Search

Cloud computing is increasing rapidly as a successful paradigm presenting on-demand infrastructure, platform, and software services to clients. Load balancing is one of the important issues in cloud computing to distribute the dynamic workload equally among all the nodes to avoid the status that some nodes are overloaded while others are underloaded. Many algorithms have been suggested to perform this task. Recently, worldview is turning into a new paradigm for optimization search by applying the osmosis theory from chemistry science to form osmotic computing. Osmotic computing is aimed to achieve balance in highly distributed environments. The main goal of this paper is to propose a hybrid metaheuristics technique which combines the osmotic behavior with bio-inspired load balancing algorithms. The osmotic behavior enables the automatic deployment of virtual machines (VMs) that are migrated through cloud infrastructures. Since the hybrid artificial bee colony and ant colony optimization proved its efficiency in the dynamic environment in cloud computing, the paper then exploits the advantages of these bio-inspired algorithms to form an osmotic hybrid artificial bee and ant colony (OH_BAC) optimization load balancing algorithm. It overcomes the drawbacks of the existing bio-inspired algorithms in achieving load balancing between physical machines. The simulation results show that OH_BAC decreases energy consumption, the number of VMs migrations and the number of shutdown hosts compared to existing algorithms. In addition, it enhances the quality of services (QoSs) which is measured by service level agreement violation (SLAV) and performance degradation due to migrations (PDMs).

Assessment of code smell for predicting software change proneness is essential to ensure its significance in the area of software quality. While multiple studies have been conducted in this regard, the number of systems studied and the methods used in this paper are quite different, thus, causing confusion for understanding the best methodology. The objective of this paper is to approve the effect of code smell on the change inclination of a specific class in a product framework. This is the novelty and surplus of this work against the others. Furthermore, this paper aims to validate code smell for predicting class change proneness to find an error in the prediction of change proneness using code smell. Six typical machine learning algorithms (Naive Bayes Classifier, Multilayer Perceptron, LogitBoost, Bagging, Random Forest, and Decision Tree) have been used to predict change proneness using code smell from a set of 8200 Java classes spanning 14 software systems. The experimental results suggest that code smell is indeed a powerful predictor of class change proneness with multilayer perceptron being the most effective technique. The sensitivity and specificity values for all the models are well over 70% with a few exceptions.

Down syndrome (DS) caused by the presence of part or all of a third copy of chromosome 21 is the most common form of aneuploidy. The prenatal screening for DS is a key component of antenatal care and is recommended to be universally offered to women irrespective of age or background. The objective of this paper is to introduce a noninvasive and accurate diagnosis procedure for DS and to minimize social and financial cost of prenatal diagnosis. Recently, machine learning has received considerable attention in predictive analytics for medical problems. However, there is few its applications on DS prediction reported due to the difficulty of dealing with highly imbalanced and feature-correlated screening data. In this paper, we propose a cascaded machine learning framework designed for DS prediction based on three complementary stages: 1) pre-judgment with isolation forest technique, 2) model ensemble by voting strategy, and 3) final judgment using logistic regression approach. The experimental results show that the performance of this framework on maternal serum screening data set, when evaluated with different evaluation parameters, is superior to those of some machine learning methods. The best suggested combination of input features for DS screening is the group of alpha-fetoprotein, human chorionic gonadotropin, unconjugated estriol, and maternal age. In addition, our method has the potential to generate further accurate prediction for imbalanced and feature-correlated data, thereby providing a novel and effective approach for certain diseases analysis.

The data reduction capability of image compression schemes is limited by the underlying compression technique. For applications with minor changes between consecutive frames, change coding can be used to further reduce the data. We explored the efficiency of change coding for data reduction in a wireless visual sensor network (WVSN). This paper presents an analysis of the compression efficiency of change coding for a variety of changes, such as different shapes, sizes, and locations of white objects in adjacent sets of frames. Compressing change frame provides a better performance compared with compressing the original frames for up to 95% changes in the number of objects in adjacent frames. Due to illumination noise, the size of the objects increases at its boundaries, which negatively affects the performance of change coding. We experimentally proved that the negative impact of illumination noise could be reduced by applying morphology on the change frame. Communication energy consumption of the VSN is dependent on the data that are transmitted to the server. Our results show that the communication energy consumption of the VSN can be reduced by 27%, 29%, and 46% by applying change coding in combination with JBIG2, Group4, and Gzip_pack, respectively. The findings presented in this paper will aid researchers in enhancing the compression potential of image coding schemes in the energy-constrained applications of WVSNs. SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)

Advanced security methods are necessary to introduce effective online voting in the whole world. Elections conducted on paper consume a lot of resources and contribute to the destruction of forests, which leads to climate deterioration. Recent online voting experiences in countries, such as the United States, India, and Brazil, demonstrated that further research is needed to improve security guarantees for future elections, to ensure the confidentiality of votes and enable the verification of their integrity and validity. In this paper, we propose a ranked choice online voting system, which addresses these challenges. It eliminates all hardwired restrictions on the possible assignments of points to different candidates according to the voters’ personal preferences. In order to protect the confidentiality of the votes, each cast ballot is encrypted using the exponential ElGamal cryptosystem before submission. Furthermore, during voting the system ensures that proofs are generated and stored for each element in the cast ballot. These proofs can then be used to verify the correctness and the eligibility of each ballot before counting without decrypting and accessing the content of the ballot. This validates the votes in the counting process and at the same time maintains confidentiality. The security and performance analyses included in this paper demonstrate that our method has achieved significant improvements in comparison with the previous systems. The outcomes of our experiments also show that our proposed protocols are feasible for practical implementations.

[EN] Indoor Localization techniques are becoming popular in order to provide a seamless indoor positioning system enhancing the traditional GPS service that is only suitable for outdoor environments. Though there are proprietary and costly approaches targeting high accuracy positioning, Wi-Fi and BLE networks are widely deployed in many public and private buildings (e.g. shopping malls, airports, universities, etc.). These networks are accessible through mobile phones resulting in an effective commercial off-the-self basic infrastructure for an indoor service. The obtained positioning accuracy is still being improved and there is on-going research on algorithms adapted for Wi-Fi and BLE and also for the particularities of indoor environments. This paper focuses not only on indoor positioning techniques, but also on a multimodal approach. Traditional proposals employ only one network technology whereas this paper integrates two different technologies in order to provide improved accuracy. It also sets the basis for combining (merging) additional technologies, if available. The initial results show that the positioning service performs better with a multimodal approach compared to individual (monomodal) approaches and even compared with Google¿s geolocation service in public spaces such as airports., This work was supported in part by the European Commission through the Door to Door Information for Airports and Airlines Project under Grant GA 635885 and in part by the European Commission through the Interoperability of Heterogeneous IoT Platforms Project under Grant 687283.

