Transmission Control Protocol (TCP) is the most widely used protocol in the cloud data centers today. However, cloud data centers using TCP experience many issues as TCP was designed based on the assumption that it would primarily be used in Wide Area Networks (WANs). One of the major issues with TCP in the cloud data centers is the Incast issue. This issue arises because of the many-to-one communication pattern that commonly exists in the modern cloud data centers. In many-to-one communication pattern, multiple senders simultaneously send data to a single receiver. This causes packet loss at the switch buffer which results in TCP throughput collapse that leads to high Flow Completion Time (FCT). Recently, Software-Defined Networking (SDN) has been used by many researchers to mitigate the Incast issue. In this paper, a detailed survey of various SDN based solutions to the Incast issue is carried out. In this survey, various SDN based solutions are classified into four categories i.e. TCP Receive Window based solutions, Tuning TCP Parameters based solutions, Quick Recovery based solutions and Application Layer based solutions. All the solutions are critically evaluated in terms of their principles, advantages, and shortcomings. Another important feature of this survey is to compare various SDN based solutions with respect to different performance metrics e.g. maximum number of concurrent senders supported, calculation of delay at the controller etc. These performance metrics are important for deployment of any SDN based solution in modern cloud data centers. In addition, future research directions are also discussed in this survey that can be explored to design and develop better SDN based solutions to the Incast issue.

In order to increase the capacity and improve the spectrum efficiency of wireless communication systems, this paper proposes a rate-based two-sided many-to-one matching game algorithm for energy-harvesting small cells with non-orthogonal multiple access (NOMA) in heterogeneous cellular networks (HCN). First, we use a heuristic clustering based channel allocation algorithm to assign channels to small cells and manage the interference. Then, aiming at addressing the user access problem, this issue is modeled as a many-to-one matching game with the rate as its utility. Finally, considering externality in the matching game, we propose an algorithm that involves swap-matchings to find the optimal matching and to prove its stability. Simulation results show that this algorithm outperforms the comparing algorithm in efficiency and rate, in addition to improving the spectrum efficiency.

The coexisting wireless body area networks (WBAN) is a very challenging issue because of strong inter-networks interference, which seriously affects energy consumption and spectrum utilization ratio. In this paper, we study a power control strategy with nearest neighbor nodes distribution for coexisting WBAN based on stochastic geometry. Using homogeneous Poisson point processes (PPP) model, the relationship between the transmission power and the networks distribution is analytically derived to reduce interference to other devices. The goal of this paper is to increase the transmission success probability and throughput through power control strategy. In addition, we evaluate the area spectral efficiency simultaneously active WBAN in the same channel. Finally, extensive simulations are conducted to evaluate the power control algorithm.

It is well-known that virtualization technology can bring many benefits not only to users but also to service providers. From the view of system security and resource utility, higher resource sharing degree and higher system reliability can be obtained by the introduction of virtualization technology in distributed cloud. The small size time-sharing multiplexing technology which is based on virtual machine in distributed cloud platform can enhance the resource utilization effectively by server consolidation. In this paper, the concept of memory block and user satisfaction is redefined combined with user requirements. According to the unbalanced memory resource states and user preference requirements in multi-virtual machine environments, a model of proper memory resource allocation is proposed combined with memory block and user satisfaction, and at the same time a memory optimization allocation algorithm is proposed which is based on virtual memory block, makespan and user satisfaction under the premise of an orderly physical nodes states also. In the algorithm, a memory optimal problem can be transformed into a resource workload balance problem. All the virtual machine tasks are simulated in Cloudsim platform. And the experimental results show that the problem of virtual machine memory resource allocation can be solved flexibly and efficiently.

