Search

The present work develops a novel hybrid method for ocular and muscular artifact removal from electroencephalography (EEG) signals, EFICA-TQWT. It is a combination of efficient fast independent component analysis (EFICA) method with the tunable Q-factor wavelet transform (TQWT). The main contribution of this paper is to apply the 3D interpolation method in the filtering system. Three EEG datasets are used in this work, two healthy and one epileptic. The choice of subjects for each dataset is made with the help of an expert in physiology. The selection criterion adopted is the presence of muscular and ocular artifacts in the processed recordings. First, a noisy channel automatic classification is performed by the support vector machine (SVM) with radial basis function in order to delete the signal(s) corresponding to the noisiest channel(s) from each EEG recording. The results of the automatic classification by the SVM were compared with those found by the expert's classification. An accuracy of 97.45%, a sensitivity of 86.66% and a 100% specificity are provided by the SVM classification. The hybrid method of artifact removal will be applied on the rest of the EEG channels of international 10/20 system for each subject. Then, a reconstruction of the eliminated channel signal(s) will be performed in order to obtain a well-filtered signal. The proposed filtering process is evaluated by calculating the mean squared error (MSE) and the signal to noise ratio (SNR). Both for the healthy and pathological EEG datasets, a comparative study of the proposed method (EFICA-TQWT) and other filtering techniques (Fast-ICA, DWT, TQWT and EFICA) is generated. The EFICA-TQWT method gave the best results with a minimum of MSE and a maximum of SNR, more particularly in the case of the application of the 3D interpolation method. Besides, in order to optimize the computing time of the proposed system, a parallel implementation of this filtering system is developed based on graphical processing units using compute unified device architecture. [ABSTRACT FROM AUTHOR]

In multiple-input multiple-output (MIMO), millimeter wave (mmWave) is considered as a promising technology for advanced communication over wireless networks due to its rich frequency spectral resources. However, recognizing the mmWave in MIMO remains a complex task that faces the issues like increased propagation loss. Therefore, this paper proposes a new optimization-assisted estimation algorithm to estimate the mmWave channel parameters. The channel estimation and hybrid precoding performance on mmWave massive MIMO system are proposed by adopting optimization process in the codebook design principles. In fact, the existing works have performed uniform distribution of azimuth angles in the codebook design, whereas the proposed work evaluates it as a single objective optimization problem without excluding the angle characteristics. In order to solve the mentioned optimization problem, dragonfly-evaluated gray wolf optimization (DA-GWO) model is introduced that hybridizes the concepts of dragonfly algorithm and GWO, respectively. Finally, the performance of proposed work is compared and validated over other state-of-the-art models with respect to channel state information and error measures. Accordingly, from the analysis, the proposed DA-GWO model concerning (64, 64) combination for 400th channel bandwidth is 80% and 95.53% superior to adaptive channel estimation and projected gradient factorization algorithms. [ABSTRACT FROM AUTHOR]

A new model of computation called Watson–Crick jumping finite automata was introduced by Mahalingam et al. , and the authors study the computing power and closure properties of the variants of the model. There are four variants of the model: no state, 1-limited, all-final and simple Watson–Crick jumping finite automata. In this paper, we introduce a restricted version that is a combination of variants of the existing model. It becomes essential to explore the computing power and closure properties of these combinations. The combination variants are extensively compared with Chomsky hierarchy, general jumping finite automata family and among themselves. We also explore the closure properties of such restricted automata. [ABSTRACT FROM AUTHOR]

The diagnosability is one of the most important measures of the reliability of networks. Consider the setting where there are large-scale failures that disconnect the network and result in many components. Then, the diagnosability is closely related to the number of components. In this paper, we define and study the |$\boldsymbol{g}$| -component diagnosability of network |$\boldsymbol{G}$|⁠ , which is denoted by |$\boldsymbol{ct_g(G)}$| and has not been addressed before. |$\boldsymbol{ct_g(G)}$| is the maximum number of nodes in the faulty node set |$\boldsymbol{F}$| of |$\boldsymbol{G}$| such that |$\boldsymbol{G-F}$| has at least |$\boldsymbol{g}$| components and diagnosis model can identify all nodes in |$\boldsymbol{F}$|⁠. Under PMC and MM |$^*$| diagnosis models, we show that, in the hypercube |$\boldsymbol{Q_n\ (n\geq 7)}$|⁠ , |$\boldsymbol{ct_{g+1}(Q_n)=-(1/2)g^2+(n-3/2)g+n}$| when |$\boldsymbol{g\leq n-1}$|⁠. Moreover, we determine the |$\boldsymbol{(n+1)}$| -component diagnosability |$\boldsymbol{ct_{n+1}(Q_n)=n^2/2+n/2-2}$| for |$\boldsymbol{n\geq 7}$|⁠. [ABSTRACT FROM AUTHOR]

Today, automated extractive text summarization is one of the most common techniques for organizing information. In extractive summarization, the most appropriate sentences are selected from the text and build a representative summary. Therefore, probing for the best sentences is a fundamental task. This paper has coped with extractive summarization as a multi-objective optimization problem and proposed a language-independent, semantic-aware approach that applies the harmony search algorithm to generate appropriate multi-document summaries. It learns the objective function from an extra set of reference summaries and then generates the best summaries according to the trained function. The system also performs some supplementary activities for better achievements. It expands the sentences by using an inventive approach that aims at tuning conceptual densities in the sentences towards important topics. Furthermore, we introduced an innovative clustering method for identifying important topics and reducing redundancies. A sentence placement policy based on the Hamiltonian shortest path was introduced for producing readable summaries. The experiments were conducted on DUC2002, DUC2006 and DUC2007 datasets. Experimental results showed that the proposed framework could assist the summarization process and yield better performance. Also, it was able to generally outperform other cited summarizer systems. [ABSTRACT FROM AUTHOR]

