A Fast IMS Service Recovery Mechanism for the Handover Over MIH-Capable Heterogeneous Networks

IP multimedia subsystem (IMS) is the core multimedia network in the next generation all-IP environment. It provides access independence for multimedia applications across fixed and mobile access networks. When a roaming IMS subscriber connects to IMS through mobile access networks, handover becomes a critical issue; this needs to be addressed. Since IMS concerns application layer handover for session mobility, the application layer handover takes a long time for recovering the suspended sessions according to the standard IMS session reestablishment procedure. This introduces noticeable service interruption to end users and cannot be tolerated for real-time applications. In this paper we propose a fast IMS service recovery mechanism to shorten the service recovery latency by combining the IEEE 802.21 Media Independent Handover service and the IRTF Media-Independent Pre-Authentication frameworks. The proposed mechanism performs the necessary IMS registration and QoS re-negotiation procedures in advance of lower-layer handover. Thus it reduces the service recovery latency for suspended services. With parallel design in time, the proposed mechanism is able to shorten overall handover relevant latency as well. Technical examination shows that it is easy to deploy the proposed mechanism in current multimedia service environments.     

A new write/erase method to improve the read disturbcharacteristics based on the decay phenomena of stress leakage currentfor flash memories

This paper describes a new write/erase method for flash memory to improve the read disturb characteristics by means of drastically reducing the stress leakage current in the tunnel oxide. This new write/erase operation method is based on the newly discovered three decay characteristics of the stress leakage current. The features of the proposed write/erase method are as follows: 1) the polarity of the additional pulse after applying write/erase pulse is the same as that of the control gate voltage in the read operation; 2) the voltage of the additional pulse is higher than that of a control gate in a read operation, and lower than that of a control gate in a write operation; and 3) an additional pulse is applied to the control gate just after a completion of the write/erase operation. With the proposed write/erase method, the degradation of the read disturb life time after 10⁶ write/erase cycles can be drastically reduced by 50% in comparison with the conventional bipolarity write/erase method used for NAND type flash memory. Furthermore, the degradation can he drastically reduced by 90% in comparison with the conventional unipolarity write/erase method fur NOR-, AND-, and DINOR-type flash memory. This proposed write/erase operation method has superior potential for applications to 256 Mb flash memories and beyond     

基于FPGA和ADV212的图像实时压缩系统设计

设计了一种基于FPGA和ADV212为核心的图像数据实时压缩系统。该系统采用LVDS传输图像数据,利用FPGA为主控单元完成图像数据的接收,以及对ADV212的模式配置,数据写入,读取并把压缩数据实时上传到上位机,经过实际测试,该系统处理速度高,压缩较好,失真度小,具有较高的实用价值。     

A LP-based Admission Control Using Artificial Neural Networks for Integrated Services in Mobile Networks

In mobile networks the traffic fluctuation is unpredictable dueto mobility and varying resource requirements of multimedia applications.Henceit is essential to maintain the traffic within the network capacity to providethe service guarantees to running applications. Thispaper proposes an Admission Control (AC) scheme in a single mobile cellularenvironment supporting real-time and non-real-time application traffic. In thecase of a real-time and non-real-time multimedia applications, eachapplication has its own distinct range of acceptable Quality of Service (QoS)requirements(e.g., packet loss, delay, jitter, etc.). The network provides the service bymaintaining the application specified QoS range. We propose a LinearProgrammingResource Reduction (LP-RR) principle for admission control by maintainingQoSguarantees to existing applications and to increase the percentage ofadmissionto real-time and non-real-time applications. Artificial Neural Networks (ANNs)are used to solve linear programming problem, which facilitates an on-lineadmissioncontrol decision in the practical systems.The simulation results demonstrate that the proposed AC schemeperforms well in terms of admitted applications and maintains lower percentageof rejection to hand-off and new applications of different traffic classes.The suggested principle also shown that it is appropriate for the fairresourceallocation with improved resource utilization.     

