-
The essence of the peer-to-peer design philosophy is to design protocols for end hosts, or "peers", to work in collaboration to achieve a certain design objective, such as the sharing of a large file. From a theoretical perspective, it has been recognized that the peer-to-peer design paradigm resembles gossip protocols, and with appropriate algorithmic design, it maximizes the network flow rates in multicast sessions. Over the past ten years, research on peer-to-peer computing and systems, a unique and intriguing category of distributed systems, has received a tremendous amount of research attention from academia and indus-try alike. Peer-to-peer computing eventually culminated in a number of successful commercial systems, showing the viability of their design philosophy in the Internet. The peer-to-peer design paradigm has pushed all design choices of innovative protocols to the edge of the Internet, and in most cases to end hosts themselves. It represents one of the best incarnation of the end-to-end argument, one of the frequently dis-puted design philosophies that guided the design of the Internet. Yet, research on peer-to-peer computing has recently receded from the spotlight, and suffered from a precipitous fall that was as dramatic as its me-teoric rise to the culmination of its popularity. This article presents a cursory glimpse of existing results over the past ten years in peer-to-peer computing, with a particular focus on understanding what has stimulated its rise in popularity, what has contributed to its commercial success, and eventually, what has led to its pre-cipitous fall in research attention. Our insights in this article may be beneficial when we develop our thoughts on the design paradigm of cloud computing.
2012年01期 v.17 1-16页 [查看摘要][在线阅读][下载 517K] [下载次数：83 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Brad Rougeau;Mea Wang;
Peer-to-peer traffic constitutes more than 60% of today's Internet traffic, resulting in high band-width cost for ISPs. Recent efforts have been made to modify BitTorrent clients to reduce inter-ISP traffic. Although the results have been encouraging, recent research also reveals that global adaptation of such an approach may harm the download time as there is no clear evidence of persistent clustering in all ISPs. To this end, many large scale measurements on BitTorrent topology have been conducted by analyzing differ-ent snapshots of the BitTorrent network. However, the analysis overlooked the download time, the actual contributions of peers, and the distribution of peers throughout the file download period since the snapshots were obtained by querying the tracker for IP addresses of peers at a certain time. In this paper, we seek to understand to what extent the distribution of peers in BitTorrent relates to their contributions in data swarm-ing and transmission rates by studying real BitTorrent download traces. In order to present an unbiased view, we collected the traces from over 100 different files, including books (in different languages), music (in different languages), movies, and software (for different operating systems). The file size ranges from 4 MB to 4 GB. We also compared traces from a regular BitTorrent client with an ISP-friendly BitTorrent client to examine the actual impact of an ISP-friendly algorithm on download time and peer contributions. Our major findings include that distance has no effect on the download rate in general, seeds or lechers cannot always be found within the same ISP, and a torrent can only benefit from an ISP-friendly approach in certain situa-tions. Suggestions are given on how BitTorrent clients can be more ISP-friendly without sacrificing download rate.
2012年01期 v.17 17-28页 [查看摘要][在线阅读][下载 1048K] [下载次数：46 ] |[网刊下载次数：0 ] |[引用频次：8 ] |[阅读次数：0 ] -
In modern Peer-to-Peer (P2P) content distribution applications, multiple swarms typically exist, each corresponding to the dissemination of one content among interested peers. A common design in the existing P2P applications is to allow peers in one swarm to help each other, while different swarms are only coupled when sharing the upload bandwidth at the dedicated content servers/publishers. In recent years, a number of proposals have emerged which advocate inter-swarm collaboration and resource sharing, where peers in one swarm may contribute their storage and bandwidth resources to help peers in the swarm of another content. Such inter-swarm collaboration can improve content availability and optimize resource uti-lization in the entire system, at the cost of additional overhead for content preloading and inter-swarm coor-dination. This paper presents a survey of studies on effective inter-swarm collaboration mechanisms in the existing literature. This paper first discusses strategies of collaboration in P2P file sharing applications, and then presents multi-channel collaborative design for P2P live and Video-on-Demand (VoD) streaming. In particular, this paper elaborates our recent design of collaboration strategies among multiple streaming channels in a P2P VoD system, and shows that the server cost can be reduced by up to 25% while high streaming qualities are guaranteed in the entire system, even during extreme scenarios such as unexpected flash crowds. This paper also discusses representative approaches to implement inter-swarm collaborations in various P2P content distribution systems.