Machine learning (ML) has shown enormous potential in various domains with the wide variations of underlying data types. Because of the miscellany in the data sets and the features, ML classifiers often suffer from challenges, such as feature miss-classification, unfit algorithms, low accuracy, overfitting, underfitting, extreme bias, and high predictive errors. Through the lens of related study and latest progress in the field, this paper presents a novel scheme to construct logical table (LT) unit with two internal sub-modules for algorithm blend and feature engineering. The LT unit works in the deepest layer of an enhanced ML engine engineering (eMLEE) process. eMLEE consists of several low-level modules to enhance the ML classifier progression. A unique engineering approach is adopted in eMLEE to blend various algorithms, enhance the feature engineering, construct a weighted performance metric, and augment the validation process. The LT is an in-memory logical component, that governs the progress of eMLEE, regulates the model metrics, improves the parallelism, and keep tracks of each module of eMLEE as the classifier learns. Optimum fitness of the model with parallel “check, validate, insert, delete, and update”mechanism in 3-D logical space via structured schemas in the LT is obtained. The LT unit is developed in Python, C#, and R libraries and tested using miscellaneous data sets. Results are created using GraphPad Prism, SigmaPlot, Plotly, and MS Excel software. To support the built and implementation of the proposed scheme, complete mathematical models along with the algorithms, and necessary illustrations are provided in this paper. To show the practicality of the proposed scheme, several simulation results are presented with a comprehensive analysis of the outcomes for the metrics of the model that the LT regulates with improved outcomes.

This paper gives two contributions to the state-of-the-art for viticulture technology research. First, we present a comprehensive review of computer vision, image processing, and machine learning techniques in viticulture. We summarize the latest developments in vision systems and techniques with examples from various representative studies, including, harvest yield estimation, vineyard management and monitoring, grape disease detection, quality evaluation, and grape phenology. We focus on how computer vision and machine learning techniques can be integrated into current vineyard management and vinification processes to achieve industry relevant outcomes. The second component of the paper presents the new GrapeCS-ML database which consists of images of grape varieties at different stages of development together with the corresponding ground truth data (e.g., pH and Brix) obtained from chemical analysis. One of the objectives of this database is to motivate computer vision and machine learning researchers to develop practical solutions for deployment in smart vineyards. We illustrate the usefulness of the database for a color-based berry detection application for white and red cultivars and give baseline comparisons using various machine learning approaches and color spaces. This paper concludes by highlighting future challenges that need to be addressed prior to successful implementation of this technology in the viticulture industry.

Action recognition is a trending topic and key research direction in computer vision, machine learning, artificial intelligence, and other fields. This research seeks to identify human action in image and video data. Its research results have been widely used in the fields of safety monitoring, disability monitoring, understanding multimedia content, human–computer interaction, virtual reality, and so on. However, the existing traditional human action recognition technology has many limitations in practical application, such as low accuracy and weak adaptive ability. Although the action recognition based on deep learning can self-learn and improve the action recognition accuracy, there are many difficulties in training the deep neural network model, such as gradient disappearance, gradient explosion, and overfitting. Therefore, this paper will reduce the abovementioned difficulties in deep neural network model training from the perspective of deep neural network model parameter initialization and then propose a model parameter initialization method based on the multilayer maxout network activation function to solve the difficulties in deep neural network model training. Then, on this basis, a method of learning the temporal and spatial characteristics of human action based on the deep neural network model is proposed. First, the method detects and tracks the human action and uses the restricted Boltzmann machine (RBM) to encode the temporal and spatial features of various parts of the human body. Second, the temporal and spatial feature codes of various parts of the human body are integrated into a global temporal and spatial feature representation method of the action video through a RBM neural network. Finally, the trained SVM classifiers are used to recognize human action. Experiments show that the human action recognition method proposed in this paper not only has high recognition accuracy but also has great adaptability. Thus, this method extracts temporal and spatial features from the shape feature sequences of various parts of the human body, thus opening up a new way to extract human action features and solving the problem of human action recognition in complex scenes. Its proposal provides an exploratory technical method and approach for self-adaptive recognition of human action. It also gives directional enlightenment to the development and improvement of self-adaptive human action methods.

Clustering Arabic text documents is of high importance for many natural language technologies. This paper uses a combined method to cluster Arabic text documents. Mainly, we use generative models and clustering techniques. The study uses latent Dirichlet allocation and $k$ -means clustering algorithm and applies them to a news data set used in previous similar studies. The aim of this paper is twofold: it first shows that normalizing the weights in the vector space, for the document-term matrix of the text documents, dramatically improves the quality of clusters and hence the accuracy of clustering when using $k$ -means algorithm. The results are compared to a recent study on clustering Arabic text documents. Second, it shows that the combined method is superior in terms of clustering quality for Arabic text documents according to external measures, such as purity, F-measure, entropy, accuracy, and other measures. It is shown in this paper that the purity of the combined method is 0.933 compared to 0.82 for ${k}$ -means algorithm, and these figures are higher in comparison to a recent similar study. This is also confirmed by the other used validation measures. The correctness of the combined method is then confirmed using different Arabic data sets.

Fault tree generation technology is a key issue for safety analysis of large complex systems. Traditional safety analysis methods usually describe the origin, propagation, or concrete behavior of the fault and do not portray the constraints between faults. However, these constraints are the system’s characteristics, and a lack of expression of these constraints will make the fault model defective, thereby resulting in a fault tree that will reduce the accuracy of the safety analysis. To improve the efficiency and accuracy of safety analysis, this paper proposes a fault tree generation method that is based on fault configuration and introduces the variability management of software product lines to model system faults and perform the formal analysis. First, the fault feature diagram is defined to describe the constraint relationships between system faults, and the fault-labeled transition system is defined based on the Kripke structure to describe the system behavior. Then, based on the model semantics, the procedure for generating fault trees by model checking is established. Finally, using temporal logic to describe the system safety attributes, we adopt the model checking tool SNIP to verify the safety attributes and generate the fault tree automatically. The fault modeling method that is proposed in this paper includes the inherent constraints between faults, which makes the system fault model more realistic and accurate. A case study demonstrates the effectiveness of the proposed method.

