Search

This paper introduces an algorithm for Facial Expression Recognition (FER) using deep Siamese Neural Networks (SNNs) that preserve the local structure of images in the embedding similarity space. We designed the network to reveal the input pairs similarity by comparing features through a designed metric. Furthermore, we developed a novel image pairing (i.e., positive and negative pairs) strategy technique to train our Siamese model. Our Siamese model comprises of a verification framework and an identification framework to learn a joint embedding space. The verification path reduces the intra-class variations by minimizing the distance between the extracted features from the same class, while the identification path increases the inter-class variations by maximizing the distance between the features extracted from different classes. We apply transfer learning to only use the identification model for facial expression classification. We evaluated our algorithm using AffectNet, FER2013, and Compound Facial Expressions of Emotion (CFEE) datasets, where better results are achieved compared to other deep learning-based approaches.

Unsupervised feature selection can play an important role in addressing the issue of processing massive unlabelled high-dimensional data in the domain of machine learning and data mining. This paper presents a novel unsupervised feature selection method, referred to as Multi-Group Adaptive Graph Representation (MGAGR). Different from existing methods, the relationship between features is explored via the global similarity matrix, which is reconstructed by local similarities of multiple groups. Specifically, the similarity of a feature compared to other features can be represented by the linear combination of all the local similarities. The local similarity of a representative group is given a large weight to reconstruct the global similarity. Besides, an iterative algorithm is given to solve the optimization problem, in which the global similarity matrix, its corresponding reconstruction weights and the self-representation matrix are iteratively improved. Experimental results on 8 benchmark datasets demonstrates that the proposed method outperforms the state-of-the-art unsupervised feature selection methods in terms of clustering performance. The source code is available at: https://github.com/misteru/MGAGR.

The goal of multi-view clustering is to partition samples into different subsets according to their diverse features. Previous multi-view clustering methods mainly exist two forms: multi-view spectral clustering and multi-view matrix factorization. Although they have shown excellent performance in many occasions, there are still many disadvantages. For example, multi-view spectral clustering usually needs to perform postprocessing. Multi-view matrix factorization directly decomposes the original data features. When the size of features is large, it encounters the expensive time consumption to decompose these data features thoroughly. Therefore, we proposed a novel multi-view clustering approach. The main advantages include the following three aspects: 1) it searches for a common joint graph across multiple views, which fully explores the hidden structure information by utilizing the compatibility among views; 2) the introduced nonnegative constraint manipulates that the final clustering results can be directly obtained; and 3) straightforwardly decomposing the similarity matrix can transform the eigenvalue factorization in spectral clustering with computational complexity O(n³) into the singular value decomposition (SVD) with O(nc²) time cost, where n and c, respectively, denote the numbers of samples and classes. Thus, the computational efficiency can be improved. Moreover, in order to learn a better clustering model, we set that the constructed similarity graph approximates each view affinity graph as close as possible by adding the constraint as the initial affinity matrices own. Furthermore, substantial experiments are conducted, which verifies the superiority of the proposed two clustering methods comparing with single-view clustering approaches and state-of-the-art multi-view clustering methods.

Searchable encryption (SE) is a powerful technology that enables keyword-based search over encrypted data becomes possible. However, most SE schemes focus on exact keyword search which can not tolerate misspellings and typos. Existing fuzzy keyword search schemes only support fuzzy search within a limited similarity threshold d, the storage cost will grow exponentially or the precision of search results will greatly decrease as $d$ increases. Moreover, the current fuzzy keyword ranked search schemes consider only the keyword weight, and disregard the influence of keyword morphology similarity on the ranking. In this paper, we propose a scalable fuzzy keyword ranked search scheme over encrypted data under hybrid clouds architecture. We use the edit distance to measure the similarity of keywords and design an edit distance algorithm over the encrypted database, in which our scheme achieves fuzzy keyword search for any similarity threshold d with constant storage size and accurate search results. Furthermore, we design a two-factor ranking function combining keyword weight with keyword morphology similarity, which is utilized to rank the search results and enhance system usability. Extensive experiments are performed to demonstrate the trade-off of efficiency and security of the proposed scheme.

Searching similarity between a pair of shapes or data is an important problem in data analysis and visualization. The problem of computing similarity measures using scalar topology has been studied extensively and proven useful in the shape and data matching. Even though multi-field or multivariate (consists of multiple scalar fields) topology reveals richer topological features, research on building tools for computing similarity measures using multi-field topology is still in its infancy. In the current article, we propose a novel similarity measure between two piecewise-linear multi-fields based on their multi-resolution Reeb spaces - a newly developed data-structure that captures the topology of a multi-field. Overall, our method consists of two steps: (i) building a multi-resolution Reeb space corresponding to each of the multi-fields and (ii) proposing a similarity measure between two multi-resolution Reeb spaces by computing a list of topologically consistent matching pairs (of nodes) and the similarity between them. We demonstrate the effectiveness of the proposed similarity measure in detecting topological features from real time-varying multi-field data in two application domains - one from computational physics and one from computational chemistry.

In product development (PD) organizations, coordinating technical dependencies among teams with different expertise in overlapping processes is a fundamental challenge. This article takes a more sophisticated approach than prior methodologies to improve coordination via organizational clustering, by accounting for both team structural and attribute similarity from the perspective of social network analysis. We built models to quantify the impact of the overlapping processes on the interaction strength among PD teams, which we then used to construct structural similarity by combining tie strength and social cohesion among teams via the design structure matrix. To evaluate the organization network, we propose social embeddedness-related centrality indices within (intracluster) and across (intercluster) team groupings. To facilitate knowledge sharing, we base team attribute similarity on product- and process-related expertise among teams. We integrate the modularity index and an improved silhouette index to find an optimal number of clusters, which we then incorporate with team similarity measures as inputs to a spectral clustering algorithm. An industrial example illustrates the proposed model. The clustering results reinforce several managerial practices but also yield new insights, such as how to measure similarity among teams based on organizational network characteristics and how structural and attribute similarities impact the optimal organizational structure.