To support a large-scale Hadoop cluster, Hadoop heartbeat messages are designed to deliver the significant messages, including task scheduling and completion messages, via piggybacking to reduce the number of messages received by the NameNode. Although Hadoop is designed and optimized for high-throughput computing via batch processing, the real-time processing of large amounts of data in Hadoop is increasingly important. This paper evaluates Hadoop's performance and costs when the heartbeat period is controlled to support latency sensitive applications. Through an empirical study based on Hadoop 2.0 (YARN) architecture, we improve Hadoop's I/O performance as well as application performance by up to 13 percent compared to the default configuration. We offer a guideline that predicts the performance, costs and limitations of the total system by controlling the heartbeat period using simple equations. We show that Hive performance can be improved by tuning Hadoop's heartbeat periods through extensive experiments.

Task scheduling is one of the key issues in improving system performance and optimizing resource management in cloud computing environment. In order to provide appropriate services for heterogeneous users, we propose a novel task scheduling strategy with service differentiation, in which the delay sensitive tasks are assigned to the rapid cloud with high-speed processing, whereas the fault sensitive tasks are assigned to the reliable cloud with service restoration. Considering that a user can receive service from either local SaaS (Software as a Service) servers or public IaaS (Infrastructure as a Service) cloud, we establish a hybrid queueing network based system model. With the assumption of Poisson arriving process, we analyze the system model in steady state. Moreover, we derive the performance measures in terms of average response time of the delay sensitive tasks and utilization of VMs (Virtual Machines) in reliable cloud. We provide experimental results to validate the proposed strategy and the system model. Furthermore, we investigate the Nash equilibrium behavior and the social optimization behavior of the delay sensitive tasks. Finally, we carry out an improved intelligent searching algorithm to obtain the optimal arrival rate of total tasks and present a pricing policy for the delay sensitive tasks.

Handling vast amount of data found in large transactional datasets is an obvious challenge for the conventional data mining algorithms. Addressing this challenge, our paper proposes a parallel approach for proper decomposition of mining problem into sub-problems in order to find frequent patterns from these datasets. The proposed, Pattern Mining for Large Distributed Dataset (PMLDD) approach, ensures minimum dependencies as well as minimum communications among sub-problems. It establishes a linear aggregation of the intermediate results so that it can be adapted to large-scale programming models like MapReduce. In this context, an algorithmic structure for MapReduce programming model is presented. PMLDD guarantees an efficient load balancing among the sub-problems by a specific selection criterion. Further, it optimizes the number of required iterations over the dataset for mining frequent patterns as compared to the existing approaches. Finally, we believe that our approach is scalable enough to handle larger datasets in terms of performance evaluation, and the result analysis justifies all these mentioned concerns.

Since designing a feedback topology is a practical way to implement interference alignment at reduced cost of channel state information (CSI) feedback, six feedback topologies have been presented in prior works for a K-user multiple-input multiple-output interference channel. To fully reveal the potential benefits of the feedback topology in terms of the saving of CSI overhead, we propose a new feedback topology in this paper. By efficiently performing dimensionality-decreasing at the transmitter side and aligning interference signals at a subset of receivers, we show that the proposed feedback topology obtains substantial reduction of feedback cost over the existing six feedback designs under the same antenna configuration.

Mobile applications and social networks tend to enhance the need for high-quality content access. To address the rapid growing demand for data services in mobile networks, it is necessary to develop efficient content caching and distribution techniques, aiming at significantly reduction of redundant content transmission and thus improve content delivery efficiency. In this article, we develop optimal cooperative content cache and distribution policy, where a geographical cluster model is designed for content retrieval across the collaborative small cell base stations (SBSs) and replacement of cache framework. Furthermore, we divide the SBS storage space into two equal parts: the first is local, the other is global content cache. We propose an algorithm to minimize the content caching delay, transmission cost and backhaul bottleneck at the edge of networks. Simulation results indicates that the proposed neighbor SBSs cooperative caching scheme brings a substantial improvement regarding content availability and cache storage capacity at the edge of networks in comparison with the current conventional cache placement approaches.