基于SRAM高速灵敏放大器的分析与设计

在SOC系统级芯片中,存储器占有很重要的地位。随着电路频率的提高,存储器的读写操作速度也要求相应的加快。SRAM中的灵敏放大器通过检测位线上的微小变化并放大到较大的信号摆幅以减少延时,降低功耗。本文提出了一种两级串联结构的SRAM高性能灵敏放大器的设计方法,降低了对信号的反应时间,提高了抗干扰能力,适应高频电路的读写操作。     

Multimedia processors

This paper describes large-scale-integration programmable processors designed for multimedia processing such as real-time compression and decompression of audio and video as well as the generation of computer graphics. As the target of these processors is to handle audio and video in real time, the processing capability must be increased tenfold compared to that of conventional microprocessors, which were designed to handle mainly texts, figures, tables, and photographs. To clarify the advantages of a high-speed multimedia processing capability, we define these chips as multimedia processors. General-purpose microprocessors for workstations and personal computers (PCs) use special built-in hardware for multimedia processing, so the multimedia processors described include these modified general-purpose microprocessors. After reviewing the history of programmable processors, we classify multimedia processors into five categories depending on their basic architecture. The categories are reduced instruction set computer (RISC) microprocessors for workstations, complex instruction set computer microprocessors for PCs, embedded RISCs, low-power digital signal processors (DSPs), which are mainly used for mobile communications devices, and media processors that support PCs for multimedia applications. These five classes are then grouped into two: microprocessors with a multimedia instruction set and highly parallel DSPs. An architectural comparison between these two groups on the basis of Moving Picture Experts Group decoding applications is made, and the advantages and disadvantages of each class are clarified. Future processors, including “system on a chip,” and their applications are also discussed     

面向大数据的分布式缓存设计

大数据平台的底层存储系统往往无法匹配上层计算应用的读写性能,而一个设计良好的分布式缓存系统将缩小CPU密集型应用和IO密集型应用之间不匹配的性能差距。设计的面向大数据应用的分布式缓存系统,在读写流程、I/O事件驱动并发模型及元数据模型等方面进行了合理设计与优化,并使用fio工具测试了顺序写、随机写、顺序读及随机读场景下的吞吐率与IOPS等性能指标,验证了该分布式缓存系统的高性能优势和应对高并发场景的扩展能力。     

HDFS一致性管理的研究

HDFS是开源云计算项目Hadoop的存储系统,具有良好的容错性和扩展性,但是HDFS原有的一致性模型不能适用于实时性要求高,数据完整性要求不严格的任务。为了让HDFS能够满足云存储不同应用场景,在已有HDFS的总体架构和读写流程基础上,从数据一致性的角度剖析HDFS的局限和不足,提出解决方案,把NWR模型引入HDFS当中,并且将文件系统的读写锁机制改进为多粒度的锁机制。实验结果证明：通过以上措施,使用户可以根据自身需要配置云存储系统,平衡一致性和可用性。     

一种高性能的异步FIFO结构

针对现有FIFO设计方法的不足,本文提出一种新的异步FIFO结构——WG-FIFO,采用加权Gray码进行指针编码,采用实时状态检测器控制写/读操作.模拟结果表明,在FIFO深度为4~16的情况下,该结构与已有的FIFO结构相比在性能、面积开销以及写/读操作效率等方面都获得了明显的改善.特别地,当FIFO的深度为8、宽度为32时,相比B-FIFO,WG-FIFO的最高时钟频率提高31.6%,单元面积减少17.1%,且写/读效率最大能提高47%.     

Mobile Real-Time Collaboration for Semantic Multimedia

Advanced mobile applications that enable new ways of interaction with digital objects become increasingly important for on-site professional communities. These new ways of interaction, e.g. in Mobile Augmented Reality (MAR) via position and 3D movement, are real needs for fieldwork domains such as cultural heritage management and the construction industry. In addition, on-site professional communities generate shared knowledge bases with multimedia content and semantic annotations through collaboration. However, current MAR applications lack real-time collaboration features. In practice, blending multimedia semantics in mobile real-time collaboration is challenging due to the limitations of mobile devices, the lack of mature dedicated designed communication infrastructures and the constraints of the remote environments. This paper presents a mobile real-time collaboration system for semantic multimedia annotations with augmented reality features. We use XMPP as a real-time protocol for the secure, scalable and interoperable processing of XML-based semantic multimedia metadata described in MPEG-7. Our prototype was evaluated in the digital documentation of historical sites for cultural heritage management. The evaluation results indicate potential for increased productivity and enhanced mutual awareness in on-site professional communities.     