Software-defined Network (SDN) is a new networking paradigm enabling innovation through network programmability. Over past few years, many applications have been built using SDN such as server load balancing, virtual-machine migration, traffic engineering and access control. In this paper, we focus on using SDN for energy-aware routing (EAR). Since traffic load has a small influence on the power consumption of routers, EAR allows putting unused links into sleep mode to save energy. SDN can collect traffic matrix and then computes routing solutions satisfying QoS while being minimal in energy consumption. However, prior works on EAR have assumed that the SDN forwarding table switch can hold an infinite number of rules. In practice, this assumption does not hold since such flow tables are implemented in Ternary Content Addressable Memory (TCAM) which is expensive and power hungry. We consider the use of wildcard rules to compress the forwarding tables. In this paper, we propose optimization methods to minimize energy consumption for a backbone network while respecting capacity constraints on links and rule space constraints on routers. In details, we present two exact formulations using Integer Linear Program (ILP) and introduce efficient heuristic algorithms. Based on simulations on realistic network topologies, we show that using this smart rule space allocation, it is possible to save almost as much power consumption as the classical EAR approach. [ABSTRACT FROM AUTHOR]

Analyzing the survivability of a cloud service is critical as the application or service migration from local to cloud is an irresistible trend. However, former research on cloud service or virtual system (VS) availability and/or reliability was only carried out from the perspective of steady state. This paper aims to analyze the survivability of the cloud service after a service breakdown occurrence by presenting a model and the closed-form solutions with the use of continuous-time Markov chain. The service breakdown may be caused by virtual machine (VM) and/or VM monitor (VMM) bugs or software rejuvenation and/or host failures and NAS (Network Area Storage) failures. In order to improve the cloud service survivability, the VS applies two techniques: VM failover and VM live-migration. Through the model proposed and the survivability metrics defined in this paper, we are able to quantitatively assess the system survivability while providing insights into the investment efforts in system recovery strategies. In order to study the impact of key parameters on system survivability, this paper also provides a parameter sensitivity analysis through numerical experiments. [ABSTRACT FROM AUTHOR]

A Watson–Crick (WK) context-free grammar, a context-free grammar with productions whose right-hand sides contain nonterminals and double-stranded terminal strings, generates complete double-stranded strings under Watson–Crick complementarity. In this paper, we investigate the simplification processes of Watson–Crick context-free grammars, which lead to defining Chomsky-like normal form for Watson–Crick context-free grammars. The main result of the paper is a modified CYK (Cocke–Younger–Kasami) algorithm for Watson–Crick context-free grammars in WK-Chomsky normal form, allowing to parse double-stranded strings in O (n 6) time. [ABSTRACT FROM AUTHOR]

The decision of migrating a service to a cloud-based system must take into consideration many different aspects. Among them, economical costs is one of the most important. This paper describes how a computing-intensive service, based on a bag-of-tasks approach, has been migrated from a grid infrastructure to the Amazon Elastic Compute Cloud (EC2) infrastructure. A cost-based model for the evaluation of the economic costs of providing the service on the cloud has also been proposed, which considers computing costs as well as storage and platform deployment costs. The model includes a wide range of different instance types and purchasing policies provided by the Amazon EC2, as well as the deadline and problem size provided by the service user. The paper also shows how the proposed cost-based model is integrated into the framework used for the service deployment and execution, making possible the interaction with the Amazon Web services for hiring the required cloud resources and efficiently use them for the execution of the service requests. [ABSTRACT FROM AUTHOR]

This paper deals with the identification of fractures in CT scan images. A large amount of significant and critical information are normally stored in medical data. Highly efficient and automated computational methods are needed to process and analyze all available data in order to help the physician in diagnosis, decisions and treatment planning. Each CT scan includes a large number of slices. In this paper, a new hierarchical segmentation algorithm is applied to all slices; it automatically extracts the bone structures using HMRF_EM segmentation method. The template-matching technique is employed to extract the affected portion. This new approach is experimented with eight patients' data and validated by radiologists. The performance of the work is analyzed and compared with recent works using sensitivity, specificity and accuracy. [ABSTRACT FROM AUTHOR]

This paper studies Bounded Model Checking (BMC) of invariant properties on compositional systems. To alleviate the path explosion problem resulting from interleaving, an ideal approach is to let the system execute in true-concurrency. However, since it is difficult for the true-concurrency execution manner to obtain all reachable global states, this technique has been rarely employed to verify those properties requiring to check all reachable global states-such as invariant properties. Verification of such properties still adheres to the interleaving semantics. Observed that even for properties such as invariants, it is possible to verify them via checking only a fraction of the global states, this paper presents a true-concurrency encoding for invariant property verification of compositional systems. The crucial innovation is a macro-step technique, which executes a sequence of consecutive transitions in true-concurrency. With this technique, we are able to (1) significantly reduce the exponential number of paths due to interleaving and (2) greatly cut down the number of SAT calls required for BMC to verify the property. Experimental results of real problems show speed increases from 4.8 to 2957 times that of the standard verification method. [ABSTRACT FROM AUTHOR]

As a basic and important primitive, hash proof system can be used to construct many cryptographic schemes and protocols. Therefore, it is significant to instantiate more efficient hash proof systems from various assumptions. Although there are many hash proof systems based on various classical assumptions, only a handful of efficient hash proof systems are known based on post-quantum assumptions. In this paper, we present several new hash proof systems based on the standard learning with errors (LWE) problem, which is at least as hard as standard worst-case lattice problems. Comparing with other existing constructions based on lattices, our main advantages are 2-fold: much simpler and more efficient. And our constructions can be easily extended to be identity-based ones and updatable ones. Throughout the paper, our main idea is to base hash proof systems on a new subset indistinguishability problem related to LWE, and employ the property of smooth parameter of q-ary orthogonal lattices to ensure smoothness. [ABSTRACT FROM AUTHOR]

