Search

Exam paper generation is an indispensable part of teaching. Existing methods focus on the use of question extraction algorithms with labels for each question provided. Obviously, manual labeling is inefficient and cannot avoid label bias. Furthermore, the quality of the exam papers generated by the existing methods is not guaranteed. To address these problems, we propose a novel approach to generating exam papers based on prediction of exam performance. As such, we update the quality of the initially generated questions one by using dynamic programming, as well as in batches by using genetic algorithms. We performed the prediction task by using Deep Knowledge Tracing. Our approach considered the skill weight, difficulty, and distribution of exam scores. By comparisons, experimental results indicate that our approach performed better than the two baselines. Furthermore, it can generate exam papers with adaptive difficulties closely to the expected levels, and the related student exam scores will be guaranteed to be relatively reasonable distribution. In addition, our approach was evaluated in a real learning scenarios and shows advantages.

Aiming at the security issues during the multi-types data storage and data transmission in autonomous Internet of Things (IoT) systems, this paper proposes an AI algorithm for data enhanced encryption used in the ends and the intermediate nodes of IoTs. The algorithm in this paper first constructs a three-dimensional Arnold transformation matrix for data unit value encryption in the end of IoTs, and designs a quantum logic intelligent mapping that effectively diffuses the encrypted data units to reduce the linear correlation of the image data and to improve the security performance of IoT edge data. Furthermore, the algorithm designs an AI access strategy for scrambling sequence nodes and builds a random-access route for the elements of the scrambling sequence which can reduce the calculation cost and improve the operating efficiency of IoT system in the ends and intermediate nodes. Finally, the data shared matrix is used to share the encrypted data to achieve the (k, n) threshold strategy. Experimental results prove that the algorithm has high plaintext and key sensitivity and can effectively resist brute force attacks, statistical analysis and differential attacks. The algorithm in this paper provides an AI solution for data security encryption in the ends and the intermediate nodes of autonomous IoT systems.

This paper proposes a new tent-multi dynamic piecewise coupled mapping lattice (TMDPCML). Through the comprehensive analysis of the performance test results, TMDPCML system increases the correlation dynamics of spatiotemporal behavior and improves the efficiency of energy diffusion between lattices. Moreover, TMDPCML system has larger parameter space, better chaos and outstanding cryptographic characteristics. Therefore, this paper proposes a privacy image encryption algorithm combined with TMDPCML system. The application of TMDPCML system in private images encryption further proves that TMDPCML system has good chaotic behavior and meets the requirements of cryptography.

This paper focuses on improving the accuracy of image matching by eliminating the residual mismatches in the matching results of standard RANSAC. Based on pixel shift clustering and RANSAC algorithms, a matching optimization algorithm called pixel shift clustering RANSAC, PSC-RANSAC in short, is proposed in this paper. Firstly, the pixel shift model of space point from two perspectives are established by parallax principle and camera projection model. Then, based on the established pixel shift model, density peaks clustering (DPC) algorithm is used to select the mismatches out to enhance the accuracy of image matching. Meanwhile the comparisons among PSC-RANSAC, standard RANSAC, progressive sample consensus and graph-cut RANSAC show that PSC-RANSAC can more effectively and robustly eliminate the residual mismatches in initial matching results. The proposed method provides an effective tool for optimization on image matching.

Surrogate-assisted evolutionary algorithms (SAEAs), which use efficient surrogate models or meta-models to approximate the fitness function in evolutionary algorithms (EAs), are effective and popular methods for solving computationally expensive optimization problems. During the past decades, a number of SAEAs have been proposed by combining different surrogate models and EAs. This paper dedicates to providing a more systematical review and comprehensive empirical study of surrogate models used in single-objective SAEAs. A new taxonomy of surrogate models in SAEAs for single-objective optimization is introduced in this paper. Surrogate models are classified into two major categories: absolute fitness models, which directly approximate the fitness function values of candidate solutions, and relative fitness models, which estimates the relative rank or preference of candidates rather than their fitness values. Then, the characteristics of different models are analyzed and compared by conducting a series of experiments in terms of time complexity (execution time), model accuracy, parameter influence, and the overall performance when used in EAs. The empirical results are helpful for researchers to select suitable surrogate models when designing SAEAs. Open research questions and future work are discussed at the end of the paper.

One-class classification is a machine learning problem, where training data has only one class. The objective is to determine if the input data is seen class or unseen class. Traditional deep learning algorithms are not suitable for this task since the algorithm can predict only class in training data. In this paper, the one-class classification algorithm using construction error of image transformation network (OCITN) is proposed. In particular, image transformation network (ITN) is introduced as a subtask, which transforms input image into one image, namely goal image. Moreover, the error of ITN, namely construction error (CE), is computed as a distance metric between the goal image and model output. ITN model is trained using only one-class images and is applied for testing images. Since the model is trained with only one-class images, the CE for one-class is small relative to other classes. Thus, one-class classification is made determining CE is large or small. The proposed method is experimented with using MNIST, Fashion MNIST, CIFAR10, CIFAR100, and Cat-vs-Dog datasets. OCITN shows good results where the goal image has high entropy. Additionally, the extension of OCITN, namely OCITNE, is implemented. This method shows the state of the art performance in MNIST (98.0), Fashion MNIST(95.6), and acceptable performance in CIFAR10(78.4). Furthermore, these methods provide high-speed processing, OCITN process 5291 images, and OCITNE 1261 images per second, 137 times and 33 times faster than state of the art. The source code used in this paper can be downloaded from: https://github.com/ToshiHayashi/OCITN .

International audience; Marketing messages are most effective if they reach the right customers. Deciding which customers to contact is an important task in campaign planning. The paper focuses on empirical targeting models. We argue that common practices to develop such models do not account sufficiently for business goals. To remedy this, we propose profit-conscious ensemble selection, a modeling framework that integrates statistical learning principles and business objectives in the form of campaign profit maximization. Studying the interplay between data-driven learning methods and their business value in real-world application contexts, the paper contributes to the emerging field of profit analytics and provides original insights how to implement profit analytics in marketing. The paper also estimates the degree to which profit-concious modeling adds to the bottom line. The results of a comprehensive empirical study confirm the business value of the proposed ensemble learning framework in that it recommends substantially more profitable target groups than several benchmarks.

