Integrating accurate resource usage prediction with cloud management systems is critical to optimize resource utilization and improve operational efficiency. The dynamic and non-linear usage patterns of resources in cloud data centers pose significant challenges for predictive modeling. Traditional single-output models, designed to predict a single value, often struggle to capture the complexities of series resource usage patterns. Current predictive models do not consider the interdependencies and interactions of various resource usage patterns in a sequence. Therefore, it is necessary to develop more robust predictive methods that can predict a series of resource usage patterns. This study introduces an innovative predictive model that uses multi-output regression combined with time series windowing, usage pattern clustering, and various transformation methods to predict a series of resource usage with high precision for heterogeneous cloud computing systems. Transformation methods include a power transformer to normalize the data distribution, a standard scaler to standardize the feature space, a polynomial transformation to enhance model complexity, and principal component analysis to reduce the dimensionality of the training feature space. The proposed model is evaluated using multi-output regression benchmarks with real cloud workloads and various evaluation metrics. The results demonstrated that the proposed approach significantly improves prediction accuracy while reducing training costs, offering substantial potential for improved performance and efficiency in cloud computing operations.

As the term implies, the main focus when designing security constrained systems is ensuring that the defined constraints are strictly adhered to. Developers of such systems must identify a balance between providing user and data security while also ensuring that the service's functionality is good. Extra security constraints can have a direct impact on other system aspects such as the communication between different devices especially in the emerging networking systems such as the Internet of Things and edge networking. In this work, we model and evaluate the main Internet of Things communication protocols including AMQP, CoAP, MQTT and XMPP in a security constrained system. We consider different evaluation metrics such the network utilization and success rate. Different protocols will react differently to the constrained security system but the increase in the communication latency is the common factor for all protocols.

Load prediction is a critical component of effective resource management in cloud computing. It ensures optimal performance and efficiency by anticipating overload, underload, and normal load periods. However, achieving accurate predictions remains challenging due to the highly dynamic and often non-linear workload patterns typical in cloud environments. Traditional methods, while helpful, have shown limitations in handling these complexities. Machine learning techniques, specifically imbalance and ensemble learning, have shown potential for improving prediction accuracy. Imbalance learning addresses the uneven distribution of load states, while ensemble learning combines multiple models to achieve better predictive performance. It is possible to create a more robust and accurate load prediction system by leveraging these two methods. This paper explores the application of imbalance and ensemble learning to improve load prediction in cloud computing systems. Through an experimental study, we illustrate how these techniques outperform traditional methods, offering potential improvements to the performance and efficiency of cloud computing operations.

Machine learning models, especially neural network (NN) classifiers, have shown tremendous potential of being used in complex tasks such as image classification, object detection and video analytics. However, to be adopted in the real-world applications, there are still problems to be answered. One of these problems is that training machine learning models, especially NN models, requires a certain level of computation and data processing. Other problems are the limited bandwidth of the network and the possibility of exposing the privacy of the users to attacks if the training data (specially video) is going to be transferred through the network. To mitigate these problems, researchers recently proposed the concept of federated learning.In this paper, we build a video analytic application for traffic management and train it using federated learning. More specifically, each traffic surveillance camera combined with its co-located small PC are seen as the worker node in federated learning. In this way, the NN model in each node can be trained on data collected from all nodes without transmitting and sharing with a central server, which resolves all of the above mentioned problems. The performance of the trained NN model is evaluated via experiments under different open sourced datasets to demonstrate that the proposed work has the potential to enhance the detection accuracy (mAP) over 40%.

The lack of security techniques that assures the integrity of data generated by the Internet of Things networks is one of the major stumbling blocks that hinders the whole development of these networks. As smart devices generate and transmit confidential and sensitive data, in these cases, data leakage can lead in many cases to drastic consequences. These types of attacks are called compromised attacks and the U2R and R2L subcategories are typical examples. Despite various intrusion detection systems designed for detecting compromised attacks, many of them are deficient and suboptimum due to the highly sophisticated behavior of these attacks that mimic normal ones, as well as the rarity of occurrence, and lack of training records keep this area inconclusive. Therefore, this paper presents an ensemble-based intrusion detection system to identify rare hard-to-detect attacks (U2R and R2L) in IoT networks. The ensemble is composed of two main tiers. Each tier consists of a major improved KNN classifier driven by multiple auxiliary classical KNN classifiers. the combined responses of these detection tires are fused to provide the optimal detection performance for minority attacks. The experimental analysis unveiled that the proposed system achieved a high detection accuracy reaches up to 96.65% and 100% for R2L and U2R respectively along with Cohen's kappa coefficient reaches up to 0.9778 and 0.996, which confirms the reliability and robustness of the proposed system to be deployed in loT networks.

Edge networking is poised to have a major impact in a number of fields, applications and services. In order to facilitate this, more advanced simulation will be necessary to model modern networked communication standards and develop edge computing frameworks which can take full advantage of the net-work's capabilities. PureEdgeSim is one such simulation system, which supports a high degree of modularity and extensibility. One extension is proposed and implemented here to add support to PureEdgeSim for 5G communication, based on parameter tuning derived from the technical specifications of 5G communication. The proposed extension of 5G communication is compared to the base with regards to task success rate, energy consumption, and network usage, and offers a difference in simulated performance consistent with expected 5G computing implementations. We used a lightweight machine earning applications like workload for experiments.

Abstract The release of millions of financial documents, which has been known as the ‘WikiLeaks’ of the financial world (a.k.a. ‘Panama Papers’), has dragged global attention in how highly structured means applied by some of the elite to conceal their financial assets. Consequently, significant financial corruption allegations were raised. We concentrate on a somewhat overlooked region, the Middle East and North Africa (MENA) region. This study aims to use social network analytics to study the information contained in these documents. We are checking the major players in the MENA’s trends and patterns to determine if it matches the known economic powers. The analysis reveals that while the constructed network enjoys some typical characteristics, many interesting observations and properties are worth discussing. Specifically, using the extracted network consisting of 62 987 nodes and 84 692 edges, our social network analysis finding shows that, perhaps surprisingly, the nodes or the social network are not necessarily directly correlated with perceived economic influence.

