorithms. [ABSTRACT FROM AUTHOR]

The issues that are related to the process of global decision-making on the basis of knowledge which is stored in a dispersed form (several local knowledge bases or classifiers) are discussed in this paper. In a decision-making system, which is described in the paper, the classification process of the test object starts with an investigation of how particular classifiers classify a test object. We describe the views of classifiers by using probability vectors over decision classes. In the system, the process of combining classifiers in coalitions is very important. Negotiation is used in the clustering process. We define three types of relations between classifiers: friendship, conflict and neutrality. The clustering process consists of two stages. In the first step, the initial groups are created. These groups contain classifiers that are in a friendship relation. In the second stage, classifiers which are in neutrality relation are attached to the existing groups. In this paper, a formal description of the clustering process is presented and mathematical properties of functions, which are used, are described. For every cluster, we find a kind of combined information. Finally, we classify the given test object by voting among clusters, using the combined information from each of the clusters. In the paper a new way of creating clusters (with a negotiation stage) is compared to the approach presented in the paper (Przybyła-Kasperek and Wakulicz-Deja, 2014) [23] (without negotiations). There are significant differences between the clusters that are generated using these two approaches, which are shown in the paper. In the new approach, the clusters are more complex and better reconstruct and illustrate the views of the classifiers on the classification. [ABSTRACT FROM AUTHOR]

Abstract: Retrieving representative information from large-scale data becomes an important research issue nowadays, especially in the context of mobile business/search where the screen size and navigability are limited. This paper focuses on certain aspects of representativeness in database queries and web search, and proposes an approach to extracting a subset of results from original search results in light of high coverage and low redundancy. In the paper, the notion of λ-represent is introduced, which enables us to describe the λ-represent relationship between the sets of data objects. Then, the λ-representative problem is formulated as an extension of the typical set covering problem, which leads to developing a heuristic approach (namely, LamRep) to coping with the problem effectively and efficiently. Notably, LamRep is incorporated with a “vote” mechanism, enhanced with an algorithmic acceleration strategy. Data experiments on benchmark data and a real-world example show that LamRep outperforms the other approaches. [Copyright &y& Elsevier]

Document Information retrieval consists of finding the documents in a collection of documents that are the most relevant to a user query. Information retrieval techniques are widely-used by organizations to facilitate the search for information. However, applying traditional information retrieval techniques is time consuming for large document collections. Recently, cluster-based information retrieval approaches have been developed. Although these approaches are often much faster than traditional approaches for processing large document collections, the quality of the documents retrieved by cluster-based approaches is often less than that of traditional approaches. To address this drawback of cluster-based approaches, and improve the performance of information retrieval both in terms of runtime and quality of retrieved documents, this paper proposes a new cluster-based information retrieval approach named ICIR (Intelligent Cluster-based Information Retrieval). The proposed approach combines k-means clustering with frequent closed itemset mining to extract clusters of documents and find frequent terms in each cluster. Patterns discovered in each cluster are then used to select the most relevant document clusters to answer each user query. Four alternative heuristics are proposed to select the most relevant clusters, and two alternative heuristics for choosing documents in the selected clusters. Thus, eight versions of the proposed approach are obtained. To validate the proposed approach, extensive experiments have been carried out on well-known document collections. Results show that the designed approach outperforms traditional and cluster-based information retrieval approaches both in terms of execution time and quality of the returned documents. [ABSTRACT FROM AUTHOR]

In this paper, we examine the problem of building a user profile from a set of documents. This profile will consist of a subset of the most representative terms in the documents that best represent user preferences or interests. Inspired by the discrete concentration theory we have conducted an axiomatic study of seven properties that a selection function should fulfill: the minimum and maximum uncertainty principle, invariant to adding zeros, invariant to scale transformations, principle of nominal increase, transfer principle and the richest get richer inequality. We also present a novel selection function based on the use of similarity metrics, and more specifically the cosine measure which is commonly used in information retrieval, and demonstrate that this verifies six of the properties in addition to a weaker variant of the transfer principle, thereby representing a good selection approach. The theoretical study was complemented with an empirical study to compare the performance of different selection criteria (weight- and unweight-based) using real data in a parliamentary setting. In this study, we analyze the performance of the different functions focusing on the two main factors affecting the selection process: profile size (number of terms) and weight distribution. These profiles are then used in a document filtering task to show that our similarity-based approach performs well in terms not only of recommendation accuracy but also efficiency (we obtain smaller profiles and consequently faster recommendations). [ABSTRACT FROM AUTHOR]

3D shape retrieval is always a challenging research topic because of complex geometric structural variations involved. Although many feature extraction and retrieval algorithms have been proposed, they generally only use single 3D model descriptor hence cannot obtain better retrieval performance. In this paper, we propose a new 3D shape retrieval framework based on compressive sensing (CS) and multi-feature fusion (MFF). Firstly, we extract three new features including the CS Chebyshev ray (CSCR) feature, the CS spatial hierarchical (CSSH) feature and the Extended Gaussian sphere (EGS) feature. Actually, CSCR, CSSH and EGS respectively represent the volume tensor, the layered detail and the statistical space distribution on the model surface of a 3D model. To make the best use of these features, a supervised learning is used to determine the weighting coefficients for these features. Finally, the features and their corresponding weighting coefficients are used to determine the similarity of 3D models in the multi-feature fusion (MFF) framework for 3D shape retrieval. For performance assessment, two publicly available datasets that contain 3D models with large geometric variations are used, including ModelNet-10 and PSB datasets. Comprehensive experimental results have demonstrated the efficacy of the proposed method for 3D shape retrieval. [ABSTRACT FROM AUTHOR]