Experton theory, a generalization of probabilistic set theory, that is of great usefulness to group decision analysis, was first proposed as a means of improving the processing and analysis of opinions issued by experts. This theory produces an information-fusion mathematical object , the experton, which can be used in predictive problems to justify decisions based on well-constructed reasoning. The aim of this paper is to present an aggregative method of several expertons, with the idea that some of the groups of experts involved in producing these expertons may have more influence than others in the decision-making process. In this article, we carry out an aggregation analysis of expertons, not experts, which culminates in the creation of a new mathematical object. This object, which is called the weighted average multiexperton, is coherent with an experton-type object created from a weighting of the initial data provided by all experts. Since the aggregation method presented has been devised to represent the decision-maker’s attitude regarding the importance of different groups of experts, this approach represents a new tool for dealing with group decision-making problems. Additionally, the study presents some properties of the new object. Finally, the paper ends with an application for business decision-making.

Convolutional neural networks (CNN) have been widely used in various tasks, largely due to their ability to efficiently extract n-gram features for text analysis and document representation. In this paper, we intend to insight the CNN model regarding its capability on text analysis. Vanilla CNNs do have weaknesses when it comes to the representation and feature extraction. Duplicate filters are inevitable with vanilla CNNs, which reduces the discriminative power of the representations. In addition, the current pooling operations either limit the CNN to the local optimum (i.e., max pooling) or they do not consider the importance of all features (i.e., mean pooling). In this paper, we propose two modules for vanilla CNNs to overcome these shortcomings. The first equips the CNN with discriminative filters (distinct filters with maximised divergence) and the second provides the ability to comprehensively extract all salient features. Specifically, our model increases the discriminative power of the model by maximizing the distance between different filters, and a novel global pooling mechanism for feature extraction. Validation tests against state-of-the-art baselines on five benchmark classification datasets achieve the competitive performance of our proposed model. Furthermore, visualization on upgrade filters and pooling features verify our hypothesis that the proposed model can receive discriminative filters and salient features.

Proliferation of Industrial Internet has dramatically changed the way we live and work. It brings convenience to our society and sometimes requires real-time processing of dramatic data at the same time. However, traditional paradigm of computing on the center cloud can’t always meet such requirement, for the non-negligible time delay of data transmission and communication. Edge computing is a novel computing paradigm proposed to resolve such a problem. As a promising technology, it extends computing from cloud center to the edge of network. Edge computing has the advantage of low latency to achieve a shorter response time, as well as potential to address the concerns of energy consuming, bandwidth burden and security issue. In this paper, we give a survey about edge computing from the aspect of methodologies, application scenarios and its role in Industrial Internet. Some open issues of edge computing are also introduced in this paper. At the end of the manuscript, a discussion about future direction is proposed. The shallow network algorithms such as broad learning system (BLS), which have achieved great improvement in computing efficiency, show an optimistic outlook in this area. We propose our conceive about future applications when shallow network methods like BLS are applied in edge computing and hope the paper will inspire research in relative directions.

Research shows that deep neural networks are vulnerable to adversarial examples due to the highly linear nature of deep neural networks (DNNs). Therefore, adversarial examples involve security of deep learning. However, there is a lack of research on the impact of adversarial examples on the biomedical segmentation model. Since a large part of medical image problems are segmentation problems, this paper analyzes the impact of adversarial examples on image segmentation models based on deep learning. We propose to fool the biomedical segmentation model and generate target segmentation masks with feature space perturbations and cross-entropy loss function. Different from the traditional gradient-based attack methods, which usually use the gradient of the final loss function, this paper adopts a Multi-scale Attack (MSA) method based on multi-scale gradients. Extensive experiments to attack U-Net on the ISIC skin lesion segmentation challenge dataset and the glaucoma optic disc segmentation dataset have proved that the predicted mask generated by this method has a high intersection over union(IoU) and pixel accuracy with the target mask. Besides, the L 2 and L ∞ distances between the adversarial and clean examples are reduced compared with the state-of-the-art method.

As a new type of network, the types of attack in the Internet of Vehicles (IoV) are constantly emerging and changing. Consequently, the machine learning based intrusion detection model has to update to cope with new attacks. However, existing machine learning based IoV intrusion detection schemes require large amounts of labeled data to complete model updates. For new attacks, the IoV cloud is also difficult to identify in time, which requires a lot of labor and time cost in IoV. To solve above issue, this paper employs transfer learning and proposes two model update schemes based on whether the IoV cloud can timely provide a small amount of labeled data for a new attack. The first one is the cloud-assisted update scheme where the IoV cloud can provide a small amount of data. And the second one is the local update scheme where the IoV cloud cannot provide any labeled data timely. In this paper, the local update scheme obtains pseudo label of the unlabeled data in new attacks via pre-classifies and uses the pseudo-labeled data for multiple rounds of transfer learning. Then the vehicle can complete the update without obtaining any labeled data through the IoV cloud. The experimental results show that compared with the existing method, our two schemes have improved the detection accuracy by at least 23%.

Acute hypotensive episode (AHE) is a common serious postoperative complication in ICU, which may raise multiple system failure (especially of cardiac and respiratory kinds), and even cause death. Timely and effective clinical intervention is obviously vital to the saving of patients. AHE detection involves physiological time-series monitoring, processing and prediction technologies, which can offer insights to neuroscientists, biologists, and even provide support for clinicians. This paper presents a hybrid artificial intelligence model combined with CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise, a typical method for physiological signal decomposition), deep learning, multiple gene expression programming and fuzzy expert system for AHE detection. In this paper, the physiological signal is selected from a benchmark dataset, for example MIMIC-II (Multiparameter Intelligent Monitoring in Intensive Care II), which collects large scale real patients’ data for clinical research. In the hybrid model, a typical signal decomposition method is employed for AHE signal processing, and an autoencoder based deep neural network is established for feature extraction. Finally, a reliable and explainable classifier is presented by fusing gene expression programming and the fuzzy method. Experimental results based on real data set demonstrate that the proposed method outperforms state-of-the-art AHE detection methods by achieving the prediction accuracy of 88.14% in 2866 records.

