In the 1960's, the problems of distributed systems management did not exist. Systems were centralized and typically housed in one facility. Over time, however, the power, complexity and connectivity of the computer systems and networks evolved. Today, businesses are dependent on their compute and networking infrastructures to operate and survive. These infrastructures are geographically and functionally distributed, and their management is critical. This paper discusses how distributed systems management has evolved, and what the future may bring.

With no doubt the Internet will achieve advantages in exploiting software agents for applications, thanks to their autonomy in carrying out tasks. In such a scenario, appropriated methodologies are needed to manage the interactions among agents. The BRAIN framework proposes an interaction model based on roles, each one composed by a set of capabilities and an expected behavior. The achieved advantages are agent-oriented features, separation of concerns and reuse of solutions and experiences. In this paper we present two interaction infrastructures, Rolesystem and RoleX, which rely on the above mentioned role-based interaction model. These infrastructures allow agents to assume roles and to interact. An application example and the comparison with other approaches show the effectiveness of our approach.

This paper presents the performance modeling application of SIP-T (Session Initiation Protocol for Telephones) signaling system based on two-class priority queueing process in carrier class VoIP (Voice over IP) network. The SIP-T signaling system defined in IETF (Internet Engineering Task Force) is a mechanism that uses SIP (Session Initiation Protocol) to facilitate the interconnection of existing PSTN (Public Switched Telephone Network) with carrier class VoIP network. One of the greatest challenges in the migration from PSTN toward NGN (Next Generation Networks) is to build a carrier class VoIP network that preserves the ubiquity, quality, and reliability of PSTN services while allowing the greatest flexibility for use of new VoIP technology. Based on IETF, the SIP-T signaling system not only promises scalability, flexibility, and interoperability with PSTN but also provides call control function of MGC (Media Gateway Controller) to set up, tear down, and manage VoIP calls in carrier class VoIP network. This paper presents the two class priority queueing model, performance analysis, and simulation of SIP-T signaling system in carrier class VoIP network focused on toll by-pass or tandem by-pass of PSTN. In this paper, we analyze the average queueing length, the mean of queueing delay, and the variance of queueing delay of SIP-T signaling system that are the major performance evaluation parameters for improving QoS (Quality of Service) and system performance of MGC in carrier class VoIP network. A mathematical model of the M/G/1 queue with two-class non-preemptive priority assignment is proposed to represent SIP-T signaling system. Then, the formulae of average queueing length, queueing delay, and delay variation for the non-preemptive priority queue are expressed respectively. Several significant numerical examples of average queueing length, queueing delay, and delay variation are presented as well. Finally, the two-class priority queueing model and performance analysis of SIP-T signaling system are shown the accuracy and robustness after the comparison between theoretical estimates and simulation results.

The explosive growth of the Web contents has led to increasing attention on two major challenges: scalability and high availability of network file system. In this paper, based on our previous reports, we introduced the concept of intermediate file handle to cover the heterogeneity of file system and proposed a new data consistency scheme to reduce the overhead of write request in the reliable network file system. In addition, we also proposed a simple load-sharing mechanism for NFS client to switch to a lightly-load server in order to improve the response time of READ requests. With such an approach, NFS Clients are always active. They issued their requests and waited the corresponding replies. Finally, we analyzed the new data consistency scheme. It shows truly that the scheme is able to improve the performance of our network file system

This paper presents measurement and analysis of various networks and applications using a high-speed IP meter. The authors have developed a high-speed IP meter with a GPS timestamp component, which enables precise measurement of packet delay and jitter in various networks. Measurement of the following networks was performed, 1) Measurement of traffic in a commercial IPv6 access service on ADSL, as a typical broadband access service network. 2) Measurement of traffic in the 54th IETF meeting in Yokohama, as a typical high-speed Internet backbone network. This paper reports the characteristics identified in these networks, e.g. asymmetricities of one-way packet delay over an ADSL access network and the difference in TCP/UDP packet delay over a high-speed backbone network. It also presents the analysis results of some multimedia applications in the Internet, and discusses the quality of service on Internet access service networks.

The QoS(Quality of Service) guarantee mechanism is one of critical issues in the wireless network. Real-time applications like VoIP(Voice over IP) in All-IP networks need smooth handoffs in order to minimize or eliminate datagram loss as a Mobile Host(MH) transitions between network links. In this paper, we design a new DB(Dynamic Buffering) mechanism for IPv6 by which an MH can request that the router on its current subnet buffers packets on its behalf while the MH completes registration procedures with the router of a new subnet. Performance results show that our proposed buffering scheme with a dynamic buffer space allocation is quite appropriate for mobile Internet, or the All-IP environment in terms of the datagram loss rate and average waiting time.