Nowadays with the help of Location-Based Social Networks (LBSNs), users of Point-of-Interest (POI) recommendation service in LBSNs are able to publish their geo-tagged information and physical locations in the form of sign-ups and share their experiences with friends on POI, which can help users to explore new areas and discover new points-of-interest, and promote advertisers to push mobile ads to target users. POI recommendation service in LBSNs is attracting more and more attention from all over the world. Due to the sparsity of users' activity history data set and the aggregation characteristics of sign-in area, conventional recommendation algorithms usually suffer from low accuracy. To address this problem, this paper proposes a new recommendation algorithm based on a novel Preference-Content-Region Model (PCRM). In this new algorithm, three kinds of information, that is, user's preferences, content of the Point-of-Interest and region of the user's activity are considered, helping users obtain ideal recommendation service everywhere. We demonstrate that our algorithm is more effective than existing algorithms through extensive experiments based on an open Eventbrite data set.

Cloud computing offers a wide range of on-demand resources over the internet. Utility-based resource allocation in cloud data centers significantly increases the number of cloud users. Heavy usage of cloud data center encounters many problems such as sacrificing system performance, increasing operational cost and high-energy consumption. Therefore, the result of the system damages the environment extremely due to heavy carbon (CO2) emission. However, dynamic allocation of energy-efficient resources in cloud data centers overcomes these problems. In this paper, we have proposed Energy and Service Level Agreement (SLA) Aware Resource Allocation Heuristic Algorithms. These algorithms are essential for reducing power consumption and SLA violation without diminishing the performance and Quality-of-Service (QoS) in cloud data centers. Our proposed model is organized as follows: a) SLA violation detection model is used to prevent Virtual Machines (VMs) from overloaded and underloaded host usage; b) for reducing power consumption of VMs, we have introduced Enhanced minPower and maxUtilization (EMPMU) VM migration policy; and c) efficient utilization of cloud resources and VM placement are achieved using SLA-aware Modified Best Fit Decreasing (MBFD) algorithm. We have validated our test results using CloudSim toolkit 3.0.3. Finally, experimental results have shown better resource utilization, reduced energy consumption and SLA violation in heterogeneous dynamic cloud environment.

In this paper, for a spectrum sensing purpose, we heuristically established a test statistic (TS) from a sample covariance matrix (SCM) for multiple antennas based cognitive radio. The TS is formulated as a scaled-energy which is calculated as a sum of scaled diagonal entries of a SCM; each of the diagonal entries of a SCM scaled by corresponding row's Euclidean norm. On the top of that, by combining theoretical results together with simulation observations, we have approximated a decision threshold of the TS which does not need prior knowledge of noise power and primary user signal. Furthermore, simulation results - which are obtained in a fading environment and in a spatially correlating channel model - show that the proposed method stands effect of noise power mismatch (non-uniform noise power) and has significant performance improvement compared with state-of-the-art test statistics.

This work is mainly focused on two major topics in cloud platforms by using OpenStack as a case study: management and provisioning of resources to meet the requirements of a service demanded by remote end-user and relocation of virtual machines (VMs) requests to offload the encumbered compute nodes. The general framework architecture contains two subsystems: 1) An orchestrator that allows to systematize provisioning and resource management in OpenStack, and 2) A resource utilization based subsystem for vibrant VM relocation in OpenStack. The suggested orchestrator provisions and manages resources by: 1) manipulating application program interfaces (APIs) delivered by the cloud supplier in order to allocate/control/manage storage and compute resources; 2) interrelating with software-defined networking (SDN) controller to acquire the details of the accessible resources, and training the variations/rules to manage the network based on the requirements of cloud service. For resource provisioning, an algorithm is suggested, which provisions resources on the basis of unused resources in a pool of VMs. A sub-system is suggested for VM relocation in a cloud computing platform. The framework decides the proposed overload recognition, VM allocation algorithms for VM relocation in clouds and VM selection.