IP networks for live TV production have unique requirements such as the ultra high bandwidth and the high sensitivity to packet loss that causes video impairments. Existing multicast protocols are not bandwidth-aware and could cause links to over-subscribe leading to packet loss and negative user quality of experience. Existing video quality error detection tools are reactive by design with no insights into the video domain. In this paper, we introduceMediaFlow, a system for bandwidth aware multicast routing, active in-network detection of video errors, and proactive recovery.MediaFlowutilizes a novel greedy online multicast routing algorithm for efficient routing and admission control. It also introduces novel per-flow video quality metric utilizing unique switch ASIC capabilities for scalable in-network video quality monitoring and rerouting. We implementMediaFlowusing data center switches and our testing results confirm thatMediaFlowalgorithm increases fabric capacity up to 60% compared to state of art multicast routing.MediaFlowcan detect errors in video flow integrity at a granularity of 100 mSec at line rate for thousands of flows. The system can proactively recover impacted flows within 1 sec.MediaFlowincreases video detection and recovery scale by a thousandfold compared to network edge solutions.

Summary With the advent of Web 2.0, numerous collaborative annotation systems have been developed in an effort to enable distant users to annotate the same multimedia resources such as texts, audio, images, and videos. However, the existing systems do not support the semantic aspect of the data available on the Web and ignore the convergence aspect when executing concurrent annotations. Based on the technologies of Semantic Web, this article presents a new conflict‐free replicated data type called OAC‐Set, which extends Open Annotation Collaboration data model to enable concurrent annotations while guaranteeing convergence, causality, and intention preservation criteria. The experimental results show that our approach is efficient and effective.

Summary Graph‐based database engines have been developed by different researchers and companies. Many optimization methods have been integrated within these engines to enable fast and efficient data processing. However, many small‐ and medium‐size organizations have not changed their database infrastructures and still rely on a relational management modeling approach. This limits their service performance, especially in today's large‐scale data processing requirements. Transformation to the use of graph‐based modeling and design is not a straightforward process. In order to make a successful transformation, correct process semantics as well as the design of vertices, edges, labels, and process relations are required. The goal of this article is to help small‐ and medium‐size organizations make this transformation successful in order to satisfy customers' expectations and meet the requirements of data‐intensive applications. The proposed graph‐based modeling approach uses a graph structure for semantic queries and applies software engineering design principles. Moreover, it provides a case study with many data transactions. The system outperformed relational database management systems by an order of magnitude. Scalability of the system is examined and compared with the regular relational‐based modeling. In addition, a load balancing solution is used to achieve high scalability.

The industrial Internet of Things (IIoT) supports recent developments in data management and information services, as well as services for smart factories. Nowadays, many mature IIoT cloud platforms are available to serve smart factories. However, due to the semicredibility nature of the IIoT cloud platforms, how to achieve secure storage, access control, information update and deletion for smart factory data, as well as the tracking and revocation of malicious users has become an urgent problem. To solve these problems, in this article, a blockchain-enhanced security access control scheme that supports traceability and revocability has been proposed in IIoT for smart factories. The blockchain first performs unified identity authentication, and stores all public keys, user attribute sets, and revocation list. The system administrator then generates system parameters and issues private keys to users. The domain administrator is responsible for formulating domain security and privacy-protection policies, and performing encryption operations. If the attributes meet the access policies and the user's ID is not in the revocation list, they can obtain the intermediate decryption parameters from the edge/cloud servers. Malicious users can be tracked and revoked during all stages if needed, which ensures the system security under the Decisional Bilinear Diffie-Hellman (DBDH) assumption and can resist multiple attacks. The evaluation has shown that the size of the public/private keys is smaller compared to other schemes, and the overhead time is less for public key generation, data encryption, and data decryption stages.

The Fifth Generation (5G) communication technology has paved the way for intelligent and diversified Internet of Connected Vehicles (IoCV) services that meet stringent Quality of Service (QoS) requirements. Both Artificial Intelligence (AI) and Blockchain are playing and will continue to play an imperative role in providing secure and decentralized resource sharing to solve complex and time-sensitive problems at the edge. The integration of both those techniques will enhance the performance of smart vehicular services, especially in beyond 5G (B5G) networks. Ensuring secure transactions in complex autonomous network architectures is an immense challenge. This article addresses computational, storage, connectivity and intelligence concerns using a collaborative approach to engage multiple Internet of Things (IoT) nodes such as connected- vehicles, drones and mobile devices for the provisioning of QoS-optimal complex service compositions in autonomous mobile networks. Continuous and fast compositions emerge using decentralized decisions and interactions with diversified neighboring nodes with the aid of reinforcement learning. Blockchain is used to ensure that nodes interact with each other verifiably and record transactions without the need for trusted intermediaries. We assess whether having an AI-enabled blockchain collaborative composition solution improves service availability and delivery of smart city vehicular services.

The rise of fast communication media both at the core and at the edge has resulted in unprecedented numbers of sophisticated and intelligent wireless IoT devices. Tactile Internet has enabled the interaction between humans and machines within their environment to achieve revolutionized solutions both on the move and in real-time. Many applications such as intelligent autonomous self-driving, smart agriculture and industrial solutions, and self-learning multimedia content filtering and sharing have become attainable through cooperative, distributed, and decentralized systems, namely, volunteer computing. This article introduces a blockchain-enabled resource sharing and service composition solution through volunteer computing. Device resource, computing, and intelligence capabilities are advertised in the environment to be made discoverable and available for sharing with the aid of blockchain technology. Incentives in the form of on-demand service availability are given to resource and service providers to ensure fair and balanced cooperative resource usage. Blockchains are formed whenever a service request is initiated with the aid of fog and mobile edge computing (MEC) devices to ensure secure communication and service delivery for the participants. Using both volunteer computing techniques and tactile internet architectures, we devise a fast and reliable service provisioning framework that relies on a reinforcement learning technique. Simulation results show that the proposed solution can achieve high reward distribution, increased number of blockchain formations, reduced delays, and balanced resource usage among participants, under the premise of high IoT device availability.