The salient region is the most important part of an image. The salient portion in images also attracts the most attention when people search for images in large-scale datasets. However, to improve image retrieval accuracy, considering only the most salient object in an image is insufficient because the background also influences the accuracy of image retrieval. To address this issue, this paper proposes a novel concept called the extended salient region (ESR). First, the salient region of an input image is detected using a Region Contrast (RC) algorithm. Then, a polar coordinate system is constructed; the centroid of the salient region is set as the pole. Next, the regions surrounding the salient region are determined by the neighboring regions, moving in a counterclockwise direction. The resulting combination of the salient region and its surrounding regions is defined as the ESR. We extract the visual content from the ESR using the well-known Bag of Words (BoW) model based on Gabor, SIFT and HSVH features and propose a graph model of the visual content nodes to represent the input image. Then, we design a novel algorithm to perform matching between two images. We also define a new similarity measure by combining the similarities of the salient region and the surrounding regions using weights. Finally, to better evaluate the image retrieval accuracy, an improved measure called the mean label average precision (MLAP) is proposed. The results of experiments on three benchmark datasets (Corel, TU Darmstadt, and Caltech 101) demonstrate that our proposed ESR model and region-matching algorithm are highly effective at image retrieval, and can achieve more accurate query results than current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the rapid development of science technology, finding prevalent spatial patterns from urban facility data has gradually become an important issue in smart city applications. Co-location pattern mining is a valid method for identifying patterns whose instances are prevalent in geographical proximity. However, existing methods treat the space as homogeneous and non-directional, and both the proximity levels and connecting directions of instances are neglected during the mining process, causing the minded patterns to be unsatisfactory. Tobler's First Law indicates that the contributions of instances to their pattern's significance diminish as the distance decreases. Moreover, the directions in which instances are connected should also be considered due to the distance decay effects. Following these threads, this paper proposes a novel co-location pattern mining algorithm mixed with a density-weighted distance thresholding consideration. Based on the framework of our previous SGCT algorithm, which concentrates on efficiency and storage issues, this solution comprises an extension called SGCT-K, which is mainly concerned with improving the effectiveness of the mined results. It adopts a kernel-density-estimation-based model to measure the proximity level of different instance types and respects their directions during the instance connecting process. We implement experiments using both synthetic and real-facility datasets in Beijing, China. The results provide sound evidence that the algorithm improves both accuracy and sensitivity compared to previous methods. [ABSTRACT FROM AUTHOR]

Abstract: Cloud computing emerges as a new computing paradigm that aims to provide reliable, customized and quality of service guaranteed computation environments for cloud users. Applications and databases are moved to the large centralized data centers, called cloud. Due to resource virtualization, global replication and migration, the physical absence of data and machine in the cloud, the stored data in the cloud and the computation results may not be well managed and fully trusted by the cloud users. Most of the previous work on the cloud security focuses on the storage security rather than taking the computation security into consideration together. In this paper, we propose a privacy cheating discouragement and secure computation auditing protocol, or SecCloud, which is a first protocol bridging secure storage and secure computation auditing in cloud and achieving privacy cheating discouragement by designated verifier signature, batch verification and probabilistic sampling techniques. The detailed analysis is given to obtain an optimal sampling size to minimize the cost. Another major contribution of this paper is that we build a practical secure-aware cloud computing experimental environment, or SecHDFS, as a test bed to implement SecCloud. Further experimental results have demonstrated the effectiveness and efficiency of the proposed SecCloud. [Copyright &y& Elsevier]

With the exponential growth of information available on the Internet and various organisational intranets there is a need for profile based information seeking and retrieval (IS&R) systems. These systems should be able to support users with their context-aware information needs. This paper presents a new approach for enterprise IS&R systems using fuzzy logic to develop task, user and document profiles to model user information seeking behaviour. Relevance feedback was captured from real users engaged in IS&R tasks. The feedback was used to develop a linear regression model for predicting document relevancy based on implicit relevance indicators. Fuzzy relevance profiles were created using Term Frequency and Inverse Document Frequency (TF-IDF) analysis for the successful user queries. Fuzzy rule based summarisation was used to integrate the three profiles into a unified index reflecting the semantic weight of the query terms related to the task, user and document. The unified index was used to select the most relevant documents and experts related to the query topic. The overall performance of the system was evaluated based on standard precision and recall metrics which show significant improvements in retrieving relevant documents in response to user queries. [ABSTRACT FROM AUTHOR]

