Search

Multicasting does not work well for video applications such as video on demand, where individual users request video content at discrete and unpredictable moments. In this paper, we study a concurrent video multicast orchestration solution for the caching-assisted and centrally controlled mobile networks. The proposed solution strives to obtain rapid video prefetch and effective traffic reduction. By rapid video prefetch, user devices can cache required contents in advance, which can effectively improve the streaming fluency in unsteady wireless environments, especially the highly mobile vehicular environment. We introduce a maximum-rate concurrent multicast (MRCM) problem whose solution is intended to maximize the total video delivery rate by a concurrent multicast manner, and prove that the MRCM problem is NP-hard. Then, we propose a dynamic concurrent multicast tree construction algorithm and a global concurrent multicast tree optimization algorithm to approximately solve the MRCM problem in polynomial time. We also introduce a cache competition mechanism that strives to maximize the total cache hit rate when the cache space is insufficient. Performance evaluations show that compared with the existing cache-assisted multicast delivery solutions, the proposed solution significantly reduces the video delivery duration and the traffic stress of backhaul links.

With the increasing connectivity between the Electronic Control Units (ECUs) and the outside world, safety and security have become stringent problems. The Controller Area Network (CAN) bus is the most commonly used in-vehicle network protocol, which lacks security mechanisms by design, so it is vulnerable to various attacks. In this paper, we propose a novel intrusion detection model called CNN-LSTM with Attention model (CLAM) for the in-vehicle network, especially CAN. The CLAM model uses one-dimensional convolution (Conv1D) to extract the abstract features of the signal values at each time step and feeds it into the Bidirectional Long Short Term Memory (Bi-LSTM) to extract the time dependence. By combining the attention mechanisms, we calculate the weight of each hidden state output by Bi-LSTM and perform a weighted summation, so that the model focuses only on locally important time steps, which can improve the convergence speed of the model and prediction accuracy. The proposed model uses the bit flip rate to extract continuous signal boundaries in the 64-bit CAN data, so it does not need to parse the CAN communication matrix and is suitable for different vehicles. The extensive evaluation results demonstrate that our proposed CLAM model can effectively detect CAN attacks, with an average F1-score of 0.951 and an error rate of 2.16%. Compared with the work in related research fields, the accuracy of attack detection is improved by 2.5%.

We identify vector perturbation (VP) precoding as a special case of nested lattice coding where the fine/coding lattice is adopted from the channel matrices, and the coarse/shaping lattice is in the self-similar form of the fine lattice. Since we still have the freedom to optimize the shaping lattice, in this work, we design an efficient algorithm to construct a rectangular shaping lattice for VP. This design is especially well-suited to the low-complexity approximations of VP, i.e., zero forcing (ZF) and successive interference cancellation (SIC) precoders. Simulations show that rectangular shaping based ZF and SIC precoders exhibit significant performance gains compared with their self-similar shaping based counterparts.

The k-winners-take-all (k-WTA) problem refers to the selection of k winners with the first k largest inputs over a group of n neurons, where each neuron has an input. In existing k-WTA neural network models, the positive integer k is explicitly given in the corresponding mathematical models. In this article, we consider another case where the number k in the k-WTA problem is implicitly specified by the initial states of the neurons. Based on the constraint conversion for a classical optimization problem formulation of the k-WTA, via modifying the traditional gradient descent, we propose an initialization-based k-WTA neural network model with only n neurons for n-dimensional inputs, and the dynamics of the neural network model is described by parameterized gradient descent. Theoretical results show that the state vector of the proposed k-WTA neural network model globally asymptotically converges to the theoretical k-WTA solution under mild conditions. Simulative examples demonstrate the effectiveness of the proposed model and indicate that its convergence can be accelerated by readily setting two design parameters.