This paper considers a practical crowd-outsourcing system model for location-based services which has become increasingly popular due to the rapid proliferation of location-aware mobile devices. In our system, multiple data owners (DOs) outsource their small number of points of interests (POIs) to the location-based service provider (LBSP), then LBSP manages these POIs datasets and allows users to share information and perform top- k queries according to their own preferences. One crucial problem in this system is how to deal with the untrusted LBSP, who may return fake or incorrect query results to users for certain motives. However, the traditional top- k query and verification schemes, where only an individual DO and a single query attribute are considered, cannot be efficiently applied to our system, as users have distinct query preferences and the query may involve multiple DOs. In this paper, we design a dominant authentication graph DAUG) to process the multi-attribute data on multiple datasets efficiently, and two schemes are proposed for users to verify the integrity of the query result based on DAUG. Finally, theoretical analysis and simulation results show our superiority to the previous scheme in terms of effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we study a new type of indoor queries, called the indoor trip planning query (iTPQ). We have observed that the existing methods for outdoor spaces cannot be applied directly to indoor spaces, due to the difference in the underlying networks. Outdoor spaces, which are normally represented as spatial road networks, are commonly modelled as a graph. In contrast, indoor spaces have distinct features (e.g. rooms, doors, hallways) that do not exist in road networks. So far, no specific solutions have been proposed for iTPQ. Even if outdoor techniques are revised for iTPQ, they fail to process iTPQ efficiently. In this paper, we propose an indoor-specific technique, based on the indoor VIP-Tree, called the VIP-Tree neighbor expansion (VNE) method, that also includes new pruning techniques in both pre-processing and query processing phases. Our experimental results show that our proposed method VNE outperforms other indoor and outdoor algorithms by several orders of magnitude in terms of processing time with low indexing cost. [ABSTRACT FROM AUTHOR]

Legal Services industries are entering a period of major disruption caused by new legal technologies (LawTech), such as artificial intelligence (AI), Internet of Things (IoT) and Blockchain. An area already undergoing major innovation is alternative dispute resolution (Alternative Dispute Resolution (2017) Wikipedia, https://en.wikipedia.org/wiki/Alternative_dispute_resolution), especially automated online dispute resolution (Online Dispute Resolution (2017) Wikipedia, https://en. wikipedia.org/wiki/Online_dispute_resolution; Katsh, E. and Rifkin, J. (2001) Online Dispute Resolution: Resolving Conflicts in Cyberspace. Jossey-Bass Wiley, New Jersey). In terms of LawTech, we broadly divide online dispute resolution into (a) Consumer ODR--uses technology to facilitate the resolution of disputes between ecommerce parties, typically online suppliers and consumers; (b) Judicial ODR--covers any means of settling 'ordinary' disputes where there is a hearing (using technology) but outside of the courtroom, such as divorce or personal injury cases; and what we refer to as (c) Corporate ODR--the use of technology to manage the resolution of any contractual disputes that may emerge from major multi-partner projects or financial transactions. This paper focuses on ODR and specifically the future use of automating anticipatory Corporate dispute resolution using AI and blockchain technologies. The paper describes the legal sector, and how it is being radically transformed by computer science. [ABSTRACT FROM AUTHOR]

Process mining has been around for more than a decade now, and, in that period, several discovery algorithms have been introduced that work fairly well on average-sized event logs, that is, event logs that contain ~50 different activities. Nevertheless, these algorithms have problems dealing with big event logs, that is, event logs that contain 200 or more different activities. For this reason, a generic approach has been developed which allows such big problems to be decomposed into a series of smaller (say, average-sized or even smaller) problems. This approach offers formal guarantees for the results obtained by it and makes existing algorithms also tractable for larger logs. As a result, discovery problems may become feasible, or may become easier to handle. This paper introduces a tool framework, called Divide And Conquer that fully supports this generic approach and that has been implemented in ProM 6. Using this novel framework, this paper demonstrates that significant speed-ups can be achieved for discovery. This paper also discusses the fact that decomposition may lead to different results, but that this may even turn out to have a positive effect. [ABSTRACT FROM AUTHOR]

Homomorphic message authentication codes (MACs) allow a user to outsource data to an untrusted server and verify the correctness of returned computation results over the outsourced data. Many cloud applications need delegation computations over outsourced data with dual capabilities. On one hand, they need to keep the outsourced data secret such that the server cannot trace and infer any sensitive information from the computation results. On the other hand, the user should be able to efficiently verify the computation results. Unfortunately, the state-of-the-art homomorphic MAC schemes are not so desirable due to either poor privacy or low verification efficiency. In this paper, we first put forward a new cryptographic primitive called privacy-preserving homomorphic MACs (PHMAC) that simultaneously provides data privacy and efficient verification. Then, we present a PHMAC construction capable for the evaluation of polynomials of fixed degree |$d\geq 1$|⁠ , in which the tag does not reveal any information of underlying authenticated data while being verifiable in constant time (in an amortized sense). As an application, we give a generic construction of homomorphic authenticated encryption (HAE) from proposed PHMAC and homomorphic encryption. Benefited from the functionalities of underlying PHMAC scheme, the derived HAE enjoys stronger authenticity and supports larger classes of functions than that of Lai et al. (Verifiable Computation on Outsourced Encrypted Data. In Computer Security—ESORICS 2014—19th European Symposium on Research in Computer Security , Wroclaw, Poland, September 7–11, Part I, pp. 273–291. Springer, Berlin). Such HAE enables verifiable delegation computations over growing outsourced encrypted data in an efficient way. [ABSTRACT FROM AUTHOR]

Saliency detection has been a hot topic in the field of computer vision. In this paper, we propose a novel approach that is based on multiscale segmentation and fuzzy broad learning. The core idea of our method is to segment the image into different scales, and then the extracted features are fed to the fuzzy broad learning system (FBLS) for training. More specifically, it first segments the image into superpixel blocks at different scales based on the simple linear iterative clustering algorithm. Then, it uses the local binary pattern algorithm to extract texture features and computes the average color information for each superpixel of these segmentation images. These extracted features are then fed to the FBLS to obtain multiscale saliency maps. After that, it fuses these saliency maps into an initial saliency map and uses the label propagation algorithm to further optimize it, obtaining the final saliency map. We have conducted experiments based on several benchmark datasets. The results show that our solution can outperform several existing algorithms. Particularly, our method is significantly faster than most of deep learning-based saliency detection algorithms, in terms of training and inferring time. [ABSTRACT FROM AUTHOR]