Dynamic adaptation policies to improve quality of service of real-time multimedia applications in IEEE 802.11e WLAN Networks

With the increased popularity of wireless broadband networks and the growing demand for multimedia applications, such as streaming video and teleconferencing, there is a need to support diverse multimedia services over the wireless medium. In order to efficiently address these diverse needs, efforts have been pursued to provide Quality of Service (QoS) mechanisms for medium access, resulting in a standard called IEEE 802.11e. One of the enhancements proposed in IEEE 802.11e is a polling-based access mechanism, which is targeted for real-time multimedia flows. In this polling-based scheme, scheduling and time allocation are based on flow reservations. Hence, the effectiveness of the mechanism is heavily dependent on the accuracy of the flow requirements in the reservation. Flow requirements, however, can vary over time and an allocation based on fixed reservations cannot address this variability. This limitation, which is present in the reference scheduler of IEEE 802.11e, leads to degraded multimedia quality for flows with variable requirements, even when channel resources are available. In order to address the above limitation, we present an adaptation framework that dynamically adjusts the polling-based access mechanism and associates flows to different modes of access (polling-based/contention-based), according to the current needs of the application, as opposed to solely relying on the reservation parameters. We demonstrate that with our adaptation, the achieved QoS for real-time multimedia streams, in terms of delay and throughput metrics, can be significantly improved compared to other known mechanisms. Additionally, we show the benefits of our adaptation framework on overall multimedia quality and system capacity. This research is supported by the University of California Discovery Grant (com02-10123) and the Center for Wireless Communications (CWC), University of California, San Diego.     

Hardware implementation of a disparity estimation scheme for real-time compression in 3D imaging applications

This paper presents a novel hardware implementation of a disparity estimation scheme targeted to real-time Integral Photography (IP) image and video sequence compression. The software developed for IP image compression achieves high quality ratios over classic methodologies by exploiting the inherent redundancy that is present in IP images. However, there are certain time constraints to the software approach that must be confronted in order to address real-time applications. Our main effort is to achieve real-time performance by implementing in hardware the most time-consuming parts of the compression algorithm. The proposed novel digital architecture features minimized memory read operations and extensive simultaneous processing, while taking into concern the memory and data bandwidth limitations of a single FPGA implementation. Our results demonstrate that the implemented hardware system can successfully process high resolution IP video sequences in real-time, addressing a vast range of applications, from mobile systems to demanding desktop displays.     

ECBRP: An Efficient Cluster-Based Routing Protocol for Real-Time Multimedia Streaming in MANETs

The dynamic characteristics of wireless networks and stringent QoS requirements of multimedia applications identify significant challenges for providing QoS guarantees for real-time multimedia streaming in such wireless environment. QoS routing protocols can decisively contribute to the QoS provision of network systems. This paper proposes an efficient cluster-based routing protocol (ECBRP) for real-time multimedia streaming in mobile ad hoc networks. First, to improve the stability of clusterheads, we introduce a new algorithm of cluster formation, in consideration of the node mobility and connectivity. Second, a link-broken detection mechanism is designed, which is able to distinguish whether packet loss is due to mobility or congestion, and to make proper reaction. This mechanism contributes to reduce route overhead, and to increase the decodable ratio of video frame at the application layer as well. Third, the routing protocol is enhanced via an adaptive packet salvage strategy, in order to alleviate the congestion in consideration of the characteristics of multimedia traffic. Our simulation experiment results demonstrate that the ECBRP leads to more stable cluster formation than the CBRP, and 80% decreases in the frequency of clusterhead changes against CBRP. As a result, the quality of real-time multimedia streaming is improved significantly, in terms of decodable frame ratio, delay and delay jitter, etc.     

Evaluation of header compression schemes for IP-based wireless access systems

For mobile IP-based telephony (voice over IP) and IP-based real-time multimedia over cellular radio systems, an economically viable solution is needed. It is an absolute requirement that, for example, the 60-octet IPv6/UPD/RTP headers on IP telephony packets be reduced in size to conserve bandwidth in the radio spectrum. We evaluate the performance of two header compression schemes, based on RFCs 2508 and 3095, under the conditions of cellular radio access technology. The results presented in this article refer to voice and Web browsing traffic and are based on the implementation of compression/decompression algorithms for the aforementioned standards. We find that RFC 3095 performs significantly better if used for mobile communications.     