The evolution of online social networks is highly dependent on the recommended links. Most of the existing works focus on predicting intra-community links efficiently. However, it is equally important to predict inter-community links with high accuracy for diversifying a network. In this work, we propose a link prediction method, called HM-EIICT, that considers both the similarity of nodes and their community information to predict both kinds of links, intra-community links as well as inter-community links, with higher accuracy. The proposed framework is built on the concept that the connection likelihood between two given nodes differs for inter-community and intra-community node-pairs. The performance of the proposed methods is evaluated using link prediction accuracy and network modularity reduction. The results are studied on real-world networks and show the effectiveness of the proposed method as compared to the baselines. The experiments suggest that the inter-community links can be predicted with a higher accuracy using community information extracted from the network topology, and the proposed framework outperforms several measures especially proposed for community-based link prediction. The paper is concluded with open research directions.

Measuring business process similarity plays an important role in the analysis, management and optimization of business in big companies. In the early days, experts paid major attention to calculating business similarity according to corresponding process models. However, models only express ideal behavior of business processes without any undesired or unexpected business routines. In order to fully model business behavior, some researchers use system logs in similarity measuring. But previous system-logs-based similarity measurements have limitations on: (1) satisfaction of algorithm properties, (2) distribution of similarity values, and (3) complexity of algorithm. In this paper, we take the advantages of token logs in process behavioral similarity measuring. Firstly, the Token Log Profile, modeled with a relation matrix, is defined as an abstraction of the initial token logs. Then, similarity between business processes is calculated based on their Token Log Profiles according to the proposed algorithm. Besides, we extend the properties that similarity algorithms should satisfy for evaluating the proposed algorithm. The experimental and analytical results show that our algorithm achieves very promising accuracy and efficiency while satisfying all the proposed properties compared with state-of-the-art algorithms.

Collaborative Filtering (CF) filters the flow of data that can be recommended, by a Recommender System (RS), to a target user according to his taste and his preferences. The target user’s profile is built based on his similarity with other users. For this reason, CF technique is very sensitive to the similarity measure used to quantify the dependency strength between two users (or two items). In this paper we provide an in-depth review on similarity measures used for CF-based RS. For each measure, we outline its fundamental background and we test its performance through an experimental study. Experiments are carried out on three standard datasets (MovieLens100k, MovieLens1M and Jester) and reveal many important conclusions. In fact, results show that ITR and IPWR are the most suitable similarity measures for a user-based RS while AMI is the best choice for an item-based RS. Evaluation metrics show that under the user-based approach, ITR obtains an MAE equal to 0.786 and 0.731 on MovieLens100k and MovieLens1M, respectively. Whereas, IPWR reach an MAE equal to 3.256 on Jester. Also, AMI gets under the item-based approach an MAE equal to 0.745, 0.724 and 3.281 on MovieLens100k, MovieLens1M and Jester, respectively.

Clustering graphs is able to provide useful insights into the structure of the data. To improve the quality of clustering, node attributes can be considered, resulting in attributed graphs. Existing attributed graph clustering methods generally consider attribute similarity and structural similarity separately. In this paper, we represent attributed graphs as star-schema heterogeneous graphs, where attributes are modeled as different types of graph nodes. This enables the use of personalized pagerank (PPR) as a unified distance measure that captures both structural and attribute similarities. We employ DBSCAN for clustering, and update edge weights iteratively to balance the importance of different attributes. The rapidly growing volume of data nowadays challenges traditional clustering algorithms, and thus, a distributed method is required. Hence, we adopt a popular distributed graph computing system Blogel, based on which, we develop four exact and approximate approaches that enable efficient PPR score computation when edge weights are updated. To improve the effectiveness of the clustering, we propose a simple yet effective edge weight update strategy based on entropy. Also, we present a game theory based method that enables trading efficiency for result quality. Extensive experiments on real-life datasets demonstrate the effectiveness and efficiency of our proposals. Many datasets including social media data and bibliographic data can be modeled as graphs. Clustering such graphs is able to provide useful insights into the structure of the data. To improve the quality of clustering, node attributes can be taken into account, resulting in attributed graphs. Existing attributed graph clustering methods generally consider attribute similarity and structural similarity separately. In this paper, we represent attributed graphs as star-schema heterogeneous graphs, where attributes are modeled as different types of graph nodes. This enables the use of personalized pagerank (PPR) as a unified distance measure that captures both structural and attribute similarities. We employ DBSCAN for clustering, and we update edge weights iteratively to balance the importance of different attributes. The rapidly growing volume of data nowadays challenges traditional clustering algorithms, and thus, a distributed method is required. Hence, we adopt a popular distributed graph computing system Blogel, based on which, we develop four exact and approximate approaches that enable efficient PPR score computation when edge weights are updated. To improve the effectiveness of the clustering, we propose a simple yet effective edge weight update strategy based on entropy. In addition, we present a game theory based method that enables trading efficiency for result quality. Extensive experiments on real-life datasets offer insights into the effectiveness and efficiency of our proposals.

