A Multi-Pronged Approach to Improving Semantic Extraction of News Video

In this paper we describe a multi-strategy approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature sets and multilingual linguistic resources, applying text retrieval approaches for image features, and establishing synergy between multiple concepts through undirected graphical models. We present a discriminative learning framework called Multi-concept Discriminative Random Field (MDRF) for building probabilistic models of video semantic concept detectors by incorporating related concepts as well as the low-level observations. The model exploits the power of discriminative graphical models to simultaneously capture the associations of concept with observed data and the interactions between related concepts. Compared with previous methods, this model not only captures the co-occurrence between concepts but also incorporates the raw data observations into a unified framework. We also describe an approximate parameter estimation algorithm and present results obtained from the TRECVID 2006 data. No single approach, however, provides a consistently better result for all concept detection tasks, which suggests that extracting video semantics should exploit multiple resources and techniques rather than naively relying on a single approach     

A Cross Layer Cluster Based Routing Approach for Efficient Multimedia Data Dissemination with Improved Reliability in VANETs

Wireless Personal Communications - Vehicular ad-hoc network (VANET) is a self-configuring decentralized dynamic network connects the vehicles through wireless links. Hence during the life time of...     

面向VANETs的服务质量的一种信道分配的新算法

车辆的高速移动,导致频繁地进行呼叫切换,这就使得信道分配成为车联网VANETs( Vehicular Ad Hoc Network)中最受关注的研究热点。为此,提出一种新的信道分配算法,标记为SBC算法。该算法引用信道再使用技术( Channel Reuse Technique)、信道借用( Channel Borrowing),并依据车辆行驶的速度计算发生切换的时间,从而提高服务质量QoS( Quality of Service)。仿真结果表明,提出的SBC算法在呼叫阻塞概率、丢失率和切换时延方面表现良好的性能。     

VANETs城市场景下基于自适应时延的Geocast路由协议

基于广播式的Geocast路由协议能够在特定的地理区域内高效地发布数据.然而,广播模式引起冗余重播,易导致广播风暴问题.另外,由于城市场景下建筑物的影响,现有的多数广播抑制方案难以应用于城市环境.为此,提出面向城市的基于自适应时延的Geocast路由协议UGAD.UGAD采用了基于自适应时延的广播抑制方案,降低发生广播风暴的概率.同时,考虑到交叉路口的地理优势,给位于交叉路口的车辆“优惠”时延,使其具有优先转发数据包权力,从而提高数据包到达率.此外,考虑到城市道路的复杂性,UAGD采用基于交叉路口转发IF和贪婪转发GF两个模式,依据不同的道路情况选择不同的转发模式,从而降低冗余重播,并保持高的数据包到达率.最后,针对城市场景进行仿真,结果表明提出的UGAD具有高的数据包到达率,低的数据包重播率.     

A Neuromorphic Architecture for Context Aware Text Image Recognition

The volume of textual data accessible on our planet is increasing every day. Extracting information hidden in this “Big Data” is a computationally intensive task. A key step of information extraction is the conversion of free text into a structured format. This step is typically achieved using regular expressions (regexs) and dictionaries. Unlike network intrusion detection systems, information extraction systems detect and report where precisely the specific and relevant information starts and ends within text documents. To improve precision and to eliminate ambiguity, regex matchers used in information extraction systems must support start and end offset position reporting, capturing groups, and specific regex-matching semantics, such as leftmost matching. This work describes a scalable regex-matching accelerator that supports such advanced regex-matching features and can be efficiently implemented in reconfigurable logic. Experiments on proprietary and open source regex sets comprising hundreds of regexs demonstrate an up to sixfold improvement of the area-delay product with respect to previous work.     

Determining the Representative Factors Affecting Warning Message Dissemination in VANETs

In this paper, we present a statistical analysis based on the 2k factorial methodology to determine the representative factors affecting traffic safety applications in Vehicular ad hoc networks (VANETs). Our purpose is to determine what are the key factors affecting Warning Message Dissemination (WMD) in order to concentrate on such parameters, thus reducing the amount of required simulation time when evaluating VANETs. Simulation results show that the key factors affecting warning messages delivery are: (i) the transmission range, (ii) the radio propagation model used, and (iii) the density of vehicles. Based on this statistical analysis, we evaluate a compound key factor: neighbor density. This factor combines the above-mentioned factors into a single entity, reducing the number of factors that must be taken into account for VANET researchers to evaluate the benefits of their proposals.     