Green Internet of things (GIoT) generally refers to a new generation of Internet of things design concept. It can save energy and reduce emissions, reduce environmental pollution, waste of resources, and harm to human body and environment, in which green smart device (GSD) is a basic unit of GIoT for saving energy. With the access of a large number of heterogeneous bottom-layer GSDs in GIoT, user access and control of GSDs have become more and more complicated. Since there is no unified GSD management system, users need to operate different GIoT applications and access different GIoT cloud platforms when accessing and controlling these heterogeneous GSDs. This fragmented GSD management model not only increases the complexity of user access and control for heterogeneous GSDs, but also reduces the scalability of GSDs applications. To address this issue, this article presents a blockchain-empowered general GSD access control framework, which provides users with a unified GSD management platform. First, based on the World Wide Web Consortium (W3C) decentralized identifiers (DIDs) standard, users and GSD are issued visual identity ( VID ). Then, we extended the GSD-DIDs protocol to authenticate devices and users. Finally, based on the characteristics of decentralization and non-tampering of blockchain, a unified access control system for GSD was designed, including the registration, granting, and revoking of access rights. We implement and test on the Raspberry Pi device and the FISCO-BCOS alliance chain. The experimental results prove that the framework provides a unified and feasible way for users to achieve decentralized, lightweight, and fine-grained access control of GSDs. The solution reduces the complexity of accessing and controlling GSDs, enhances the scalability of GSD applications, as well as guarantees the credibility and immutability of permission data and identity data during access.

Diversified Internet of Things services are becoming more complex and strictly user-defined. Traditional cloud solutions proved to be both costly in terms of resources and time efficiency. To overcome such a burden, researchers developed fog solutions for faster service responsiveness. Fog-to-Fog communication and cooperation was then introduced to compose services on-the-go for user-specific requests with the aid of mobile edge devices. This paper introduces a blockchain-based decentralized service composition solution for complex multimedia service delivery to cloud subscribers. The proposed work dynamically creates user-defined services without requiring any intermediary service or network provider entities to authenticate and deliver composite services. The composition process uses a reinforcement learning technique to construct secure and reliable composition paths. Participants are rewarded by cloud and fog entities for solving complex composition processes. Simulation results conducted on the system show that by adapting the proposed technique, fog and cloud entities require less resources and reduced power usage with increased service delivery success rates to cloud subscribers.

Providing an acceptable level of security for Internet of Things (IoT)-based critical infrastructures, such as the connected vehicles, considers as an open research issue. Nowadays, blockchain overcomes a wide range of network limitations. In the context of IoT and blockchain, Byzantine Fault Tolerance (BFT)-based consensus protocol, that elects a set of authenticated devices/nodes within the network, considers as a solution for achieving the desired energy efficiency over the other consensus protocols. In BFT, the elected devices are responsible for ensuring the data blocks’ integrity and preventing the concurrently appended blocks that might contain some malicious data. In this paper, we evaluate the fault-tolerance with different network settings, i.e., the number of connected vehicles. We verify and validate the proposed model with MATLAB/Simulink package simulations. The results show that our proposed hybrid scenario performed over the non-hybrid scenario taking throughput and latency in the consideration as the evaluated metrics.

Summary With mobile computing being the number one user paradigm of choice, and cloud computing becoming the chosen supporting infrastructure, the aggregation of these two areas is inevitable. Yet due to their novelty, they suffer from both inherited and new issues. Social computing theory can apply well to this fusion, such as pooling together in a social model to create ad hoc mobile clouds or by providing a greater functionality for mobile devices through resource augmentation from an external cloud. However, due to the highly contested resources within this setting, these resources must be negotiated within a social context. This paper argues that the application of social models to mobile cloud computing can allow mobile devices to employ cooperative strategies for resource sharing to allow aspects such as energy and costs to be minimised. Social computing is the means of using computing resources to augment human intelligence, mobiles can provide these enhancements to social intelligences but in a peer‐to‐peer manner. This paper proposes the design of a novel system which employs aggregated user and application resource profiling, in order to determine the most optimal place to process data, locally or on a remote cloud. Negotiation with the local cloud will then find a balance between optimum energy and resource utilisation.

Summary Classification and clustering techniques are used in different applications. Large‐scale big data applications such as social networks analysis applications need to process large data chunks in a short time. Classification and clustering tasks in such applications consume a lot of processing time. Improving the performance of classification and clustering algorithms enhances the performance of applications that use such type of algorithms. This paper introduces an approach for exploiting the graphics processing unit (GPU) platform to improve the performance of classification and clustering algorithms. The proposed approach uses two GPUs implementations, which are the pure GPU or GPU‐only implementation and the GPU‐CPU hybrid implementation. The results show that the hybrid implementation, which optimizes the subtask scheduling for both the CPU and the GPU processing elements, outperforms the approach that uses only the GPU.

Summary The growing popularity of Digital Social Networks (DSNs) among young students demands an introspection of its impact across different dimensions, such as students' academic performance and daily life. The results of the existing literature on the issue vary across societies due to differences in cultural and religious values. This research aims to examine the social network usage among students to analyze their bonding within their social and personal lives. As a case study, we selected Pakistani students as a convenient sample. Multiple social aspects like in‐person interaction of students with their family members, physical activities, religious knowledge, social capital, and level of students' trust in DSNs are considered. Considering the complex nature of the network, a Complex Adaptive System (CAS) approach is used to model the relationships between different nodes of the network. In addition, Linear Regression models are created to predict a node from the combination of different nodes based on their relationships.

Fog-to-fog communication has been introduced to deliver services to clients with minimal reliance on the cloud through resource and capability sharing of cooperative fogs. Current solutions assume full cooperation among the fogs to deliver simple and composite services. Realistically, each fog might belong to a different network operator or service provider and thus will not participate in any form of collaboration unless self-monetary profit is incurred. In this paper, we introduce a fog collaboration approach for simple and complex multimedia service delivery to cloud subscribers while achieving shared profit gains for the cooperating fogs. The proposed work dynamically creates short-term service-level agreements (SLAs) offered to cloud subscribers for service delivery while maximizing user satisfaction and fog profit gains. The solution provides a learning mechanism that relies on online and offline simulation results to build guaranteed workflows for new service requests. The configuration parameters of the short-term SLAs are obtained using a modified tabu-based search mechanism that uses previous solutions when selecting new optimal choices. Performance evaluation results demonstrate significant gains in terms of service delivery success rate, service quality, reduced power consumption for fog and cloud datacenters, and increased fog profits.

