Search

Cloud Computing is playing a huge role in future technology. Further, with the explosive growth of the Internet and cloud computing, several service providers, such as Amazon, Microsoft, IBM, and Google, have expanded their data centers and rapidly deployed data centers in different places around the world to deliver various cloud computing services. However, several challenges are raised with the wide spread use of cloud environment such as power consumption, load balance, reliability, scalability, and security. This paper tackles the power consumption problem and presents an efficient algorithm, called Task Consolidation based Power Minimization (TCPM), to efficiently schedule tasks onto available resources of the cloud environment so as to minimize power consumption. In proposed TCPM algorithm, several benefits of the existing algorithms are enhanced and incorporated into the TCPM algorithm, where the best-fit procedure is used to achieve the best possible resource utilization and avoid wasting energy. The results of the proposed TCPM algorithm are compared with other recent algorithms such as FCFS, WWO, and MCT algorithms using the CloudSim toolkit.

This paper presents a hybrid approach based Binary Artificial Bee Colony (BABC) and Pareto Dominance strategy for scheduling workflow applications considering different Quality of Services (QoS) requirements in cloud computing. The main purpose is to schedule a given application onto the available machines in the cloud environment with minimum makespan (i.e. schedule length) and processing cost while maximizing resource utilization without violating Service Level Agreement (SLA) among users and cloud providers. The proposed approach is called Enhanced Binary Artificial Bee Colony based Pareto Front (EBABC-PF). Our proposed approach starts by listing the tasks according to priority defined by Heterogeneous Earliest Finish Time (HEFT) algorithm, then gets an initial solution by applying Greedy Randomized Adaptive Search Procedure (GRASP) and finally schedules tasks onto machines by applying Enhanced Binary Artificial Bee Colony (BABC). Further, several modifications are considered with BABC to improve the local searching process by applying circular shift operator then mutation operator on the food sources of the population considering the improvement rate. The proposed approach is simulated and implemented in the WorkflowSim which extends the existing CloudSim tool. The performance of the proposed approach is compared with Heterogeneous Earliest Finish Time (HEFT) algorithm, Deadline Heterogeneous Earliest Finish Time (DHEFT), Non-dominated Sort Genetic Algorithm (NSGA-II) and standard Binary Artificial Bee Colony (BABC) algorithm using different sizes of tasks and various benchmark workflows. The results clearly demonstrate the efficiency of the proposed approach in terms of makespan, processing cost and resources utilization.

Cloud computing applications have grown rapidly in the last decade, where many organizations are migrating their applications to cloud data center as they expected high performance, reliability, and the best quality of service. Data centers deploy a variety of technologies, such as software-defined networks (SDN), to effectively manage their resources. The SDN approach is a highly flexible network architecture that automates network configuration using a centralized controller to overcome traditional network limitations. This paper proposes an SDN-based monitoring algorithm to detect the performance anomaly and identify the bottleneck of the distributed application in the cloud data center using the support vector machine algorithm. It collects the data from the network devices and calculates the performance metrics for the distributed application components that are used to train the SVM algorithm and build a baseline model of the normal behavior of the distributed application. The SVM model detects performance anomaly behavior and identifies the root cause of bottlenecks using one-class support vector machine (OCSVM) and multi-class support vector machine (MCSVM) algorithms. The proposed method does not require any knowledge about the running applications or depends on static threshold values for performance measurements. Simulation results show that the proposed method can detect and locate the failure occurrences efficiently with high precision and low overhead compared to statistical methods, Naive Bayes Classifier and the decision tree machine learning method.

The widespread usage of cloud computing in different fields causes many challenges as resource scheduling, load balancing, power consumption, and security. To achieve a high performance for cloud resources, an effective scheduling algorithm is necessary to distribute jobs among available resources in such a way that maintain the system balance and user tasks are responded to quickly. This paper tackles the multi-objective scheduling problem and presents a modified Harris hawks optimizer (HHO), called elite learning Harris hawks optimizer (ELHHO), for multi-objective scheduling problem. The modifications are done by using a scientific intelligent method called elite opposition-based learning to enhance the quality of the exploration phase of the standard HHO algorithm. Farther, the minimum completion time algorithm is used as an initial phase to obtain a determined initial solution, rather than a random solution in each running time, to avoid local optimality and satisfy the quality of service in terms of minimizing schedule length, execution cost and maximizing resource utilization. The proposed ELHHO is implemented in the CloudSim toolkit and evaluated by considering real data sets. The obtained results indicate that the presented ELHHO approach achieves results better than that obtained by other algorithms. Further, it enhances performance of the conventional HHO.