The first practical approach to 100-Gigabit Ethernet, i.e., Ethernet with a throughput of 100-Gb/s, is proposed for use in the next generation of LANs for GRID computing and large-capacity data centers. New structures, including a coding architecture, de-skewing method and high-speed packaging techniques, are introduced to the PHY layer to obtain the required data rate. Our form of 100-Gigabit Ethernet uses 10-Gb/s 10-channel CWDM or parallel-optical links. The coding architecture is formed of 64B/66B codes, modified for the CWDM and parallel links. In the de-skewing of the parallel signals, specially designed IDLE characters are used to compensate for skewing of data in the respective signal lanes. Advanced packaging techniques, which suppress the propagation loss and reflection of the 10-Gb/s lanes to obtain high-speed, good integrity and low-noise signaling, are proposed and evaluated. The proposed architectural features make this 100-Gigabit Ethernet concept practical for next-generation LANs.

Hash-based IP traceback is a technique to generate audit trails for traffic within a network. Using the audit trails, it reconstructs not only the true attack paths of a Distributed Denial of Service attack (DDoS attack), but also the true path of a single packet attack. However, hash-based IP traceback cannot identify attacker nodes themselves because it has no audit trail on the subnet's layer-2 network under the detected leaf router, which is the nearest node to an attacker node on a layer-3 network. We propose a layer-2 extension to hash-based IP traceback, which stores two identifiers with packets' audit trails while reducing the memory requirement for storing identifiers. One of these identifiers shows the leaf router's interface through which an attacking packet came, and the other represents the ingress port on a layer-2 switch through which the attacking packet came. We implement a prototype on FreeBSD and evaluate it in a preliminary experiment.

The recent evolution on the network tomography have successfully provided principles and methodologies of inferring network-internal (local) characteristics solely from end-to-end measurements, which should be followed by deployment in practical use. In this paper, two kinds of user-oriented tools for inferring one-way packet losses based on the network tomography are proposed. They can infer one-way packet loss rates on paths or path segments from/to a user-host (a client) to/from a specified target host (an application server or a router) without any measurement on the target, and thus can find the congested area along the path between the client and an application server. One is a stand-alone tool running on the client, and the other is a client-server style tool running on both the client and a proxy measurement server distributed in the Internet. Prototypes of the tools have been developed and evaluated by experiments in the actual Internet environment, which shows that the tools can infer the loss rates within 1% errors in various network conditions.

Various network resources, including wireless access services and multimedia appliances (device) are expected to be available in ubiquitous computing environments. Since resource availability can change when a user migrates from one place to another, functions to monitor the availability of resources in use and, if necessary, switch from obsolete resources to new ones are necessary for continuous service provision. This paper proposes adaptive terminal middleware called AMID that performs policy-based dynamic resource selection and host-based session management to ease network administrative tasks, and hide session failures and resource changes from applications and a user. AMID supports two kinds of mobility; session maintenance on vertical handoff and device handoff (service mobility). By AMID, a mobile host keeps entire handoff control and session state to eliminate the need for network-layer or intermediate-node mobility support, and mitigate responsibility of devices for session management. AMID realizes a Reliable Virtual Socket (RVS), on top of real sockets, which employs a seamless session handoff mechanism for resource changes, and a reliable session resume mechanism against unplanned disconnection of a wireless link. It achieves seamless session handoff through a proactive soft handoff method; to conceal setup and signaling latency, it initiates setup procedures with neighbor resources in advance of actual handoff and utilizes multiple wireless interfaces and devices redundantly. We implemented AMID and a follow-me audio application on top of it to evaluate the performance. Redirection of audio streams from built-in speakers to external ones, and handoff between 802.11b and Cellular are autonomously performed when a user migrates in the house. We confirmed that AMID achieved reliable session maintenance against wireless link failure, concealed latency of handoff management, and prevented packet loss during handoff.