The content-based image retrieval (CBIR) has been widely studied along with the increasing importance of images in our daily life. Compared with the text documents, images consume much more storage and thus are very suitable to be stored on the cloud servers. The outsourcing of CBIR to the cloud servers can be a very typical service in cloud computing. For the privacy-preserving purposes, sensitive images, such as medical and personal images, need to be encrypted before being outsourced, which will cause the CBIR technologies in plaintext domain unusable. In this paper, we propose a scheme that supports CBIR over the encrypted images without revealing the sensitive information to the cloud server. Firstly, the feature vectors are extracted to represent the corresponding images. Then, the pre-filter tables are constructed with the locality-sensitive hashing to increase the search efficiency. Next, the feature vectors are protected by the secure k-nearest neighbor (kNN) algorithm. The security analysis and experiments show the security and efficiency of the proposed scheme. [ABSTRACT FROM AUTHOR]

Order preserving encryption (OPE) is a kind of encryption designed to support searches on ciphertexts. OPE encrypts plaintexts to ciphertexts with the same order, making it possible to efficiently compare ciphertexts without decryption. Because of its efficiency, OPE has been used in systems aimed at practical use. However, even though many OPE schemes have been proposed, all suffer from security and ciphertext expansion problems. This paper proposes the notation of semi-order preserving encryption (SOPE) as a substitute for OPE. SOPE uses a semi-order preserving condition instead of strict order preserving condition to support a range query on ciphertexts. By this means, SOPE can enhance security and reduce storage cost with some sacrifice of precision. The loss of precision can be eliminated with the cost of extra communication and computation, because it is easy to generate a query on ciphertexts including all required plaintexts. To study the relationship among precision, security and ciphertext expansion, we introduce semi-order preserving degree d , which measures the difference between SOPE and OPE. The theoretical derivation shows that security will increase with d , while precision and ciphertext expansion will decrease with d . Thus SOPE can balance precision, security and ciphertext expansion by adjusting semi-order preserving degree d according to a concrete condition. Finally, we present an implementation of SOPE. [ABSTRACT FROM AUTHOR]

In the last years, and thanks to improvements on computing and communications technologies, wireless networks formed by vehicles (called vehicular networks) have emerged as a key topic of interest. In these networks, the vehicles can exchange data by using short-range radio signals in order to get useful information related to traffic conditions, road safety, and other aspects. The availability of different types of sensors can be exploited by the vehicles to measure many parameters from their surroundings. These data can then be shared with other drivers who, on the other side, could also explicitly submit queries to retrieve information available in the network. This can be a challenging task, since the data is scattered among the vehicles belonging to the network and the communication links among them have usually a short life due to their constant movement. In this paper, we use mobile agent technology to help to accomplish these tasks, since mobile agents have a number of features that are very well suited for mobile environments, such as autonomy, mobility, and intelligence. Specifically, we analyze the benefits that mobile agents can bring to vehicular networks and the potential difficulties for their adoption. Moreover, we describe a query processing approach based on the use of mobile agents. We focus on range queries that retrieve interesting information from the vehicles located within a geographic area, and perform an extensive experimental evaluation that shows the feasibility and the interest of the proposal. [ABSTRACT FROM AUTHOR]

In this paper, we discuss a contribution towards the integration of social information in the index structure of an IR system. Since each user has his/her own understanding and point of view of a given document, we propose an approach in which the index model provides a Personalized Social Document Representation (PerSaDoR) of each document per user based on his/her activities in a social tagging system. The proposed approach relies on matrix factorization to compute the PerSaDoR of documents that match a query, at query time. The complexity analysis shows that our approach scales linearly with the number of documents that match the query, and thus, it can scale to very large datasets. PerSaDoR has been also intensively evaluated by an offline study and by a user survey operated on a large public dataset from delicious showing significant benefits for personalized search compared to state of the art methods. [ABSTRACT FROM AUTHOR]

Social information has been widely applied in the research fields of information retrieval and recommendation systems. However, most research efforts have been conducted to investigate social information with a specific type (e.g. tags ), which ignores the relationships among these various types of heterogeneous social information. In this paper, taking Pseudo Relevance Feedback (PRF) as an example of classical IR models, we propose a novel and generic PRF framework for searching and recommendation with heterogeneous social information. Firstly, through the representations, social information is categorized into structured and unstructured information, then a correlation graph for terms occurred in queries and social information is built to express rich semantic contexts for their relationships. Inspired by the correlation graph, we respectively design diverse term selection strategies for structured information (e.g. tags, ratings ) and unstructured information (e.g. reviews, annotations ). Particularly, we modify the conventional distribution-based term selection models for structured information due to the “semantic indivisibility”, meanwhile we also introduce several transformation term selection models for unstructured information with an additional consideration of ratings when constructing weighting functions. Finally, we construct an effective searching system, where learning-to-rank is utilized adaptively to combine results from various PRF strategies with different social information. Extensive evaluations and comparisons on CLEF/INEX Social Book Search Track (SBS) and three other collections verify the effectiveness and robustness of the proposed framework and term selection models. Furthermore, statistics indicate that the historic records of all 4-year SBS tracks are refreshed by our proposed method. [ABSTRACT FROM AUTHOR]