Multi-label classification is a machine learning task to construct a model for assigning an entity in the dataset to two or more class labels. In order to improve the performance of multi-label classification, a multi-objective feature selection algorithm has been proposed in this paper. Feature selection as a preprocessing task for Multi-label classification problems aims to choose a subset of relevant features. Selecting a small number of high-quality features decreases the computational cost and at the same time maximizes the classification performance. However extreme decreasing the number of features causes the failure of classification. As a result, feature selection has two conflicting objectives, namely, minimizing the classification error and minimizing the number of selected features. This paper proposes a multi-objective optimization algorithm to tackle the multi-label feature selection. The task is to find a set of solutions (a subset of features) in a sophisticated large-scale search space using a reference-based multi-objective optimization method. The proposed algorithm utilizes an opposition-based binary operator to generate more diverse solutions. Injection of extreme point of the Pareto-front is another component of the algorithm which aims to find feature subsets with less classification error. The proposed method is compared with two other existing methods on eight multi-label benchmark datasets. The experimental results show that the proposed method outperforms existing algorithms in terms of various multi-objective evaluation measures, such as Hyper-volume indicator, Pure diversity, Two-set coverage, and Pareto-front proportional contribution. The proposed method leads to get a set of well-distributed trade-off solutions which reach less classification error in comparing with competitors, even with the fewer number of features.

The growing demand of users for video streaming services has brought huge challenges to the streaming media service system. The cooperative edge-cloud computing architecture that combines cloud computing and edge computing can effectively reduce the burden on streaming media service systems. The streaming content caching under the cooperative edge-cloud computing architecture is important to improve the quality of user service. Based on this, this paper proposed a cache strategy based on user mobility and content popularity. In this cache strategy, the Markov model is used to describe the user mobility, the multiple linear regression model is used for content popularity prediction, and the content caching operation is performed according to the user mobility and the content popularity. To reduce the load of edge servers and further improve the quality of user service, this paper proposed a content placement strategy based on marginal gain. In this content placement strategy, a content placement problem is established by considering the content access latency and the content placement cost. Then a content placement algorithm based on marginal gain is proposed to solve the content placement problem. The content placement operation is performed by analyzing the marginal gain brought by placing the contents on edge servers to achieve the optimal performance of content placement. The experimental results show that the proposed strategies can effectively improve the performance in terms of the cache hit ratio, the content access latency, the storage cost and the remote data access cost.

Highlights • The minimum cost consensus model is proposed to coordinate the opinions of experts. • A new method of LSGDM clustering is proposed to improve CRP efficiency. • A consensus index CI reflecting the harmony degree between experts is devised. • A robust counterpart of robust optimization consensus is implemented., Recently, large-scale group decision making (LSGDM) in social network comes into being. In the practical consensus of LSGDM, the unit adjustment cost of experts is difficult to obtain and may be uncertain. Therefore, the purpose of this paper is to propose a consensus model based on robust optimization. This paper focuses on LSGDM, considering the social relationship between experts. In the presented model, an expert clustering method, combining trust degree and relationship strength, is used to classify experts with similar opinions into subgroups. A consensus index, reflecting the harmony degree between experts, is devised to measure the consensus level among experts. Then, a minimum cost model based on robust optimization is proposed to solve the robust optimization consensus problem. Subsequently, a detailed consensus feedback adjustment is presented. Finally, a case study and comparative analysis are provided to verify the validity and advantage of the proposed method.

This paper addresses the access control issue for the comprehensive and distributed Internet of Things (IoT) environments. The typical eXtensible Access Control Markup Language (XACML) which implements the sophisticated access conditions in XML files, is widely used to guarantee access control decisions for the distributed IoT environments. To the best of our knowledge, the typical XACML-based access control schemes never consider the authentication run-time parameters. Moreover, the access control schemes that are mainly based on the typical XACML cannot secure themselves against some kinds of attacks, such as the Masquerade attack. Also, those schemes are not secure in opposition to Man-in-the-Middle (MITM) attack. Therefore, this paper proposes an adaptive XACML scheme that extends the typical XACML by integrating an access code generation and verification schemes for heterogeneous distributed IoT environments. Our adaptive XACML scheme considers some sensitive authentication run-time parameters before authorizing the user. Moreover, our scheme is proven secure against the Masquerade attack and MITM attack through hashing the generated access code using Message Digest Algorithm-5 (MD5) and Secure Hash Algorithm-1 (SHA-1) Checksum Utility. The experimental analysis of many different configurations supports the efficacy and efficiency of our adaptive XACML. It also shows exceptional compatibility and performance with different implementations. The processing time comparison between our adaptive XACML and Typical XACML, has shown that there is a low time overhead when using our adaptive XACML. This processing time overhead is nothing compared to the extra features that have been achieved in excess of the typical XACML and the security against Masquerade and MITM attacks. Therefore, our adaptive XACML scheme has the capability to be applied in various distinct distributed environments not only IoT.

Considering that most popular models solving aspect-level sentiment classification problems mainly focus on designing complicated neural networks to scale the importance of each word in the sentence, this paper addresses this problem from the view of semantic space. Motivated by the fact that the senses of a word can be sophisticatedly embedded into the semantic space using a distributed representation, this paper hypothesizes that each sense of a word can be represented by one or more specific dimensions, and thus the target of aspect-level sentiment classification can be simplified into searching the related dimensions for the aspects and sentiments concerned. Particularly, an Attention Vector (ATV) based on attention mechanism is designed for each aspect in terms of a specific task, which involves two sub-vectors, i.e., a Dimension Attention Vector (DATV) and a Sentiment Attention Vector (SATV). The DATV determines the significances of different dimensions based on their correlations with an aspect; and the SATV allocates weights for the attributes of words, which are decided by sentiment polarities and part-of-speech (PoS) tagging. Given a sub-dataset related to an aspect, the ATV will be optimized by an Artificial Bee Colony (ABC) algorithm with a Support Vector Machine (SVM) classifier, the objective of which is to maximize classification accuracy. Intrinsically, the DATV can reduce the ambiguity existing in polysemy, meanwhile, the SATV is an auxiliary means for the optimization of the DATV, which can help eliminate the misunderstandings caused by antonyms. Then, the optimized DATV will be applied on a Convolutional Neural Network (CNN) model via simply scaling the pretrained word embeddings as inputs (named as ATV-CNN model). Experimental results show that the ATV-CNN model can have substantial advantages when compared with state-of-the-art models.

