Decentralized and unstructured peer-to-peer (P2P) networks such as Gnutella are attractive for large-scale information retrieval and search systems because of their scalability, fault-tolerance, and self-organizing nature. Because of this decentralized architecture, however, traditional P2P keyword search systems are difficult to globally share useful semantic knowledge among nodes. As a result, traditional P2P keyword search systems cannot support semantic search (support only naive text-match search). In this paper, we describe a design of the semantic P2P keyword search system. We exploit the semantics of correlation among keywords rather than synonym. The key mechanism is query expansion, where a received query is expanded based on keyword relationships. Keyword relationships are improved through search and retrieval processes and each relationship is shared among nodes holding similar data items. This semantic P2P search system has two main advantages. First, expanding search results through query expansion increases the possibility of locating desired data items which would not be found by traditional P2P search systems due to the keywords' textual mismatch. Second, keyword relationships originally introduced for query expansion, can be used for result ranking. Our main challenges are 1) managing keyword relationships in a fully decentralized manner and 2) maintaining the quality of search results, while suppressing result implosion. We also describe the prototype implementation and evaluation of the semantic P2P search system.

Various demands for next generation networks can be condensed into always-best-connected, ubiquitous, mobile, all-IP, application-aware, and converged networks. Vehicles have also come to be ubiquitous computing platforms associated with mobile communication functions. IPv6 has been introduced for all-IP ubiquitous communications. This paper proposes application-aware resource management for in-vehicle IPv6 networks, which are adaptive to different hardware configurations. We focus on power and bandwidth, since their management is critical for mobile communications. To manage these two critical resources, we identify the mobility characteristics and hardware configurations of in-vehicle networks. Based on these characteristics, we propose vehicle-aware power saving schemes. Our main idea for power saving is to dynamically adjust the mobile router (MR) advertisement interval and binding update lifetime. In addition, depending on the hardware configuration of the wireless environment, we propose two adaptive bandwidth management schemes using multihoming, which we refer to as best-connected MR selection based on location and high-data-rate MR selection based on priority. We evaluate the performance of our bandwidth management schemes by performing simulations, and that of our power saving schemes by mathematical analysis. Based on the results, it was found that the performance of each software scheme depends on the hardware configuration, so that an application-aware adaptive scheme is needed to optimize resource consumption.

A very general form of the probability density distribution of the fading envelope has been presented by M.Nakagami, including the Nakagami-Rice and Nakagami-Hoyt distributions as special cases. This paper gives the series form expanded in positive terms of the m-distribution for it. Previously, the feasibility of such an expansion was predicted, but there has been no explicit description to date. The properties of the well-known m-distribution and the positive sign in each term of this series make it practical for numerical calculation, approximation and analysis.

Mobile agent systems are essential in the next generation of electronic commercial applications. However, existing solutions for mobile agents to sign documents without user intervention are problematic because there is no restriction on who can generate the signatures. In this paper, we present a modified version of undetachable signature scheme with which the power to generate digital signatures can be designated to a neutral party. We also give a transaction model to support the scheme. Discussions regarding the security of the signature scheme as well as some attacks on its application in our model are presented too.

A routing algorithm, utilizing two-hop relaying when necessary, is proposed to enhance the system capacity of code division multiple access (CDMA) cellular systems. Up to now, multihop relaying is applied to cellular systems mainly with the aim of decreasing the transmit power of each mobile station or extending the cell coverage area. Here, in this paper, potential benefit of multihop relaying is studied so as to increase the system capacity. A condition for the interference to be reduced by changing single-hop connections to two-hop connections is analyzed. In addition, a new route selection criterion maximizing the amount of interference reduction is proposed. Simulation results reveal that the proposed criterion is superior to the conventional criterion minimizing the total transmit power in respect of the amount of interference reduction. By using this criterion, an efficient routing algorithm for two-hop CDMA cellular systems is proposed to enhance the system capacity. Simulation results also indicate that by using the proposed routing algorithm in combination with a call admission control, the system capacity is increased even under heavy traffic conditions.

A new excitation enhancement technique based on a harmonic model is proposed in this paper to improve the speech quality of low-bit-rate speech coders. This technique is employed only in the decoding process of speech coders and improves high-frequency components of excitation. We develop the procedure of harmonic model parameters estimation and harmonic generation and apply the technique to a current state-of-art low bit rate speech coder. Experiments on spectrum reading and spectrum distortion measurement show that the proposed excitation enhancement technique improves speech quality.

This paper proposes a new type of relationship between layers in layered architecture and shows how to concretize the relationship between layers into design constraints. The meaning of layer relationship is explained with examples from design patterns and Microsoft COM. In addition, a prototype tool to check conformance is implemented and the architecture document of an open-source software project is checked against the actual architecture extracted from source code developed by many international developers. As a result of checking, parts that do not conform to the architecture document are investigated and it is pointed out that their modifications should be controlled with caution.