A Context Quantization Approach to Universal Denoising

We revisit the problem of denoising a discrete-time, continuous-amplitude signal corrupted by a known memoryless channel. By modifying our earlier approach to the problem, we obtain a scheme that is much more tractable than the original one and at the same time retains the universal optimality properties. The universality refers to the fact that the proposed denoiser asymptotically (with increasing block length of the data) achieves the performance of an optimum denoiser that has full knowledge of the distribution of a source generating the underlying clean sequence; the only restriction being that the distribution is stationary. The optimality, in a sense we will make precise, of the denoiser also holds in the case where the underlying clean sequence is unknown and deterministic and the only source of randomness is in the noise. The schemes involve a simple preprocessing step of quantizing the noisy symbols to generate quantized contexts. The quantized context value corresponding to each sequence component is then used to partition the unquantized symbols into subsequences. A universal symbol-by-symbol denoiser (for unquantized sequences) is then separately employed on each of the subsequences. We identify a rate at which the context length and quantization resolution should be increased so that the resulting scheme is universal. The proposed family of schemes is computationally attractive with an upper bound on complexity which is independent of the context length and the quantization resolution. Initial experimentation seems to indicate that these schemes are not only superior from a computational viewpoint, but also achieve better denoising in practice.      

Application of Cognitive Techniques to Adaptive Routing for VANETs in City Environments

The evolution of smart vehicles has widened the application opportunities for vehicular ad hoc networks. In this context, the routing issue is still one of the main challenges regarding to the performance of the network. Although there are multiple ad hoc routing proposals, the traditional general-purpose approaches do not fit the distinctive properties of vehicular network environments. New routing strategies must complement the existing protocols to improve their performance in vehicular scenarios. This paper introduces a novel intelligent routing technique that makes decisions in order to adaptively adjust its operation and obtain a global benefit. The nodes sense the network locally and collect information to feed the cognitive module which will select the best routing strategy, without the need of additional protocol message dissemination or convergence mechanism.     

A Sequential Patterns Data Mining Approach Towards Vehicular Route Prediction in VANETs

Behavioral patterns prediction in the context of Vehicular Ad hoc Networks (VANETs) has been receiving increasing attention due to the enabling of on-demand, intelligent traffic analysis and real-time responses to traffic issues. One of these patterns, sequential patterns, is a type of behavioral pattern that describes the occurrence of events in a timely and ordered fashion. In the context of VANETs, these events are defined as an ordered list of road segments traversed by vehicles during their trips from a starting point to their final intended destination. In this paper, a new set of formal definitions depicting vehicular paths as sequential patterns is described. Also, five novel communication schemes have been designed and implemented under a simulated environment to collect vehicular paths; such schemes are classified under two categories: RSU (Road Side Unit)-based and Vehicle-based. After collection, extracted frequent paths are obtained through data mining, and the probability of these frequent paths is measured. In order to evaluate the effectiveness and efficiency of the proposed schemes, extensive experimental analysis has been realized.     

A Bayesian Approach to Adaptive Detection in Nonhomogeneous Environments

We consider the adaptive detection of a signal of interest embedded in colored noise, when the environment is nonhomogeneous, i.e., when the training samples used for adaptation do not share the same covariance matrix as the vector under test. A Bayesian framework is proposed where the covariance matrices of the primary and the secondary data are assumed to be random, with some appropriate joint distribution. The prior distributions of these matrices require a rough knowledge about the environment. This provides a flexible, yet simple, knowledge-aided model where the degree of nonhomogeneity can be tuned through some scalar variables. Within this framework, an approximate generalized likelihood ratio test is formulated. Accordingly, two Bayesian versions of the adaptive matched filter are presented, where the conventional maximum likelihood estimate of the primary data covariance matrix is replaced either by its minimum mean-square error estimate or by its maximum a posteriori estimate. Two detectors require generating samples distributed according to the joint posterior distribution of primary and secondary data covariance matrices. This is achieved through the use of a Gibbs sampling strategy. Numerical simulations illustrate the performances of these detectors, and compare them with those of the conventional adaptive matched filter.     