Cloud computing (CC) is a complete online system of specialized technical resources for data computing and storage management. Many organizations, including small and start-ups, have recommended using CC technology rather than building their own high-costed data centers. Due to the diversity of cloud service providers, identifying appropriate cloud services that can meet users' and organizations' requirements, including trust, is a major challenge. In this paper, we propose a trust framework utilization to evaluate cloud services trust using multi-criteria decision-making and fuzzy logic techniques from different perspectives based on performance, agility, finance, security and usability criteria. The comparison of obtained results with related ones shows that ours are efficient and promising decisions for cloud users and organizations as well. [ABSTRACT FROM AUTHOR]

This paper plans to develop the optimal brain tumor classification model with diverse intelligent methods. The main phases of the proposed model are '(a) image pre-processing, (b) skull stripping, (c) tumor segmentation, (d) feature extraction and (e) classification'. At first, pre-processing of the image is performed by converting the image from red green blue to gray followed by median filtering. Further, skull stripping is done for removing the extra-meningeal tissue from the head image, which is done by Otsu thresholding. As the main contribution, the tumor segmentation is done by the optimized threshold-based tumor segmentation using multi-objective randomly updated beetle swarm and multi-verse optimization (RBS-MVO). The objective constraints considered for the segmentation of the tumor is entropy and variance. Next, the feature extraction techniques like gray level co-occurrence matrix, local binary pattern and gray-level run length matrix is accomplished to extract the set of features. The classification side uses the combination of neural network (NN) and deep learning model called convolutional neural network (CNN) for tumor classification. The extracted features are subjected to NN, and the segmented image is taken as input to CNN. In addition, the weight function of NN and hidden neurons of CNN is optimized by the RBS-MVO. [ABSTRACT FROM AUTHOR]

This paper presents comparative evaluation of an application of deep convolutional neural networks (dCNNs) to age invariant face recognition. To this end, we use four distinct dCNN models, the AlexNet, VGGNet, GoogLeNet and ResNet. We assess their performance to recognize face images across aging variations, firstly by fine-tuning the models and secondly using them as face feature extractor. We also suggest a novel synthesized aging augmentation technique suitable for age-invariant face recognition using dCNNs. The face recognition experiments are conducted on three challenging FG-NET, MORPH and LAG aging datasets, and results are benchmarked with a simple CNN. The comparative study allows us to answer (i) when and why transfer learning or feature extraction strategies are useful in age-invariant face recognition scenarios, (ii) the potential of aging synthesized augmentation to increase accuracy and (iii) the choice of appropriate feature normalization and distance metrics to be used with deeply learned features. The extensive experiments, and valuable insights presented in this study can be extended to the design of effective age-invariant face recognition algorithms. [ABSTRACT FROM AUTHOR]

Reliability evaluation of interconnection networks is of significant importance to the design and maintenance of interconnection networks. The component connectivity is an important parameter for the reliability evaluation of interconnection networks and is a generalization of the traditional connectivity. The |$g$| -component connectivity |$c\kappa _g (G)$| of a non-complete connected graph |$G$| is the minimum number of vertices whose deletion results in a graph with at least |$g$| components. Determining the |$g$| -component connectivity is still an unsolved problem in many interconnection networks. Let |$Q_{n,k}$| (⁠|$1\leq k\leq n-1$|⁠) denote the |$(n, k)$| -enhanced hypercube. In this paper, let |$n\geq 7$| and |$1\leq k \leq n-5$|⁠ , we determine |$c\kappa _{g}(Q_{n,k}) = g(n + 1) - \frac{1}{2}g(g + 1) + 1$| for |$2 \leq g \leq n$|⁠. The previous result in Zhao and Yang (2019, Conditional connectivity of folded hypercubes. Discret. Appl. Math. , 257 , 388–392) is extended. [ABSTRACT FROM AUTHOR]

Finding groups in networks is very common in many practical applications, and most work mainly focus on dense groups. However, in scenarios like reviewer selection or weak social friends recommendation, we need to emphasize the privacy of individuals or minimize the possibility of information dissemination. So the internal relationship between individuals should be as tenuous as possible, but existing works cannot suit well to the requirement. Some works have focused on finding tenuous groups. However, these works only aim to find the most tenuous group and do not consider containing certain vertices. In this paper, we study the problem of finding tenuous groups in attributed networks that contain specific vertices. We first propose a new problem called Tenuous Attributed Group Query, and a new indicator, k-tenuity, to measure the structural tenuity of a group. Then we propose a method TAG-Basic to find proper groups by gradually selecting the vertices with optimal influence. We further design an advanced method TAG-ADV to improve the efficiency by forming a candidate set before selecting the optimal vertex. Experiment results show that k-tenuity is more effective than other state-of-the-art measurements, and our methods obtain the best result on group quality compared with other benchmark methods. [ABSTRACT FROM AUTHOR]

The extensive usage of social media polarity analysis claims the need for real-time analytics and runtime outcomes on dashboards. In data analytics, only 30% of the time is consumed in modeling and evaluation stages and 70% is consumed in data engineering tasks. There are lots of machine learning algorithms to achieve a desirable outcome in prediction points of view, but they lack in handling data and their transformation so-called data engineering tasks, and reducing its time remained still challenging. The contribution of this research paper is to encounter the mentioned challenges by presenting a parallelly, scalable, effective, responsive and fault-tolerant framework to perform end-to-end data analytics tasks in real-time and batch-processing manner. An experimental analysis on Twitter posts supported the claims and signifies the benefits of parallelism of data processing units. This research has highlighted the importance of processing mentioned URLs and embedded images along with post content to boost the prediction efficiency. Furthermore, this research additionally provided a comparison of naive Bayes, support vector machines, extreme gradient boosting and long short-term memory (LSTM) machine learning techniques for sentiment analysis on Twitter posts and concluded LSTM as the most effective technique in this regard. [ABSTRACT FROM AUTHOR]

Super-resolution offers a new image with high resolution from the low-resolution (LR) image that is highly employed for the numerous remote sensing applications. Most of the existing techniques for formation of the super-resolution image exhibit the loss of quality and deviation from the original multi-spectral LR image. Thus, this paper aims at proposing an efficient super-resolution method using the hybrid model. The hybrid model is developed using the support vector regression model and multi-support vector neural network (MSVNN), and the weights of the MSVNN is tuned optimally using the proposed algorithm. The proposed DolLion algorithm is the integration of the dolphin echolocation algorithm and lion optimization algorithm that exhibits better convergence and offers a global optimal solution. The experimentation is performed using the datasets taken from the multi-spectral scene images. The optimal and effective formation of the super-resolution image using the proposed hybrid model outperforms the existing methods, and the analysis using the second-derivative-like measure of enhancement (SDME) ensures that the proposed method is better and yields a maximum SDME of 67.6755 dB. [ABSTRACT FROM AUTHOR]