Due to the serious effectiveness of congestion problem in the Internet performance, congestion control has the most concern in the network community. Several End-to- End mechanisms were developed to overcome this problem. However, most of the existing mechanisms adapt the sending rate at the sender, when detecting congestion, without considering the network status. This behavior degrades the Internet performance. This paper presents a new fuzzy controller to adjust the sending rate at the sender dynamically based on the network load. The intended controller is employed to enhance the TCP-Vegas and the performance is evaluated by using the well-known Network Simulator NS-2. The results indicate that the intended controller the AT&T real network increases the throughput and decreases both the packet loss and packet delay.

This paper presents a hybrid approach based discrete Particle Swarm Optimization (PSO) and chaotic strategies for solving multi-objective task scheduling problem in cloud computing. The main purpose is to allocate the summited tasks to the available resources in the cloud environment with minimum makespan (i.e. schedule length) and processing cost while maximizing resource utilization without violating Service Level Agreement (SLA) among users and cloud providers. The main challenges faced by Particle Swarm Optimization (PSO) when used to solve scheduling problems are premature convergence and trapping into local optimum. This paper presents an enhanced Particle Swarm Optimization algorithm hybridized with Chaotic Map strategies. The proposed approach is called Enhanced Particle Swarm Optimization based Chaotic Strategies (EPSOCHO) algorithm. Our proposed approach suggests two Chaotic Map strategies: sinusoidal iterator and Lorenz attractor to enhanced PSO algorithm in order to get good convergence and diversity for optimizing the task scheduling in cloud computing. The proposed approach is simulated and implemented in Cloudsim simulator. The performance of the proposed approach is compared with the standard PSO algorithm, the improved PSO algorithm with Longest job to fastest processor (LJFP-PSO), and the improved PSO algorithm with minimum completion time (MCT-PSO) using different sizes of tasks and various benchmark datasets. The results clearly demonstrate the efficiency of the proposed approach in terms of makespan, processing cost and resources utilization.

Nowadays, optimization has become a brand methodology for different applications. One of the most promising fields for application of optimization is the image processing field, especially image fusion. A new effective deterministic optimization technique is the modified central force optimization (MCFO) that overcomes the low convergence rate drawback of the central force optimization (CFO). In this paper, the MCFO is applied with standard image fusion methods as a novel brand to improve the fusion efficiency either qualitatively or quantitatively. Intensity-hue-saturation (IHS), high-pass filtering (HPF), and discrete wavelet transform (DWT) are powerful standard techniques for satellite image fusion that are implemented with MCFO optimization in this paper. They are performed on satellite panchromatic (PAN) and multispectral (MS) images. The target of using the MCFO is to reduce some spectral and spatial distortions that may occur without optimization. Different qualitative indices have been used to validate the proposed approach comprising optimization for satellite image fusion.

Big data have acquired big attention in recent years. As big data makes its way into companies and business so there are some challenges in big data analytics. Apache spark framework becomes very popular for using in distributed data processing. Spark is an analytic machine for big data processing with various modules for SQL, streaming, graph processing and machine learning. Different scheduling algorithms vary with its behavior, design and also the goal required solving a problem like data locality, energy and time. The main goal in this research is to represent a comprehensive survey on job scheduling modes using in spark, the types of different scheduler, and existing algorithms with advantages and issues. In this paper, various adaptive ways to schedule jobs on spark and development algorithms to improve performance in Spark will be discussed, analyzed and evaluated. A comparison between different scheduling algorithms, strength and weakness points of them are provided. This can aid to the researchers understanding of which scheduling mechanisms best applied for Big Data.