This paper considers device-to-device (D2D) network with Simultaneous Wireless Information and Power Transfer (SWIPT) enabled devices to ensure self-sustained communication in situations like disasters. Such direct link networks can ensure connectivity with devices having drained back-up, when trapped in collapsed infrastructure, through mutual sharing of energy on RF link. To guarantee successful execution of SWIPT session for an isolated device in wake of disasters, it is pertinent to select a reliable peer with ultimate aim to maximize link Energy Efficiency (EE). In practice, Energy Harvesting (EH) is not achievable after Information Decoding (ID); however, it has been made possible through splitting the signal in the time domain. Selection of D2D peer for self-sustained communication with an objective to maximize EE through optimum time based splitting of signal has not been extensively studied. In this paper to manifest the aforesaid goal, we worked out a joint problem of peer association and time switching ratio allocation with an objective to maximize the EE for a device contained under collapsed infrastructure. We propose an Energy efficient Peer Selection and Time switching Ratio Allocation (EPS-TRA) algorithm to solve the proposed mixed integer problem. Numerical results validate our proposed approach in acquiring better EE when compared with Uniform Allocation Scheme of time slots for EH & ID. Furthermore, results explain how EE of the link varies with the choice of constrained variables i.e., data rate and harvested energy.

Intrusion Detection Systems (IDSs) can identify the malicious activities and anomalies in networks and present robust protection for these systems. Clustering of attacks plays an important role in defining IDS defense policies. A key challenge in clustering has been finding the optimal value for the number of clusters. In this paper, we propose an automatic clustering algorithm as part of an IDS architecture. This algorithm is based on concepts of coherence and separation. Our automatic clustering algorithms find clusters with the most similarity between the proposed cluster elements and the least similarity with other clusters. The proposed clustering is further optimized by considering two types of objective index functions, and Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), and Differential Evolution (DE) methods. Comparison of the results obtained with other work in the literature shows improvements in terms of the low average number of evaluations functions, high accuracy, and low computation cost.

Aspect-Based Sentiment Analysis (ABSA) is a very important problem with numerous applications. The three editions of SemEval's ABSA Shared Task have been instrumental in fostering the development in this field. One of its sub-tasks is the sentence-level ABSA. This sub-task has received a lot of attention and new techniques and better results are reported on it frequently. The purpose of this work is to achieve the highest accuracy for this problem. We follow a state-of-the-art (SOTA) approach that is based on multi-grain attention networks and infuse it with better embedding mechanisms in order to improve the results. For the famous SemEval's ABSA Shared Task, the results of the SOTA approaches reach 81.25 accuracy and 71.94 F1 score, whereas our approach surpasses them with 83.75 accuracy and 75.75 F1 score.

Attributing a piece of text to its true author is called Authorship Authentication (AA). This work addresses the AA problem of Arabic tweets. Arabic language is both challenging and understudied. Existing approaches on authenticating Arabic tweets used bag of words features or Stylometric Features coupled with classifiers like SVM. However, the reported accuracy for these approaches is rather low and did not even reach 69%. In this work, we address this problem using two approaches. (a) A baseline approach that uses SVM along with BoW features, and (b) a character-level linear classifier (char-LC) with a rank constraint and a fast loss approximation along with word embeddings based on fasttext. Both approaches give significantly higher accuracies than the results reported in literature with 78.28% for the SVM along with BoW approach and 79.4% for the char-LC.

With the emerge of Internet of Things, billions of devices and humans are connected directly or indirectly to the internet. This significant growth in the number of connected devices rises the needs for a new development for the current network paradigm (e.g., cloud computing). The new network paradigm, such as fog computing, along with its related edge computing paradigms, are seen as promising solutions for handling the large volume of securely-critical and delay-sensitive data that is being produced by the IoT nodes. In this paper, we give a brief overview on the IoT related computing paradigms, including their similarities and differences as well as challenges. Next, we provide a summary of the challenges and processing and storage capabilities of each network paradigm.

Mobile Edge Computing (MEC) and Network Slicing techniques have a potential to augment 5G-IoT network services. Telecommunication operators use a diverse set of radio access technologies to provide services for users. Mobility management is one such service that needs attention for new 5G deployments. The QoS requirements in 5G networks are user specific. Network slicing along with MEC has been promoted as a key enabler for such on-demand service schemes. This paper focuses on radio resource access across heterogeneous networks for mobile roaming users. A unified service architecture is proposed enabling seamless handover between a 5G (New Generation Core) service and a 4G (Evolved Packet Core) service via the network slicing paradigm. An identifier-locator (I-L) concept that allows active source-IP sessions is used to handle the seamless hand-over. Signaling costs, service disruptions and other resource reservation requirements are considered in the evaluation to assure that profit for mobile edge operators is achieved. Simulation experiments are considered to provide performance comparisons against the state-of-the-art Distributed Mobility Management Protocol (DMM).

Brain computer interface translates electroencephalogram (EEG) signals into control commands so that paralyzed people can control assistive devices. This human thought translation is a very challenging process as EEG signals contain noise. For noise removal, a bandpass filter or a filter bank is used. However, these techniques also remove useful information from the signal. Furthermore, after feature extraction, there are such features which do not play any significant role in effective classification. Thus, soft computing-based EEG classification followed by extraction and then selection of optimal features can produce better results. In this paper, subband common spatial patterns using sequential backward floating selection is being proposed in order to classify motor-imagery-based EEG signals. The signal is decomposed into subband using a filter bank having overlapped frequency cutoffs. Linear discriminant analysis followed by common spatial pattern is applied to the output of each filter for features extraction. Then, sequential backward floating selection is applied for selection of optimal features to train radial basis function neural networks. Two different datasets have been used for evaluation of results, i.e., Open BCI dataset and EEG signals acquired by Emotiv Epoc. The proposed system shows an overall accuracy of 93.05% and 85.00% for both datasets, respectively. The results show that the proposed optimal feature selection and neural network-based classification approach with overlapped frequency bands is an effective method for EEG classification as compared to previous techniques.