2012年01期 v.17 29-39页 [查看摘要][在线阅读][下载 608K] [下载次数：61 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] Detection of pedestrians in images and video sequences is important for many applications but is very challenging due to the various silhouettes of pedestrians and partial occlusions. This paper describes a two-stage robust pedestrian detection approach. The first stage uses a full body detector applied to a single image to generate pedestrian candidates. In the second stage, each pedestrian candidate is verified with a detector ensemble consisting of part detectors. The full body detector is trained based on improved shapelet features, while the part detectors make use of Haar-like wavelets as features. All the detectors are trained by a boosting method. The responses of the part detectors are then combined using a detector ensemble. The verification process is formulated as a combinatorial optimization problem with a genetic algorithm for optimization. Then, the detection results are regarded as equivalent classes so that multiple detections of the same pedestrian are quickly merged together. Tests show that this approach has a detection rate of over 95% for 0.1% FPPW on the INRIA dataset, which is significantly better than that of the original shapelet feature based approach and the existing detector ensemble approach. This approach can robustly detect pedestrians in different situations.
2012年01期 v.17 40-50页 [查看摘要][在线阅读][下载 1558K] [下载次数：223 ] |[网刊下载次数：0 ] |[引用频次：22 ] |[阅读次数：0 ] -
Content-based video copy detection is an active research field due to the need for copyright pro-tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score (F1) by 8%.
2012年01期 v.17 51-59页 [查看摘要][在线阅读][下载 620K] [下载次数：48 ] |[网刊下载次数：0 ] |[引用频次：5 ] |[阅读次数：0 ] Broadcast delivery of bulk multimedia files is an important wireless LAN application for densely populated scenarios such as inside high-speed train carriages. However, it is a challenge to adapt the broadcast link rate due to heterogeneity and varying channel conditions of the broadcast receivers to achieve both high bandwidth efficiency and fairness. In this paper, the broadcast link rate adaption problem is formulated as a quadratic programming problem with a broadcast link rate adaption algorithm named FBB (Fair and Bandwidth-efficient Broadcast). Simulation results show that the algorithm significantly outperforms fixed rate broadcast with only a small loss compared to its theoretical performance. The algorithm has been successfully applied in a practical wireless LAN access point.
2012年01期 v.17 60-66页 [查看摘要][在线阅读][下载 678K] [下载次数：56 ] |[网刊下载次数：0 ] |[引用频次：6 ] |[阅读次数：0 ] -
Intra refresh is an efficient and simple technique for suppressing temporal error propagation in video transmission over error-prone networks. However, most existing intra refresh algorithms do not make good use of the visual perceptual mechanism of the Human Visual System (HVS). This paper presents an intra refresh algorithm based on an attention model and a loss impact model. Intra refresh rates are allowed to vary for different image regions according to the HVS characteristic and the channel conditions to protect the most important macro-blocks against packet loss. A joint source-channel rate-distortion model was de-veloped taking into account the HVS characteristic to achieve an optimal end-to-end distortion for a better subjective quality. Tests demonstrate that, for the same bit rate and packet loss rate, this method provides a much better subjective feeling than existing intra refresh methods.
2012年01期 v.17 67-72页 [查看摘要][在线阅读][下载 561K] [下载次数：47 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] This paper presents a theoretical comparison of a single carrier system and a multi-carrier system through an analysis of the achievable rate under frequency selective fading with channel state information at the receiver. A scheme was designed to compare the achievable rates of a single carrier system and an Or-thogonal Frequency Division Multiplexing (OFDM) system. A thorough theoretical analysis of the two-path channel was conducted, and simulations were also used to analyze practical stochastic channels. Analysis and simulation results show that the achievable rates of the two approaches are comparable when the channel is flat fading. However, when the channel is frequency selective fading, the single carrier system outperforms the OFDM system. The achievable rate of the OFDM system is about 10% lower than that of the single carrier system at higher SNRs.