Pan-sharpening considers one of the most important applications for satellite images as it enhances spectral and spatial information for the images. Empirical Mode Decomposition (EMD) is one of the most powerful techniques for pan-sharpening. It first decomposes the image into a set of Intrinsic Mode Functions (IMFs) and a residual component. These panchromatic and multispectral components are then fused to create an enhanced pan-sharpened image. This paper presents an efficient hybrid method for enhancing pan-sharpening of multiband images transmitted from satellite to ground stations. The proposed approach combines this EMD technique with the most powerful conventional method; Discrete Wavelet Transform (DWT), to maximize the pan-sharpening gain. The proposed hybrid method is validated using satellite images of Nile Valley and Suez Canal region, Egypt, captured by Spot-4 and Landsat-8 satellites. The results imply that the proposed hybrid method provides better qualitative and quantitative quality comparing with the individual and the most common pan-sharpening methods.

DNA methylation is a covalent alteration in the DNA genome that modifies the expression of gene. DNA methylation occurs by adding methyl group to DNA molecule at fifth carbon of Cytosine ring. This process alters DNA activities but doesn’t change the sequence. This modification may cause tumorigenesis and cancer progression. Therefore, there is an urgently need to detect the methylated sites in DNA sequences and their regulation mechanisms which effect the epigenetics transformation. Predominantly, these epigenetic changes are in small regions in DNA called CpG islands, which exist with various frequencies in DNA sequences but mostly detected in promoter regions. Recently, a lot of efforts have been dedicated to computationally detect CpG islands, build large-scaled databases with visualization tools and develop analysis methods for DNA methylation data. Here, we provide a review on CpG islands detectors and classifier algorithms. We focus on genome-wide methylation databases of human cancers. We present an overview of methodologies available for DNA deferential methylation analysis. We aimed to summarize the recent efforts in DNA methylation changes and their significance in human cancers to open the door for more development in mechanisms and treatment perspectives.

Cloud computing has grown rapidly in the last decade, where many tenants are using various cloud applications. Cloud computing users expect and demand to run their applications with the highest performance, reliability, and best quality of service. So, load balancing techniques are essential components and widely used in the cloud data center network to manage users’ requests and distribute applications traffic among available data center resources. Software-defined networking is a highly flexible network architecture that automates network configuration using a centralized controller to overcome the traditional network limitations and manual configuration for every network device. This paper proposes a dynamic load balancing technique using software-defined networking for the cloud data center that can handle different application types in real-time based on traffic type and the required quality of service. The proposed method aims to bridge the gap between application requirements and the resources in the cloud data center by choosing the best path for data transmission and selecting the best performance server to process the users' requests according to traffic type for efficient resources’ utilization, minimizing response time, and maximizing throughput. The simulation results show that the proposed method enhances the performance of the running applications’ and utilizes the data center resources efficiently compared with the current load balancing techniques.

Providing healthcare services without emergency waiting is the one of important challenges for healthcare organizations. The poor patient readmission management increasing the emergency waiting and maybe cause a risk on the patient life. The current prediction models working on batching processing model, and not provides real time tracking of patient status. However, the patient profile growth every second by new records or new attributes and the accuracy of analysis is insufficient when the quality of health data is incomplete, old, or not clean. Indeed, all patient data need to analyze using big data technologies in real time to extract important features from the data. So, this paper tackles most problems that hinder extracting features for readmission prediction models in real time. The new model called High-Risk Readmission Prediction model (HR2P). This model based on machine learning and big data technology to be able streaming patient data from Internet of Things (IoT) and electronic health records (EHR) storage. The new approach allows healthcare organizations to minimize waiting time for patients and emergency cases.

The task allocation problem in a multi-robot system (MRS) may be characterized as the problem of assigning a set of tasks to a group of robots in order to improve some performance parameters. However, when many requests are received simultaneously by a robot, the current scheduling approaches may make unreasonable decisions, delaying the execution of some requests and so affecting the system performance. This paper addresses this issue and proposes a new scheduling mechanism for task allocation in MRS. The presented approach implements a universal allocation depend on Water Wave Optimization (WWO) algorithm with the Genetic Algorithm (WWO_GA). The result of this approach is compared with the conventional Water Wave Optimization (WWO) and the Particle Swarm Optimization (PSO) algorithms. Simulation results prove that the introduced approach enhances the performance of the multi-robot system in terms of total traveled distance and computation time.