Wireless sensor network has been widely used in Internet of Things (IoT) applications to support large and dense networks. As sensor nodes are usually tiny and provided with limited hardware resources, the existing multiple access methods, which involve high computational complexity to preserve the protocol performance, is not available under such a scenario. In this paper, we propose an intelligent Medium Access Control (MAC) protocol selection scheme based on machine learning in wireless sensor networks. We jointly consider the impact of inherent behavior and external environments to deal with the application limitation problem of the single type MAC protocol. This scheme can benefit from the combination of the competitive protocols and non-competitive protocols, and help the network nodes to select the MAC protocol that best suits the current network condition. Extensive simulation results validate our work, and it also proven that the accuracy of the proposed MAC protocol selection strategy is higher than the existing work.

Recent works have validated the possibility of reducing the energy consumption in wireless heterogeneous networks, achieved by switching on/off some base stations (BSs) dynamically. In this paper, to realize energy conservation, the discrete time Markov Decision Process (DTMDP) is developed to match up the BS switching operations with the traffic load variations. Then, an asynchronous decision-making algorithm, which is based on the Bellman equation and the on/off priorities of the BSs, is firstly put forward and proved to be optimal in this paper. Through reducing the state and action space during one decision, the proposed asynchronous algorithm can avoid the "curse of dimensionality" occurred in DTMDP frequently. Finally, numerical simulations are conducted to validate the effectiveness and advantages of the proposed asynchronous on/off strategies.

Energy-efficient task scheduling on multi-core server is a fundamental issue in green cloud computing. Multi-core processors are widely used in mobile devices, personal computers, and servers. Existing energy efficient task scheduling methods chiefly focus on reducing the energy consumption of the processor itself, and assume that the cores of the processor are controlled independently. However, the cores of some processors in the market are divided into several voltage islands, in each of which the cores must operate on the same status, and the cost of the server includes not only energy cost of the processor but also the energy of other components of the server and the cost of user waiting time. In this paper, we propose a cost-aware scheduling algorithm ICAS for computation intensive tasks on multi-core server. Tasks are first allocated to cores, and optimal frequency of each core is computed, and the frequency of each voltage island is finally determined. The experiments' results show the cost of ICAS is much lower than the existing method.

Single pixel imaging technology has developed for years, however the video acquisition on the single pixel camera is not a well-studied problem in computer vision. This work proposes a new scheme for single pixel camera to acquire video data and a new regularization for robust signal recovery algorithm. The method establishes a single pixel video compressive sensing scheme to reconstruct the video clips in spatial domain by recovering the difference of the consecutive frames. Different from traditional data acquisition method works in transform domain, the proposed scheme reconstructs the video frames directly in spatial domain. At the same time, a new regularization called spatial cluster is introduced to improve the performance of signal reconstruction. The regularization derives from the observation that the nonzero coefficients often tend to be clustered in the difference of the consecutive video frames. We implement an experiment platform to illustrate the effectiveness of the proposed algorithm. Numerous experiments show the well performance of video acquisition and frame reconstruction on single pixel camera.

Object detection and tracking is the basic capability of mobile robots to achieve natural human-robot interaction. In this paper, an object tracking system of mobile robot is designed and validated using improved multiple instance learning algorithm. The improved multiple instance learning algorithm which prevents model drift significantly. Secondly, in order to improve the capability of classifiers, an active sample selection strategy is proposed by optimizing a bag Fisher information function instead of the bag likelihood function, which dynamically chooses most discriminative samples for classifier training. Furthermore, we integrate the co-training criterion into algorithm to update the appearance model accurately and avoid error accumulation. Finally, we evaluate our system on challenging sequences and an indoor environment in a laboratory. And the experiment results demonstrate that the proposed methods can stably and robustly track moving object.