In this paper, an improved cross coupled map lattice (CCML) which is derived from CCML is proposed. The experimental analysis of CCML shows that it exhibits weak or even lose chaotic behaviors in a large range of parameters. To enhance its chaotic performance, the new model changes the internal chaotic map of CCML from the logistics map to the tent map and introduces the module operations to limit the obtained value. The theoretical analysis and experimental results prove that the proposed model has a broad chaotic regime over an extensive range of system parameters, positive Lyapunov exponents, higher information entropies and lower mutual information values when compared to CCML, which are highly suitable for chaos-based image encryption. Moreover, this paper applies that model on a bit-level image encryption scheme. The algorithm consists of three main operations: the generation of secret keys, confusion and diffusion operations that can break the limitation of row and column. To confirm the novel algorithm's effectiveness and safety against the common types of attacks, many experiments are done and security analyses are discussed. It demonstrates the good chaos of the proposed model from the aspect of encryption performance.

In this paper, a chaotic image encryption algorithm based on the matrix semi-tensor product (STP) with a compound secret key is designed. First, a new scrambling method is designed. The pixels of the initial plaintext image are randomly divided into four blocks. The pixels in each block are then subjected to different numbers of rounds of Arnold transformation, and the four blocks are combined to generate a scrambled image. Then, a compound secret key is designed. A set of pseudosecret keys is given and filtered through a synchronously updating Boolean network to generate the real secret key. This secret key is used as the initial value of the mixed linear-nonlinear coupled map lattice (MLNCML) system to generate a chaotic sequence. Finally, the STP operation is applied to the chaotic sequences and the scrambled image to generate an encrypted image. Compared with other encryption algorithms, the algorithm proposed in this paper is more secure and effective, and it is also suitable for color image encryption.

The Choquet integral model is mainly applied to describe non-additive multi-criteria decision-making (MCDM) problems. This paper considers the Choquet integral as a classifier which deals with complicated high-dimensional data. Although previously conducted studies have investigated the problem of classification using the Choquet integral and provided corresponding models, these models usually need to estimate a large number of fuzzy measure coefficients, which are not suitable when considering real situations. Sugeno et al. proposed the hierarchical Choquet integral (HCI) model to overcome this problem. However, the HCI model requires partition information of the criteria, which often cannot be obtained practically. This paper proposes two HCI models—shallow and deep models—by employing genetic algorithms (GAs) and neural networks (NNs) to automatically construct the structure of the HCI. The results of numerical experiments show that the proposed model outperforms the existing Naive Bayes, decision tree, and NN models.

Bot detection is a fundamental and crucial task for tracing and mitigating cyber threats in the Internet. This paper aims to address two major limitations of current bot detection systems. First, existing flow-based bot detection approaches ignore structural information of botnets, which lead to false detection. Second, they cannot identify the interactive behavioral patterns among heterogeneous botnet objects. In this paper, we propose a novel bot detection framework, namely Bot-AHGCN, which models fine-grained network flow objects (e.g., IP, response) as a multi-attributed heterogeneous graph and transforms bot detection problem into a semi-supervised node classification task on the graph. Particularly, we first build a multi-attributed heterogeneous information network (AHIN) to model the interdependent relationships among botnet objects. Second, we present a weight-learning based node embedding method, which learns the interactive behavioral patterns among bots and integrates them into weighted similarity graphs. Finally, we perform graph convolution on the learned similarity graphs to characterize more comprehensive and discriminative features of bots, and feed them into a forward neural network to identify bots. The overall experimental results on two real-world datasets confirm that Bot-AHGCN outperforms the existing state-of-the-art approaches, and presents better interpretability by introducing meaningful meta-paths and meta-graphs.

User interactions are generally utilized to impose the hard constraint and estimate the label prior probability in the interactive image segmentation methods. The conventional interactive approaches cannot work well when the user inputs contain incorrect marks. The existing error tolerance methods mainly focus on the interaction itself and try to eliminate the influence of incorrect hard constraint, which however ignore the label prior estimation. This paper mainly focuses on solving the label prior estimation problem when error marks appear. The prior probability is generally defined as the matching degree between pixels and the cluster centers of marked pixels. Incorrect interaction leads to the formation of incorrect clusters. Therefore, a reliability learning model is constructed in this paper by 1) assigning smaller weighting factors to incorrect clusters, 2) assigning larger weighting factors to correct clusters with higher matching degree. Accurate label prior probability can be obtained by the weighted averaging. Then referring to the existing methods, an error-tolerant segmentation model is designed as a ratio energy function, which can both overcome the hard constraint and the label prior limitation with error marks. Experiments on the challenging Berkeley segmentation data set and Microsoft GrabCut database demonstrate the effectiveness of the proposed method.

In this paper, we present the problem formulation and methodology framework of Super Resolution Perception (SRP) on smart meter data. With the widespread use of smart meters, a massive amount of electricity consumption data can be obtained. Smart meter data is the basis of automated billing and pricing, appliance identification, demand response, etc. However, the provision of high-quality data may be expensive in many cases. In this paper, we propose a novel problem - the SRP problem as reconstructing high-quality data from unsatisfactory data in smart grids. Advanced generative models are then proposed to solve the problem. This technology makes it possible for empowering existing facilities without upgrading existing meters or deploying additional meters. We first mathematically formulate the SRP problem under the Maximum a Posteriori (MAP) estimation framework. The dataset namely Super Resolution Perception Dataset (SRPD) is designed for this problem and released. A case study is then presented, which performs SRP on smart meter data. A network namely Super Resolution Perception Convolutional Neural Network (SRPCNN) is proposed to generate high-frequency load data from low-frequency data. Experiments demonstrate that our SRP models can reconstruct high-frequency data effectively. Moreover, the reconstructed high-frequency data can lead to better appliance identification results.

Association Rule Mining (ARM) is a significant task for discovering frequent patterns in data mining. It has achieved great success in a plethora of applications such as market basket, computer networks, recommendation systems, and healthcare. In the past few years, evolutionary computation-based ARM has emerged as one of the most popular research areas for addressing the high computation time of traditional ARM. Although numerous papers have been published, there is no comprehensive analysis of existing evolutionary ARM methodologies. In this paper, we review emerging research of evolutionary computation for ARM. We discuss the applications on evolutionary computations for different types of ARM approaches including numerical rules, fuzzy rules, high-utility itemsets, class association rules, and rare association rules. Evolutionary ARM algorithms were classified into four main groups in terms of the evolutionary approach, including evolution-based, swarm intelligence-based, physics-inspired, and hybrid approaches. Furthermore, we discuss the remaining challenges of evolutionary ARM and discuss its applications and future topics.