Multi-view clustering has attracted increasing attention in multimedia, machine learning and data mining communities. As one kind of the essential multi-view clustering algorithm, multi-view subspace clustering (MVSC) becomes more and more popular due to its strong ability to reveal the intrinsic low dimensional clustering structure hidden across views. Despite superior clustering performance in various applications, we observe that existing MVSC methods directly fuse multi-view information in the similarity level by merging noisy affinity matrices; and isolate the processes of affinity learning, multi-view information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing multiple affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful to eliminate noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels matrix are learned simultaneously in a unified framework. By doing so, the three steps can negotiate with each other to best serve the clustering task, leading to improved performance. Accordingly, we propose an iterative algorithm to solve the resulting optimization problem. Extensive experiment results on benchmark datasets demonstrate the superiority of our method against other state-of-the-art approaches.

The rapid growth of information technology and Internet applications has provided users with an explosion of information. Mobile e-commerce applications and web search engines are of great interest in extracting representative information from the original abundant information. However, the information extracted by several existing methods, such as top-k, are often quite similar, which is difficult to meet users’ demand for diversified information. In order to increase the diversity of representative information, this article proposes a data-driven approach to automatically identifying a subset of the original dataset that can cover more themes and content. The data-driven approach consists of two stages. First, a new unified similarity measure is proposed for handling dataset with categorical and numeric attributes. We inject external knowledge and attribute interactions into the similarity learning process to improve the accuracy of similarity estimation between data objects. Second, we develop an enhanced density peaks clustering algorithm based on shared nearest neighbors to automatically identify representative objects according to the previous estimated similarity. The enhanced density peaks algorithm takes the local structure in the entire data space into consideration, which makes the proposed approach relatively insensitive to variations in dataset’ density and dimensionality. Theoretical analysis demonstrates that the time complexity of the proposed approach can achieve the best $\bm {O}({\bm {N}\log \bm {N}})$ . Extensive comparison experiments were conducted on artificial and real-world datasets. The experimental results demonstrate the effectiveness and robustness of the proposed approach.

How variable is the functionally-defined structure of early visual areas in human cortex and how much variability is shared between twins? Here we quantify individual differences in the best understood functionally-defined regions of cortex: V1, V2, V3. The Human Connectome Project 7T Retinotopy Dataset includes retinotopic measurements from 181 subjects, including many twins. We trained four “anatomists” to manually define V1-V3 using retinotopic features. These definitions were more accurate than automated anatomical templates and showed that surface areas for these maps varied more than three-fold across individuals. This three-fold variation was little changed when normalizing visual area size by the surface area of the entire cerebral cortex. In addition to varying in size, we find that visual areas vary in how they sample the visual field. Specifically, the cortical magnification function differed substantially among individuals, with the relative amount of cortex devoted to central vision varying by more than a factor of 2. To complement the variability analysis, we examined the similarity of visual area size and structure across twins. Whereas the twin sample sizes are too small to make precise heritability estimates (50 monozygotic pairs, 34 dizygotic pairs), they nonetheless reveal high correlations, consistent with strong effects of the combination of shared genes and environment on visual area size. Collectively, these results provide the most comprehensive account of individual variability in visual area structure to date, and provide a robust population benchmark against which new individuals and developmental and clinical populations can be compared.Significance StatementAreas V1, V2, and V3 are among the best studied functionally-defined regions in human cortex. Using the largest retinotopy dataset to date, we characterized the variability of these regions across individuals and the similarity between twin pairs. We find that the size of visual areas varies dramatically (up to 3.5x) across healthy young adults, far more than the variability of the cerebral cortex size as a whole. Much of this variability appears to arise from inherited factors, as we find very high correlations in visual area size between monozygotic twin-pairs, and lower but still substantial correlations between dizygotic twin pairs. These results provide the most comprehensive assessment of how functionally defined visual cortex varies across the population to date.

Pythagorean fuzzy set (PFS) is a broadening of intuitionistic fuzzy set that can represent the situations where the sum of membership and the non-membership values exceeds one. Adding parameterization to PFS we obtain a structure named as Pythagorean fuzzy soft set (PFSS). It has a higher capacity to deal with vagueness as it captures both the structures of a PFS and a soft set. Several practical situations demand the measure of similarity between two structures, whose sum of membership value and non-membership value exceeds one. There are no existing tools to measure the similarity between PFSS and this paper put forward similarity measures for PFSS. An axiomatic definition for similarity measure is proposed for PFSS and certain expressions for similarity measure are introduced. Further, some theorems which express the properties of similarity measures are proved. A comparative study between proposed expressions for similarity measure is carried out. Also, a clustering algorithm based on PFSS is introduced by utilizing the proposed similarity measure.

We provide the first behavioral characterization of nested logit, a foundational and widely applied discrete choice model, through the introduction of a non-parametric version of nested logit that we call Nested Stochastic Choice (NSC). NSC is characterized by a single axiom that weakens Independence of Irrelevant Alternatives based on revealed similarity to allow for the similarity effect. Nested logit is characterized by an additional menu-independence axiom. Our axiomatic characterization leads to a practical, data-driven algorithm that identifies the true nest structure from choice data. We also discuss limitations of generalizing nested logit by studying the testable implications of cross-nested logit.

The advance of smart eHealthcare has greatly enabled patients to enjoy high-quality healthcare services, e.g., disease prediction. Meanwhile, to support the dramatic increase of healthcare data, healthcare centers often outsource the on-premises data to the cloud. However, since the healthcare data contain some sensitive information and the cloud server is not fully trusted, healthcare centers need to encrypt the data before outsourcing them. Unfortunately, data encryption inevitably hinders some advanced data applications like the similarity range query. Although many studies on similarity range queries over encrypted data have been reported, most of them still have some limitations in security, efficiency, accuracy, and practicality. Aiming at this challenge, in this paper, we propose an efficient, privacy-preserving, and practical similarity range query (EPSim) scheme. Specifically, we first present a modified asymmetric scalar-product-preserving encryption (ASPE) scheme and prove its security. Then, we introduce a Quadsector tree to represent the data and employ a filtration condition to design an algorithm for efficient similarity range queries over the Quadsector tree. Finally, we propose our EPSim scheme by integrating the modified ASPE scheme and Quadsector tree. Detailed security analysis and performance evaluations indicate our scheme is really secure and efficient in similarity range queries.