Multicast is widely deployed in data centers for point-to-multi-point communications. Multicast is increasingly being used to carry uncompressed video in media data centers with very large bandwidth requirements per flow. Multicast control protocols such as IGMP and PIM build multicast trees without trying to maximize the overall fabric capacity, leading to decreased fabric utilization and inability to service flows. In addition, existing multicast protocols are not bandwidth-aware and could cause links to over-subscribe leading to packet loss and negative user quality of experience. In this paper, we formulate offline optimization for multicast trees in clos fabric. We then design and implement two novel algorithms, iRP and LiRP, to optimize multicast tree formation and increase overall fabric multicast capacity. iRP algorithm optimizes online formation of multicast trees while addressing bandwidth requirements using SDN controller. We share analysis of TV studio repetitive traffic patterns the benefits of time series forecasting to predict multicast group membership and bring online optimization efficiency closer to offline optimization results. We then implement and test LiRP algorithm to increases iRP's fabric efficiency by implementing k-fold cross validation method to predict future multicast group memberships leading to optimized multicast tree placement. We implement iRP and LiRP algorithms using controller-based system and test both algorithms using Cisco Nexus commercially available switches. Testing results confirm that iRP Algorithm increases fabric capacity by 60% compared to PIM performance. LiRP system increases the efficiency of iRP by up to 40% through prediction of multicast group memberships with online arrival.

Social Networking Sites (SNSs) impact on deaf and hard of hearing people (D/HoH) and characteristics of deaf people in Jordan were investigated in this paper. The main purpose of this paper is to show whether deaf people can effectively use and communicate through SNSs. To this end, a questionnaire was used to find the preferences and experiences of deaf people on SNSs. It was distributed to 138 deaf people. Furthermore, some demographic characteristics of the sample were discussed in the paper. This survey shows how SNSs are integrated with deaf people as a communication tool and the positive impact resulted from using them. It was found that Arabic sign language is most frequently used more than any other communication mode. In addition, they communicate with individuals with hearing loss using sign language more often than using written and spoken language. It was reported that they used SNSs once or more times per day. Furthermore, the most used SNSs website is Facebook, then WhatsApp comes second. Smartphones are used more frequently than any other devices. Last but not least, they use SNSs to exchange photos and watch videos more often than any other purposes and this is highly related to their reading and writing skills.

The significant advancements achieved in wireless communications over the past few years has facilitated successful deployment of LTE-A, and heralded great efforts in 5G development. However, with the increase in the number and variety of connected devices, wireless video transmission in real-time is challenging for the aforementioned network paradigm. Many studies have shown that the centric focus of communications should be the content type, rather than the communication itself, which means real-time multimedia communications are considered crucial for future Internet architectures. This requires high capacity channels and techniques to mitigate inherent wireless channel errors. Thus, we propose an application-layer and middleware-based solutions that increase network reliability and flexibility and provide Quality of Service (QoS) control based on Scalable Video Coding (SVC). Due to the real-time and QoS support of the Data Distribution Service (DDS) middleware, it can be used to implement the three types of SVC scalability: Viz. Temporal, Spatial, Quality (SNR). The open source Scalable Video-streaming Evaluation Framework (SVEF) tool has been used to assess the video transmission performance with performance metrics, Viz. Peak Signal to Noise Ratio (PSNR), Mean Opinion Score (MOS), and frame delay. The results showed a graceful degradation of video quality when using the DDS-based SVC, particularly when the number of receivers is increased. The acquired results show excellent improvements which can be applied to different Future Internet architectures.

This paper reviews the research articles published in the years between 2016 and 2017 with a focus on using Linked Data technologies for enhancing learning. For this purpose, a survey was conducted and articles were selected according to two main criteria: (1) the paper must be in the technology-enhanced learning domain and published in one of the well-recognized journals indexed by the Institute for Scientific Information (ISI) and listed in the Social Science Citation Index (SSCI), and (2) the paper must clearly show how to consume, produce, or both consume and produce Linked Data in the learning context. The survey results show the importance of using Linked Data as a powerful educational technology.

Modern electronic devices(such as TVs, laptops, and mobile devices) come with a huge variety in screen sizes, resolutions, and aspect ratios. Image retargeting is a technique to retarget or (resize) an image to better utilize the viewing device screen and to protect the main content of the image. Different retargeting techniques have been proposed in the literature that mainly utilizes one of the following main techniques: cropping, seam carving, and scale and stretch. The current problem of image retargeting is that it is very hard to determine the best technique to use on an image to get a target dimension. To apply techniques such as machine learning to determine the best technique to perform image retargeting, an annotated image set is needed to perform the training step. In this work, we build and annotate an image set that is suitable to develop such advance retargeting techniques. We build a dataset that include 500 original images. We apply 4 different retargeting techniques to get two different sizes. The resulting image set contains 4000 images annotated by three people. We also analyze the annotation results to get useful remarks from the annotators perceptual point of view.

Cloud computing (CC) is a computing model that enables its customers to access a shared pool of resources (e.g., storage, network, servers, etc.) through the Internet with a pay-per-use pricing model. Different service models are employed in CC including the Platform-as-a-Service (PaaS) model, in which the costumers request a certain set of resources and the cloud service providers provide these resources in the form of a virtual machine (VM) running on one of the thousands of hosting servers or physical machines (PMs) of a data center. Where to "place" VMs, how to "execute" them and whether there is a need to "move/migrate" them are important decisions that affect the overall resource utilization and power consumption in the hosting data center. VM consolidation is a technique of migrating or consolidating VMs to PMs in order to prevent the PMs from being overloaded or reduce the number of active PMs and increase their utilization. Consolidation techniques measure PM utilization to decide whether to consolidate the VMs running on it or migrate some of them to another PM. This study aims to optimize resource utilization and energy efficiency in cloud data centers by proposing a new Logistic Regression based host overloading prediction technique that can be used by any VM consolidation technique. The new algorithm have been evaluated using a dynamic workload using the CloudSim simulator. The simulation results show that the proposed algorithm outperforms all other known host status prediction techniques.

Mobile Edge Computing (MEC) enables ubiquitous and efficient cloud services to mobile users which facilitates mobile cloud computing (MCC) more easily by providing storage and processing capacity within the access range of the mobile devices. To achieve the goals of MEC, Mobile Edge (ME) servers are co-placed with the mobile network base station (at the edge of the mobile network). This eliminates the need to move computation and storage intensive tasks from a mobile device to a centralized cloud server. This in turn reduces the network communication load and delay and it also enhances the quality of service provided for the mobile end users. Applications, such as smart grid applications, content delivery networks, crowed sourcing, traffic management and E-health, will greatly benefit from such deployment. Unfortunately, a large-scale deployment of ME servers that is needed to make hundreds of applications available to millions of users, comes with great management complexity. The emerging technique of Software-Defined Systems (SDSys) abstracts the management complexities of many systems at different layers by utilizing software components. In this paper, we build a software-defined based framework that enable efficient and ubiquitous MCC services by integrating different SDSys components with the MEC system. The integrated framework is implemented and it is evaluated for its feasibility, flexibility and potential superiority.