Nowadays, computer science has the ability of assisting experts in different application areas. Recently there has been increasing attention in the health area, and there exist different approaches based on artificial intelligence that have been proposed in the diagnosis of several kinds of diseases. In particular, fuzzy systems have been successfully used as Diagnosis Systems, in this way helping doctors to realize a faster and more accurate diagnosis. However, with the emergence of Type-2 Fuzzy Systems, there have been important improvements in handling the uncertainty with respect to traditional Fuzzy Systems (now called Type-1 Fuzzy Systems) in different kinds of problems. In the present paper, a new approach to Fuzzy Diagnosis based on Type-2 Fuzzy Systems is proposed and compared with respect to Type-1 Fuzzy Systems on a set of diagnosis problems, in order to evaluate the relevance of the uncertainty handling in this kind of problems. On the other hand, the paper is also aiming at observing the accuracy behavior in Fuzzy Diagnosis Systems by changing the uncertainty level in the models. Finally, a comparison of Interval Type-2 Fuzzy Systems with respect to General Type-2 Fuzzy Systems for a set of diagnosis problems is presented.

Cyber code analysis is fundamental to malware detection and vulnerability discovery for defending cyber attacks. Traditional approaches resorting to manually defined rules are gradually replaced by automated approaches empowered by machine learning. This revolution is accelerated by big code from open source projects which support machine learning models with outstanding performance. In the context of a data-driven paradigm, this paper reviews recent analytic research on cyber code of malicious and common software by using a set of common concepts of similarity, correlation and collective indication. Sharing security goals in recognizing anomalous code that may be malicious or vulnerable. The ability to do so is not determined in isolation, rather drawn for code correlation and context awareness. This paper demonstrates a new research methodology of data driven cyber security (DDCS) and its application in cyber code analysis. The framework of the DDCS methodology consists of three components, i.e., cyber security data processing, cyber security feature engineering, and cyber security modeling. Some challenging issues are suggested to direct the future research.

In this paper, we propose a simple and effective method for creating accurate trimaps based on input images. Most advanced matting algorithms require the user to provide prior information to estimate high-quality alpha masks, where the prior information is primarily in the form of trimaps. A precise trimap is one of the most important factors affecting the performance of the matting algorithm. It is a very tedious task for users to specify a large number of accurate trimaps, and it is even impractical in some applications. Based on manifold ranking, we use strokes to mark the superpixel nodes to create high-quality trimaps. The experimental results show that the method given in this paper can generate high-quality trimaps, thus ensuring the accuracy of the alpha masks that are estimated by the matting algorithm. We verify the performance of the trimaps that are created using the method given in this paper for various matting algorithms.

To reduce the damage caused by earthquakes, the paper develops a decision-making method under uncertainty, which validly addresses the site selection for earthquake shelters. Since site selection after earthquakes is an emergency decision-making process, during which there always exists inaccuracy and complexity, it is more rational to adopt fuzzy theory to handle this problem. Therefore, we introduce a hesitant multiplicative linguistic preference relation (HMLPR) and propose its consistency measure based on the eigenvector method . An adjustment method is provided to repair the unacceptably consistent HMLPR into acceptably consistent one, and the parameter of the adjustment method is also discussed. To manifest the validity and availability of the proposed method, we choose the Wenchuan Earthquake on May 12th 2008 as the background event. Upon establishing the indicators including scale and location, risk of disaster, rescue facilities, feasibility and resident aspect, three experts from Institute for Disaster Management and Reconstruction of Sichuan University are invited to address the site selection for temporary shelters. The obtained result is approved by the experts as the optimal choice in the case of this paper. Finally, we complete the comparative analysis. The processing efficiency of the proposed method keeps stable and fast when the number of experts and the number of criteria increase from 3 to 10 respectively, which demonstrates that the proposed method is more robust and efficient than the existing method.

Clustering technique plays a critical role in data mining, and has received great success to solve application problems like community analysis, image retrieval, personalized recommendation, activity prediction, etc. This paper first reviews the traditional clustering and the emerging multiple clustering methods, respectively. Although the existing methods have superior performance on some small or certain datasets, they fall short when clustering is performed on CPSS big data because of the high cost of computation and storage. With the powerful cloud computing, this challenge can be effectively addressed, but it brings enormous threat to individual or company’s privacy. Currently, privacy preserving data mining has attracted widespread attention in academia. Compared to other reviews, this paper focuses on privacy preserving clustering technique, guiding a detailed overview and discussion. Specifically, we introduce a novel privacy-preserving tensor-based multiple clustering, propose a privacy-preserving tensor-based multiple clustering analytic and service framework, and give an illustrated case study on the public transportation dataset. Furthermore, we indicate the remaining challenges of privacy preserving clustering and discuss the future significant research in this area.

Task scheduling, which plays a vital role in cloud computing, is a critical factor that determines the performance of cloud computing. From the booming economy of information processing to the increasing need of quality of service (QoS) in the business of networking, the dynamic task-scheduling problem has attracted worldwide attention. Due to its complexity, task scheduling has been defined and classified as an NP-hard problem. Additionally, most dynamic online task scheduling often manages tasks in a complex environment, which makes it even more challenging to balance and satisfy the benefits of each aspect of cloud computing. In this paper, we propose a novel artificial intelligence algorithm, called deep Q-learning task scheduling (DQTS), that combines the advantages of the Q-learning algorithm and a deep neural network. This new approach is aimed at solving the problem of handling directed acyclic graph (DAG) tasks in a cloud computing environment. The essential idea of our approach uses the popular deep Q-learning (DQL) method in task scheduling, where fundamental model learning is primarily inspired by DQL. Based on developments in WorkflowSim, experiments are conducted that comparatively consider the variance of makespan and load balance in task scheduling. Both simulation and real-life experiments are conducted to verify the efficiency of optimization and learning abilities in DQTS. The result shows that when compared with several standard algorithms precoded in WorkflowSim, DQTS has advantages regarding learning ability, containment, and scalability. In this paper, we have successfully developed a new method for task scheduling in cloud computing.