Event sequences are central to the analysis of data in domains that range from biology and health, to logfile analysis and people's everyday behavior. Many visualization tools have been created for such data, but people are error-prone when asked to judge the similarity of event sequences with basic presentation methods. This article describes an experiment that investigates whether local and global alignment techniques improve people's performance when judging sequence similarity. Participants were divided into three groups (basic versus local versus global alignment), and each participant judged the similarity of 180 sets of pseudo-randomly generated sequences. Each set comprised a target, a correct choice and a wrong choice. After training, the global alignment group was more accurate than the local alignment group (98 versus 93 percent correct), with the basic group getting 95 percent correct. Participants' response times were primarily affected by the number of event types, the similarity of sequences (measured by the Levenshtein distance) and the edit types (nine combinations of deletion, insertion and substitution). In summary, global alignment is superior and people's performance could be further improved by choosing alignment parameters that explicitly penalize sequence mismatches.

To address the problems in the existing video super-resolution methods, such as noise, over smooth and visual artifacts, which are caused by reliance on limited external training or mismatch of internal similarity instances, this study proposes a video super-resolution reconstruction algorithm based on deep learning and spatio-temporal feature similarity (DLSS-VSR). The video super-resolution reconstruction mechanism with joint internal and external constraints is established utilizing both external deep correlation mapping learning and internal spatio-temporal nonlocal self-similarity prior constraint. A deep learning model based on deep convolutional neural network is constructed to learn the nonlinear correlation mapping between low-resolution and high-resolution video frame patches. A spatio-temporal feature similarity calculation method is proposed, which considers both internal video spatio-temporal self-similarity and external clean nonlocal similarity. For the internal spatio-temporal feature self-similarity, we improve the accuracy and robustness of similarity matching by proposing a similarity measure strategy based on spatio-temporal moment feature similarity and structural similarity. The external nonlocal similarity prior constraint is learned by patch group-based Gaussian mixture model. The time efficiency for spatio-temporal similarity matching is further improved based on saliency detection and region correlation judgment strategy. Experimental results demonstrate that the DLSS-VSR achieves competitive super-resolution quality compared to other state-of-the-art algorithms.

The important role of microRNA (miRNA) in human diseases has been confirmed by some studies. However, only using biological experiments has greater blindness, leading to higher experimental costs. In this paper a high-efficiency algorithm based on a variety of biological source information and applying a combination of a convolutional neural network (CNN) feature extractor and an extreme learning machine (ELM) classifier is proposed. Specifically, the semantic similarity of diseases, the gaussian interaction profile kernel similarity of the four biological information of miRNA, disease, long non-coding RNA (lncRNA) and environmental factors (EFs), and the similarities of miRNAs are fused together. Among them, miRNAs similarity is composed of miRNA target information, sequence information, family information, and function information. Then, the dimensionality of the data set is reduced by the autoencoder (AE). Finally, deep features are extracted through CNN, and then the association between miRNA and disease is predicted by ELM. The experimental results show that the average AUC value based on the multi-biological source information (MSCNE) model is 0.9630, which can reach higher performance than the other classic classifier, feature extractor mentioned and the other existing algorithms. The results show the MSCNE algorithm is effective to predict the correlation of miRNA-disease.

Heterogeneous bounded confidence opinion dynamics with an adaptation policy of the agents' confidence thresholds is considered. The strategy implemented by each agent consists of increasing his confidence thresholds when he has no active neighbor, thus strengthening his heterophilous propensity. Moreover, his adaptation algorithm is stopped if there is a minimal number of agents within his similarity interval. The heterogeneity of the model could lead to interesting scenarios, e.g. steady-state oscillatory behaviors and practical clustering. Sufficient conditions for reaching in finite time a practical consensus are proposed. An upper bound on the maximum number of steady-state practical clusters which depends on the parameters of the confidence thresholds adaptation algorithm is obtained. The steady-state behaviors in the presence of one-sided confidence thresholds and stubbornness are discussed. Numerical simulations verify the theoretical results.

Summary Clinical trials often aim to compare two groups of patients for efficacy and/or toxicity depending on covariates such as dose. Examples include the comparison of populations from different geographic regions or age classes or, alternatively, of different treatment groups. Similarity of these groups can be claimed if the difference in average outcome is below a certain margin over the entire covariate range. In this article, we consider the problem of testing for similarity in the case that efficacy and toxicity are measured as binary outcome variables. We develop a new test for the assessment of similarity of two groups for a single binary endpoint. Our approach is based on estimating the maximal deviation between the curves describing the responses of the two groups, followed by a parametric bootstrap test. Further, using a two-dimensional Gumbel-type model we develop methodology to establish similarity for (correlated) binary efficacy–toxicity outcomes. We investigate the operating characteristics of the proposed methodology by means of a simulation study and present a case study as an illustration.

The successful applications of deep transfer learning to intelligent fault diagnosis testify to a positive correlation between transferable feature similarity and knowledge transferability across diagnostic tasks. This correlation makes feature similarity possible to assess diagnostic knowledge transferability. Therefore, researchers have attempted various measures for feature similarity, and distance metrics have been adopted as an objective measure for feature distribution discrepancy. However, the commonly used distance metrics cannot address the joint distribution discrepancy (JDD) due to the difficulty in fitting conditional distributions of target-domain samples. To overcome the problem, we resort to explore cluster-conditional distributions instead and propose an optimal transport-embedded joint distribution similarity measure (OT-JDSM) that is implemented in two steps. First, a cluster-true label propagation spreads labels from a small number of labelled target domain samples to the whole. Second, the JDD of transferable features is produced via an efficient solution of optimal transport. OT-JDSM is demonstrated on synthetic examples and 144 transfer diagnosis tasks that are created by public and private bearing datasets. The results show that OT-JDSM of transferable features has a stronger correlation with diagnostic knowledge transferability than other distance metrics. Moreover, the OT-JDSM gain can quantify the transfer performance of diagnostic models on tasks.