Recently routing protocols for QoS aware multicast are actively studied, but there are few studies focusing on the scalability of link state advertisement when the available bandwidth of a link is updated along with the QoS aware multicast tree construction. This paper proposes a new QoS aware multicast routing protocol that is scalable in terms of the link state advertisement exchange. Our protocol has the following features; (1) A multicast network is divided into domains, and the advertisement of information on links within a domain is limited within the domain. (2) Among the border multicast routers, only the link state information of inter-domain links is advertised. As a result, the number of link state advertisement messages will be drastically reduced. (3) When a multicast tree spreads over multiple domains, the tree construction needs to be performed without information on links in other domains, and it is possible that the construction may fail. In order to cope with this problem, the crank back mechanism of a tree construction is introduced. This paper describes the detailed procedures and the message formats of our protocol. It also describes the evaluation of the number of exchanged link state advertisement messages and shows that our protocol can reduce the number comparing with the conventional protocols.

The auction is a popular way of trading. Despite of the popularity of the auction, only a small number of papers have addressed the protocol which realize the double auction. In this paper, we propose a new method of double auction which improves the algorithm of the existing double auction protocol. Our new method is based on the idea of number comparison which is realized by homomorphic encryption. The new method solves the problem of the privacy of losing bids found in the existing algorithm. The buyers and the sellers can embed a random number in their bidding information by the use of the homomorphic encryption. The players in an auction cannot get anyone else's bidding information. The new method is more efficient than the existing ones. Our new method satisfies the criteria for the auction protocol.

We previously proposed a change-of-measure based performance measurement method which combines active and passive measurement to estimate performance experienced by user packets and applied this to estimate packet delay. In this paper, we apply it to estimating loss rate. Since packets are rarely lost in current networks, rate measurement usually requires a huge number of probe packets, which imposes a non-negligible load on networks. We propose a loss-rate estimation method which requires significantly fewer number of probe packets. In our proposed method, the correlation between delay and loss is measured in advance, and at the time of measurement, the time-averaged loss rate is estimated by using the delay of probe packets and the correlation. We also applied our change-of-measure framework to estimating the loss rate in user packets by using this time-averaged loss rate. We prove that the mean square error in our method is lower than that simple loss measurement, which is estimated by dividing the number of lost packets by the total number of sent packets. We evaluated our method through simulations and actual measurements and found that it can estimate below 10^-3 packet loss rate with only 900 probe packets.

We have developed an OC-48c (2.4 Gbps) PCI-compliant network interface card and drivers with the aim of evaluating the effectiveness of our proposed link layer protocol MAPOS. In this paper, we study the effectiveness of MAPOS particularly from the viewpoint of the influence of packet sizes up to the 64-kbyte jumbo MTU size and the effectiveness of our new implementation of the non-interrupt-driven sending process and interrupt batching receiving process deployed to improve the throughput in short-packet transmissions. Our main findings are as follows;
Enlarging the packet size up to 64-kbyte MTU improves the performance in transmission. OC-48c wire speed is achieved with packet sizes larger than 16 kbytes.
Implementation of the non-interrupt-driven sending process and the interrupt batching receiving process improves the performance of short-packet transmission. In particular, the transmission throughput is improved by 50% when 64-byte short packets are used. The maximum loss-free receive rate is also raised by 50% when 4-kbyte packets arrive.
With a high-performance CPU, the data-transfer speed of the DMA controller for jumbo packets cannot keep up with the packet-queueing speed of the CPU. Our proposed procedure for adaptive algorithm switching method can resolve this problem.
The maximum TCP throughput observed in our measurement using the latest PCs and MAPOS OC-48c PCI card was 2342.5 Mbps. This throughput represents the highest performance in a legacy-PCI-based system according to the results database of the benchmarking software.

A tree 3-spanner T of a graph G is a spanning tree of G such that the distance between any two vertices in T is at most 3 times of their distance in G. Madanlal et al. have presented an O(n + m) time algorithm for finding a tree 3-spanner of a permutation graph. However, the complexity of their algorithm is not optimal, and their algorithm can not be easily parallelized. In this paper, we will propose an improved algorithm to solve the same problem in O(n) time. Moreover, our algorithm can be easily parallelized so that a tree 3-spanner of a permutation graph can be found in O(log n) time with processors on the EREW PRAM computational model.

To speed up on-line analytical processing (OLAP), data warehouse, which is usually derived from operational databases, is introduced. When the operational databases happen to change, the data warehouse gets stale. To maintain the freshness of data warehouse, operational database changes need to be frequently and concurrently propagated into the data warehouse. However, if several update transactions are allowed to execute concurrently without an appropriate concurrency control, data inconsistency between data warehouse and operational databases could arise due to incorrect propagation of changes on the operational databases into the data warehouse. In this paper, we propose a new concurrency control scheme, which could execute a number of update transactions in a consistent way. Whenever an update transaction tries to update a data that is being used by OLAP transactions, our scheme allows the update transaction to create a new version of the data. To investigate the applicable areas of our scheme, its performance is evaluated by means of simulation approach. Our experimental results show that the proposed scheme enables OLAP transactions to continuously read a very fresh data without wasting a lot of time to find out an appropriate version of the data from the version pool.