Load balancing is one of the main issues related to task scheduling in cloud environment. Load balancing aims at avoiding the situation whenever some virtual machines are overloaded and others are under loaded, or idle. It may cause Service Level Agreement (SLA) violation and further may lead to the reduction of customer satisfaction level. In this study, we propose Improved Active Monitoring Load Balancer with Hill Climbing Algorithm (IAMLBHC) to improve the performance metrics such as response time and processing cost. The proposed approach is simulated and implemented in CloudAnalyst simulator. The performance of the proposed approach is compared with the most recent existing load balancing algorithms via the simulation. The experimental results show that the proposed approach IAMLBHC gives better performance in terms of response time, and processing cost compared with the existing similar algorithms.

Charities face a difficult funding environment, mainly because charities are not highly transparent. Day over day It became more difficult to know whether donations are reaching the right place, or taking another course, such as financing suspicious campaigns, terrorist projects, etc. As a result, donors lose faith in these organizations, leading to a halt to interactions with charitable organizations. This makes it more difficult for charities to raise money at a great cost. This research proposed a solution to the mentioned problem using Blockchain technology, a decentralized database that provides security, transparency, and lower funding cost by eliminating the presence of third parties between donors and charities. A new track donation model was proposed which introduced several new participants that control the process of donation and remove suspicion of the charity. All donations can be tracked in Blockchain, allowing donors to know where and how their money is being used. The proposed model was implemented using Hyperledger composer then it was tested to obtain a live full track of a donation process. All donations are made using smart contracts, which allow donors to know exactly when and how their donations will be received. The Blockchain track donation system results in time-saving, reducing the cost of donation, and reduces the risk of reaching suspicious campaign donations or terrorist projects. A website was created as a facilitator for users for ease of use of the proposed system.

Recently, Power Consumption is one of The Most Important Researches on Cloud Computing Systems such as CPU central Processors, Drives, memory, and temperature that affect on consuming the amount of energy. But also the amount of software approach has more effective on it, such as scheduling, resource allocation, and task consolidation.Task Consolidation is an effective technique that is used to save power consumption which consolidates tasks by virtualization technologies. The goal of this optimizing is not only to minimize energy costs in cloud computing systems but also to respond to government and environmental rules. There are more than techniques to minimize energy consumption here we focus on the task consolidation technique and its important algorithms. In task consolidation, idle resources consume a major amount of energy consumption. Virtualization is an important part of the task consolidation strategy.In this survey, we discuss how efficient task consolidation algorithms affect cloud resource power consumption.

Choosing the appropriate IoT protocol for a certain application was and still a critical issue for IoT applications, as protocols vary in behavior in different applications and under different network status. IoT application protocols have a recent focus of attention especially those protocols for the low-powered IoT applications and constrained devices. A brief survey of IoT layers and applied protocols for each layer and their applications were presented, besides, a detailed survey of IoT protocols with a presentation of the main researches that have been done to evaluate their performance. As a use case for this comparative study, the MQTT protocol was chosen because of its simplicity and its publish /subscribe model to be evaluated and compared against other application protocols.

Data mining algorithms are more important today as it allows stakeholders to get a 360-degree view of their customers. Recently, powerset has become the basic core for many algorithms and t...

Deep learning, in general, is about multi layered neural networks copying the structure and intellectual procedure of the human mind. Rather than handcrafted features, it permits the procurement of knowledge straightforwardly from information. They relapse mind boggling target works in a nested system, where more complex forms with bigger receptive fields are estimated using less abstract ones. Deep learning additionally makes it conceivable to consider formal domain knowledge and supplant an extensive collection of traditional algorithmic methods with flexible differentiable modules. These all strengthen and empower deep learning and make it adaptable while establishing the connection between the input information and target yield. Research frontiers are presently moving toward the rest of the difficulties. This paper presents a complete overview about deep learning. It illustrates where did deep learning initiate from, what had been accomplished using deep learning, What research areas are currently being investigated via deep learning, and most importantly What are the challenges and open problems of deep learning - as those are the issues, once handled, will lead to achieve the general conscious Artificial Intelligence (AI). The purpose is to empower graduates, practitioners, researchers and fans toward a powerful cooperation in the field of deep learning.