Local information has significant contributions to visual sentiment analysis (VSA). Recent studies about local region discovery need manually annotate region location. Affective local information learning and automatic discovery of sentiment-specific region are still the challenges in VSA. In this paper, we propose an end-to-end VSA method for weakly supervised sentiment-specific region discovery. Our method contains two branches: an automatic sentiment-specific region discovery branch and a sentiment analysis branch. In the sentiment-specific region discovery branch, a region proposal network with multiple convolution kernels is proposed to generate candidate affective regions. Then, we design the multiple instance learning (MIL) loss to remove redundant and noisy candidate regions. Finally, the sentiment analysis branch integrates both holistic and localized information obtained in the first branch by feature map coupling for final sentiment classification. Our method automatically discovers sentiment-specific regions by the constraint of MIL loss function without object-level labels. Quantitative and qualitative evaluations on four benchmark affective datasets demonstrate that our proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In the context of object detection, sliding-window classifiers and single-shot convolutional neural network (CNN) meta-architectures typically yield multiple overlapping candidate windows with similar high scores around the true location of a particular object. Non-maximum suppression (NMS) is the process of selecting a single representative candidate within this cluster of detections, so as to obtain a unique detection per object appearing on a given picture. In this paper, we present a highly scalable NMS algorithm for embedded graphics processing unit (GPU) architectures that is designed from scratch to handle workloads featuring thousands of simultaneous detections on a given picture. Our kernels are directly applicable to other sequential NMS algorithms such as FeatureNMS, Soft-NMS or AdaptiveNMS that share the inner workings of the classic greedy NMS method. The obtained performance results show that our parallel NMS algorithm is capable of clustering 1024 simultaneous detected objects per frame in roughly 1 ms on both Tegra X1 and Tegra X2 on-die GPUs, while taking 2 ms on Tegra K1. Furthermore, our proposed parallel greedy NMS algorithm yields a 14–40x speed up when compared to state-of-the-art NMS methods that require learning a CNN from annotated data. [ABSTRACT FROM AUTHOR]

Evaluating readability of web documents has gained attention due to several factors such as improving the effectiveness of writing and to reach a wider spectrum of audience. Current practices in this direction follow several statistical measures in evaluating readability of the document. In this paper, we have proposed a machine learning-based model to compute readability of web pages. The minimum educational standards required (grade level) to understand the contents of a web page are also computed. The proposed model classifies the web pages into highly readable, readable or less readable using specified feature set. To classify a web page with the aforementioned categories, we have incorporated the features such as sentence count, word count, syllable count, type-token ratio and lexical ambiguity. To increase the usability of the proposed model, we have developed an accessible browser extension to perform the assessments of every web page loaded into the browser. [ABSTRACT FROM AUTHOR]

Nowadays, mobile applications have been widely used in various health and social domains. While there are large number of smart devices that connect and transmit their context data in free manner, these mobile applications have limitations regarding the increasing number of heterogeneous context data sent by devices, conducting the problem of identifying user-centric situations and providing services in real-time. Many smart mobile health systems were proposed to ensure context-aware personal health monitoring and diseases detection, while most of them are failed to ensure a right level of dynamicity and enough flexibility for assisting users everywhere, anytime, through widespread sensors and mobile devices. In fact, it becomes necessary to rethink a new way to minimize the response time combining competitive agents with semantic-based situation reasoning strategy. In this paper, we introduce a novel agent-based platform with three-layered ontology for the semantic description and parallel management of services selection approach dedicated to context-aware health mobile applications. In addition, we propose an innovative parallel services discovery and optimal selection process, which involved a set of filtered and classified semantic health multipath according to user's context and preferences with consistent mobility of users and limited resources (low battery, processing capabilities, memory and others). Experimental results show the effectiveness of the proposed approach as it includes the semantic service information on cooperative agents. In addition, the proposed approach ensures fast response time and prolongs the continuity of the mobile application. [ABSTRACT FROM AUTHOR]

Existing iterative compilation and machine learning-based optimization techniques have been proven very successful in achieving better optimizations than the standard optimization levels of a compiler. However, they were not engineered to support the tuning of a compiler's optimizer as part of the compiler's daily development cycle. In this paper, we first establish the required properties that a technique must exhibit to enable such tuning. We then introduce an enhancement to the classic nightly routine testing of compilers, which exhibits all the required properties and thus is capable of driving the improvement and tuning of the compiler's common optimizer. This is achieved by leveraging resource usage and compilation information collected while systematically exploiting prefixes of the transformations applied at standard optimization levels. Experimental evaluation using the LLVM v6.0.1 compiler demonstrated that the new approach was able to reveal hidden cross-architecture and architecture-dependent potential optimizations on two popular processors: the Intel i5-6300U and the Arm Cortex-A53-based Broadcom BCM2837 used in the Raspberry Pi 3B+. As a case study, we demonstrate how the insights from our approach enabled us to identify and remove a significant shortcoming of the CFG simplification pass of the LLVM v6.0.1 compiler. [ABSTRACT FROM AUTHOR]

Step counting is not only the key component of pedometers (which is a fundamental service on smartphones), but is also closely related to a range of applications, including motion monitoring, behavior recognition, indoor positioning and navigation. Due to the limited battery capacity of current smartphones, it is of great value to reduce the energy consumption of such a popular service. Therefore, this paper focuses on the energy efficiency of step-counting algorithms. First of all, we formulate a theoretical error model based on the well-known auto-correlation coefficient step-counting (ACSC) algorithm, so as to analyze the factors affecting step-counting accuracy. And then, in light of this model and an adaptive sampling strategy, we propose a novel energy-efficient step-counting algorithm by adaptively substituting the computationally intensive auto-correlation with simple mean absolute deviation. On these grounds, an Android pedometer is implemented. Two individual experiments are carried out and verify both the theoretical error model and the proposed algorithm. It is shown that our algorithm outperforms two famous counterparts, i.e. the original ACSC algorithm and peak detection step-counting algorithm, in terms of both accuracy and energy efficiency. [ABSTRACT FROM AUTHOR]