2012年01期 v.17 73-77页 [查看摘要][在线阅读][下载 416K] [下载次数：49 ] |[网刊下载次数：0 ] |[引用频次：5 ] |[阅读次数：0 ] - Albert Wang;
Traditional planar inductors in Radio Frequency (RF) Integrated Circuits (ICs) are plagued by large areas, low quality, and low frequencies. This paper describes a magnetic-based CMOS-compatible RF in-ductor. Magnetic-core inductors with various ferrite-filled structures, spiral structures, and magnetic material permeabilities were simulated to show that this inductor greatly improves the inductance by up to 97% and quality factor by 18.6% over a multi-GHz frequency range. The results indicate that the inductor is a very promising and viable solution to realize miniature, high quality, and high frequency on-chip inductors for high-end RF ICs.
2012年01期 v.17 78-83页 [查看摘要][在线阅读][下载 726K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] An equivalent circuit representation is presented for a set of coupled transmission lines. An ap-proximation of the hyperbolic secant function allows a simple derivation of a staged model that accounts for the complex frequency dependent parameters. The model converts the T-ladder network into a π-network with controlled sources. The equivalent circuit based approach presented here is not only intriguing but also enhances the computed accuracy and efficiency. Numerical simulations verify the accuracy of this approach for both time and frequency domain responses.
2012年01期 v.17 84-93页 [查看摘要][在线阅读][下载 798K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ] - Ikuyo Yoshinaga;
The phonation of Noh, a traditional Japanese style of singing, was investigated using electroglot-tographic and acoustical analyses. The dynamics of the laryngeal vibratory behaviors were analyzed for the singing voice of the Noh play compared with natural speech based on the Electroglottography (EGG) pa-rameters, EGG waveform, spectrum, and spectrogram. The result shows that Noh singing is characterized by low open quotient and high speed quotient. Three types of phonations are used in the singing with pressed, Vocal-Ventricular Mode (VVM), and growl voices. It was hypothesized that the period doubling ob-served in the EGG signal was reflective of VVM, which was caused by the phase difference in the vocal and ventricular fold oscillations, while the damped peak amplitude in every other cycle in the EGG signal was the result of the oscillations of the aryepiglottic folds at a frequency of half of the fundamental frequency. Sub-harmonics generated by the supraglottal oscillations add unique timbre to the sounds. The results suggest that the combination of phonation types is the key factor in generating their peculiar voice qualities.
2012年01期 v.17 94-103页 [查看摘要][在线阅读][下载 915K] [下载次数：32 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] Cross-correlating traffic flow data at different intersections in an urban transportation network is important for understanding the collective behavior of constituents in a complex system and for predicting the risk of network-wide congestion. In this work, a Random Matrix Theory (RMT) based method is used to describe the collective behavior from massive traffic data sets. Nonrandom correlations between traffic flow series recorded in the Beijing road network occur both with and without detrending. The effect of the traffic load on the correlation patterns of network-wide traffic flows is analyzed using the RMT analysis of a simulated data set collected from Paramics. The RMT analysis is also used to evaluate the impact of incidents on the network-wide traffic status. Cluster analysis is used to find the largest cluster in the network which indicates the critical congestion caused by the incident. All the results show that RMT analyses are an effective method for investigating systematic interactions in urban transportation systems.
2012年01期 v.17 104-112页 [查看摘要][在线阅读][下载 830K] [下载次数：69 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] -
<正>Tsinghua Science and Technology (Tsinghua Sci Technol), a comprehensive academic journal sponsored byTsinghua University, is published bimonthly. This journal aims at presenting the up-to-date scientific achievementswith high creativity and great significance in engineering fields, especially in computer and electronic engineering.
2012年01期 v.17 113页 [查看摘要][在线阅读][下载 646K] [下载次数：14 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ] 下载本期数据