A two stage non-scan design for testability method is proposed. The first stage selects test points based on an earlier testability measure conflict. A new design for testability algorithm is proposed to select test points by a fault-oriented testability measure conflict+ in the second stage. Test points are selected in the second stage based on the hard faults after the initial ATPG run of the design for testability circuit in the preliminary stage. The new testability measure conflict+ based on conflict analysis of hard-faults in the process of test generation is introduced, which emulates most general features of sequential ATPG. The new testability measure reduces testability of a fault to the minimum D or controllability of the primary outputs, and therefore, does not need observability measure any more. Effective approximate schemes are adopted to get reasonable estimation of the testability measure. A couple of effective techniques are also adopted to accelerate the process of the proposed design for testability algorithm. Experimental results show that the proposed method gets even better results than two of the recent non-scan design for testability methods nscan and lcdft.

Files of 3D mesh models are often large and hence time-consuming to retrieve from a storage device or to download through the network. Most 3D viewing applications need to obtain the entire file of a 3D model in order to display the model, even when the user is interested only in a small part, or a low-resolution version, of the model. Therefore, coding that enables multiresolution and ROI (Region Of Interest) transmission of 3D models is desired. In this paper, we propose a coding algorithm of 3D models based on partitioning schemes. The algorithm actually partitions the 3D meshes into some small sub-meshes according to some geometric criteria (such as curvatures), and then codes each small sub-meshes separately to transmit it progressively to users on demand. The key idea of this paper lies in the mesh partitioning procedure prior to its LOD control, which enables good compression ratio of the mesh data as well as some other good capable properties through network transmission such as ROI coding, view-adaptive transmission, error resilient coding, etc.

Constraints have been used extensively for the construction of graphical user interfaces. User interface constraints that are declarative are more favorable but require sophisticated constraint planning algorithms. Constraint planning algorithms proposed previously are getting more and more complicated as they were asked to handle more general requirements. We believe that the difficulty is mainly caused by the complicated data structure that is translated directly from the problem. By a transformation, we propose a simplified graph model for the problem and prove that the constraint planning problem can be reduced to finding feedback vertex sets on the simplified graph model. We also consider the general problem of handling non-uniform user interface constraints.

This paper presents a novel digit-level algorithm for motion estimation (ME) and its hardware implementations. It uses the most-significant-digit-first (MSD-first) processing and on-line arithmetic ME components. A dedicated array architecture is also proposed for applications with high-throughput ME. Various fast search algorithms were presented in literatures to reduce the complexity but sacrifice the motion vector (MV) quality. Our MSD-first ME decomposes the summation of absolute differences (SAD) and comparison operations to digit level with MSD-plane first. These comparisons are interleaved into SADs to distinguish the MV as soon as possible. The algorithm precisely extracts the impossible candidates and removes their rest operations. It saves 47.4 % to 64.3 % of SAD computations in full search block matching (FSBM) ME. In the past, the high implementation cost of redundant number system prevented the practical use of on-line arithmetic. Besides, the redundant SAD removal results in irregular data flow in system-level integration. All these problems are solved by our novel architecture design. In this paper, we propose novel architecture designs to solve these problems. Besides, the architecture requires only one memory access per pixel to lower memory bandwidth by extensive data parallelism and a particular memory addressing while keeping the controller simple. A 4 4 array processor is implemented in 0.35 µm 1P4M CMOS cell library, with 2.84 ns cycle time and 1510 gates. It can support 83 M FSBM operations per second. After normalization, our implementation can support 2.67 times SAD operations per unit area (estimated in gate count) of the conventional two's complement ones. MSD-first ME can realize with other ME algorithms to improve the performance as well.