Vehicular license plate (LP) recognition system has risen as a significant field of research recently because various explorations are currently being conducted by the researchers to cope with the challenges of LPs which include different illumination and angular situations. This research focused on restricted conditions such as using image of only one vehicle, stationary background, no angular adjustment of the skewed images. A real time vehicular LP recognition scheme is proposed for the skewed images for detection, segmentation and recognition of LP. In this research, a polar co-ordinate transformation procedure is implemented to adjust the skewed vehicular images. Besides that, window scanning procedure is utilized for the candidate localization that is based on the texture characteristics of the image. Then, connected component analysis (CCA) is implemented to the binary image for character segmentation where the pixels get connected in an eight-point neighbourhood process. Finally, optical character recognition is implemented for the recognition of the characters. For measuring the performance of this experiment, 300 skewed images of different illumination conditions with various tilt angles have been tested. The results show that proposed method able to achieve accuracy of 96.3% in localizing, 95.4% in segmenting and 94.2% in recognizing the LPs with an average localization time of 0.52s.

A voice is one of the most significant non-verbal elements for communication. Disorders in vocal organs, or habitual muscular setting for articulatory cause vocal disorders. Therefore, by analyzing the vocal disorders, it is possible to predicate vocal diseases. In this paper, a method of predicting vocal disorders using the jitter, shimmer, and harmonics-to-noise ratio (HNR) extracted from vocal records is proposed. In order to extract jitter, shimmer, and HNR, one-second's voice signals are recorded in 44.1khz. In an experiment, 151 voice records are collected. The collected data set is clustered using cobweb clustering method. 21 classes with 12 leaves are resulted from the data set. According to the semantics of jitter, shimmer, and HNR, the class whose centroid has lowest jitter and shimmer, and highest HNR becomes the normal vocal group. The risk of vocal disorders can be predicted by measuring the distance and direction between the centroids.

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

This research uses artificial intelligence methods for computer network intrusion detection system modeling. Primary classification is done using self-organized maps (SOM) in two levels, while the secondary classification of ambiguous data is done using Sugeno type Fuzzy Inference System (FIS). FIS is created by using Adaptive Neuro-Fuzzy Inference System (ANFIS). The main challenge for this system was to successfully detect attacks that are either unknown or that are represented by very small percentage of samples in training dataset. Improved algorithm for SOMs in second layer and for the FIS creation is developed for this purpose. Number of clusters in the second SOM layer is optimized by using our improved algorithm to minimize amount of ambiguous data forwarded to FIS. FIS is created using ANFIS that was built on ambiguous training dataset clustered by another SOM (which size is determined dynamically). Proposed hybrid model is created and tested using NSL KDD dataset. For our research, NSL KDD is especially interesting in terms of class distribution (overlapping). Objectives of this research were: to successfully detect intrusions represented in data with small percentage of the total traffic during early detection stages, to successfully deal with overlapping data (separate ambiguous data), to maximize detection rate (DR) and minimize false alarm rate (FAR). Proposed hybrid model with test data achieved acceptable DR value 0.8883 and FAR value 0.2415. The objectives were successfully achieved as it is presented (compared with the similar researches on NSL KDD dataset). Proposed model can be used not only in further research related to this domain, but also in other research areas.

Virtualization technology has been widely applied in the area of computer security research that provides a new method for system protection. It has been a hotspot in system security research at present. Virtualization technology brings new risk as well as progress to computer operating system (OS). A multi-level perception security model using virtualization is proposed to deal with the problems of over-simplification of risk models, unreliable assumption of secure virtual machine monitor (VMM) and insufficient integration with virtualization technology in security design. Adopting the enhanced isolation mechanism of address space, the security perception units can be protected from risk environment. Based on parallel perceiving by the secure domain possessing with the same privilege level as VMM, a mechanism is established to ensure the security of VMM. In addition, a special pathway is set up to strengthen the ability of information interaction in the light of making reverse use of the method of covert channel. The evaluation results show that the proposed model is able to obtain the valuable risk information of system while ensuring the integrity of security perception units, and it can effectively identify the abnormal state of target system without significantly increasing the extra overhead.