As the size of a multiprocessor system grows, the probability that faults occur in this system increases. One measure of the reliability of a multiprocessor system is the probability that a fault-free subsystem of a certain size still exists with the presence of individual faults. In this paper, we use the probabilistic fault model to establish the subgraph reliability for |$AG_n$|⁠ , the |$n$| -dimensional alternating group graph. More precisely, we first analyze the probability |$R_n^{n-1}(p)$| that at least one subgraph with dimension |$n-1$| is fault-free in |$AG_n$|⁠ , when given a uniform probability of a single vertex being fault-free. Since subgraphs of |$AG_n$| intersect in rather complicated manners, we resort to the principle of inclusion–exclusion by considering intersections of up to five subgraphs and obtain an upper bound of the probability. Then we consider the probabilistic fault model when the probability of a single vertex being fault-free is nonuniform, and we show that the upper bound under these two models is very close to the lower bound obtained in a previous result, and it is better than the upper bound deduced from that of the arrangement graph, which means that the upper bound we obtained is very tight. [ABSTRACT FROM AUTHOR]

Dynamic frequency scaling (DFS) is one of the most important approaches for on-the-fly power optimization in modern-day processors. Owing to the trend of chip size shrinkage and increasing the complexity of system design, the problem of achieving an efficient DFS depends upon multi-parametric, non-linear optimization. Hence, it becomes extremely important to identify an optimal underclocking frequency on-the-fly, which depends upon numerous parameters that do not share direct relationship amongst each other. This paper proposes a machine learning approach to DFS of a ubiquitous single-core processor. Several performance parameters of the processor were monitored under an application of a number of clocking frequencies. The dataset thus generated was used to train four artificial neural networks (ANNs) viz. generalized regression (GRNN), decision tree classifier, random forest classifier and backpropagation technique. Under changing parametric conditions of the proposed network, the modes were fit to data while running three applications, i.e. 64- and 1024-point fast fourier transform (FFT) and basicmath applications. The performance of all ANNs was found to be promising and good generalization was obtained with all datasets. In the view of optimizing both speed and power of a system, the results indicate towards suitability of trained GRNN for on-chip deployment for implementing DFS. [ABSTRACT FROM AUTHOR]

The prevalence of short texts on the Web has made mining the latent topic structures of short texts a critical and fundamental task for many applications. However, due to the lack of word co-occurrence information induced by the content sparsity of short texts, it is challenging for traditional topic models like latent Dirichlet allocation (LDA) to extract coherent topic structures on short texts. Incorporating external semantic knowledge into the topic modeling process is an effective strategy to improve the coherence of inferred topics. In this paper, we develop a novel topic model—called biterm correlation knowledge-based topic model (BCK-TM)—to infer latent topics from short texts. Specifically, the proposed model mines biterm correlation knowledge automatically based on recent progress in word embedding, which can represent semantic information of words in a continuous vector space. To incorporate external knowledge, a knowledge incorporation mechanism is designed over the latent topic layer to regularize the topic assignment of each biterm during the topic sampling process. Experimental results on three public benchmark datasets illustrate the superior performance of the proposed approach over several state-of-the-art baseline models. [ABSTRACT FROM AUTHOR]

In this paper, we present a full-reference quality assessment metric based on the information of visual saliency. The saliency information is provided under the form of degrees associated to each vertex of the surface mesh. From these degrees, statistical attributes reflecting the structures of the reference and distorted meshes are computed. These are used by four comparisons functions genetically optimized that quantify the structure differences between a reference and a distorted mesh. We also present a statistical comparison study of six full-reference quality assessment metrics for 3D meshes. We compare the objective metrics results with humans subjective scores of quality considering the 3D meshes in one hand and the distorsion types in the other hand. Also, we show which metrics are statistically superior to their counterparts. For these comparisons we use the Spearman Rank Ordered Correlation Coefficient and the hypothetic test of Student (ttest). To attest the pertinence of the proposed approach, a comparison with a ground truth saliency and an application associated to the assessment of the visual rendering of smoothing algorithms are presented. Experimental results show that the proposed metric is very competitive with the state-of-the-art. [ABSTRACT FROM AUTHOR]

The subtree number index of a graph, defined as the number of subtrees, attracts much attention recently. Finding a proper algorithm to compute this index is an important but difficult problem for a general graph. Even for unicyclic and bicyclic graphs, it is not completely trivial, though it can be figured out by try and error. However, it is complicated for tricyclic graphs. This paper proposes path contraction carrying weights (PCCWs) algorithms to compute the subtree number index for the nontrivial case of bicyclic graphs and all 15 cases of tricyclic graphs, based on three techniques: PCCWs, generating function and structural decomposition. Our approach provides a foundation and useful methods to compute subtree number index for graphs with more complicated cycle structures and can be applied to investigate the novel structural property of some important nanomaterials such as the pentagonal carbon nanocone. [ABSTRACT FROM AUTHOR]

At present, the tactile perception of 3D geometric bumps (such as sinusoidal bumps, Gaussian bumps, triangular bumps, etc.) on touchscreens is mainly realized by mapping the local gradients of rendered virtual surfaces to lateral electrostatic friction, while maintaining the constant normal feedback force. The latest study has shown that the recognition rate of 3D visual objects with electrovibration is lower by 27 |$\%$| than that using force-feedback devices. Based on the custom-designed tactile display coupling with electrovibration and mechanical vibration stimuli, this paper proposes a novel tactile rendering algorithm of 3D geometric bumps, which simultaneously generates the lateral and the normal perceptual dimensions. Specifically, a mapping relationship with the electrostatic friction proportional to the gradient of 3D geometric bumps is firstly established. Then, resorting to the angle between the lateral friction force and the normal feedback force, a rendering model of the normal feedback force using mechanical vibration is further determined. Compared to the previous works with electrovibration, objective evaluations with 12 participants showed that the novel version significantly improved recognition rates of 3D bumps on touchscreens. [ABSTRACT FROM AUTHOR]