The objective of this paper is to study the relationship between a visual stimulus and the amplitude and phase of the alpha wave as a first step to investigating a change in the background wave after a sensory stimulus and an evoked potential. We examined the effect of a single visual stimulus on the amplitude and phase of alpha waves using the complex demodulation method. The visual stimuli were generated by an LED mounted in goggles with the eyes-closed condition. The amplitude of the alpha wave decreased gradually after the stimulus, until it reached a minimum at around 300 ms after the stimulus. The alpha wave continued to increase, showing some rebound, and returning again to the pre-stimulus level. The phase variation after the stimulus tends to be considerably larger than that before the stimulus. Moreover, the average phase returned to the same slope as the pre-stimulus by 2550 ms after the stimulus. The visual stimulus has an effect on the alpha wave until about 2500 ms after the stimulus. The phase variation difference before and after stimulus is significant from 112 ms to 678 ms after the stimulus. This finding suggests there is a partially pararell time course between the change in VEPs plus ERP complex and the alpha wave.

We have developed a three-dimensional eye movement simulator that simulates eye movement. The simulator allows us to extract the instantaneous eye movement rotation axes from clinical data sequences. It calculates the plane formed by rotation axes and displays it on an eyeball with rotation axes. It also extracts the innervations for eye muscles. The developed simulator is mainly programmed by a CG programming language, OpenGL. First, the simulator was applied to saccadic eye movement data in order to show the so-called Listing's plane on which all hypothetical rotation axes lie. Next, it was applied to clinical data sequences of two patients with benign paroxysmal positional vertigo (BPPV). Instantaneous actual rotation axes and innervations for eye muscle extracted from data sequences have special characteristics. These results are useful for the elucidation of the mechanism of vestibular symptoms, particularly vertigo.

Digital Subtraction Angiography (DSA) is a technique used for enhancement of small details in angiogram imaging systems. In this approach, X-ray images of a subject, after injection, are subtracted from a reference X-ray image, taken from the same subject before injection. Due to the exponential absorption property of X-rays, effects of small details at different depth appear differently on X-ray images. Consequently, image subtraction cannot be employed on the original images without any adjustment or modification. Proper modification, in this case, is to use some form of logarithmic operation on images before subtraction. In medical imaging systems, the system designer has a choice to implement this logarithmic operation in the analog domain, before digitization of the video signal, or in the digital domain after analog-to-digital conversion (ADC) of the original video signal. In this paper, the difference between these two approaches is studied and upper bounds for quantization error in both cases are calculated. Based on this study, the best approach for utilization of the logarithmic function is proposed. The overall effects of these two approaches on the inherent signal noise are also addressed.

In this note, we present some results about parses of codes. First we present a sufficient condition of a bifix code to have the bounded indicator. Next we consider a proper parse, introduced notion. We prove that for a strongly infix code, the number of proper parses is at most three under some condition. We also prove that if a code X has a unique proper parse for each word under the same condition, then X is a strongly infix code.

This article describes a new method for converting an arbitrary topology mesh into one having subdivision connectivity. First, a base mesh is produced by applying a sequence of edge collapse operations to the original mesh with irregular connectivity. Then, the base mesh is iteratively subdivided. Each subdivided mesh is optimized to reduce its distance from the original mesh and to improve its global smoothness and compactness. A set of corresponding point pairs, which is required to compute the distance from the original mesh to the subdivided mesh, is determined by combining the initial parameterization and the multi-resolution projection. Experimental results show that the proposed method yields good performance in terms of global smoothness, small distortion, and good compactness, compared with conventional methods.

In the virtual home environment (VHE), which was proposed to offer global roaming and personal service environment portability, user's profiles and service logics are conveyed from home network to visited network to provide services at the visited network. Because user's profiles and service logics may contain confidential information, some procedures for mutual authentication among entities for offering confidence are needed. For these issues, we propose and analyze 3 party mutual authentication protocols adaptable to the VHE in 3G.

A fast winner search method based on separating all codewords in the original codebook completely into a promising group and an impossible group is proposed. Group separation is realized by using sorted both L₁ and L₂ norms independently. As a result, the necessary search scope that guarantees full search equivalent PSNR can be limited to the common part of the 2 individual promising groups. The high search efficiency is confirmed by experimental results.

A novel motion vector re-estimation technique for transcoding into lower spatial resolution is proposed. This technique is based on the fact that the block matching error is proportional to the complexity of the reference block with Taylor series expansion. It is shown that the motion vectors re-estimated by the proposed method are closer to optimal ones and offer better quality than those of previous techniques.

We propose a dependency parsing model for head-final, variable word order languages. Based on the observation that each word has its own preference for its modifying distance and the preferred distance varies according to surrounding context of the word, we define a parsing model that can reflect the preference. The experimental result shows that the parser based on our model outperforms other parsers in terms of precision and recall rate.