During the recent years, the issue of preserving the integrity of digital text has become a focus of interest in the transmission of online content on the Internet. Watermarking has a useful tool in the protection of digital text content as it solves the problem of tampering, duplicating, unauthorized access, and security breaches. The rapid development currently observable in information transfer and access is the consequences of the widespread usage of the Internet. When it comes to the different types of digital data, text constitutes the most complex and challenging type to which the method of text watermarking can be applied. Text watermarking constitutes a highly complex task, most of all, since only limited research has been done in this field. In order to ensure the successful evaluation, analysis, and implementation, a comprehensive research needs to be performed. This paper studies the theory, methods, and applications of text watermarking, which includes the discussion on the definition, embedding and extracting processes, requirements, approaches, and language applications of the established text watermarking methods. This paper reviews in detail the new classification of text watermarking, which is through embedding process and its related issues of attacks and language applicability. Open research challenges and future directions are also investigated, with a focus on its information integrity, information availability, originality preservation, information confidentiality, protection of sensitive information, document transformation, cryptography application, and language flexibility.

In the practical study of cybersecurity, students benefit greatly from having a full control of physical equipment and services. However, this presents far too great a risk to security to be permitted on university campus networks. This paper describes an approach, used successfully at Northumbria University, in which students have control of an off-campus network laboratory, with a dedicated connection to the Internet. The laboratory is flexible enough to allow the teaching of general purpose networking and operating systems courses, while also supporting the teaching of cybersecurity through the safe integration of honeypot devices. In addition, this paper gives an analysis of honeypot architectures and presents two in detail. One of these offers students the opportunity to study cybersecurity attacks and defences at very low cost. It has been developed as a stand-alone device that can also be integrated safely into the laboratory environment for the study of more complex scenarios. The main contributions of this paper are the design and implementation of an off-campus, physical network laboratory; a small, low-cost, configurable platform for use as a “lightweight”honeypot; and a laboratory-based, multi-user honeypot for large-scale, concurrent, cybersecurity experiments. This paper outlines how the laboratory environment has been successfully deployed within a university setting to support the teaching and learning of cybersecurity. It highlights the type of experiments and projects that have been supported and can be supported in the future.

With the increasing attention paid to many-objective optimization in the evolutionary multi-objective optimization community, various approaches have been proposed to solve many-objective problems. However, existing experimental comparative studies are usually restricted to a few methods. Few studies have encompassed most of the recently proposed state-of-the-art approaches and made an experimental comparison. To this end, this paper offers a systematic comparison of 13 algorithms covering various categories to solve many-objective problems. The experimental comparison is conducted on three groups of test functions by using two performance metrics and a visual observation in the decision space. The experimental results demonstrate that different approaches have different search abilities. None of the test approaches outperform the others on all types of problems. However, some of the approaches are competitive on a large number of test problems. Moreover, inconsistent results from the hypervolume and the inverted generational distance metrics are revealed in this paper. Based on these comparative results, researchers can obtain useful suggestions for choosing appropriate algorithms for different problems.

This paper proposes a new deep learning method, the greedy deep weighted dictionary learning for mobile multimedia for medical diseases analysis. Based on the traditional dictionary learning methods, which neglects the relationship between the sample and the dictionary atom, we propose the weighted mechanism to connect the sample with the dictionary atom in this paper. Meanwhile, the traditional dictionary learning method is prone to cause over-fitting for patient classification of the limited training data set. Therefore, this paper adopts $\mathrm {l}_{2}$ -norm regularization constraint, which realizes the limitation of the model space, and enhances the generalization ability of the model and avoids over-fitting to some extent. Compared with the previous shallow dictionary learning, this paper proposed the greedy deep dictionary learning. We adopt the thinking of layer by layer training to increase the hidden layer, so that the local information between the layer and the layer can be trained to maintain their own characteristics, reduce the risk of over-fitting and make sure that each layer of the network is convergent, which improves the accuracy of training and learning. With the development of Internet of Things and the soundness of healthcare monitoring system, the method proposed have better reliability in the field of mobile multimedia for healthcare. The results show that the learning method has a good effect on the classification of mobile multimedia for medical diseases, and the accuracy, sensitivity, and specificity of the classification have good performance, which may provide guidance for the diagnosis of disease in wisdom medical.

In a cloud data center, there is usually a large waste of physical resources and link resources, which leads to increased energy consumption. This paper discusses reducing the loss of link resources from the perspective of connectivity between virtual machines. When the virtual machines of a single user request are concentrated to reduce energy consumption, there will be decreased request reliability. This paper considers a single point of failure to ensure the reliability of the requests. Finally, this paper proposes a multi-objective particle swarm optimization algorithm. It takes the physical resource utilization rate and the link loss rate as the optimization targets and uses service reliability and quality of the tenant as constraint conditions. The simulation results show that the method proposed in this paper reliably satisfies the tenant request, effectively controls the link loss in the data center, and significantly reduces the energy consumption of the data center.

Smart campus is based on the Internet of Things (IoT) technology, and its purpose is to achieve the intelligent management and service on campus. Through the IoT, the mutual blending of teachers and students, learning facilities, and information generated by facilities is realized. This paper introduces and analyzes the current research status of smart campus and the difficulties in integrating various kinds of service data in smart campus. After analyzing various kinds of situational data, this paper analyzes and designs smart campus service discovery algorithm and perceptual data fusion algorithm on the basis of previous research on the situational awareness system framework for smart campus. Compared with the traditional campus platform, smart campus can manage perceptual data more efficiently, which brings convenience to campus service and management.

The traditional big-data analytical approaches use data clustering as small buckets while providing distributed computation among different child nodes. These approaches bring the issues especially concerning network capacity, specialized tools and applications not capable of being trained in a short period. Furthermore, raw data generated through IoT forming big data comes with the capability of producing highly unstructured and heterogeneous form of data. Such form of data grows into challenging task for the real-time analytics. It is highly valuable to have computational values available locally instead of through distributed resources to reduce real-time analytical challenges. This paper proposes a fusion of three different data models like relational, semantical, and big data based data and metadata involving their issues and enhanced capabilities. A case study is used to represent data fusion in action from RDB to Resource Description Framework. Whereas, issues and their feasible solutions are also being discussed in this paper.

The aim of this paper is to develop a novel consensus ranking method that uses a mixed choice strategy for multiple criteria decision analysis (MCDA) under complex uncertainty based on Pythagorean fuzzy (PF) sets. The majority of MCDA methods have focused almost exclusively on “criterion-specific”choice tasks that are the tasks in which all alternatives are decomposed into distinct components and evaluated on specific criteria. However, in certain MCDA problems in practical applications, category-based choices tend to be more holistic in nature, especially in affective-like aspects. Therefore, this paper incorporates a mixed choice strategy (i.e., a combination of a category-based strategy and a criterion-specific strategy) into the core structure of the developed MCDA method. Furthermore, this paper utilizes the theory of Pythagorean fuzziness to provide a powerful modeling tool for complex and varied decision-making environments. Employing the developed concepts of a PF precedence index based on PF information and a disagreement indicator based on distances between rankings, this paper proposes a novel consensus ranking method by means of a comprehensive disagreement-based assignment model for addressing a mixed-choice-strategy-based MCDA problem in the PF context. As an application of the proposed methodology, a real-world case study of a luxury car selection problem is investigated. The application results, along with a comparative analysis, demonstrate the practicality and effectiveness of the developed approach, which is capable of handling hybrid category-based and criterion-specific choice tasks and managing complex uncertainty in practical situations.