The vision of the Internet of Things (IoT) covers not only the well-regulated processes of specific applications in different areas but also includes ubiquitous connectivity of more generic objects (or things and devices) in the physical world and the related information in the virtual world. For example, a typical IoT application, such as a smart city, includes smarter urban transport networks, upgraded water supply, and waste-disposal facilities, along with more efficient ways to light and heat buildings. For smart city applications and others, we require unique naming of every object and a secure, scalable, and efficient name resolution which can provide access to any object's inherent attributes with its name. Based on different motivations, many naming principles and name resolution schemes have been proposed. Some of them are based on the well-known domain name system (DNS), which is the most important infrastructure in the current Internet, while others are based on novel designing principles to evolve the Internet. Although the DNS is evolving in its functionality and performance, it was not originally designed for the IoT applications. Then, a fundamental question that arises is: can current DNS adequately provide the name service support for IoT in the future? To address this question, we analyze the strengths and challenges of DNS when it is used to support ubiquitous IoT. First, we analyze the requirements of the IoT name service by using five characteristics, namely security, mobility, infrastructure independence, localization, and efficiency, which we collectively refer to as SMILE. Then, we discuss the pros and cons of the DNS in satisfying SMILE in the context of the future evolution of the IoT environment.

Background In matrix completion fields, the traditional convex regularization may fall short of delivering reliable low-rank estimators with good prediction performance. Previous works use the alternation least squares algorithm to optimize the nonconvex regularization. However, this algorithm has high time complexities and requires more iterations to reach convergence, which cannot scale to large-scale matrix completion problems. We need to develop faster algorithm to examine large amount of data to uncover the correlations between items for the big data analytics. Results In this work, we adopt the randomized SVD decomposition and Nesterov’s momentum to accelerate the optimization of nonconvex matrix completion. The experimental results on four real world recommendation system datasets show that the proposed algorithm achieves tremendous speed increases whilst maintaining comparable performance with the alternating least squares (ALS) method for nonconvex (convex) matrix completions. Conclusions Our novel algorithm can achieve comparable performance with previous algorithms but with shorter running time.

The Normalized Discounted Cumulative Gain (NDCG) is used to measure the performance of ranking algorithms. Much of the work on learning to rank by optimizing NDCG directly or indirectly is based on list-wise approaches. In our work, we approximately optimize a variant of NDCG called NDCGβ using pair-wise approaches. NDCGβ utilizes the linear discounting function. We first prove that the DCG error of NDCGβ is equal to the weighted pair-wise loss; then, on that basis, RankBoostndcg and RankSVMndcg are proposed to optimize the upper bound of the pair-wise 0–1 loss function. The experimental results from applying our approaches and ten other state-of-the-art methods to five public datasets show the superiority of the proposed methods, especially RankSVMndcg. In addition, RankBoostndcg are less influenced by the initial weight distribution.

Domain Name System(DNS) is one of the most foundational and essential services on the Internet, the security and robustness of DNS are of great significance. However, the stable operation of DNS has been threatened by Distributed Denial of Service(DDoS) for quite a long time, especially when the number of registered names of. CN are over 20 million on November 11, 2016. According to our observation, the frequency of volume-based DDoS attacks increased rapidly in recent years, and when the attack happened, not only the authoritative servers were affected, servers of Top Level Domain(TLD) also suffered a lot. In this paper, a model based on Random Forest[1] is applied to traffic classification with an accuracy of 99.2% on Spark. The result shows that the model could be used to deal with large-scale DNS query flows, which is fast enough to be used in practice.

Two of the most promising candidate solutions for realizing the next-generation all-IP mobile networks are Mobile IPv6 (MIPv6), which is the host-based and global mobility supporting protocol, and Proxy MIPv6 (PMIPv6), which is the network-based and localized mobility supporting protocol. However, the unprecedented growth of mobile Internet traffic has resulted in the development of distributed mobility management (DMM) architecture by the Internet engineering task force DMM working group. The extension of the basic MIPv6 and PMIPv6 to support their distributed and scalable deployment in the future is one of the major goals of the DMM working group. We propose an all-IP-based mobility management architecture that leverages the concept of Named Data Networking (NDN), which is a distributed content management and addressing architecture. In the proposed solution, mobility support services are distributed among multiple anchor points at the edge of the network, thereby enabling a flat architecture that exploits name-based routing in NDN. Our approach overcomes some of the major limitations of centralized IP mobility management solutions, by extending existing routing protocol and mobility management architecture, to distribute the mobility management function of anchor points in the IP network and optimize the transmission path of mobile traffic.