Owing to the tremendous size of electronic biomedical documents, users encounter difficulties in seeking useful biomedical information. An efficient and smart access to the relevant biomedical information has become a fundamental need. In this research paper, we set forward a novel biomedical MeSH-based semantic indexing approach to enhance biomedical information retrieval. The proposed semantic indexing approach attempts to strengthen the content representation of both documents and queries by incorporating unambiguous MeSH concepts as well as the adequate senses of ambiguous MeSH concepts. For this purpose, our proposed approach relies on a disambiguation method to identify the adequate senses of ambiguous MeSH concepts and introduces four representation enrichment strategies so as to identify the best appropriate representatives of the adequate sense in the textual entities representation. To prove its effectiveness, the proposed semantic indexing approach was evaluated by intensive experiments. These experiments were carried out on OHSUMED test collection. The results reveal that our proposal outperforms the state-of-the-art approaches and allow us to highlight the most effective strategy. [ABSTRACT FROM AUTHOR]

In the current state of the video game productions, most of the video game levels are created by the human operators working as level designers. This manual process is not only time-consuming and resource-intensive but also hard to guarantee uniform quality in the contents created by the level designers. One way to address this issue is to use computer-assisted level design techniques. In this paper, we have proposed a novel framework for computer-assisted video game level design that leverages neural networks, particularly generative adversarial networks (GANs) and autoencoders. The general idea is to learn over a dataset of high-quality levels and subsequently improve the ones created by the level designers. The proposed method is independent of the graphical dimensionality of the game and will work for 2D and 3D games in general. The autoencoder is used to create an intermediate representation of the level that is itself changed using the backpropagation technique according to the feedback obtained by feeding the output of the autoencoder to the discriminator component of the GAN. After performing a series of evaluations on the proposed framework and by automatically improving a series of purposefully corrupted game levels, the results demonstrate a noticeable improvement compared with the usage of simple autoencoders used to improve the video game levels in the previous researches. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment is the problem of determining the likelihood of a landslide occurrence in a particular area with respect to the geographical and morphological properties of the area. This paper presents a hybrid method, namely SkySlide , that incorporates clustering, skyline operator, classification and majority voting principle for region-scale landslide susceptibility assessment. Clustering and skyline operator are utilized to model landslides while classification and majority voting principle are utilized to assess landslide susceptibility. The contribution of the study is 2-fold. First, the proposed method requires properties of landslide-occurring data only to model landslides. Second, the proposed method is evaluated on imbalanced data and experimental results include performance metrics of imbalanced data. Experiments conducted on two real-life datasets show that clustering greatly improves performance of SkySlide. Experiments further demonstrate that SkySlide achieves higher class balance accuracy, Matthews correlation coefficient, geometric mean and bookmaker informedness scores compared with the most commonly used methods for landslide susceptibility assessment such as support vector machines, logistic regression and decision trees. [ABSTRACT FROM AUTHOR]

Traffic accidents are a common problem in any transportation network. Road traffic accidents are predicted to be the seventh leading cause of deaths by the year 2030. Recently research in the integration of geographical information systems (GIS) for analyzing accidents, road design and safety management has increased considerably. The perpetual use of GIS tools, lead this study to propose the identification of accident hotspots by exploiting GIS technology coupled with kernel density estimation (KDE). This paper proposes the use of KDE technique and GIS technology to automatically identify the accident hotspots using UK as the study area. Analysis shows that most of the accidents occur when there is a 30 mph speed limit, a weekend, in the evening time, during the months of October and November, on the single carriageway, where there is 'T' or staggered junction and on 'A' road class. Moreover, this study also proposed techniques to classify the accident severity that is classified as either fatal, serious or slight. The driver behavior and environmental features achieved an accuracy up to 85% on the severity classification with Bagging technique. Further, the shortcomings, limitations and recommendations for future work are also identified. [ABSTRACT FROM AUTHOR]

Due to the rapid increase in the exchange of text information via internet networks, the security and the reliability of digital content have become a major research issue. The main challenges faced by researchers are authentication, integrity verification, and tampering detection of the digital contents. In this paper, a Robust English Text Watermarking and Natural Language Processing Approach (RETWNLPA) is proposed based on word mechanism and first level order of Markov model to improve the accuracy of tampering detection of sensitive English text. The RETWNLPA approach embeds and detects the watermark logically without altering the original text document. Based on the hidden Markov model (HMM), the first-level order of word mechanism is used to analyze the interrelationship between English text. The extracted features are used as watermark information and integrated with text zero-watermarking techniques. To detect eventual tampering, RETWNLPA has been implemented and validated with attacked English text. Experiments were performed on four datasets of varying sizes under random locations of common tampering attacks. The simulation results prove the tampering detection accuracy of our method against all kinds of tampering attacks. Comparison results show that RETWNLPA outperforms baseline approaches HNLPZWA (an intelligent hybrid of natural language processing and zero-watermarking approach) and ZWAFWMMM (Zero-Watermarking Approach based on Fourth level order of Word Mechanism of Markov Model) in terms of tampering detection accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, Cloud computing is a new computing model in the field of information technology and research. Generally, the cloud environment aims in providing the resource that depends upon the user's necessity. The major problem caused by cloud computing is task scheduling. Nevertheless, the previous scheduling methods concentrate only on the resource needs, memory, implementation time and cost. In this paper, we introduced an optimal task-scheduling algorithm of the local pollination-based moth search algorithm (LPMSA), which is the hybridization of moth search algorithm (MSA) and flower pollination algorithm (FPA). The proposed LPMSA chooses an optimal solution for proper task scheduling in the cloud. Moreover, the exploitation capacity of MSA is improved by using the local search of the FPA algorithm. In this work, we use 2-fold simulation processes that are implemented under the platform of JAVA. The proposed LPMSA for task-scheduling performance is evaluated using low and high heterogeneous machines with uniform and non-uniform parameters. The experimental analysis demonstrates that the proposed LPMSA approach is well suitable for cloud task scheduling thereby reducing the makespan and energy consumption during proper task scheduling. [ABSTRACT FROM AUTHOR]