With the rapid development of mobile crowdsensing applications, task allocation has emerged as a new problem to be solved. Many task allocation strategies have been proposed to select the proper participants to complete tasks. Those methods need participants to submit their real locations to the platform in order to realize the optimal task assignment. However, those traditional task allocation strategies have two weaknesses. First, centralized task allocations result in high computing and communications loads. Second, the exposure of real locations increases participants’ concerns regarding location privacy. To address these problems, in this paper, we propose an optimal geo-indistinguishable task allocation (GITA) mechanism using mobile edge clouds. First, the new task that is received by the remote cloud is sent to the mobile edge cloud that is nearest to the task location. Then, the mobile edge clouds serve as distributed controllers to allocate the assigned tasks to the proper candidates. To protect the candidates’ real locations, we utilize a geo-indistinguishable mechanism based on differential privacy to preserve location privacy. Specifically, we obfuscate the participants’ real locations as disturbed locations, and realize the optimal task allocation based on these disturbed locations. Furthermore, we apply multiobjective mixed integer nonlinear optimization to solve this problem. Finally, extensive experimental results show that, compared with the traditional Laplace mechanism and another privacy-preserving task allocation strategy, the GITA mechanism that is proposed in this paper can decrease users’ moving distances and raise the task completion rate.

Class imbalanced datasets are common across different domains including health, security, banking and others. A typical supervised learning algorithm tends to be biased towards the majority class when dealing with imbalanced datasets. The learning task becomes more challenging when there is also an overlap of instances from different classes. In this paper, we propose an undersampling framework for handling class imbalance in binary datasets by removing potential overlapped data points. Our methods are designed to identify and eliminate majority class instances from the overlapping region. Accurate identification and elimination of these instances maximise the visibility of the minority class instances and at the same time minimises excessive elimination of data, which reduces information loss. Four methods based on neighbourhood searching with different criteria to identify potential overlapped instances are proposed in this paper. Extensive experiments using simulated and real-world datasets were carried out. Results show comparable performance with state-of-the-art methods across different common metrics with exceptional and statistically significant improvements in sensitivity.

A kernel-based one-class classifier is mainly used for outlier or novelty detection. Kernel ridge regression (KRR) based methods have received quite a lot of attention in recent years due to its non-iterative approach of learning. In this paper, KRR-based one-class classifier (KOC) has been extended for learning using privileged information (LUPI) framework. LUPI-based KOC method is referred to as KOC+ in this paper. This privileged information is available as feature/features of the dataset, but only during training (not during testing). KOC+ utilizes privileged features information differently compared to other features information. It uses this information in KOC+ by the help of so-called correction function . This information helps KOC+ in achieving better generalization performance . Existing and proposed classifiers are evaluated on the datasets taken from UCI machine learning repository and MNIST dataset. Moreover, experimental results exhibit that KOC+ outperforms KOC and other LUPI-based state-of-the-art one-class classifiers. Source code of this paper is provided on the corresponding author’s GitHub homepage: https://github.com/Chandan-IITI/KOCPlus_or_OCKELMPlus_or_OCLSSVMPlus

Internet of Things (IoT) is expanding rapidly and so is the number of devices, sensors and actuators joining this world. IoT devices are an important part of the data collection process in Big Data systems, so by protecting them we support and improve the security of the whole system. ZigBee is a secure communication system for the underlying Internet of Things (IoT) infrastructure. Even though ZigBee has a strong security stack built on a variety of secret keys, ZigBee devices are vulnerable to the side-channel and key extraction attacks. Due to the low cost and limited resources, most ZigBee devices store their secret keys in plaintext. In this paper, we focus on protecting the storage of ZigBee secret keys and show how Physical Unclonable Functions (PUFs) can help the ZigBee devices to be robust tamper-resistant against the physical attacks. The proposed schemes include PUF-based key storage protection and key generation. The experiments in this paper were done using SRAM-PUF. Furthermore, two algorithms were proposed to overcome the defects in the randomness of keys generated using SRAM-PUF and, at the same time, to increase the reliability of these keys. We were able to significantly improve the hardware security of ZEDs by protecting their keying materials using costless, high secure, random, stable and volatile PUF-based secret keys.

Attention Deficit/Hyperactivity Disorder (ADHD) is one kind of neurodevelopmental disorders common in children. Due to the complexity of the pathological mechanism, there is a lack of objective diagnostic methods up to now. This paper aimed to propose automatic ADHD diagnostic method using resting state functional magnetic resonance imaging (rs-fMRI) data with the spatio-temporal deep learning models . Unlike traditional methods, this paper constructed a deep learning method called 4-D CNN based on granular computing which were trained based on derivative changes in entropy , and can calculate granularity at a coarse level by stacking layers. Considering the structure of rs-fMRI as time-series 3-D frames, several models of spatial and temporal granular computing and fusion were proposed, including feature pooling, long short-term memory (LSTM) and spatio-temporal convolution . This paper introduced an approach to augment dataset which can sample one subject's rs-fMRI frames into several relatively short term pieces with a fixed stride. The public dataset of ADHD-200 Consortium was used to train and validate our method. And the results of evaluations showed that our method outperformed traditional methods on the dataset (accuracy: 71.3%, AUC: 0.80). Therefore, our 4-D CNN method can be used to build more accurate automatic assistant diagnosis tool of ADHD.

This paper proposes a novel top-down approach to rule-based fuzzy systems, one that begins with the product—an equation—and then addresses the unique features of the product, without requiring the reader to know anything about fuzzy sets and systems. The "products" are adaptive variable-structure basis function expansions , where "adaptive variable-structure" means that different subsets of its basis functions are active (non-zero) in different regions of the state space, something that occurs automatically by virtue of the structure of the basis functions, so that the products can be said to "adapt" to locations in the state space. These products are novel candidates for machine learning . Unique features of all products are: (1) Number of basis functions is no longer a variable and is established locally through type-1 or type-2 uncertainty partitioning of each variable; (2) Both coarse and fine sculpting of the state space are achieved, and are described in terms of first- and second-order partitions of the state space, respectively; and (3) Linguistic interpretability is obtained, which may be of value to an end-user. Learning about rule-based fuzzy systems can be greatly compressed by using the top-down approach that is described in this paper.