Billions of active online users are continuously feeding the world with multimedia Big Data through their smart phones and PCs. These heterogenous productions are existing in different social media platforms, such as Facebook and Twitter, delivering a composite message in the form of audio, visual and textual signals. Analyzing multimedia Big Data to understand the intended delivered message, had been a challenge to audio, image, video and text processing researchers. Thanks to the recent advances in deep learning algorithms, researchers had been able to improve the performance of multimedia Big Data analytics and understanding techniques This paper presents a survey on how a multimedia file is analyzed, key challenges facing multimedia analysis, and how deep learning is helping conquer and advance beyond those challenges. Future directions of multimedia analysis are also addressed. The aim is to stay objective all through this study, bringing both empowering enhancements and in addition inescapable shortcomings, wishing to bring up fresh questions and stimulating new research frontiers for the reader.

Pan-sharpening is one of the most important tasks performed on satellite images as it enhances spectral and spatial information of the images. Empirical mode decomposition (EMD) is one of the powerful methods for pan-sharpening. It first decomposes the image into a set of intrinsic mode functions and a residual component. These panchromatic and multi-spectral components are then fused to create an enhanced pan-sharpened image. This paper presents two efficient hybrid methods to enhance pan-sharpening of multi-spectral images. The new proposals combine the EMD with the two pan-sharpening methods: high-pass filtering and discrete wavelet transform to maximize the pan-sharpened image quality. The two methods are evaluated using satellite images of Cairo and Suez Canal region, Egypt, captured by Spot-4 and Landsat-8 satellites, respectively. The results imply that the proposed hybrid methods provide better qualitative and quantitative results compared to the individual and the common pan-sharpening methods.

Efficient resource distribution for multiple users is one of the most challenging problems of the cloud service provider (CSP). This problem is more difficult when each user submits multi-tasks to the cloud environment. Hence, CSP needs an efficient framework to optimize multiple objectives, e.g., cost, time, and load balancing as well as to manage tasks of different users in a secure way. This paper presents a new efficient scheduling framework, called highest priority first execute (HPFE), for serving multiple users with multiple tasks in a secure and optimized way. Computational results show that the proposed HPFE reduces the makespan and increases the load balancing degree comparing to the most recent algorithms; Min–Min, Max–Min, minimum completion time, first come first serve, genetic algorithm and simulated annealing.

Cloud computing is a popular model that allows users to store, access, process, and retrieve data remotely. It provides a high-performance computing with large scale of resources. However, this model requires an efficient scheduling strategy for resources management. Recently, several algorithms are presented to solve the resource scheduling problem. Nevertheless, still the problem exists with complex applications such as workflows, which need an efficient algorithm to be scheduled on the available resources. This paper presents a novel hybrid algorithm, called CR-AC, combining both the chemical reaction optimization (CRO) and ant colony optimization (ACO) algorithms to solve the workflow-scheduling problem. The proposed CR-AC algorithm is implemented in the CloudSim toolkit and evaluated by using real applications and Amazon EC2 pricing model. Moreover, the results are compared with the most recent algorithms: modified particle swarm optimization (PSO) and cost-effective genetic algorithm (CEGA). The experimental results indicate that the CR-AC algorithm achieves better results than the traditional CRO, the ACO, the modified PSO and CEGA algorithms, in terms of total cost, time complexity, and schedule length.

Quality-of-Services (QoS) is one of the most important requirements of cloud users. So, cloud providers continuously try to enhance cloud management tools to guarantee the required QoS and provide users the services with high quality. One of the most important management tools which play a vital role in enhancing QoS is scheduling. Scheduling is the process of assigning users’ tasks into available Virtual Machines (VMs). This paper presents a new task scheduling approach, called Online Potential Finish Time (OPFT), to enhance the cloud data-center broker, which is responsible for the scheduling process, and solve the QoS issue. The main idea of the new approach is inspired from the idea of passing vehicles through the highways. Whenever the width of the road increases, the number of passing vehicles increases. We apply this idea to assign different users’ tasks into the available VMs. The number of tasks that are allocated to a VM is in proportion to the processing power of this VM. Whenever the VM capacity increases, the number of tasks that are assigned into this VM increases. The proposed OPFT approach is evaluated using the CloudSim simulator considering real tasks and real cost model. The experimental results indicate that the proposed OPFT algorithm is more efficient than the FCFS, RR, Min-Min, and MCT algorithms in terms of schedule length, cost, balance degree, response time and resource utilization. Keywords: Cloud computing, Task scheduling, QOS, Load balancing