Fuzzy clustering is one of the most popular clustering approaches and has attracted considerable attention in many fields. However, high computational cost has become a bottleneck which limits its applications in large-scale problems. Moreover, most fuzzy clustering algorithms are sensitive to noise. To address these issues, a novel fuzzy clustering algorithm, called Fast Fuzzy Clustering based on Anchor Graph (FFCAG), is proposed. The FFCAG algorithm integrates anchor-based similarity graph construction and membership matrix learning into a unified framework, such that the prior knowledge of anchors can be further utilized to improve clustering performance. Specifically, FFCAG first constructs an anchor-based similarity graph with a parameter-free neighbor assignment strategy. Then it designs a quadratic programming model to learn the membership matrix of anchors, which is very different from traditional fuzzy clustering algorithms. More importantly, a novel balanced regularization term is introduced into the objective function to produce more accurate clustering results. Finally, we adopt an alternating optimization algorithm with guaranteed convergence to solve the proposed method. Experimental results performed on synthetic and real-world datasets demonstrate the proposed FFCAG can significantly reduce the computational time with comparable even superior clustering performance, compared with state-of-the-art algorithms.

Similarity query over time series data plays a significant role in various applications. Meanwhile, driven by the reliable and flexible cloud services, encrypted time series data are often outsourced to the cloud, so the similarity query over encrypted time series data has recently attracted considerable attention. Nevertheless, existing solutions still have issues in supporting similarity queries over time series data with different lengths, query accuracy and query efficiency. To address these issues, in this paper, we propose an efficient and privacy-preserving similarity range query scheme, where the time warp edit distance (TWED) is used as the similarity metric. Specifically, we first organize time series data into a kd-tree by leveraging TWED's triangle inequality and design an efficient similarity range query algorithm for the kd-tree. Second, based on a symmetric homomorphic encryption technique, we devise a suite of privacy-preserving protocols to provide a security guarantee for kd-tree based similarity range queries. After that, by using the similarity range query algorithm and these protocols, we propose our similarity query scheme, in which we elaborate two strategies to make our scheme resist the cloud inference attack. Finally, the security analysis and performance evaluation demonstrate that our scheme is indeed privacy-preserving and efficient.

This paper show how the novelty search (NS) algorithm can be used for similarity-based software product line testing

Online social networks have gained tremendous popularity and have dramatically changed the way we communicate in recent years. However, the publishing of social network data raises more and more privacy concerns. To protect user privacy, social networking data are usually anonymized before being released. Nevertheless, existing anonymization techniques do not have sufficient protection effects. A large number of deanonymization attacks have arisen, and they mainly make use of either network topology or node attribute information to successfully reidentify anonymized users. In this article, we model a social network as a structure-attribute network (SAN) integrating the structural characteristics and the attribute information associated with social network users. A novel similarity measurement of social network nodes is proposed by considering the structural similarity and attribute similarity. A two-phase scheme is then designed to perform deanonymization by first dividing a social network (graph) into smaller subgraphs based on spectral graph partitioning and then applying the proposed deanonymization algorithm on each matched subgraph pair. We simulate the deanonymization attack with extensive experiments on three real-world datasets, and the experimental results demonstrate that our approach can improve the accuracy and time complexity of deanonymization compared with the state of the art.

Complex networks in real world are always in the state of evolution and composed of numerous overlapping communities. The discovery of overlapping communities in dynamic networks plays an important role in community detection research. In recent years, methods based on incremental clustering have become increasingly popular owing to their high efficiency. However, few of them can deal with communities that are both overlapping and dynamic. In this article, we propose an incremental clustering algorithm for discovering overlapping communities in dynamic networks. In the initial snapshot of a dynamic network, a degree-based seed selection strategy with concise and effective rules is employed to obtain stable and high-quality overlapping communities, in which the degree of nodes is the number of their neighboring nodes in the subgraph composed of free nodes. In the subsequent snapshots, a four-staged framework based on cascade information diffusion is proposed to update the communities incrementally. In this framework, a cascade information diffusion model is used to simulate the evolution of communities and then the fitness of nodes to the communities they belong to is updated based on node similarity. Experiments conducted on both real-world and artificial datasets show that the proposed algorithm can discover overlapping communities in dynamic networks effectively and outperform to the state-of-art baseline algorithms.

We investigate whether spurious pairs created by multiple hypothesis testing can be minimized when firm characteristics are used to identify pairs. The results show that the portfolios of pairs that have higher fundamental similarity outperform those that are fundamentally less similar by minimizing the non-convergence risk. The cost of trading spurious pairs is significant despite the empirical results that the profitability of pairs trading has continued to decline since 2003 and is not significant any more. Accounting information plays a crucial role in identifying pairs rather than market trading data, and the importance of firm fundamentals in pairs trading increases during market crises.