Similarity join is an essential operator in data processing, mining and analysis. However, it is resource intensive and time consuming, particularly when processing big data. There is also a need to ensure data confidentiality in similarity joins, as joining between two files may result in personal information disclosure . Based on these two considerations, this paper proposes a MapReduce-based similarity joins with differential privacy technology (hereafter, referred to as PSJoin). The proposed parallel algorithm is designed to achieve high efficiency, in terms of answering similarity join queries privately and effectively. Specifically, the use of PSJoin ensures the preservation of privacy during the similarity join process and in the published results. A new private global ordering approach is presented in this paper, which is designed to deal with potential disclosure issues during the process, and a differential private similarity function is provided for this algorithm. Findings from our evaluations using large-scale real-world datasets demonstrate that our method can effectively guarantee privacy with only minimal accuracy loss in similarity queries, while offering good scalability consistently.

To ensure security, image encryption algorithms generally include two stages: permutation and diffusion. The traditional image permutation algorithms include the sort-based permutation algorithm, Arnold-based permutation algorithm, Baker-based permutation algorithm and the cyclic shift permutation algorithm, etc. However, these algorithms have the disadvantages of either high time complexity or poor permutation performance. Therefore, in combination with cyclic shift and sorting, this paper proposes a permutation algorithm that can not only guarantees good permutation performance but also guarantee low time and space complexity. Most importantly, this paper proposes a parallel diffusion method. This method ensures the parallelism of diffusion to the utmost extent and achieves a qualitative improvement in efficiency over traditional streaming diffusion methods. Finally, combined with the proposed permutation and diffusion, the paper proposes a computational model for parallel image encryption algorithms.

The big data samples are important source for analytics. However, its relevant/irrelevant information, unspecified variables/scales, noise/null, and so forth impose huge challenges on the analysis of relevance, feature, cause, and evaluation. This paper proposes an evidential analytics to disclose buried information in big data samples. Technically, it models memberships composed of relevant preference and replaces data with these priors. Its operations include generating analytics baselines, reducing variables, identifying sparse features, and inducing rules by taking advantage of evidence. In illustration, a case study of semiconductor manufacturing in UCI secom is presented. It discloses relevant signals, key factors, variables’ thresholds, sparse characteristics, and causal effect of damages buried in normal samples. The contribution of this paper not only contains these achievements but provides priori data for inference.

In recent years, healthcare spending has risen and become a burden on governments especially in the US. One of the reasons for this increase is hospital readmissions. Decreasing the number of readmissions can reduce the healthcare spending. The first part of this paper examines state-of-the-art applications that aim to reduce the number of readmissions at hospitals. We categorize these applications into three different categories and highlight not only their benefits, but also their weaknesses. Moreover, we describe the limitations and challenges faced by these systems to demonstrate the possible future research paths. The second part of this paper presents novel algorithms to reduce the number of readmissions by applying the concept of personalization and actionable patterns. First, we start by extracting all possible procedure paths (course of treatments) for a given procedure. Then, we cluster patients according to the similarities in their diagnoses in order to increase the predictability of the next procedure. Finally, we present a novel algorithm that provides recommendations (actionable knowledge) to the physicians to put patients on a treatment path that would result in optimal reduction of the number of readmissions on average case.

Image quality assessment (IQA) measures predict the perceived quality of evaluated images, aiming to replace time-consuming human evaluation. This is particularly important for the automatic comparison of image processing techniques which often modify image content. Since the presence of noise highly affects the perception of images and only a few IQA measures address this type of distortion, a new no-reference IQA measure is proposed in this paper. In the introduced measure, two aspects of the Human Visual System (HVS) are considered. The sensitivity of the HVS to local image distortions is expressed by similarities between descriptors obtained with Speeded-Up Robust Features (SURF) technique. In order to improve the quality prediction, image patches for description are extracted from a gradient map of an input image. Noise also affects the visual saliency, since it decreases attention caused by image content. In the approach, visual saliency models of image patches are obtained and evaluated using adapted Visual Saliency-based Index (VSI). Experimental evaluation on popular IQA benchmarks reveals that the proposed measure outperforms the related state-of-the-art techniques . The applicability of the proposed method to an automatic selection of the best denoising algorithm is also discussed in the paper.

The choice of the most promising algorithm to model and predict a particular phenomenon is one of the most prominent activities of the temporal data forecasting. Forecasting (or prediction), similarly to other data mining tasks , uses empirical evidence to select the most suitable model for a problem at hand since no modeling method can be considered as the best. However, according to our systematic literature review of the last decade, few scientific publications rigorously expose the benefits and limitations of the most popular algorithms for time series prediction. At the same time, there is a limited performance record of these models when applied to complex and highly nonlinear data. In this paper, we present one of the most extensive, impartial and comprehensible experimental evaluations ever done in the time series prediction field. From 95 datasets, we evaluate eleven predictors, seven parametric and four non-parametric, employing two multi-step-ahead projection strategies and four performance evaluation measures. We report many lessons learned and recommendations concerning the advantages, drawbacks, and the best conditions for the use of each model. The results show that SARIMA is the only statistical method able to outperform, but without a statistical difference, the following machine learning algorithms : ANN , SVM , and k NN-TSPI. However, such forecasting accuracy comes at the expense of a larger number of parameters. The evaluated datasets, as well detailed results achieved by different indexes as MSE , Theil’s U coefficient, POCID, and a recently-proposed multi-criteria performance measure are available online in our repository. Such repository is another contribution of this paper since other researchers can replicate our results and evaluate their methods more rigorously. The findings of this study will impact further research on this topic since they provide a broad insight into models selection, parameters setting, evaluation measures, and experimental setup.

Granular computing is an efficient and scalable computing method. Most of the existing granular computing-based classifiers treat the granules as a preliminary feature procession method, without revising the mathematical model and improving the main performance of the classifiers themselves. So far, only few methods, such as the G-svm and WLMSVM, have been combined with specific classifiers. Because of the complete symmetry of the ball and its simple mathematical expression, it is relatively easy to be combined with the other classifiers’ mathematical models. Therefore, this paper uses a ball to represent the grain, namely the granular ball, and not only the granular balls’ labels but also the distance between a pair of balls is defined. Based on that, this paper attempts to propose a new granular classifier framework by replacing the point inputs with the granular balls. We derive the basic model of both the granular ball support vector machine and granular ball k-nearest neighbor algorithm (GBkNN). In addition, the GBkNN is compared with the k-means tree based kNN, which is the most efficient and effective kNN as far as we known, on both public and artificial data sets. The Experimental results demonstrate the effectiveness and efficiency of the proposed framework.