Cloud computing has emerged as a new computing paradigm with enormous benefits that have attracted many businesses and service providers. As a result, it is critical to ensure highly available and resilient cloud system that continues to operate correctly under different circumstances. This is endangered by risks of cloud insider attacks. In this work, we propose an artificial intelligence based system to detect cloud insider attacks. A hierarchical detection system is used to ensure high detection accuracy and speed. In the first layer, we use a simple expert system to classify the insider as a normal, an attacker, or a probable attacker. The system reacts accordingly by allowing normal insiders to continue their work, blocking attackers, and performing further investigation on probable attackers in the second layer using a decision tree. Simulation results show that our system is able to detect insider attacks with 99.67% detection accuracy.

Mobile devices are used to perform many useful tasks in our daily life. All around the world, many people are using their smart phones to communicate with others, identify their location, and do online shopping. These useful applications involve sharing personal and sensitive information. Also, the smart devices have many weaknesses, such as: limited battery life time, limited processing capacity and security issues. The mobile cloud computing (MCC) can be used to overcome these limitations. Using MCC improved the performance of many applications by conducting the processing at the cloud and sending back the results to the mobile device. But there are still many issues need to be addressed and considered when using MCC specially when dealing with applications that need live interaction and protecting the privacy. In this paper, we will study the main issues associated with mobile cloud computing models that include: security, performance, and quality of service. Then, we will present secure implementation of the cloudlet-based mobile cloud computing framework with its prototype that uses trust delegation technique to provide better security/performance tradeoffs.

Big data is a main problem for data mining methods. Fortunately, the rapid advances in affordable high performance computing platforms such as the Graphics Processing Unit (GPU) have helped researchers in reducing the execution time of many algorithms including data mining algorithms. This paper discusses the utilization of the parallelism capabilities of the GPU to improve the the performance of two common clustering algorithms, which are K-Means (KM) and Fuzzy C-Means (FCM) algorithms. Two main parallelism approaches are presented: pure and hybrid. These different versions are tested under different settings including two different GPU-equipped machines (a laptop and a server). The results show excellent improvement gains of the hybrid implementations compared with the pure parallel and sequential ones. On the laptop, the best gains of the hybrid implementations compared with the sequential ones are 11.3X for KM and 10.9X for FCM. As for the server, the best gains are 13.5X for KM and 16.3X for FCM. Moreover, the paper explores the usage of a recent memory management technique for GPU called Unified Memory (UM). The results show a decrease in the performance gain of the hybrid implementations that is equal to 44% for hybrid version of KM and 61% for FCM. On the other hand, the use of UM does introduce a small advantage for the pure parallel implementation.

The advances in IT sector, cloud computing, the wide usage of sensors and mobile devices, and the Internet-of-Things (IoT) made our world looks like a small town. These rapid developments keep us connected all the day and seven days a week. Also, the IoT enables the connection of the devices around us (including different sensors) to the internet via different wireless and wired communication technologies. These networked sensors can be used to collect different types of data from different applications (healthcare, agriculture, civil and social life) and send it for processing and extraction of appropriate decisions. The mobile cloud computing technology is an efficient solution to process different types of collected data and respond with the required answer in real time situations where the quick response is very important. In this paper, we build a multipurpose integrated sensors system. This integrated system consists of networked sensors for different purposes and applications. For example, the sensors can be health sensors to measure the pulse and blood pressure of patients, or it can be sensors to measure the temperature to indicate a fire accident. The networked sensors will transfer the sensed data through wireless technologies to a Cloud for processing and notifying the listed users to take the proper action.

Parallel programming has many benefits that can help developers and researchers to improve the performance of some algorithms to become more efficient in real life. This is especially true for systems involving medical images. Image segmentation for volume extraction is a famous segmentation process that takes long time to finish execution. In this paper, we consider a new version of the Fuzzy C-Means (FCM) segmentation algorithm (known as IT2FPCM) and provide a parallel implementation of it that is 12X time faster than the sequential implementation. The considered algorithm is based on Interval Type-2 FCM and combines fuzzy and possibilistic ideas in order to obtain higher accuracy. We conduct our experiments using two different machines and the results show that the improvement gains for both machines 11X and 12X, respectively.

In tweet authentication, we are concerned with correctly attributing a tweet to its true author based on its textual content. The more general problem of authenticating long documents has been studied before and the most common approach relies on the intuitive idea that each author has a unique style that can be captured using stylometric features (SF). Inspired by the success of modern automatic document classification problem, some researchers followed the Bag-Of-Words (BOW) approach for authenticating long documents. In this work, we consider both approaches and their application on authenticating tweets, which represent additional challenges due to the limitation in their sizes. We focus on the Arabic language due to its importance and the scarcity of works related on it. We create different sets of features from both approaches and compare the performance of different classifiers using them. To the best of our knowledge, this is the first study of its kind to combine these different sets of features for authorship analysis of Arabic tweets. The results show that combining all the feature sets we compute yields the best results.

Cloud computing provides a convenient and on-demand access to virtually unlimited computing resources. Mobile cloud computing (MCC) is an emerging technology that integrates cloud computing technology with mobile devices. MCC provides access to cloud services for mobile devices. With the growing popularity of cloud computing, researchers in this area need to conduct real experiments in their studies. Setting up and running these experiments in real cloud environments are costly. However, modeling and simulation tools are suitable solutions that often provide good alternatives for emulating cloud computing environments. Several simulation tools have been developed especially for cloud computing. In this paper, we present the most powerful simulation tools in this research area. These include CloudSim, CloudAnalyst, CloudReports, CloudExp, GreenCloud, and iCanCloud. Also, we perform experiments for some of these tools to show their capabilities.

Cloud security has become one of the emergent issues because of the immense growth of cloud services. A major concern in cloud security is the insider threat because of the harm that it poses. Therefore, defending cloud systems against insider attacks has become a key demand. This work deals with insider threat in cloud relational database systems. It reveals the flaws in cloud computing that insiders may use to launch attacks and discusses how load balancing across availability zones may increase insider threat. To mitigate this kind of threat, the paper proposes four models, which are peer-to-peer model, centralized model, Mobile-Knowledgebases model, and Guided Mobile-Knowledgebases model, and it discusses their advantages as well as their limitations. Moreover, the paper provides experiments and analysis that compare among the proposed models, demonstrate their effectiveness, and show the conditions under which they work with highest performance. Copyright © 2016 John Wiley & Sons, Ltd.