With geological big data becoming a focus of geoscience research, the vast amount of textual geoscience data provides both opportunities and challenges for data analysis and data mining. In fact, it does not seem possible to meet the demands of the big data age through the traditional manual reading for information extraction and gaining knowledge. In this paper, a workflow is proposed to extract prospecting information by text mining based on convolutional neural networks (CNNs). The aim is to classify the text data and extract the prospecting information automatically. The procedure involves three parts: 1) text data acquisition; 2) text classification based on CNN; and 3) statistics and visualization. First, the large amount of available text data was acquired based on geoscience big data acquisition methodologies. After text preprocessing, the CNN was used to classify the geoscience text data into four categories (geology, geophysics, geochemistry, and remote sensing), with each category consisting of three levels of text scales (word, sentence, and paragraph). Second, the word frequency statistics, co-occurrence matrix statistics, and term frequency–inverse document frequency (TF-IDF) statistics were for words, sentences, and paragraphs, respectively, which aimed to obtain the key nodes and links derived from the content-words. Finally, the deep semantic information of the big data mining of relevant geoscience texts was visualized by word clouds, knowledge graphs (e.g., the chord and bigram graphs), and TF-IDF statistical graphs. The Lala copper deposit in Sichuan province was taken as a test case, for which the prospecting information was extracted successfully by the developed text mining methodologies. This paper provides a strong basis for research into establishing mineral deposits prospecting models based on logical knowledge trees. In addition, it shows the great potential of this method for intelligent information extraction within geoscience big data.

The reliable implementation of software in an Internet system directly influences information transmission especially for the Internet of Things (IoT) system. Once defects in the system are found, the communication between things and things and the interaction between people and things in the IoT will be greatly affected. Therefore, rapid and effective defect assignment to the right developer is the key to ensuring software quality and bringing down time consumption in the IoT software life cycle. However, as the size of the software becomes increasing larger, the requirement of users grows, and a large number of software bugs will be found every day. It is difficult for managers to assign the software defects to the appropriate developers. In this paper, a novel hybrid method based on a diversified feature selection and an ensemble extreme learning machine (ELM) is proposed. First, the useful information is extracted from defect reports; then, the data are preprocessed to establish a vector space model; and the diversified feature selection is preprocessed in order to select a smallest set of representative non-redundant features with maximal statistical information. Finally, an ensemble GA-based ELM training classifier is used. Experimental results show that, compared to SVM, C4.5, NaiveBayes, and KNN classifiers, the proposed ELM-based bug triage approach with representative feature selection techniques in this paper significantly improves the efficiency and the effectiveness of bug triages.

In critical applications, such as medical diagnosis, security related systems, and so on, the cost or risk of action taking based on incorrect classification can be very high. Hence, combining expert opinions before taking decision can substantially increase the reliability of such systems. Such pattern recognition systems base their final decision on evidence collected from different classifiers. Such evidence can be of data type, feature type, or classifier type. Common problems in pattern recognition, such as curse of dimensionality, and small sample data size, among others, have also prompted researchers into seeking new approaches for combining evidences. This paper presents a criteria-based framework for multi-classifiers combination techniques and their areas of applications. The criteria discussed here include levels of combination, types of thresholding, adaptiveness of the combination, and ensemble-based approaches. The strengths and weaknesses of each of these categories are discussed in details. Following this analysis, we provide our perspective on the outlook of this area of research and open problems. The lack of a well-formulated theoretical framework for analyzing the performance of combination techniques is shown to provide a fertile ground for further research. In addition to summarizing the existing work, this paper also updates and complements the latest developments in this area of research.

Currently, majority of persons were immobilized and need aid from caretakers due to disability. To reduce and overcome such problem, there was a need for developing human-computer interface (HCI) with the help of biosignals. In this paper, we propose a two-channel elecctrooculograpy (EOG)-based HCI to encourage the contact ability as well as value of life for paralyzed persons who cannot speak or shift their extremity by using 20 subjects with the help of ADT26 Bio amplifier. EOG signals were collected for 11 tasks from both vertical and horizontal eye movement by using gold-platted electrodes. The extracted EOG signals were processed with convolution and Plancherel theorem to obtain the features. Layered recurrent neural network (LRNN) was implemented to analyze the extracted features and then converted into a sequence of commands to control the HCI. A graphical user interface was developed using MATLAB to help a user to convey their thoughts. This paper shows an average classification accuracy of 90.72% for convolution features and 91.28% for Plancherel features. Off-line single trail analysis was also performed to analyze the recognition accuracy of the proposed HCI system. The off-line analysis displayed that Plancherel features using LRNN were high compared to convolution features using LRNN. From this paper, we found that LRNN architecture using Plancherel features was more suitable for developing EOG-based HCI. Single trail analysis was conducted to identify the recognizing accuracy in offline. The off-line results indicated that in comparison with other EOG-based HCI systems, our system was user friendly and needs minimum training to operate.

Since the end of the 1990s, the world has witnessed a tremendous growth in the area of information and communication technology (ICT), starting with grid computing, cloud computing (CC), and fog computing to recently introduced edge computing. Although, these technologies are still in very good shape, they do heavily rely on connectivity, i.e., Internet. To address this challenge, this paper proposes a novel dew-cloud architecture that brings the power of CC together with the dew computing (DC). Originally, the dew-cloud architecture is an extension of the existing client-server architecture, where two servers are placed at both ends of the communication link. With the help of a dew server, a user has more control and flexibility to access his/her personal data in the absence of an Internet connection. Primarily, the data are stored at the dew server as a local copy upon which instantiation of the Internet is synchronized with the master copy at the cloud side. Users can browse, read, write, or append data on the local dew site, which is a local Web form of an actual website. With the incorporation of the dew domain naming system and dew domain name redirection, mapping between different local dew sites has become possible. Novel services, such as infrastructure-as-a-dew, software-as-a-dew service, and software-as-a-dew product, are, hereby, introduced along with the DC. This paper presents the following as key contributions: 1) a precise and concrete definition of DC; 2) detailed and comprehensive discussions of its concept and working principle; 3) application potentials; and 4) technical challenges. The motto of this paper is to conceptualize the fact of empowerment of the ICT-user base with almost an Internet-free surfing experience in coming days.