The person re-identification (ReID) method in a single-domain achieves appealing performance, but its reliance on label information greatly limits its extensibility. Therefore, the unsupervised cross-domain ReID method has received extensive attention. Its purpose is to optimize the model by using the labelled source domain and the unlabelled target domain and finally make the model well generalized in the target domain. We propose an unsupervised cross-domain ReID method based on median stable clustering (MSC) and global distance classification (GDC). Specifically, the measurement method used by MSC comprehensively considers the similarity between clusters, the number of samples in a cluster, and the combined similarity within a cluster. Different from the method based on triple loss, GDC can separate the distance distribution of positive and negative sample pairs in a global scope. In addition, considering that model performance is very sensitive to probability parameters when source domain memory is reconsolidated, we designed a dynamic memory reconsolidation (DMR) method to reduce the influence of parameters on performance. Extensive experiments on large-scale datasets (Market-1501, DukeMTMC-reID and MSMT17) demonstrate the superior performance of MSC-GDC over the state-of-the-art methods.

The performance of most the clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix. However, the pairwise similarity is notoriously known for its vulnerability of noise contamination or the imbalance in samples or features, and thus hinders accurate clustering. To tackle this issue, we propose to use information among samples to boost the clustering performance. We proved that a simplified similarity for pairs, denoted by a fourth order tensor, equals to the Kronecker product of pairwise similarity matrices under decomposable assumption, or provide complementary information for which the pairwise similarity missed under indecomposable assumption. Then a high order similarity matrix is obtained from the tensor similarity via eigenvalue decomposition. The high order similarity capturing spatial information serves as a robust complement for the pairwise similarity. It is further integrated with the popular pairwise similarity, named by IPS2, to boost the clustering performance. Extensive experiments demonstrated that the proposed IPS2 significantly outperformed previous similarity-based methods on real-world datasets and it was capable of handling the clustering task over under-sampled and noisy datasets., 10 pages, 7 figures, 2 tables, 4 pages supplementary information appendix

Medical time series of laboratory tests has been collected in electronic health records (EHRs) in many countries. Machine-learning algorithms have been proposed to analyze the condition of patients using these medical records. However, medical time series may be recorded using different laboratory parameters in different datasets. This results in the failure of applying a pretrained model on a test dataset containing a time series of different laboratory parameters. This article proposes to solve this problem with an unsupervised time-series adaptation method that generates time series across laboratory parameters. Specifically, a medical time-series generation network with similarity distillation is developed to reduce the domain gap caused by the difference in laboratory parameters. The relations of different laboratory parameters are analyzed, and the similarity information is distilled to guide the generation of target-domain specific laboratory parameters. To further improve the performance in cross-domain medical applications, a missingness-aware feature extraction network is proposed, where the missingness patterns reflect the health conditions and, thus, serve as auxiliary features for medical analysis. In addition, we also introduce domain-adversarial networks in both feature level and time-series level to enhance the adaptation across domains. Experimental results show that the proposed method achieves good performance on both private and publicly available medical datasets. Ablation studies and distribution visualization are provided to further analyze the properties of the proposed method.

Theory predicts that horizontal acquisitions can effectively increase incumbent firms’ market power in concentrated industries with high product similarity. Using a novel measure for industry product similarity, we show that in such industries firms’ propensity to make horizontal acquisitions is greater and that the acquisitions result in more positive announcement returns for the acquirer and rival firms and in a larger premium paid for the target. Also, the deals harm dependent customer and supplier firms and they are more likely to be challenged by antitrust authorities. Overall, by emphasizing the importance of product similarity, our results help explain mixed empirical findings on whether horizontal acquisitions are used to reduce competition intensity.

Typical aging is associated with increases in false memory rates among older adults. Such errors are frequently associated with differential neural activity during encoding and retrieval in older compared to younger adults within visual cortices, hippocampus, and front-parietal regions. It remains unknown how pattern similarity reductions relate to false memories in healthy aging. Using encoding-retrieval similarity (ERS) analyses in a sample of younger and older adults, we examined how the similarity of neural patterns between memory phases associated with target and lure objects was impacted by age and contributed to false memory rates. Single-item ERS for targets and lures was reduced by age throughout much of the ventral visual stream and the posterior hippocampus. Furthermore, ERS associated with perceptual lures within the visual stream maintained differential relationships with false memory. Finally, a global ERS metric accounted for age deficits in single-item ERS, but did not contribute to false memory rates. These findings highlight the contribution of age-related reductions in ERS across multiple representational levels to false memories in healthy aging.

Similarity measures have been widely used in applications dealing with reasoning, classification and information retrieval. In this paper, we first propose three new Interval Type-2 Fuzzy Similarity measures (IT-2 FSMs) as a dual concept of some semi-metric distances between Intuitionistic Fuzzy Sets (IFSs). We also prove that the extended IT-2 FSMs satisfy many common properties (i.e. reflexivity, transivity, symmetry and overlapping). Experiments are carried out on a variety of datasets including UCI Learning Machine and real data. Comparative studies between the proposed IT-2 FSMs and the other well-known existing similarity measures (Gorzalczany, Bustince, Mitchell, Zeng and Li as well as VSM and Jaccard) are performed. Obviously, the best results are obtained with the IT-2 FSMs being resilient to the high levels of uncertainty noise. We also prove that our IT-2 FSMs can overcome the drawbacks of some existing similarity measures based on the accuracy rate measure. In addition, the proposed IT-2 FSMs are joined with Fuzzy cmeans algorithm as a clustering method and the proposed system is compared against the existing clustering algorithms (Type- 1 Fuzzy k-means, Type-1 and Type-2 Fuzzy c-means, Cluster Forest, Bagged Clustering, Evidence Accumulation and Random Projection). Relying on the clustering quality parameters R and C (equivalent to the standard classification accuracy), the advanced IT-2FSMs show higher classification accuracy of about 86% which outperforms nearly the other classifiers.