With the widespread of the Internet and the rapid growth of technologies, several challenges face data hiding process. Although watermarking is widely used to hide/embed critical data into a cover image, the watermarked image may be attacked/hacked and the embedded data may be extracted or damaged. This paper presents an efficient two-level security approach to protect colored watermark images. In the first level, the color image is embedded into a grayscale image using a multi-level Discrete Wavelet Transform (DWT), Singular Value Decomposition (SVD), and wavelet fusion. In the second level, an additional encryption process on the watermarked image is done by using two-dimensional logistic chaotic map in a case and Advanced Encryption Standard (AES) in another case. The proposed scheme is evaluated by using several images and different hacks on the transmitted image. The experimental results show that the proposed scheme is efficient and can face many attacks such as Gaussian, Blur, Wrap, and Cropping. In addition, the extracted watermarks are recognized even when the marked images suffered from attacks.

Nowadays, deep learning achieves higher levels of accuracy than ever before. This evolution makes deep learning crucial for applications that care for safety, like self-driving cars and helps consumers to meet most of their expectations. Further, Deep Neural Networks (DNNs) are powerful approaches that employed to solve several issues. These issues include healthcare, advertising, marketing, computer vision, speech processing, natural language processing. The DNNs have marvelous progress in these different fields, but training such DNN models requires a lot of time, a vast amount of data and in most cases a lot of computational steps. Selling such pre-trained models is a profitable business model. But, sharing them without the owner permission is a serious threat. Unfortunately, once the models are sold, they can be easily copied and redistributed. This paper first presents a review of how digital watermarking technologies are really very helpful in the copyright protection of the DNNs. Then, a comparative study between the latest techniques is presented. Also, several optimizers are proposed to improve the accuracy against the fine-tuning attack. Finally, several experiments are performed with black-box settings using several optimizers and the results are compared with the SGD optimizer.

There is evidence that early detection of cancer diseases can improve the treatment and increase the survival rate of patients. This paper presents an efficient CAD system for cancer diseases diagnosis by gene expression profiles of DNA microarray datasets. The proposed CAD system combines Intelligent Decision Support System (IDSS) and Multi-Agent (MA) system. The IDSS represents the backbone of the entire CAD system. It consists of two main phases; feature selection/reduction phase and a classification phase. In the feature selection/reduction phase, eight diverse methods are developed. While, in the classification phase, three evolutionary machine learning algorithms are employed. On the other hand, the MA system manages the entire operation of the CAD system. It first initializes several IDSSs (exactly 24 IDSSs) with the aid of mobile agents and then directs the generated IDSSs to run concurrently on the input dataset. Finally, a master agent selects the best classification, as the final report, based on the best classification accuracy returned from the 24 IDSSs The proposed CAD system is implemented in JAVA, and evaluated by using three microarray datasets including; Leukemia, Colon tumor, and Lung cancer. The system is able to classify different types of cancer diseases accurately in a very short time. This is because the MA system invokes 24 different IDSS to classify the diseases concurrently in parallel processing manner before taking the decision of the best classification result.

Cloud computing now becomes the accomplished infrastructure model for delivering the cloud service to its user over the Internet. Virtualization is one of the key concepts, which makes the dynamic sharing of physical resources of cloud more effective. In virtualization, virtual machine is placed over the physical machine in data centre and VM placement is one of the challenging issues in cloud computing, so cloud service provider needs good VM placement policy to increase the utilization of physical resources as well as reduce the load-balancing problem. In this paper, we proposed a new VM placement policy called Efficient of service Best Fit Decreasing (EBFD). From the simulation experiments result, we see that the proposed policy performs much better performance compared with first-fit and best-fit policy.