Mobile devices including smart phones are becoming an essential component of our daily life. These devices have powerful capabilities and useful applications to help us performing several tasks in less time and effort especially within cloud services. On the other hand, mobile devices have serious limitations such as battery life time, computation power, and storage capacity. Mobile Cloud Computing (MCC) is an emerging technology that helps in avoiding such limitations in mobile devices, mainly saving energy. In this paper, we will address the energy efficiency in Mobile Cloud Computing since it is the most important design requirement for mobile devices. We will present techniques and prototypes in MCC to reduce power consumption and increase resources efficiency and utilization.

Over the recent decades, bioinformatics has acquired a major concern due to the rapid growth in biological data that includes protein structures and genome sequences. Many considerable efforts have been conducted by computer scientists, mathematicians and biologists to coup with complex biological problems such as sequence alignment problem, using several techniques to formulate/model the targeted biological problems as computational problems and design algorithms to solve them in an accurate and efficient manner. Needleman-Wunsch algorithm as well as other alignment algorithms have been the subject of many studies to improve their performance due to their importance and the large scale of the data they have to handle (e.g., aligning strings of hundreds of thousands of characters). Approaches included a mixture of different parallel implementations using specialized hardware such as Graphical Processing Units (GPUs) and a vectorized approach of reading and processing the input data. In this work, a parallel implementation of NW algorithm is presented using GPU due to its efficiency and high speed, to solve the slowness problem associated with this algorithm when processing large data sets, as well as to enhance the performance of the algorithm especially when processing vectors of adjacent cells parallel to the matrix miner diagonal. The experiments show that the proposed implementation improves the performance of the algorithm by 99%.

The diversity, continuous expansion and the large number of smart grid resources increase the complexity of such systems and arise the need to find a new way to manage these resources and, at the same time, reduce the complexity in the control and monitoring operations. Moreover, smart grid Systems are considered critical systems requiring reliable and real time data delivery and an efficient, flexible, scalable control solution to satisfy the system requirements. Thus, in this paper, we introduce a new architecture model for smart grid networks based on the Software Defined Systems (SDSys) paradigm. The main idea behind the SDSys revolves around abstracting the control plane out of the data plane and setting it at a separate layer in the middleware. Different forms of SDSys like Software Defined Network (SDN), Software Defined Storage (SDStore), Software Defined Security (SDSec) and Software Defined Internet of Things (SDIoT) are used to provide a comprehensive smart grid control solution which hide the complexity that exists in traditional control techniques. Meanwhile, we show how the proposed model can provide an accurate, reliable, secure, extensible and network-aware architecture design for smart grid network. Furthermore, we explain how it can provide a single point of view for all smart grid resources and a programmable interface to adapt the network for any sudden changes.

With the rapid growth of data centers and the unprecedented increase in storage demands, the traditional storage control techniques are considered unsuitable to deal with this large volume of data in an efficient manner. The Software Defined Storage (SDStore) comes as a solution for this issue by abstracting the storage control operations from the storage devices and set it inside a centralized controller in the software layer. Building a real SDStore system without any simulation and emulation is considered an expensive solution and may have a lot of risks. Thus, there is a need to simulate such systems before the real-life implementation and deployment. In this paper we present SDStorage, an experimental framework to provide a novel virtualized test bed environment for SDStore systems. The main idea of SDStorage is based on the Mininet Software Defined Network (SDN) Open Flow simulator and is built over of it. The main components of Mininet, which are the host, the switch and the controller, are customized to serve the needs of SDStore simulation environments.

Summary Efficiently scheduling MapReduce tasks is considered as one of the major challenges that face MapReduce frameworks. Many algorithms were introduced to tackle this issue. Most of these algorithms are focusing on the data locality property for tasks scheduling. The data locality may cause less physical resources utilization in non‐virtualized clusters and more power consumption. Virtualized clusters provide a viable solution to support both data locality and better cluster resources utilization. In this paper, we evaluate the major MapReduce scheduling algorithms such as FIFO, Matchmaking, Delay, and multithreading locality (MTL) on virtualized infrastructure. Two major factors are used to test the evaluated algorithms: the simulation time and the energy consumption. The evaluated schedulers are compared, and the results show the superiority and the preference of the MTL scheduler over the other existing schedulers. Also, we present a comparison study between virtualized and non‐virtualized clusters for MapReduce tasks scheduling. Copyright © 2015 John Wiley & Sons, Ltd.

Internet of Things (IoT) has become a common buzzword nowadays in the Web. However, there is no search tool currently in place for discovering and learning about the different types of IoT elements. Hence, this paper presents a topical search engine for IoT. The motivation for a topical search engine comes from the relatively poor performance of general-purpose search engines, which depend on the results of generic Web crawlers. The topical search engine is a system that learns the specialization from examples, and then explores the Web, guided by a relevance and popularity rating mechanism. The results show that the proposed topical search engine outperforms other general search engines.

The analysis of large-scale data for the purpose of extracting patterns is applicable to several research fields. In this paper, a dataset of climate related historical data from Jordan is collected. The main focus is to study evolution criteria of weather attributes in Jordan over the evaluated period of time and how it is connected to climate change. Results showed that humidity and dew point weather attributes are going to face a significant increase in the future. Such an increase is expected to have a direct, as well as an indirect impact on human life.

Text classification (TC) is one of the fundamental problems in text mining. Plenty of works exist on TC with interesting approaches and excellent results; however, most of these works follow a word-based approach for feature extraction. In this work, we are interested in an alternative (byte-based or character-based) approach known as compression-based TC (CTC). CTC has been used for some languages such as English and Portuguese and it is shown to have certain advantages/ disadvantages compared with word-based approaches. This work applies CTC on the Arabic language with the purpose of investigating whether these advantages/disadvantages exists for the Arabic language as well. The results are encouraging as they show the viability of using CTC for Arabic TC.