Users of cloud computing technology can lease resources instead of spending an excessive charge for their ownership. For service delivery in the infrastructure-as-a-service model of the cloud computing paradigm, virtual machines (VMs) are created by the hypervisor. This software is installed on a bare-metal server, called the host, and acted as a broker between the hardware of the host and its VMs. The host is responsible for the allocation of required resources, such as CPU, RAM and network bandwidth, for VMs. Therefore, allocating resources to a VM is equivalent to finding the location of the VM on the hosts. In this paper, we propose a model for resource allocation of a datacenter that includes clusters of hosts. This model is based on the birth–death process of queueing systems and continuous-time Markov chains. We will focus on RAM-intensive VMs and consider the allocation of RAM for a VM as a job in the queueing systems. The purpose of this modeling is to keep the number of running hosts minimum while guaranteeing the quality of service in terms of response. When the utilization of active hosts reaches a predefined threshold value, a new host is added to prevent response time violation, and when host utilization is reduced to a certain threshold, one of the hosts can be deactivated. The experimental results show that, in the long run, the odds of working with more jobs are increased. [ABSTRACT FROM AUTHOR]

The visible blood vein in sclera has unique characteristics for each person, and it can be captured in visible light conditions. Therefore, the sclera vessels have been used as an important feature to improve the performance of identification recognition systems, for example, mobile payment and phone encryption system. But recent studies show that unsatisfactory sclera segmentation and tedious matching process are the two critical issues to degrade the performance of sclera identification system. In this paper, we propose a robust sclera recognition system with high accuracy and efficiency. First, a novel sclera segmentation method that provides adaptive threshold is proposed. Second, we have designed an improved vessels enhancement method based on the local grey distribution and local texture information, and least square linearization and moment invariants are utilized to extract features. Finally, an efficient matching strategy is put forward based on the detected significant vessels. The experimental results on one database with images captured in colour illumination prove that the proposed sclera recognition method has an obvious improvement regarding efficiency and accuracy over other sclera recognition systems. [ABSTRACT FROM AUTHOR]

It is a hot spot in the field of computer application to diagnose complex brain diseases such as Asperger syndrome (AS) using machine learning technology. To identify AS patients and detect lesions, this paper proposes a novel clustering-evolutionary random support vector machine (SVM) ensemble (CERSVME) based on graph theory. Firstly, we extract graph theory indexes from the resting-state functional magnetic resonance imaging (fMRI) data as sample features and construct an ensemble learner by integrating multiple SVM classifiers. Secondly, the base learners with high redundancy and poor classification ability are deleted through clustering evolutions to improve the performance of the model. Then the CERSVME model is used to classify fMRI image of AS patients and healthy controls. According to the classification results, a multi-stage analysis scheme is designed to find the AS-related brain areas. We validate the proposed approach on 135 participants from autism brain imaging data exchange cohort. The highest accuracy reported by the CERSVME reaches 95.24%. More importantly, the diseased brain areas such as middle frontal gyrus, hippocampus and precuneus are found based on their contributions to classification performances of the CERSVME. Our study provides useful assistances for the clinical detection of patients with AS. [ABSTRACT FROM AUTHOR]

Microaneurysm is a kind of small targets in color retinal image, and it is an essential work to recognize the small target for the early diagnosis of diabetic retinopathy. This paper proposes an efficient method to accurately recognize microaneurysm. A symmetric extended curvature Gabor wavelet is presented to generate candidate objects, where some novel features are extracted for classification. A kind of statistic features is generated to distinguish between microaneurysm and thin vessels, in terms of the shape similarity of cross-section profiles. Furthermore, the visual attention-based features are proposed to compute local contrast of small targets in complex background. Random undersampling with AdaBoost (RUSBoost) classifier is employed to discriminate true microaneurysm from an overwhelming amount of candidate objects. Experimental results demonstrate that the proposed method achieves significant sensitivity and accuracy on the public datasets, in comparison to the state-of-the-arts. [ABSTRACT FROM AUTHOR]

In this paper, we propose to overcome the challenge of digesting opinions in a news article. Our objective is to provide a summary of opinions delivered by many sources about a main topic in an Arabic news article. In literature, several studies addressed issues related to opinion summarization. However, we noticed a lack of studies that address this problem in Arabic language. So, we have proposed two different methods: multi-criteria and machine learning-based methods. We proceed by comparing the results provided by the proposed methods for opinionated sentence extraction. The proposed methods were evaluated using two feature types: text-based features and opinion-specific features. Experimental results show the robustness of machine learning method to extract opinionated sentences with consideration of two sets of features. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) emerged as a highly relevant signal to human emotion, brain diagnosing and brain–computer interfaces (BCI) applications. In this paper, the EEG signal is used to evaluate the cognitive response of subjects during watching test video clips. The measurements are performed with 25 subjects using eight channels while simultaneously running the video clips. The β and γ waves of the EEG signal are used to extract the features that represent the evoked activity in each group of frames using the Peak-Over-Threshold (POT) technique. Significant EEG patterns are derived from the time-correlated measurements, which can be related to the subjects' interests. In addition, the conjunctions that represent the occurrence of segments-of-interest in more than one channel are determined. The results show that ~15% of the segments attracted the attention of the viewers in each test video clip. Such a technique can potentially be implemented in neuromarketing analysis or to develop a new video compression technique that depends on the human cognitive system. [ABSTRACT FROM AUTHOR]

Perceptible visual tracking acts as an important module for distinct perception tasks of autonomous robots. Better features help in easier decision-making process. The evaluation of tracking objects, dynamic positions and their visual information in results are quite difficult tasks. Until now, most real-time visual tracking algorithms suffer from poor robustness and low occurrence as they deal with complex real-world data. In this paper, we have proposed more robust and faster visual tracking framework using scale invariant feature transform (SIFT) and the optical flow in belief propagation (BF) algorithm for efficient processing in real scenarios. Here, a new feature-based optical flow along with BF algorithm is utilized to compute the affine matrix of a regional center on SIFT key points in frames. Experimental results depict that the proposed approach is more efficient and more robust in comparison with the state-of-the-art tracking algorithms with more complex scenarios. [ABSTRACT FROM AUTHOR]