Conjugate gradient (CG) methods are a class of important methods for solving linear equations and nonlinear optimization problems. In this paper, we propose a new stochastic CG algorithm with variance reduction and we prove its linear convergence with the Fletcher and Reeves method for strongly convex and smooth functions. We experimentally demonstrate that the CG with variance reduction algorithm converges faster than its counterparts for four learning models, which may be convex, nonconvex or nonsmooth. In addition, its area under the curve performance on six large-scale data sets is comparable to that of the LIBLINEAR solver for the L2-regularized L2-loss but with a significant improvement in computational efficiency, 10 pages, 4 figures, appeared in IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, CGVR algorithm is available on github: https://github.com/xbjin/cgvr

Despite the great success of graph-based transductive learning methods, most of them have serious problems in scalability and robustness. In this paper, we propose an efficient and robust graph-based transductive classification method, called minimum tree cut (MTC), which is suitable for large-scale data. Motivated from the sparse representation of graph, we approximate a graph by a spanning tree. Exploiting the simple structure, we develop a linear-time algorithm to label the tree such that the cut size of the tree is minimized. This significantly improves graph-based methods, which typically have a polynomial time complexity. Moreover, we theoretically and empirically show that the performance of MTC is robust to the graph construction, overcoming another big problem of traditional graph-based methods. Extensive experiments on public data sets and applications on web-spam detection and interactive image segmentation demonstrate our method's advantages in aspect of accuracy, speed, and robustness.

Phishing, also called brand spoofing, has become the most troubling scam on the Internet, which seriously threatens the Web security. The essence of phish is that "robbers" use false sites, which look like a trustworthy brand site, where favicon, logo and copyright notice are important brand identities. We analyzed 78-day phishing data of PhishTank and Anti-Phishing Working Group APWG. The statistics show that more than 98.93% phishing sites contain at least one brand entity-favicon, logo or copyright notice. Indeed, only a few lowest-quality phishing campaigns do not use such brand elements. Obviously, brand entities are powerful weapons of phishers to trick users. By analyzing the characteristics of brand entities in phishing sites, several brand identity features are extracted. However, only brand entities do not consider whether the Web page with brand entities belongs to the corresponding brand or has an authorization to use the brand entities. To solve this problem, redirection, incoming links and Domain Name System DNS information-based brand authorization features are further extracted to discriminate the sites with branding rights from phishing sites. Based on extracted features, statistical anti-phishing classification models are trained. We collected a diverse spectrum of corpora containing 3863 phishing cases from PhishTank and APWG, and 17571 legitimate samples from DMOZ, Google and DNS resolution log. Experimental evaluations show that the model achieves 98.8% true positive rate and 0.09% false positive rate, which demonstrates the competitive performances of extracted features for statistical anti-phishing in practice. Copyright © 2014 John Wiley & Sons, Ltd.

Based on the Information-Centric Networking (ICN) concept and the mature model of the current TCP/IP-based Internet, we propose content searching based on universal and scalable resource description, namely ISBORD (Internet Searching based on Resource Description). This novel concept aims to improve the efficiency of content searching and simplifies the end-user functionality to support the evolution of the content-centric Internet.

This paper presents a two-tiered reliable application layer multicast (ALM) solution, called HRALM, to provide lossless ALM services. HRALM builds a domain-based multicast tree, and divides the members into two transport planes (i.e., Plane 1 and Plane 2) in terms of the tree. In any domain, the distance between each member and the domain header is below a given threshold, which improves the capability of topology-awareness. According to the loss detected by members in different planes, HRALM adopts different but correlated recovery solutions. In HRALM, a member duplicates and forwards the received recovery packet to each of its children if it has not received the data unit carried by the recovery packet before receiving the recovery packet, which can actively recover the loss at the downstream nodes. The simulation experiments show that HRALM has desirable transport and recovery performance.

With the rapid growth of wireless technologies and handheld devices, m-commerce is becoming a promising research area. Personalization is especially important to the success of m-commerce. This paper proposes a novel collaborative filtering-based framework for personalized services in m-commerce. The framework extends our previous work by using Online Analytical Processing (OLAP) to represent the relations among user, content and context information, and adopting a multi-dimensional collaborative filtering model to perform inference. It provides a powerful and well-founded mechanism to personalization for m-commerce. We implemented it in an existing m-commerce platform, and experimental results demonstrate its feasibility and correctness.

In the protocol conformance testing, many existing test methods can effectively detect the possible faults of the implementation under test. However, it is difficult to diagnose the found faults in terms of the test results. This paper presents a diagnosable input/output (DIO) sequence, to differentiate a state from other states under a given condition. We further propose a two-tier protocol conformance testing and diagnosing method based on DIO sequences. The proposed method can effectively detect and diagnose the possible faults of the implementation of a protocol.