Pattern separation and pattern completion are generally studied in humans using mnemonic discrimination tasks such as the Mnemonic Similarity Task (MST) where participants identify similar lures and repeated items from a series of images. Failures to correctly discriminate lures are thought to reflect a failure of pattern separation and a propensity toward pattern completion. Recent research has challenged this perspective, suggesting that poor encoding rather than pattern completion accounts for the occurrence of false alarm responses to similar lures. In two experiments, participants completed a continuous recognition task version of the MST while eye movement (Experiments 1 and 2) and fMRI data (Experiment 2) were collected. In Experiment 1, we replicated the result that fixation counts at study predicted accuracy on lure trials (consistent with poor encoding predicting mnemonic discrimination performance), but this effect was not observed in our fMRI task. In both experiments we found that target-lure similarity was a strong predictor of accuracy on lure trials. Further, we found that fMRI activation changes in the hippocampus were significantly correlated with the number of fixations at study for correct but not incorrect mnemonic discrimination judgments when controlling for target-lure similarity. Our findings indicate that while eye movements during encoding predict subsequent hippocampal activation changes for correct mnemonic discriminations, the predictive power of eye movements for activation changes for incorrect mnemonic discrimination trials was modest at best.

Real-life systems involving interacting objects are typically modeled as graphs and can often grow very large in size. Revealing the community structure of such systems is crucial in helping us better understand their complex nature. A critical relevant challenge is the discovery of the overlapping communities of a given node in a billion-node graph. In this work, we propose a scalable local community detection approach to efficiently unfold the communities of individual target nodes. Our goal is to reveal the clusters formed around nodes by leveraging the relations within all different contexts these nodes participate in. To this end, we consider the similarity of pairs of links in the graph as well as the extent of their participation in multiple contexts. Then, we determine the order in which we should group the pairs of links so that we form meaningful hierarchical communities. We are not affected by constraints existing in previous techniques such as the need for several seed nodes. Our experimental evaluation on large real-world networks shows that we significantly outperform state-of-the-art methods on both accuracy and efficiency. Moreover, we show that we uncover very effectively the hierarchical structure of overlapping communities by producing detailed dendrograms.

Business process similarity measures are of vital importance for process repository management applications, such as process query, process recommendation, and process clustering. Most existing approaches measure process similarity by relying on control-flow structures only. This article investigates the role of data in process similarity measure. To incorporate data-flow information into business process control flow, it proposes a data-aware workflow net (DWF-net) by extending the classical workflow net with data reading and writing semantics. Then, we introduce three types of similarity measures, i.e., data item set-based similarity, data operation set-based similarity, and data-aware behavior-based similarity, to quantify the similarity of data-aware business processes from different perspectives. Next, a methodology is introduced to help process analysts apply these three measures in a systematical way. Finally, we evaluate the effectiveness and applicability of the proposed similarity measures by a group of comparative experiments.

In this paper, we propose a new semi-supervised graph construction method, which is capable of adaptively learning the similarity relationship between data samples by fully exploiting the potential of pairwise constraints, a kind of weakly supervisory information. Specifically, to adaptively learn the similarity relationship, we linearly approximate each sample with others under the regularization of the low-rankness of the matrix formed by the approximation coefficient vectors of all the samples. In the meanwhile, by taking advantage of the underlying local geometric structure of data samples that is empirically obtained, we enhance the dissimilarity information of the available pairwise constraints via propagation. We seamlessly combine the two adversarial learning processes to achieve mutual guidance. We cast our method as a constrained optimization problem and provide an efficient alternating iterative algorithm to solve it. Experimental results on five commonly-used benchmark datasets demonstrate that our method produces much higher classification accuracy than state-of-the-art methods, while running faster.

Federated Learning (FL) is a distributed machine learning approach in which clients contribute to learning a global model in a privacy preserved manner. Effective aggregation of client models is essential to create a generalised global model. To what extent a client is generalisable and contributing to this aggregation can be ascertained by analysing inter-client relationships. We use similarity between clients to model such relationships. We explore how similarity knowledge can be inferred from comparing client gradients, instead of inferring similarity on the basis of client data which violates the privacy-preserving constraint in FL. The similarity-guided FedSim algorithm, introduced in this paper, decomposes FL aggregation into local and global steps. Clients with similar gradients are clustered to provide local aggregations, which thereafter can be globally aggregated to ensure better coverage whilst reducing variance. Our comparative study also investigates the applicability of FedSim in both real-world datasets and on synthetic datasets where statistical heterogeneity can be controlled and studied systematically. A comparative study of FedSim with state-of-the-art FL baselines, FedAvg and FedProx, clearly shows significant performance gains. Our findings confirm that by exploiting latent inter-client similarities, FedSim’s performance is significantly better and more stable compared to both these baselines.

Trajectory similarity computation is a fundamental problem for many intelligent applications such as trip trajectory mining to find the most popular routes and road anomaly detection. Existing similarity computation methods for vehicle trajectory, such as Dynamic Time Wrapping(DTW) and Frechet distance, are dynamic programming problems with a quadratic time complexity in all cases and need to handle local time shifts when computing the distance between trajectories, thus limiting the scalability of these methods. In addition, GPS-based vehicle trajectories usually contain errors such as noise and outliers due to poor satellite visibility in urban regions and non-uniform sampling rates. To this end, we propose an embedding-based method for trajectory similarity computation with linear time complexity, which encodes a trajectory as a vector via deep representation learning and learns the similarity between trajectories with an attention-based learning to rank model. We use an interpolation-based approach to reduce noise and outliers by considering vehicle trajectory is physically constrained to the road network. Experiments on a massive vehicle trajectory dataset show that the proposed approach outperforms state-of-the-art baselines consistently and significantly.