Brain signal processing is important for not only the physiologist doing analysis investigation, but also for the clinician inspecting patients, biomedical engineer who is responsible for collecting, processing, and interpreting the electroencephalogram signals by modeling systems and algorithms for their manipulations. The abundant materials on the subject of brain signal/image processing are scattered in different scientific, technological and physiological journals, international conference proceedings, and also in various databases. Therefore, it is altogether a difficult, too time-consuming, and much tiresome work, exclusively to the newcomers in this field. Therefore, this paper focuses on providing the list of popular databases available belonging to the neurological signals, brain signal/image collections, and so on. The count and the kinds of attacks across the networked computer systems have hiked the significance of computer network security. At present, network administrators use to inspect, examine, scrutinize, review, and analyze the network traffic to figure out what is going on and to set up a prompt response in the event of an identified attack. This paper analyzes the different sweep techniques such as Ping sweep, TCP sweep, and Null sweep on the popular databases about the brain signal/image collections. The results of the Ping sweep support status, TCP sweep times, and Null scan times on different servers are discussed finally.

Since 2010, annual StarCraft artificial intelligence (AI) competitions have promoted the development of successful AI players for complex real-time strategy games. In these competitions, AI players are ranked based on their win ratio over thousands of head-to-head matches. Although simple and easily implemented, this evaluation scheme may less adequately help develop more human-competitive AI players. In this paper, we recruited 45 human StarCraft players at different expertise levels (expert/medium/novice) and asked them to play against the 18 top AI players selected from the five years of competitions (2011–2015). The results show that the human evaluations of AI players differ substantially from the current standard evaluation and ranking method. In fact, from a human standpoint, there has been little progress in the quality of StarCraft AI players over the years. It is even possible that AI-only tournaments can lead to AIs being created that are unacceptable competitors for humans. This paper is the first to systematically explore the human evaluation of AI players, the evolution of AI players, and the differences between human perception and tournament-based evaluations. The discoveries from this paper can support AI developers in game companies and AI tournament organizers to better incorporate the perspective of human users into their AI systems.

Electronic health records (EHRs) contain patient diagnostic records, physician records, and records of hospital departments. For heart failure, we can obtain mass unstructured data from EHR time series. By analyzing and mining these time-based EHRs, we can identify the links between diagnostic events and ultimately predict when a patient will be diagnosed. However, it is difficult to use the existing EHR data directly, because they are sparse and non-standardized. Thus, this paper proposes an effective and robust architecture for heart failure prediction. The main contribution of this paper is to predict heart failure using a neural network (i.e., to predict the possibility of cardiac illness based on patient’s electronic medical data). Specifically, we employed one-hot encoding and word vectors to model the diagnosis events and predicted heart failure events using the basic principles of a long short-term memory network model. Evaluations based on a real-world data set demonstrate the promising utility and efficacy of the proposed architecture in the prediction of the risk of heart failure.

Alvis is a formal modeling language intended for developing systems consisting of concurrently operating units (real-time, embedded, and distributed systems). This paper describes the timed version of Alvis that is suitable for modeling discrete-time systems. This paper is the first relatively complete description of timed Alvis. We present formal definition and semantics of timed models and the algorithm of labeled transition system generation and introduce the computer software that we developed to support Alvis. All concepts are illustrated by examples.

Falling is a common and dangerous event for the elderly population. Fall detection is an interesting scientific problem and an ill-defined process that can be solved through various methods. In this paper, various methods and detection algorithms based on wearable sensors are introduced. A benchmark database, namely, a fall detection database, is presented to evaluate the performance of detection algorithms. This database collects sample data from 26 males and 24 females performing 15 kinds of activities, including falls and activities of daily life, such as walking, running, and walking upstairs. The subjects comprise 50 males and females ranging from 21 to 60 years of age, 1.55 to 1.90 m in height, and 40 to 85 kg in weight. A full comparison between the existing databases and the proposed database is presented. Four baseline algorithms (the artificial neutral network, k nearest neighbor, support vector machine, and kernel Fisher discriminant) are used to evaluate the databases’ reliabilities. Evaluation protocols based on the fall detection database are discussed, and the performance of the four algorithms as a baseline are presented for the following objectives: 1) to elementarily assess the database through the fall detection algorithms; 2) to identify the strengths and weaknesses of the common algorithms; and 3) to obtain the evaluation results for two classes and multiple classes based on the database. In hospitals, it is helpful to build a fall detection system for some patients who are unconscious and unable to call for help after falling down. Therefore, this paper has implications for the construction of a medical IOT platform.

With the increasing popularity of cloud computing, a growing data owners are motivated to outsource their huge data to cloud servers in order to facilitate access and save data management cost. To protect user privacy and data security, sensitive data should be encrypted before outsourced to the cloud server, which obsoletes data utilization like efficient search over encrypted data. In this paper, we present a privacy-preserving conjunctive keyword search scheme over encrypted cloud data, which simultaneously supports dynamic update operations. Specifically, we construct an index structure based on multi-attribute tree (MAT) and present an efficient search algorithm over the index tree, named as the searchMAT algorithm. We propose a multi-attribute conjunctive keyword search scheme based on MAT, named as the MCKS-MAT scheme, which can achieve equality conjunction, subset conjunction and range conjunction, as well as satisfy privacy requirements under the known background attack model. In addition, this paper is accompanied by an adequate of experiments for evaluating the effectiveness of the proposed scheme. Experiments demonstrate that, compared to the linear search, the proposed scheme needs the slightly higher preprocessing cost on account of constructing the tree-based index, however, it achieves lower computational overhead in initialization, trapdoor generation and queries.

Recent advances have shown that convolutional neural networks (CNNs) perform excellent in the tasks of image classification and face recognition when the size of data sets is sufficiently large, i.e., over hundreds of thousands training images. Nevertheless, when public data sets are not suitable for training the model for new application scenarios, it is painful to obtain sufficient training examples, especially when the samples have to be labeled manually. Besides, training and inference using CNNs requires significant resources of energy, computation, and memory usage. Therefore, implanting deep CNN models trained and executed on high performance GPU clusters to resource constrained devices, i.e., Internet of Things (IoT) devices, which have permeated into every aspect of modern life, is not appropriate and impractical. Compression technology is an important and popularly used tool to accelerate the training and inference of the CNN models. In this paper, we aim for a step forward in this area: we propose a new compressed CNN model termed CS-CNN for image classification by incorporating the theory of compressive sensing at the input layer of the CNN models to both reduce the resources consumption (evaluated as computation time in this paper) and a required number of training samples. According to our extensive evaluations on the multiple public data sets for deep learning tasks, e.g., MINST and CIFAR-10, using different metrics, we illustrate that the CS-CNN is able to speed up the process of training and inference by a factor of magnitude. Meanwhile, it achieves higher classification accuracy compared with the traditional large CNN models when the size of training database is small.