In a Distributed Computing Systems (DCS) tasks submitted to it, are usually partitioned into different modules and these modules may be allocated to different processing nodes so as to achieve minimum turn around time of the tasks utilizing the maximum resources of the existing system such as CPU speed, memory capacities etc. The problem lies on how to obtain the optimal allocation of these multiple tasks by keeping in mind that no processing node is overloaded due to this allocation. This paper proposes an algorithm A*RS, using well-known A*, which aims to reduce the search space and time for task allocation. It aims at minimization of turn around time of tasks in the way so that processing nodes do not become overloaded due to this allocation. Our experimental results justify the claims with necessary supports by comparing it with the earlier algorithm for multiple tasks allocation.

Fault-tolerance is an essential feature of the distributed systems where the possibility of a failure increases with the growth of the system. In spite of extensive researches over two decades, fault-tolerance systems have not succeeded in practical use. It is due to the high overhead and the unhandiness of the previous fault-tolerance systems. In this paper, we propose MPICH-GF, a user-transparent checkpointing system for grid-enabled MPICH. Our objectives are to fill the gap between the theory and the practice of fault-tolerance systems, and to provide a checkpointing-recovery system for grids. To build a fault-tolerant MPICH version, we have designed task migration, dynamic process management, and atomic message transfer. MPICH-GF requires no modification of application source codes, and it affects the MPICH communication characteristics as less as possible. The features of MPICH-GF are that it supports the direct message transfer mode and that all of the implementation has been done at the lower layer, that is, the abstract device level. We have evaluated MPICH-GF using NPB applications on Globus middleware.

Graph data in large scientific/engineering applications are often too massive to fit inside the computer's main memory. The resulting input/output (I/O) costs could be a major performance bottleneck. This paper proposes an extension to extant multilevel graph partitioning algorithms with improved I/O-efficiency. The input graph is envisioned as the union of disjoint blocks (subgraphs) of almost the same size. Each block is coarsened in turn. Recursive matching and contraction are the operations in this phase. All the coarsened blocks are then merged in an iterative manner in order to ensure that the resulting graph fits in the main memory. This graph is then treated with an in-core multilevel graph partitioning algorithm in the usual way. Our experimental results show that the larger graph size is, the more dependent on the I/O-efficiency the performance is. And our modification can easily partition very large graphs. It also exhibits considerable improvement in I/O-complexity.

Cluster computation has been used in the applications that demand performance, reliability, and availability, such as cluster server groups, large-scale scientific computations, distributed databases, distributed media-on-demand servers and search engines etc. In those applications, multicast can play the vital roles for the information dissemination among groups of servers and users. This paper proposes a set of novel efficient fault-tolerant multicast routing algorithms on hypercube interconnection of cluster computers using multicast shared tree approach. We present some new algorithms for selecting an optimal core (root) and constructing the shared tree so as to minimize the average delay for multicast messages. Simulation results indicate that our algorithms are efficient in the senses of short end-to-end average delay, load balance and less resource utilizations over hypercube cluster interconnection networks.

In policy-based management, in addition to deliver and enforce policies in managed systems, it is inevitable to manage the policy life-cycle. We mean the policy life-cycle as cyclic iteration of processes involving monitoring to see if the enforced policies actually work at operators' will and their adaptation based on monitoring. Enabling such policy life-cycle management by the current centralized management paradigm such as SNMP may, however, result in poor scalability and reliability. This is typically due to much bandwidth consumption for monitoring and communication failure between a management system and a managed system. It may also impose a heavy burden on the operators in analyzing management information for the policy adaptation. For a solution to that, we propose a scalable and reliable policy-based management scheme enabling the policy life-cycle management based on distributed management paradigm. In the scheme, we provide a new management script describing policies and how their life-cycle should be managed, and execute the script on the managed system with enough computation resources. The scheme can make the current policy-based management more scalable by reducing management traffic, more reliable by distributing management tasks to the managed systems, and more promising by relieving of the operators' burden. We implement a prototype system based on the scheme taking Differentiated Services as a policy enforcement mechanism, and evaluate the scheme from the following viewpoints: 1) the reliability, 2) relievability, and 3) scalability. The first two will be shown with a policy adaptation scenario in an operational network. The last one will be investigated in terms of the management traffic reduction by a management script, the management traffic required for the management of a management script, and the load on a managed system to execute management scripts. As deployment consideration of the proposed scheme besides technical aspects, we also discuss how the prototype system could be integrated with managed systems compliant to the standards emerging in the marketplace.

The multiplication of large spare matrices is a basic operation in many scientific and engineering applications. There exist some high-performance library routines for this operation. They are often optimized based on the target architecture. For a parallel environment, it is essential to partition the entire operation into well balanced tasks and assign them to individual processing elements. Most of the existing techniques partition the given matrices based on some kind of workload estimation. For irregular sparse matrices on PC clusters, however, the workloads may not be well estimated in advance. Any approach other than run-time dynamic partitioning may degrade performance. In this paper, we apply our super-programming approach to parallel large matrix multiplication on PC clusters. In our approach, tasks are partitioned into super-instructions that are dynamically assigned to member computer nodes. Thus, the load balancing logic is separated from the computing logic; the former is taken over by the runtime environment. Our super-programming approach facilitates ease of program development and targets high efficiency in dynamic load balancing. Workloads can be balanced effectively and the optimization overhead is small. The results prove the viability of our approach.