基于FPGA技术的DRAM分时存取方法

介绍了一种基于现场可编程技术对DRAM进行读写和刷新操作的方法，根据现场可编程器件设计的特点，结合DRAM读写和刷新时序的要求，提出了同步化操作DRAM的思想，给出了具体同步化操作DRAM的实现方法，针对现场可编程器件设计中经常有多模块同时存取DRAM芯片的需求，提出了对DRAM芯片进行分时存取的方法，讨论了该方法的实现机制，结合具体的项目设计，给出了分时存取方法的关键时序，避开了复杂的DRAM控制器，节省了设计资源，简单方便地解决了DRAM操作的仲裁问题。     

Selective encryption for consumer applications

Selective encryption is a technique to save computational complexity or enable interesting new system functionality by only encrypting a portion of a compressed bitstream while still achieving adequate security. Although suggested in a number of specific cases, selective encryption could be much more widely used in consumer electronic applications ranging from mobile multimedia terminals through digital cameras were it subjected to a more thorough security analysis. We describe selective encryption and develop a simple scaler quantizer example to demonstrate the power of the concept, list a number of potential consumer electronics applications, and then describe an appropriate method for developing and analyzing selective encryption for particular compression algorithms. We summarize results from application of this method to the MPEG-2 video compression algorithm.     

Streaming Multimedia for the Internet

Multimedia streaming enables Web sites to be enhanced with real-time audio and video content. Through the appropriate use of video compression technologies, audio and video content can be delivered directly into the Web browser environment to create a rich mix of text, graphics and multimedia. The audio quality and video window size available to viewers is primarily determined by network access speeds. For the Internet, audio and video can be successfully streamed at rates between 20 kbit/s and 37 kbit/s over a PSTN modem link. In the corporate intranet environment, where higher end-to-end network speeds exist, audio and video can easily be streamed at rates between 56 kbit/s and 450 kbit/s. This paper illustrates how commodity video compression techniques facilitate the introduction of real-time multimedia streaming over IP networks. It describes the technology components within a basic video streaming system and provides an overview of two applications that utilise this technology, namely Intranet TV and BT Results Webcast. The underlying network protocols required to support real-time Internet applications are also discussed and network measurement statistics obtained from Intranet TV and BT Results Webcast are also presented.     

一种能耗优化的RAID小写预读方法

视频监控、备份、归档等应用产生海量存储数据，导致存储能耗急剧增加.S-RAID采用局部并行数据布局，可显著降低该类应用的存储能耗.为使更多磁盘待机节能，S-RAID通常执行"小写"操作，写操作时会额外引入等量的读操作，会显著降低性能.现有预读机制主要发生在文件级，无法感知RAID级小写引发的读旧数据、旧校验数据等读操作，因此不会也无法预读该类数据.为此，提出一种面向S-RAID的RAID级小写预读算法，由小写操作触发并在RAID级执行预读，根据S-RAID的数据布局方式，大粒度异步预读小写需要的旧数据、旧校验数据，有效减少I/O数和寻道数，提高磁盘的利用率.该方法可显著提高S-RAID的写性能，并且不依赖于任何额外硬件，具有更高的可用性.     

A User-Centered Approach to Active Replica Management in Mobile Environments

A replication scheme determines the number and location of replicas in a distributed system. Traditional static replication schemes do not perform well in mobile environments due to the assumptions of fixed hosts, relatively static access patterns, and the lack of considerations on users' behalf. For effective data management in mobile environments, we define the notion of activity-data dependency for inferring the information requirement of mobile users based on their scheduled activities. We then propose a dynamic replication scheme which employs user profiles for recording users' mobility schedules, accesses behaviors and read/write patterns, and actively reconfigures the replicas to adapt to changes in user locations, data requests, and system status. Simulation results demonstrate that the scheme can accurately predict the data requirement to facilitate effective replication, reduce response time, and increase data availability     

A Multi-Shared Register File Structure for VLIW Processors

The available instruction level parallelism allowed by current register file organizations is not always fully exploited by media processors when running a multimedia application. This paper introduces a novel register file organization, called multi-shared register file, that eliminates this superfluous instruction scheduling flexibility by reducing the number of read and write ports and partitioning the register file in a special ring structure. A parameterized generic VLIW architecture is used to explore different configurations of our proposed register file structure in terms of estimated silicon area, minimum clock period, estimated power consumption, and multimedia task processing performance. Moreover, a metric highly related to multimedia applications is introduced to study trade-offs between hardware cost and performance. The results show that by substituting a monolithic register file with an equivalent multi-shared register file, the estimated area and the power consumption are considerably reduced at the cost of a negligible performance degradation.