Imbalanced data exists commonly in machine learning classification applications. Popular classification algorithms are based on the assumption that data in different classes are roughly equally distributed; however, extremely skewed data, with instances from one class taking up most of the dataset, is not exceptional in practice. Thus, performance of algorithm often degrades significantly when encountering skewed data. Mitigating the problem caused by imbalanced data has been an open challenge for years, and previous researches mostly have proposed solutions from the perspectives of data re-sampling and algorithm improvement. In this paper, focusing on two-class imbalanced data, we have proposed a novel divergence-encouraging autoencoder (DEA) to explicitly learn features from both of the two classes and have designed an imbalanced data classification algorithm based on the proposed autoencoder. By encouraging maximization of divergence loss between different classes in the bottleneck layer, the proposed DEA can learn features for both majority and minority classes simultaneously. The training procedure of the proposed autoencoder is to alternately optimize reconstruction and divergence losses. After obtaining the features, we directly compute the cosine distances between the training and testing features and compare the median of distances between classes to perform classification. Experimental results illustrate that our algorithm outperform ordinary and loss-sensitive CNN models both in terms of performance evaluation metrics and convergence properties. To the best of our knowledge, this is the first paper proposed to solve the imbalanced data classification problem from the perspective of explicitly learning representations of different classes simultaneously. In addition, designing of the proposed DEA is also an innovative work, which could improve the performance of imbalanced data classification without data re-sampling and benefit future researches in the field.

This paper proposes a new simple image encryption technique using the Beta chaotic map for performing the confusion and diffusion of input plain image. This image encryption is further applied to the multiple secret sharing (MSS). The former existing scheme in MSS employs the Chinese remainder theorem (CRT) and eXclusive- OR (XOR) operations to convert the secret image to become a set of shared images. The former scheme yields a good result while the number of secret images is even. However, it has slight limitation while the number of secret images is odd. This paper aims to overcome this problem by utilizing the proposed image encryption along with three new MSS approaches: 1) incorporating an additional random images; 2) performing $k$ image encryption; and 3) using two different masking coefficients. As documented in the experimental section, the proposed method performs well in the MSS task. It solves the problem in former scheme on dealing with odd number of secret images. In addition, the proposed method is superior compared with the other competing schemes. The proposed image encryption also improves the security level in the MSS system.

Cloud computing and Internet of Things (IoT) are computing technologies that provide services to consumers and businesses, allowing organizations to become more agile and flexible. Therefore, ensuring quality of service (QoS) through service-level agreements (SLAs) for such cloud-based services is crucial for both the service providers and service consumers. As SLAs are critical for cloud deployments and wider adoption of cloud services, the management of SLAs in cloud and IoT has thus become an important and essential aspect. This paper investigates the existing research on the management of SLAs in IoT applications that are based on cloud services. For this purpose, a systematic mapping study (a well-defined method) is conducted to identify the published research results that are relevant to SLAs. This paper identifies 328 primary studies and categorizes them into seven main technical classifications: SLA management, SLA definition, SLA modeling, SLA negotiation, SLA monitoring, SLA violation and trustworthiness, and SLA evolution. This paper also summarizes the research types, research contributions, and demographic information in these studies. The evaluation of the results shows that most of the approaches for managing SLAs are applied in academic or controlled experiments with limited industrial settings rather than in real industrial environments. Many studies focus on proposal models and methods to manage SLAs, and there is a lack of focus on the evolution perspective and a lack of adequate tool support to facilitate practitioners in their SLA management activities. Moreover, the scarce number of studies focusing on concrete metrics for qualitative or quantitative assessment of QoS in SLAs urges the need for in-depth research on metrics definition and measurements for SLAs.

In this paper, a differential-evolution-based approach implementing a global search strategy to find a near-optimal axis-parallel decision tree is introduced. In this paper, the internal nodes of a decision tree are encoded in a real-valued chromosome, and a population of them evolves using the training accuracy of each one as its fitness value. The height of a complete binary decision tree whose number of internal nodes is not less than the number of attributes in the training set is used to compute the chromosome size, and a procedure to map a feasible axis-parallel decision tree from one chromosome is applied, which uses both the smallest-position-value rule and the training instances. The best decision tree in the final population is refined replacing some leaf nodes with sub-trees to improve its accuracy. The differential evolution algorithm has been successfully applied in conjunction with several supervised learning methods to solve numerous classification problems, due to it exhibiting a good tradeoff between its exploitation and exploration skills, and to the best of our knowledge, it has not been utilized to build axis-parallel decision trees. To obtain reliable estimates of the predictive performance of this approach and to compare its results with those achieved by other methods, a repeated stratified ten-fold cross-validation procedure is applied in the experimental study. A statistical analysis of these results suggests that our approach is better as a decision tree induction method as compared with other supervised learning methods. Also our results are comparable to those obtained with random forest and one multilayer-perceptron-based classifier.

Fuzzy logic systems are useful for solving problems in many application fields. However, these systems are usually stored in specific formats and researchers need to rewrite them to use in new problems. Recently, the IEEE Computational Intelligence Society has sponsored the publication of the IEEE Standard 1855-2016 to provide a unified and well-defined representation of fuzzy systems for problems of classification, regression, and control. The main aim of this standard is to facilitate the exchange of fuzzy systems across different programming systems in order to avoid the need to rewrite available pieces of code or to develop new software tools to replicate functionalities that are already provided by other software. In order to make the standard operative and useful for the research community, this paper presents JFML, an open source Java library that offers a complete implementation of the new IEEE standard and capability to import/export fuzzy systems in accordance with other standards and software. Moreover, the new library has associated a Website with complementary material, documentation, and examples in order to facilitate its use. In this paper, we present three case studies that illustrate the potential of JFML and the advantages of exchanging fuzzy systems among available software, This work was supported in part by the XXII Own Research Program (2017) of the University of Córdoba, in part by the Spanish Ministry of Economy and Competitiveness under Grants RYC-2016-19802 (Ramón y Cajal contract), TIN2017-84796-C2-1-R, TIN2014-56633-C3-3-R, TIN2014-57251-P, and TIN2015-68454-R, in part by the Andalusian Government under Grant P11-TIC-7765, in part by the Xunta de Galicia (accreditation 2016-2019), and in part by the European Union (European Regional Development Fund).