In this paper, a coefficient-parameter reduction method is proposed for invertible deinterlacing with variable coefficients. Invertible deinterlacing, which the authors have developed before, can be used as a preprocess of frame-based motion picture codec, such as Motion-JPEG2000 (MJP2), for interlaced videos. When the conventional field-interleaving is used instead, comb-tooth artifacts appear around edges of moving objects. On the other hand, the invertible deinterlacing technique allows us to suppress the comb-tooth artifacts and also to recover an original picture on demand. As previous works, the authors have developed a variable coefficient scheme with a motion detection filter, which realizes adaptability to local characteristics of given pictures. When applying this deinterlacing technique to an image codec, it is required to send coefficient parameters to receivers for original picture recovery. This work proposes a parameter decimation technique and shows that this reduction approach can be achieved without significant loss of comb-tooth suppression capability and improves the quality at high bit-rate decoding.

This paper analyzes the input-dependent sample-time error in MOS sampling circuits caused by the finite slope of the sampling clock, and clarifies the following: (i) Input-dependent sampling jitter causes phase modulation in the sampled data. (ii) The formulas for SDR due to such sampling errors are explicitly derived. (iii) NMOS sampling circuits generate even-order harmonics, which are greatly reduced by using a differential topology. (iv) CMOS sampling circuits without clock skew between Vclk and generate odd-order harmonics which a differential topology cannot help cancel, whereas circuits with clock skew generate even-order as well as odd-order harmonics. (v) For single-ended sampling circuits, the SDR of CMOS circuits without clock skew is better than that of NMOS circuits. (vi) NMOS differential sampling circuits are relatively insensitive to input-dependent sampling-time error effects, which would be the best regarding to the input-dependent sampling-time error effects. (vii) Its effects in case of NMOS differential samplers with finite skew between plus and minus path clocks are discussed. (viii) Its effects in CMOS samplers with finite skew between PMOS and NMOS clocks are discussed.

In this paper, we consider QoS-guaranteed wavelength allocation for WDM networks with limited-range wavelength conversion. In the wavelength allocation, the pre-determined number of wavelengths are allocated to each QoS class depending on the required loss probability. Moreover, we consider two wavelength selection rules and three combinations of the rules. We analyze the connection loss probability of each QoS class for a single link using continuous-time Markov chain. We also investigate the connection loss probability for a uni-directional ring network by simulation. In numerical examples, we compare connection loss probabilities for three combinations of selection rules and show how each combination of selection rules affects the connection loss probability of each QoS class. Furthermore, we show how wavelength conversion capability affects the connection loss probability. It is shown that the proposed allocation with appropriate wavelength selection rule is effective for QoS provisioning when the number of wavelengths is large. We also show the effective combination of wavelength selection rules for the case with small wavelength conversion capability.

For an additive white Gaussian noise (AWGN) channel, a performance evaluation of parallel concatenated turbo trellis-coded modulation (turbo TCM) using bit-interleavers is reported. By obtaining weight distribution, the performance is evaluated by using a union bound method. Comparison between the result of evaluated performance and simulation results is shown, and the usefulness of the evaluated performance is shown. An optimum code and an optimum mapping are sought. The result of the optimum code with the optimum mapping is a new interleaver size N dependency which is proportional to N-3. It is better than the interleaver size dependency for Benedetto code with the natural mapping which is proportional to N-1. The reasons why these dependencies can happen are also discussed.

An information retrieval (IR) system with query expansion on a low-cost high-performance PC cluster environment is implemented. We study how query performance is affected by query expansion and two declustering methods using two standard Korean test collections. According to the experiments, the greedy method shows about 20% enhancement overall when compared with the lexical method.

We had previously proposed a fuzzy logic-based buffer management scheme (BMS) called fuzzy early detection (FED), which was designed to improve transmission control protocol (TCP) performance over the unspecified bit rate (UBR) service of asynchronous transfer mode (ATM) networks. Since a weakness in FED was discovered later, we present a refined version of it named FED+ here. Maintaining the design architecture and the algorithm of FED, FED+ further adopts a specific per virtual connection accounting algorithm to achieve its design goals. The effects of TCP implementation, TCP maximum segment size, switch buffer size and network propagation delay on FED+ performance are studied through simulation. Its performance is then compared with those of pure early packet discard (EPD), P-random early detection (P-RED) and FED. Our evaluations show that FED+ is superior to the others if the issues of efficiency, fairness, robustness, buffer requirement and the ease of tuning control parameters of a BMS are considered collectively.

We numerically and experimentally investigated the upgradability of the longest and the typical segments of the JIH system. Through these studies, we confirmed that a 100 GHz-spaced 25 42.7 Gbit/s transmission with the total capacity of 1 Tbit/s can be attainable even by using NRZ signal and standard FEC for the typical segments. We also found that RZ signal format was desirable for the longest segment and a further wide system margin could be expected by using adjacent channel polarization control and advanced FEC technologies.