Background: Manual segment target volumes were time-consuming and inter-observer variability couldn’t be avoided. With the development of computer science, auto-segmentation had the potential to solve this problem. Objective: To evaluate the accuracy and stability of Atlas-based and deep-learning-based auto-segmentation of the intermediate risk clinical target volume, composed of CTV2 and CTVnd, for nasopharyngeal carcinoma quantitatively. Methods and Materials: A cascade-deep-residual neural network was constructed to automatically segment CTV2 and CTVnd by deep learning method. Meanwhile, a commercially available software was used to automatically segment the same regions by Atlas-based method. The datasets included contrast computed tomography scans from 102 patients. For each patient, the two regions were manually delineated by one experienced physician. The similarity between the two auto-segmentation methods was quantitatively evaluated by Dice similarity coefficient, the 95th Hausdorff distance, volume overlap error and relative volume difference, respectively. Statistical analyses were performed using the ranked Wilcoxon test. Results: The average Dice similarity coefficient (±standard deviation) given by the deep-learning- based and Atlas-based auto-segmentation were 0.84(±0.03) and 0.74(±0.04) for CTV2, 0.79(±0.02) and 0.68(±0.03) for CTVnd, respectively. For the 95th Hausdorff distance, the corresponding values were 6.30±3.55 mm and 9.34±3.39 mm for CTV2, 7.09±2.27 mm and 14.33±3.98 mm for CTVnd. Besides, volume overlap error and relative volume difference could also predict the same situations. Statistical analyses showed significant difference between the two auto-segmentation methods (p Conclusions: Compared with the Atlas-based segmentation approach, the deep-learning-based segmentation method performed better both in accuracy and stability for meaningful anatomical areas other than organs at risk.

In computer-based search systems, similarity plays a key role in replicating the human search process. Indeed, the human search process underlies many natural abilities such as image recovery, language comprehension, decision making, or pattern recognition. The search for images consists of establishing a correspondence between the available image and that sought by the user, by measuring the similarity between the images. Image search by content is generaly based on the similarity of the visual characteristics of the images. The distance function used to evaluate the similarity between images depends notonly on the criteria of the search but also on the representation of the characteristics of the image. This is the main idea of a content-based image retrieval (CBIR) system. In this article, first, we constructed type-2 beta fuzzy membership of descriptor vectors to help manage inaccuracy and uncertainty of characteristics extracted the feature of images. Subsequently, the retrieved images are ranked according to the novel similarity measure, noted type-2 fuzzy nearness measure (IT2FNM). By analogy to Type-2 Fuzzy Logic and motivated by near sets theory, we advanced a new fuzzy similarity measure (FSM) noted interval type-2 fuzzy nearness measure (IT-2 FNM). Then, we proposed three new IT-2 FSMs and we have provided mathematical justification to demonstrate that the proposed FSMs satisfy proximity properties (i.e. reflexivity, transitivity, symmetry, and overlapping). Experimental results generated using three image databases showing consistent and significant results.

Set similarity search, aiming to search the similar sets to a query set, has wide application in today's recommendation services. Meanwhile, the rapid advance in cloud technique has promoted the boom of data outsourcing. However, since the cloud is not fully trustable and the data may be sensitive, data should be encrypted before outsourced to the cloud. Undoubtedly, data encryption will hinder some basic functionalities, e.g., set similarity search. For achieving set similarity search over encrypted data, many solutions were proposed, yet they either only satisfy weak security requirements, or only achieve approximate similarity, or have low efficiency. Therefore, in this paper, we propose a new efficient and privacy-preserving exact set similarity search scheme. Specifically, we first design a symmetric-key predicate encryption (SPE-Sim) scheme, which can support similarity search over binary vectors. Then, we represent the set records to be binary vectors and employ the B+ tree to build an index for them. After that, based on SPE-Sim and the B+ tree based index, we propose our scheme and it can achieve efficient set similarity search while preserving the privacy of set records and query contents. Finally, security analysis and performance evaluation indicate that our scheme is privacy-preserving and efficient.

Image denoising is a vital pre-processing phase, used to refine the image quality and make it more informative. Many image-denoising algorithms have been proposed with their own pros and cons. This paper presents a comprehensive study of the median filter and its different variants to reduce or remove the impulse noise from gray scale images. These filters are compared with respect to their functionality, time complexity and relative performance. For performance evaluation of the existing algorithms, extensive MATLAB based simulations have been carried out on a set of images. For benchmarking the relative performance, we have used Peak Signal to Noise Ratio (PSNR), Root Mean Square Error (RMSE), Universal Image Quality Index (UQI), Structural Similarity Index (SSIM) and Edge-strength Similarity (ESSIM) as quality assessment metrics. The Extended median filter (EMF) and Modified BDND are best in terms of relative statistical ratios and pleasant visual results where IAMF is having the best time complexity among existing algorithms.

Numerous microbes inhabit human body, making a vast difference in human health and disease. Therefore, understanding associations between microbes and diseases is beneficial to disease prevention and treatment. In this study, we develop a prediction method called HNGFL by Learning global graph feature on the heterogeneous network. Firstly, a heterogeneous network is integrated by known microbe-disease associations and multiple similarities. For microbe similarity network, on the basis of Gaussian interaction profile (GIP) kernel similarity, we consider different effects of these microbes on organs in the human body to further improve microbe similarity. For disease similarity network, we combine GIP kernel similarity, disease semantic similarity and disease-symptom similarity. And then, we use an embedding algorithm called GraRep to learn global structural information for this network. According to vector feature of every node, we utilize Support Vector Machine (SVM) classifier to calculate the relevance for each microbe-disease pair. HNGFL achieves a reliable performance in cross validation, outperforming the compared methods. In addition, we carry out case studies of three diseases. Results show that HNGFL can be considered as a reliable method for microbe-disease association prediction.