Software defined networking (SDN) provides a novel network resource management framework that overcomes several challenges related to network resources management. On the other hand, Cognitive Radio (CR) technology is a promising paradigm for addressing the spectrum scarcity problem through efficient dynamic spectrum access (DSA). CR provides unlicensed secondary users with the ability to coexist with licensed users in non-interfering mode. In this paper, we introduce a virtualization based SDN resource management framework for cognitive radio networks (CRNs). The framework uses the concept of multilayer hypervisors for efficient resources allocation. It also introduces a semi-decentralized control scheme that allows the CRN base station (BS) to delegate some of the management responsibilities to the network users. CRN resource virtualization allows dynamic, infrastructure free and efficient resources allocation to the CR users. The main objectives of the proposed framework is to reduce the CR users' reliance on the CRN BS and physical network resources while improving the network performance by reducing control overhead.

IEEE 802.22 Wireless Regional Area Network (WRAN) is the first wireless standard based on cognitive radio (CR) technology. WRAN is designed to allow secondary users (SUs) to opportunistically utilize idle TV channels on a non-interfering manner. A major challenge in enabling efficient WRAN communications is the interference-and-coexistence problem. There are two types of co-existence; incumbent co-existence and self-coexistence. In this paper, we investigate the self-coexistence problem among multiple overlapped WRANs. Specifically, we propose an adaptive cooperative exclusive traffic-aware channel allocation scheme (TAECA) that attempts to minimize the unnecessary blocking of SU transmissions in the overlapped cells, which consequently maximizes spectrum utilization. TAECA employs a novel max-min weighted fair mechanism for adaptively allocating idle channels to the different WRANs cells depending on their prevailing traffic conditions. Simulation results indicate that compared to reference allocation mechanisms, TAECA increases the number of served SU transmissions by up to 40%, which significantly improves spectrum utilization.

Network virtualization is a promising technology that enables the deployment of multiple virtual networks over a single physical network. These virtual networks are allowed to share the set of available resources in order to provide different services to their intended users. Although many projects are studying different aspects of network virtualization, the field of wireless network virtualization is not well investigated. In this work, we propose a dynamic cognitive radio virtualization framework in which several virtual networks are built over a set of physical nodes managed and controlled by a Base Station (BS). This framework is proposed to virtualize Cognitive Radio Networks (CRNs) in order to reduce the control overhead on the BS side by delegating some of its responsibilities to the node side. The proposed framework is applied to a network with multiple overlapping cells. To cope with the self-coexistence problem, we use a resource allocation algorithm to distribute the available channels over the overlapping cells based on their traffic loads with the goal of avoiding harmful interference, enhancing blocking rates and increasing throughput.

In this work we investigate the problem of video streaming in cognitive radio networks from a cognitive radio video source to a set of cognitive radio destinations using multicasting. Our objective is to improve the overall quality of the received video by all destinations. To achieve this, we propose a cross layer approach to multicast the video packets. The video source implements the proposed approach to multicast a video packet to all destinations at the same time by selecting the best unified channel of all available channels for all destinations to send the video packet on. To select the best unified channel, the source jointly considers the required transmission time of the packet and the average spectrum availability time of the available channels. Moreover, by using the proposed approach, the video source guarantees that the required transmission time of the packet over the selected channel is less than its average spectrum availability time. We conduct simulation experiments to evaluate the performance of our proposed protocol under various network parameters. We compare our protocol with three multicast protocols. The first one selects the unified channel based on the minimum transmission time. The second one selects the unified channel based on the average spectrum availability time. The last one selects the unified channel randomly. We use packet delay, the ratio of bad frames, and control overhead as performance metrics. Simulation results demonstrate that the proposed multicasting routing protocol achieves significantly better performance compared to the other studied routing protocols in terms of all studied performance metrics. Specifically, it reduces the packet delay by at least 25%, the control overhead by at least 5%, and the ratio of bad frames 44%.

Mobile Cloud Computing (MCC) has been introduced as a viable solution to the inherited limitations of mobile computing. These limitations include battery lifetime, processing power, and storage capacity. By using MCC, the processing and the storage of intensive mobile device jobs will take place in the cloud system and the results will be returned to the mobile device. This will reduce the required power and time for completing such intensive jobs. However, connecting mobile devices with the cloud suffers from the high network latency and the huge transmission power consumption especially when using 3G/LTE connections. In this paper, we introduce a Cloudlet based MCC system aiming to reduce the power consumption and the network delay while using MCC. We merged the MCC concepts with the proposed Cloudlet framework and propose a new framework for the MCC model. Our practical experimental results showed that using the proposed model reduces the power consumption from the mobile device, besides reducing the communication latency when the mobile device requests a job to take place remotely while keeping high quality of service stander.

This paper presents an FPGA architecture for a new version of the Advanced Encryption Standard (AES) algorithm. The efficient hardware that implements the algorithm is also proposed. The new algorithm (AES-512) uses input block size and key size of 512-bits which makes it more resistant to cryptanalysis with tolerated area increase. AES-512 will be suitable for applications with high security and throughput requirements and with less chip area constrains such as multimedia and satellite communication systems. An FPGA architectural for AES-512 was developed using VHDL, and synthesized using Virtix-6 and Virtex-7 chips. AES-512 show tremendous throughput increase of 230% when compared with the implementation of the original AES-128.

There is a need for accelerated discovery cycles (ADCs) for integrating experimental and observational data to capture large-scale dynamic ecosystem complexity, to instantly process massive datasets, to test contrasting mechanistic models and to drive the next set of experiments. The overreaching objective is to enable ADCs by coupling advances in computational models and cyber-systems with the unique experimental infrastructure of Biosphere 2 (B2), a large-scale earth system science facility now under management by the University of Arizona. In the context of ADCs, there is a need for software development environment for modeling complex systems and a middleware for data streaming from the field into the models. Kepler is an open source tool that enables the end user to design scientific workflows in order to manage scientific data and perform complex analysis on the data. Ring buffered network bus (RBNB) data turbine is a middleware system that is used to integrate sensor-based environment observing systems with data processing systems. Currently the integration between Kepler and data turbine is limited to reading from the data turbine only. In ADC, multiple hypotheses are tested with different assimilation models. These models run on a distributed computing environment, therefore capability of simultaneous reads and writes to the data turbine is a necessity. In this paper we show how to integrate Kepler with RBNB data turbine to achieve this capability. We also exploit the open-source features of Kepler system and create customized processing models in order to accelerate and automate the experiments in ecosystems research. We describe in further details our implementation approach to enable future studies on Kepler and data turbine integration.