With the rapid growing proliferation of online travel agent (OTA) services, personalized recommendations are highly valuable as they can improve customer experiences by preventing the information overload problem. The accurate prediction of users' expectations for price plays an important role in the personalized recommendation of hotels in OTA platforms. Considering that customers' preferences for hotel prices are actually acceptable ranges and traditional point estimations may neglect some informative aspects of the prediction, interval estimation is more suitable for the problem investigated in this paper. However, existing related methods are not applicable due to some specific issues. To provide a better personalized recommendation of hotels in OTA platforms, this paper proposes a novel interval forecasting solution to improve the accuracy of predicting users' price preferences. The novel interval forecasting solution first puts forward a customized objective function which could directly measure the quality of constructed intervals, while also allowing for adjustable tradeoffs between interval tightness and prediction reliability. Then, it combines alternating direction optimization and the gradient boosting framework to efficiently aggregate weak individual predictors to optimize the introduced learning objective. Empirical comparisons conducted on several benchmark standard datasets and a large-scale dataset shared with us by a major Chinese OTA site demonstrate the effectiveness of the proposed approach.

Attribute-based encryption is a popular cryptographic technology to protect the privacy of clients’ data in cloud computing. In order to make the scheme have the functionality of comparing ciphertext, Zhu et al. combined concepts of key-policy attributed-based encryption with public key encryption with equality test and proposed key-policy attributed-based encryption with equality test. They defined its security model and put forward a scheme from bilinear pairing. In this paper, we first use two methods to show that their scheme is not secure for one-way under chosen ciphertext attack. Next, we show that the scheme is not secure for a test under chosen ciphertext attack defined in their paper yet. Finally, we point out the definition of a test under chosen ciphertext attack is very strong, which causes no scheme to satisfy the model.

This paper presents a novel method for structural data recognition using a large number of graph models. In general, prevalent methods for structural data recognition have two shortcomings: 1) Only a single model is used to capture structural variation. 2) Naive recognition methods are used, such as the nearest neighbor method. In this paper, we propose strengthening the recognition performance of these models as well as their ability to capture structural variation. The proposed method constructs a large number of graph models and trains decision trees using the models. This paper makes two main contributions. The first is a novel graph model that can quickly perform calculations, which allows us to construct several models in a feasible amount of time. The second contribution is a novel approach to structural data recognition: graph model boosting. Comprehensive structural variations can be captured with a large number of graph models constructed in a boosting framework, and a sophisticated classifier can be formed by aggregating the decision trees. Consequently, we can carry out structural data recognition with powerful recognition capability in the face of comprehensive structural variation. The experiments shows that the proposed method achieves impressive results and outperforms existing methods on datasets of IAM graph database repository., Comment: 8 pages

Information retrieval systems embed temporal information for retrieving the news documents related to temporal queries. One of the important aspects of a news document is the focus time , a time to which the content of document refers. The contemporary state-of-the-art does not exploit focus time to retrieve relevant news document. This paper investigates the inverted pyramid news paradigm to determine the focus time of news documents by extracting temporal expressions, normalizing their value and assigning them a score on the basis of their position in the text. In this method, the news documents are first divided into three sections following the inverted pyramid news paradigm. This paper presents a comprehensive analysis of four methods for splitting news document into sections: the paragraph-based method, the words-based method, the sentence-based method, and the semantic-based method (SeBM). Temporal expressions in each section are assigned weights using a linear regression model. Finally, a scoring function is used to calculate a temporal score for each time expression appearing in the document. These temporal expressions are then ranked on the basis of their temporal score, where the most suitable expression appears on top. The effectiveness of the proposed method is evaluated on a diverse dataset of news related to popular events; the results revealed that the proposed splitting methods achieved an average error of less than 5.6 years, whereas the SeBM achieved a high precision score of 0.35 and 0.77 at positions 1 and 2, respectively.

Prediction of quality of service (QoS) is a critical area of research for cloud service recommendation. The disadvantage of QoS values is that they are directly related to time series of service status and network condition and thus instantly vary over time. The main contribution of this paper is to consider service invocation time as a dynamic factor in the collaborative filtering model and recommend high-quality services for target user. In particular, this paper proposes a time-aware matrix factorization (TMF) model that integrates QoS time series to provide two-phase QoS predictions for cloud service recommendation. The TMF model uses an adaptive matrix factorization model on a sparse QoS dataset to predict the missing QoS values. A temporal smoothing method is then developed and applied to the predicted result to perform the time-varying QoS prediction that accounts for the dependence of QoS values at different time intervals. The numerical experiments presented are conducted to validate the accuracy of the proposed method on a public QoS dataset.

This paper proposed a clustering scheme named as the credit-based clustering (CBC) scheme for point of interests’ (POIs’) geo data sharing in vehicular social network (VSN). In the proposed CBC scheme, a number of vehicles that belong to the same VSN can form a cluster to download POIs’ geo data when they are approaching to a new set of POIs. One vehicle is selected as the cluster head to download POIs’ geo data using its cellular network and shares the downloaded POIs’ geo data to its cluster members using IEEE 802.11p network. This paper 1) uses GPS to get vehicles’ locations to calculate the timing of triggering the clustering process, 2) proposes a clustering method to organize a group of vehicles that belong to the same VSN and are proximate with each other for a while during their touring to become a cluster, and 3) deploys a credit scheme to evaluate the credit that the cluster head can get and each cluster member needs to pay to encourage all vehicles to share POIs’ geo data. The simulation results show that the proposed scheme can achieve the goal of fairness, the higher successful ratio of the complete sharing of downloaded POIs’ geo data and the better receiving efficiency.

This paper proposes a framework to improve the existing distortion functions designed for JPEG steganography, which results in a better capability of countering steganalysis. Different from the existing steganography approach that minimizes image distortion, we minimize the feature distortion caused by data embedding. Given a JPEG image, we construct a reference image close to the image before JPEG compression. Guided by both the reference image and the feature distortion minimization, the state-of-the-art distortion functions designed for syndrome trellis coding embedding are improved by distinguishing the embedding costs for +1 versus -1 embedding. This paper has three contributions. First, the proposed framework outperforms the traditional, since we use the constructed reference image and the public steganalytic knowledge for data embedding. Second, the proposed framework is universal for improving distortion functions that were designed for JPEG steganography. Finally, experimental results also prove that the proposed approach has a better undetectability when examined by modern steganalytic tools.

In recent years, different types of review systems have been developed with the recommender system (RS). RSs are developed based on user textual reviews, ratings, and comparative opinions. RSs for social media resources, such as blogs, forums, social network websites, social bookmarking websites, video portals, and chat portals help users to collaborate effectively. Social media resources are used in the RS for recommending contents, articles, news, e-commerce products, and users. Although research on social media in RSs has increased annually, comprehensive literature review and classification of these RS studies are limited and must, therefore, be improved. This paper aims to provide a comprehensive review of the social media RS on research articles published from 2011 to 2015 by exploiting a methodological decision analysis in six aspects, including recommendation approaches, research domains, and data sets used in each domain, data mining techniques, recommendation type, and the use of performance measures. A total of 61 articles are reviewed among the initial 434 articles on RS research published in Web of Science and Scopus between 2011 and 2015. To accomplish the aim of this paper, a comprehensive review and analysis was performed on extracted articles to explore various recommendation approaches which are used in the RS. In addition, various social media domains are identified, where RSs have been employed. In each identified domain, publicly available data sets are also reported. Furthermore, various data mining techniques, recommendation types, and performance measures are also analyzed and reviewed in technical aspects. Finally, potential open research directions are also presented for future researchers intended to work in social media RS domain.