Understanding video files is a challenging task. While the current video understanding techniques rely on deep learning, the obtained results suffer from a lack of real trustful meaning. Deep learning recognizes patterns from big data, leading to deep feature abstraction, not deep understanding. Deep learning tries to understand multimedia production by analyzing its content. We cannot understand the semantics of a multimedia file by analyzing its content only. Events occurring in a scene earn their meanings from the context containing them. A screaming kid could be scared of a threat or surprised by a lovely gift or just playing in the backyard. Artificial intelligence is a heterogeneous process that goes beyond learning. In this article, we discuss the heterogeneity of AI as a process that includes innate knowledge, approximations, and context awareness. We present a context-aware video understanding technique that makes the machine intelligent enough to understand the message behind the video stream. The main purpose is to understand the video stream by extracting real meaningful concepts, emotions, temporal data, and spatial data from the video context. The diffusion of heterogeneous data patterns from the video context leads to accurate decision-making about the video message and outperforms systems that rely on deep learning. Objective and subjective comparisons prove the accuracy of the concepts extracted by the proposed context-aware technique in comparison with the current deep learning video understanding techniques. Both systems are compared in terms of retrieval time, computing time, data size consumption, and complexity analysis. Comparisons show a significant efficient resource usage of the proposed context-aware system, which makes it a suitable solution for real-time scenarios. Moreover, we discuss the pros and cons of deep learning architectures.

Presently, cloud computing has become a very popular platform in the computing world. It provides users with high efficient resources on demand. Nevertheless, due to the strong turnout to use the cloud in everything in the Information Technology (IT) field, cloud platforms have become very crowded with heavy loads. Therefore, providers need to use new techniques to manage resources allocation to users. One of the most important techniques, in managing cloud resources, is scheduling technique. Recently, many heuristic and meta-heuristic techniques are developed to solve the scheduling problem. However, each technique is efficient to solve a part of the problem but unable to solve the overall problem. This paper presents a new technique called Water Pressure Change Optimization (WPCO) to solve the scheduling problem in cloud computing. The new WPCO technique is inspired from the phenomenon of water density changing when increasing the pressure due to the changing in the physical characteristics of the water. The new technique is evaluated and compared with the most recent existing techniques. The results indicate that the WPCO can distribute any number of tasks on the available resources in low time complexity. In addition, it improves schedule length, load balancing, resources utilization, memory usage and throughput of the cloud system.

This paper employs an intelligent control technique (Fuzzy logic) in the area of Internet congestion control. Generally, congestion problem occurs when traffic load increases. This problem decreases network utilization and increases traffic delay. Hence, an intelligent congestion control is required to avoid the mentioned problem. Nevertheless, the main challenge in utilizing fuzzy controller is how to choice the number of membership functions. A greater resolution is achieved with a large number of membership functions. In this paper, two different cases as considered: the first case employs 3-memberships while the second case employs 5-memberships. The proposed controller is evaluated by using NS2 simulation tool and the results are compared with the most recent protocols. The results indicate that the proposed controller increases the throughput and decreases both the packet loss and packet delay.

Cloudlet scheduling in cloud computing is one of the most issues that face the cloud computing environment. This paper presents a new efficient approach, called Traveling Salesman Approach for Cloudlet Scheduling (TSACS), to solve the cloudlet-scheduling problem. The main idea is to convert the cloudlet-scheduling problem into an instance of the Traveling Salesman Problem (TSP) and then apply one of the TSP solution strategies to solve the problem. The proposed approach consists of three phases: clustering phase, converting phase, and assignment phase. In the clustering phase, the proposed approach converts the large size cloudlet-scheduling problem into a small size cluster-scheduling problem to minimize computation time complexity of the proposed approach. In the converting phase, the approach forms the cluster-scheduling problem as an instance of the TSP. In the assignment phase, the approach schedules the clusters into the available virtual machines by using the nearest neighbor algorithm. The proposed approach is evaluated by using the CloudSim and the results are compared with that obtained by the most recent algorithms. The results show that the proposed approach enhances the overall system performance in terms of schedule length, balancing degree, and time complexity. In addition, the proposed TSACS overcomes the oscillation problem of the existing cloudlet-scheduling algorithms.

As expectations for the data processing platforms to support processing for healthcare data, new services need to be deployed in healthcare services. One of them is Electronic health records. It raised its importance recently from the data become shareable, connection oriented, high available, and united. Therefore, a first motivation is to help healthcare organizations to define which the appropriate processing platform can support real time processing for huge electronic health records data. Although define different platforms that enhanced analytics and prediction methods of healthcare entities which produces a huge amount of data. A second possible motivation is to go beyond the limitations of traditional processing techniques that used in electronic health records. The big data processing is the cheaper solution that performing real-time analysis on the huge data. This paper identifies and discusses new data processing platforms that can be used in electronic health records.