With the continued growth of interoperable software developed for Internet of Things (IoT), there is a growing demand to predict software defect at various testing and operational phases. This paper solves the software defect prediction problem by proposing a novel model with the help of a local tangent space alignment support vector machine (LTSA-SVM) algorithm. The model employs the SVM algorithm as the basic classifier of software defect distribution prediction model. Then, the model parameters are optimized by combining a grid search method and ten-fold cross validation. In the traditional dimensionality reduction algorithms, data loss caused by the poor attributes of data nonlinearity reduces the accuracy of SVM. Aiming at this problem, this paper uses a LTSA algorithm to extract the intrinsic structure of low-dimensional data and performs effective dimension reduction. The SVM algorithm is trained by the reduced dimension data. Finally, the feasibility of the prediction model is verified. Compared with the single SVM and the LLE-SVM prediction algorithm, the prediction model in this paper improves the prediction accuracy and F-measure by 1–4%.

© 2018 Elsevier Inc. An effective security strategy for Wireless Sensor Networks (WSNs) is imperative to counteract security threats. Meanwhile, energy consumption directly affects the network lifetime of a wireless sensor. Thus, an attempt to exploit a low-consumption Intrusion Detection System (IDS) to detect malicious attacks makes a lot of sense. Existing Intrusion Detection Systems can only detect specific attacks and their network lifetime is short due to their high energy consumption. For the purpose of reducing energy consumption and ensuring high efficiency, this paper proposes an intrusion detection model based on game theory and an autoregressive model. The paper not only improves the autoregressive theory model into a non-cooperative, complete-information, static game model, but also predicts attack pattern reliably. The proposed approach improves on previous approaches in two main ways: (1) it takes energy consumption of the intrusion detection process into account, and (2) it obtains the optimal defense strategy that balances the system's detection efficiency and energy consumption by analyzing the model's mixed Nash equilibrium solution. In the simulation experiment, the running time of the process is regarded as the main indicator of energy consumption of the system. The simulation results show that our proposed IDS not only effectively predicts the attack time and the next targeted cluster based on the game theory, but also reduces energy consumption.

With an exponential increase in the utilization of intellective appliances, meeting the energy demand of consumers by traditional power grids is a significant challenge. In integration, the amalgamation of electric vehicles, industrial Internet-of-Things (IoT), and smart communities with power grids has escalated the global energy demand. Consequently, the desideratum for a reliable energy supply and resilient energy ecosystem has incentivized the evolution of Smart Grids (SG). Such intelligent grids are equipped with autonomous controllers and advanced technologies like advanced metering infrastructure , smart sensors , and accounting management software. However, the existing demand response management and energy supply techniques are lagging behind in meeting the desired objectives in the SG ecosystem. In order to handle these challenges, a Demand Replication Optimization Scheme (DROpS) for the smart energy ecosystem is designed in this paper. In addition, a Multi-Leader Multi-Follower Stackelberg game is formulated in this paper to operate with the proposed scheme. However, the success of DROpS depends heavily on real-time communication between the consumers and the suppliers. Hence, dynamic and scalable network architecture is required to handle the seamless data generated by a sizably voluminous number of connected sensors, devices, and smart appliances deployed in the SG. For the successful operation of the architecture, a Software-Defined Networking (SDN)-enabled control scheme for flow management is additionally developed. In the proposed scheme, the SG ecosystem is divided into multiple zones such that the dedicated virtual SDN controllers are deployed for network resource utilization in an optimized manner. The proposed scheme is evaluated using a real smart home test bed and data traces from the Haryana power grid. The effectiveness of the proposed scheme is demonstrated in terms of significant gains observed for load variation and latency.

Advanced analytics such as event detection, pattern recognition, clustering, and classification with electroencephalogram (EEG) data often rely on extracted EEG features. Most of the existing EEG feature extraction approaches are hand-designed with expert knowledge or prior assumptions, which may lead to inferior analytical performances. In this paper, we develop a fully data-driven EEG feature extraction method by applying recurrent autoencoders on multivariate EEG signals. We use an Echo State Network (ESN) to encode EEG signals to EEG features, and then decode them to recover the original EEG signals. Therefore, we name our method feature extraction based on echo state network, or simply FE-ESN. We show that the well-known autoregression-based EEG feature extraction can be seen as a simplified variation of our FE-ESN method. We have conducted experiments on real-world EEG data to evaluate the effectiveness of FE-ESN for both classification tasks and clustering tasks. Experimental results demonstrate the superiority of FE-ESN over the state-of-the-art methods. This paper not only provides a novel EEG feature extraction method but also opens up a new way towards unsupervised EEG feature design.

This paper presents a novel Differential Evolution algorithm for protein folding optimization that is applied to a three-dimensional AB off-lattice model. The proposed algorithm includes two new mechanisms. A local search is used to improve convergence speed and to reduce the runtime complexity of the energy calculation. For this purpose, a local movement is introduced within the local search. The designed evolutionary algorithm has fast convergence speed and, therefore, when it is trapped into the local optimum or a relatively good solution is located, it is hard to locate a better similar solution. The similar solution is different from the good solution in only a few components. A component reinitialization method is designed to mitigate this problem. Both the new mechanisms and the proposed algorithm were analyzed on well-known amino acid sequences that are used frequently in the literature. Experimental results show that the employed new mechanisms improve the efficiency of our algorithm and that the proposed algorithm is superior to other state-of-the-art algorithms. It obtained a hit ratio of 100% for sequences up to 18 monomers, within a budget of $10^{11}$ solution evaluations. New best-known solutions were obtained for most of the sequences. The existence of the symmetric best-known solutions is also demonstrated in the paper., Comment: 22 pages, 8 figures, 10 tables, journal

This study provides a comprehensive overview of the publications in Information Sciences (INS) from 1968 to 2016 inclusive, which encompasses the history of this journal from its inception. 7721 articles containing 153,606 references, which are the primary data source were downloaded from the Web of Science. It studies the most prolific authors, most cited authors, most representative articles, top influential institutions and the nationalities of the authors whose papers were published in the journal. The key contributors and INS articles that have made profound impact are highlighted on a basis of bibliometric and customized text mining techniques. CiteSpace, a data visualization software, was used to make the comprehensive analysis of the 153,606 citations and construct the co-citation network maps, which can illustrate salient patterns and emerging trends. This paper not only provides the important reference to future studies by exploring the structures and trends of INS publications, which have evolved over time, but also offers a demonstration of an effective analytical method for evaluating journal citation and co-citation data in the future.