Secure patterns provide a solution for the security requirement of the software. There are large number of secure patterns, and it is quite difficult to choose an appropriate pattern. Moreover, selection of these patterns needs security knowledge; generally, developers are not specialized in the domain of security knowledge. This paper can help in the selection of secure pattern on the basis of tradeoffs of the secure pattern using text categorization. A repository of secure design patterns is used as a data set and a repository of requirements artifacts in the form of software requirements specification (SRS) are used for this paper. A text categorization scheme, which begins with preprocessing, indexing of secure patterns, ends up by querying SRS features for retrieving secure design pattern using document retrieval model. For the evaluation of the proposed model, we have used three different domains’ SRS. These three SRS documents represent three different domains, i.e., e-commerce, social media, and desktop utility program. A traditional precision and recall method along with F-measure used for evaluation of information/document retrieval model is used to evaluate the results. F-measure for 17 different design problems shows around 81% accuracy with recall up to 0.69%.

Learning from imbalanced data is a challenging task in the fields of machine learning and data mining. As an effective and efficient solution, cost-sensitive learning has been widely adopted to address class imbalance learning (CIL) problems. Weighted extreme learning machine (WELM), which is constructed based on ELM, is a significant member in the cost-sensitive-learning algorithmic family. WELM can effectively deal with CIL problems. However, it has two main drawbacks: 1) it has high time complexity on large-scale data since a large-matrix multiplication operation is required in the solution procedure and 2) it lacks flexibility since it can only tune the training error for each instance and not for each class label. In this paper, we present an alternative to WELM, which is called label-WELM (LW-ELM). Unlike WELM, LW-ELM copes with CIL problems by tuning the training error of each class label. Specifically, the expected output (or training class label) that corresponds to the minority class is augmented, thereby providing stronger tolerance to training errors of the minority-class instances. In this paper, we design two types of weight allocation strategies, both of which are based on the class-imbalance ratio (CIR). In contrast with WELM, LW-ELM is fast and flexible, where fast means that it has low-time complexity and flexible indicates that it can also be used to tackle imbalanced multi-label learning problems, while WELM cannot. The experimental results on binary-class, multiclass, and multi-label data sets with skewed class distributions show the effectiveness and superiority of the proposed LW-ELM algorithm.

Nowadays research is heading towards the integration of cloud computing and Internet of Things thus creating a Cloud of Things (CoT). This combination generates a new paradigm for pervasive and ubiquitous computing. However, reliable CoT-based services, particularly, highly delay-sensitive services, such as, healthcare, require energy-efficient CoT architectures. Considerable efforts have been proposed to improve the efficiency of CoT architectures. This paper analyses CoT architectures and platforms, as well as the implementation of CoT in the context of smart healthcare. Subsequently, the paper explains some related issues of CoT, including the lack of standardization. Moreover, it focuses on energy efficiency with an in depth analysis of the most relevant proposals available in the literature. An evaluation of all the energy efficiency solutions investigated in this paper shows there is still a need to improve energy efficiency, especially regarding QoS and performance.

Due to the monumental growth of Internet applications in the last decade, the need for security of information network has increased manifolds. As a primary defense of network infrastructure, an intrusion detection system is expected to adapt to dynamically changing threat landscape. Many supervised and unsupervised techniques have been devised by researchers from the discipline of machine learning and data mining to achieve reliable detection of anomalies. Deep learning is an area of machine learning which applies neuron-like structure for learning tasks. Deep learning has profoundly changed the way we approach learning tasks by delivering monumental progress in different disciplines like speech processing, computer vision, and natural language processing to name a few. It is only relevant that this new technology must be investigated for information security applications. The aim of this paper is to investigate the suitability of deep learning approaches for anomaly-based intrusion detection system. For this research, we developed anomaly detection models based on different deep neural network structures, including convolutional neural networks, autoencoders, and recurrent neural networks. These deep models were trained on NSLKDD training data set and evaluated on both test data sets provided by NSLKDD, namely NSLKDDTest+ and NSLKDDTest21. All experiments in this paper are performed by authors on a GPU-based test bed. Conventional machine learning-based intrusion detection models were implemented using well-known classification techniques, including extreme learning machine, nearest neighbor, decision-tree, random-forest, support vector machine, naive-bays, and quadratic discriminant analysis. Both deep and conventional machine learning models were evaluated using well-known classification metrics, including receiver operating characteristics, area under curve, precision-recall curve, mean average precision and accuracy of classification. Experimental results of deep IDS models showed promising results for real-world application in anomaly detection systems.

Many real world decision making problems often involve uncertainty data, which mainly originating from incomplete data and imprecise decision. The soft set theory as a mathematical tool that deals with uncertainty, imprecise, and vagueness is often employed in solving decision making problem. It has been widely used to identify irrelevant parameters and make reduction set of parameters for decision making in order to bring out the optimal choices. In this paper, we present a review on different parameter reduction and decision making techniques for soft set and hybrid soft sets under unpleasant set of hypothesis environment as well as performance analysis of the their derived algorithms. The review has summarized this paper in those areas of research, pointed out the limitations of previous works and areas that require further research works. Researchers can use our review to quickly identify areas that received diminutive or no attention from researchers so as to propose novel methods and applications.

Social networking has become part of our life in recent years, allowing users to converse and connect with people sharing similar interests in real world. However, networking via the social media suffers from serious privacy issues, and one of which is profile attribute leakage in friend discovery. While existing studies mainly focus on leveraging rich cryptographic algorithms to prevent privacy leak, we propose a novel perturbation-based private profile matching mechanism by mixing the private data with random noise to preserve privacy in this paper. In this paper, we consider the case where the profiles are fine-grained, meaning that each attribute is associated with a user-specific numerical value to indicate the level of interest. By carefully tuning the amount of information owned by each party, we guarantee that privacy is effectively preserved while the matching result of users’ profiles can be cooperatively obtained. We first give an introduction to a basic scheme, then detail two improved ones by, respectively, taking collusion attack and verifiability into consideration. As no expensive encryption algorithms get involved, our methods are computationally efficient; thus they are more practical for real-world applications. Theoretical security analysis as well as comparison-based simulation studies are carried out to evaluate the performance of our designs.