Over the last few years computer networks have experienced an explosive growth, causing congestion collapse problem, where no data transfers through the network, the throughput drops to zero, the response time tends to infinity, and as a result causing performance degradation. Congestion is handled at the end systems using end-to-end congestion control protocols, and at the network routers using network-assistant congestion control strategies, active queue management techniques (AQM) for example. Differ from data applications which built on top of transmission control protocol (TCP), most real-time traffics, have been built on top of unreliable connectionless user datagram protocol (UDP), such as voice-over-IP or streaming video over the Internet, since real-time applications can accept loss more than delay and jitter. Buffer control techniques are used to manage the queue size, and to enforce approximate fairness among a large number of different internet flows by queue management and scheduling disciplines. In this paper a new class-based dynamic scheduling technique is proposed. With this proposed technique, quality of service (QoS) requirements can be provided for multimedia video and audio traffic as same as that for the best-effort TCP-based data traffic applications. Using the network simulator NS-2 the proposal is compared with the most well-known scheduling approaches.

The deployment of Ad-hoc network is crucial for confined area, military, and emergency application. So, topology generation of connected Ah-hoc network is vital for dealing with such networks. Simulation tool is very important for ad hoc networks topology generation due to the expensive and difficulty of real experiments. In this paper we reviewed some of the available methods that concerned with the generation of Ad-hoc random graphs indicating their weakness. Two proposals for topology generation are presented and discussed in this paper. The proposed algorithms enable the user to generate various graphs by deciding 1) the number of nodes, 2) the radio range and 3) the minimum distance between any two nodes in the graph. The results show that the proposed algorithms are faster, accurate, and dependable than the traditional method.

"> Cloud storages in cloud data centers are used for enterprises and individuals to store and access their data remotely anywhere anytime without any additional burden. By data outsourcing, users can relieve the burden of local data storage and maintenance. However, one of the major problems of cloud environment is data storage security. Therefore, data auditing is introduced to verify the data in the cloud storages with the aid of Third Party Auditor (TPA). However, the TPA is leased by cloud service provider and after a time the provider may contract with the TPA to conceal the loss of data from the user to prevent the defamation. This paper presents a new hybrid approach for data storage security in cloud computing to protect organizations’ data from the cloud provider, the third party auditor and some users who may use their old accounts to access the data stored on the cloud. The hybrid approach enhances the authentication level of security by combining two efficient authentication techniques; Time-based One Time Password (TOTP) for cloud users verification and Automatic Blocker Protocol (ABP) to fully protect the system from unauthorized TPA. The experimental results demonstrate the effectiveness and efficiency of the proposed approach when auditing shared data integrity.

Display Omitted DNA microarrays appearances empowered the simultaneous observing of expression levels of a large number of genes.In the proposed methodology, Information gain (IG) is first used for feature selection, then Genetic Algorithm (GA) is employed for feature reduction and finally Genetic Programming (GP) is used for cancer types' classification. A cancers disease in virtually any of its types presents a significant reason behind death surrounding the world. In cancer analysis, classification of varied tumor types is of the greatest importance. Microarray gene expressions datasets investigation has been seemed to provide a successful framework for revising tumor and genetic diseases. Despite the fact that standard machine learning ML strategies have effectively been valuable to realize significant genes and classify category type for new cases, regular limitations of DNA microarray data analysis, for example, the small size of an instance, an incredible feature number, yet reason for limitation its investigative, medical and logical uses. Extending the interpretability of expectation and forecast approaches while holding a great precision would help to analysis genes expression profiles information in DNA microarray dataset all the most reasonable and proficiently. This paper presents a new methodology based on the gene expression profiles to classify human cancer diseases. The proposed methodology combines both Information Gain (IG) and Standard Genetic Algorithm (SGA). It first uses Information Gain for feature selection, then uses Genetic Algorithm (GA) for feature reduction and finally uses Genetic Programming (GP) for cancer types' classification. The suggested system is evaluated by classifying cancer diseases in seven cancer datasets and the results are compared with most latest approaches. The use of proposed system on cancers datasets matching with other machine learning methodologies shows that no classification technique commonly outperforms all the others, however, Genetic Algorithm improve the classification performance of other classifiers generally.

The original version of this article unfortunately contained a mistake. All algorithms are missing in the online PDF version. The original version has been corrected.