智能教室中情境感知的多通道融合方法

现有的智能教室中多通道融合方法普遍缺乏情境信息的感知能力,融合策略固定、简单,不能很好解决多通道输入的二义性、非精确、冲突性和时间偏序关系。针对以上问题,采用EMMA标注语言调整时序关系,用层次任务网络规划器HTN规划动作行为,用证据理论融合各个情感检测通道的检测结果,提出了一种通用可扩展的基于情境感知的多通道融合模型及方法。实验结果表明,该方法较好地解决了多通道学生情感检测的冲突性、二义性,提高了检测的精确性与正确性。     

A Cluster-Based Beaconing Approach in VANETs: Near Optimal Topology Via Proximity Information

A key component for safety applications in Vehicular ad-hoc network (VANET) is the use of periodic beacon messages which provide vehicles with a real-time vehicle proximity map of their surroundings. Based on this map, safety applications can be used for accident prevention by informing drivers about evolving hazardous situations. In order to allow synchronized and cooperative reactions, the target of this work is to design a beacon dissemination process that provides a real-time, broad and coordinated map under the challenging VANET conditions. In order to obtain the desired map, we consider an aggregation-dissemination based scheme for a beacon dissemination process that based on top of a cluster-based topology. To this end, we propose the Distributed Construct Underlying Topology (D-CUT) algorithm tailed specifically to provide an optimized topology for such beacon dissemination process. To deal with the heavy load of beacon messages required for an accurate and broad map, we propose a topology that allows the execution of extensive but reliable spatial bandwidth reuse. Our D-CUT algorithm exploits the real-time and coordinated map for constructing an adaptive and robust topology to deal with the dynamic nature of the VANET environment. We present theoretically provable bounds demonstrating the ability of the algorithm to deal with the dynamic nature of the VANET environment supported by simulation results.     

An Asynchronous Power Aware and Adaptive NoC Based Circuit

In complex embedded applications, optimisation and adaptation of both dynamic and leakage power have become an issue at SoC grain. A fully power-aware globally-asynchronous locally-synchronous network-on-chip (NoC) circuit is presented in this paper. Network-on-chip architecture combined with a globally-asynchronous locally-synchronous paradigm is a natural enabler for DVFS mechanisms. The circuit is arranged around an asynchronous network-on-chip providing scalable communication and a 17 Gb/s throughput while automatically reducing its power consumption by activity detection. Both dynamic and static power consumptions are globally reduced using adaptive design techniques applied locally for each synchronous NoC units. No fine control software is required during voltage and frequency scaling. Power control is localized and a minimal latency cost is observed.      

Coverage Differentiation Based Adaptive Tx-Power for Congestion and Awareness Control in VANETs

The use of Information and Communication Technology (ICT) as a copilot for the drivers has a potential to improve traffic safety and efficiency. A key challenge in integrating ICT in vehicular networks is to provide the mechanisms for the delivery of safety messages called beacons. In particular, finding the trade-off between providing sufficient coverage and controlling channel congestion remains the focus in the stipulated amendments for safety message transmissions. In this paper, we handle this trade-off by proposing a Multi-metric Power Control (MPC) approach, which uses application requirements and channel states to determine a transmit power for safety messages. The MPC gives a best-effort approach to satisfy the coverage range requirement of a message as specified by the application. Moreover, the concept distinguishes among message types to provide coverage differentiation. We show that the best-effort approach of providing coverage for different messages can control congestion and as a result improve awareness by minimizing beacon collisions. The performance analysis of MPC using discrete event simulation confirms its practicality.     

一种参数途径的自适应时延估计方法

时差定位应用中,需要首先对2个分开的传感器侦收的来波信号进行离散采样,然后估计时差。时差通常不是采样间隔的整数倍,导致常用时差估计方法的估计误差值可能达到0.5倍采样间隔。研究人员常用插值运算减小估计误差,但运算量较大。参数途径时延估计方法可以直接估计非整数倍采样间隔的时差,且不需要插值运算,运算量较小。应用(LMS)算法来实现参数途径时延估计方法,通过理论推导给出了时延估计的方法和步骤。计算机仿真验证表明了新方法的有效性和正确性。     

Real Time ML-Based QoE Adaptive Approach in SDN Context for HTTP Video Services

Wireless Personal Communications - Due to the high dynamism of network conditions, operators and service providers are facing the challenge of providing satisfactory user experience during a...     

Metadata and API Based Environment Aware Content Delivery Architecture

1IntroductionWiththe popularization of broadband network serviceand the rapid development of broadband applicationswith streaming media,the Quality of Service(QoS)requirement of networks is also increasing greatly.Althoughthe bandwidth is increasing and t…     

Node Attitude Aware Information Dissemination Model Based on Evolutionary Game in Social Networks

Mobile Networks and Applications - The information dissemination in social networks is affected by many factors. However, node attitude which is an important influence factor of information...