Recent attractive high-speed networks require network file servers with high-speed read performance to deliver huge multimedia files, like voice or movie files. This paper proposes new design and implementation techniques that yield high-speed file servers based on UNIX. The techniques are request reduction, in which contiguous blocks on UNIX file system (UFS) are gathered for reducing the number of command requests from the file system to the device driver, and a direct access method for cutting through the buffer cache mechanism. A file server prototype based on a general-purpose personal computer (PC) is constructed and its performance is evaluated. The preliminary results show that the prototype achieves high-speed file read performance in excess of 100 Mbytes/s even on an OpenBSD PC-UNIX system with 3 RAID controllers and 9 hard drives in RAID level 0 configuration.

In a real-time system, it is required to reduce the response time to an interrupt signal, as well as the execution time of a Real-Time Operating System (RTOS). In order to satisfy this requirement, we have proposed a method of implementing some of the functionalities of an RTOS using hardware. Based on this idea, we have implemented a VLSI chip, called STRON (silicon TRON: The Realtime Operating system Nucleus), to enhance the performance of an RTOS, where the STRON chip works as a peripheral unit of any MPU. In this paper we describe the hardware architecture of the STRON chip and the performance evaluation results of the RTOS using the STRON chip. The following results were obtained. (1) The STRON chip is implemented in only about 10,000 gates when the number of each object (task, event flag, semaphore, and interrupt) is 7. (2) The task scheduler can execute within 8 clocks in a fixed period using the hardware algorithm when the number of tasks is 7. (3) Most of the basic µITRON system calls using the STRON chip can be executed in a fixed period of a few microseconds. (4) The execution time of a system call, measured by a multitask application program model, can be reduced to about one-fifth that in the case of the conventional software RTOS. (5) The total performance, including context switching, is about 2.2 times faster than that of the software RTOS. We conclude that the execution time of the part of the system call implemented by the STRON chip can almost be ignored, but the part of the interface software and context switching related to the architecture of a MPU strongly influence the total performance of an RTOS.

In general, when many functions and services are added to a system, verification and validation become difficult. In design and development in telecommunication services, conflicts that arise from combined telecommunication services have been discussed from various viewpoints. However, correctly and efficiently detecting all conflicts is still not possible and the resolution of conflicts primarily depends on expert designers, who are finding that these problems are beyond their ability. Thus, the burden on the designer must also be alleviated at the design stage. Service interference, which is discussed in this paper, is a kind of conflict. A problem of service interference is that during service, other services interfere with the ongoing service behavior. That is to say, a strange state arises, or an input event doesn't work, or a strange transition occurs, etc. The detection of service interference by only comparing states among services is not enough since the state transition must be considered in the service interference. This paper proposes how to automatically detect the service interference with a rule-based system and an extended adjacency matrix. The proposed method uses and combines features of both the adjacency matrix and rule-based system. The method first generates the extended adjacency matrix by the rule application, then extracts sequences of the state, the event, and the rule applications, and then detects the service interference with the extracted sequences.

At the Information-technology Promotion Agency (IPA), we have been developing a network intrusion detection system called IDA (Intrusion Detection Agent system). IDA system has two distinctive features that most conventional intrusion detection systems lack. First, it has a mechanism for tracing the origin of a break-in by means of mobile agents. Second, it has a new and efficient method of detecting intrusions: rather than continuously monitoring the user's activities, it watches for an event that meets the criteria of an MLSI (Mark Left by Suspected Intruders) and may relate to an intrusion. By this method, IDA described herein can reduce the processing overhead of systems and networks. At present, IDA can detect local attacks that are initiated against a machine to which the attacker already has access and he or she attempts to exceed his or her authority. This paper mainly describes how IDA detects local attacks and traces intrusions.

For cluster systems consisting of multiple nodes and shared servers which consist of an on-line and a backup server, we propose a hot-standby scheme of shared servers. In this scheme for shared servers, the shared servers have user data and control data. The on-line shared server sends only the control data to the backup server when it receives an update command. When the on-line shared server fails, the backup shared server reconstructs the shared data by using the latest control data sent from the on-line server and the user data sent from each node. We evaluated the system recovery time and the performance overhead for the hot-standby scheme. This enables the system recovery time to be shortened to 30 seconds and the performance overhead to be reduced to 2%.

In this paper, we describe the PS3 load distribution scheme. A target service is a transaction service consisting of multiple processes that communicate with each other. A target system consists of workstations connected by a LAN. PS3 determines the process allocation by estimating response times and throughputs. It allows us to set an upper limit of a response time, and to set lower and upper limits for the throughput of each service. PS3 tries to find a process allocation that provides the minimum response time under conditions set by the user in advance. We measured the response times and throughputs and compared the values with the estimated ones. The results show that PS3 provides an appropriate process allocation, and that calculated results agree well with the measured ones.

This paper proposes a new method to improve cooperation in concurrent systems within the framework of Multi-Agent Systems (MAS) by utilizing reinforcement learning. When subsystems work independently and concurrently, achieving appropriate cooperation among them is important to improve the effectiveness of the overall system. Treating subsystems as agents makes it easy to explicitly deal with the interactions among them since they can be modeled naturally as communication among agents with intended information. In our approach agents try to learn the appropriate balance between exploration and exploitation via reward, which is important in distributed and concurrent problem solving in general. By focusing on how to give reward in reinforcement learning, not the learning equation, two kinds of reward are defined in the context of cooperation between agents, in contrast to reinforcement learning within the framework of single agent. In our approach reward for insistence by individual agent contributes to facilitating exploration and reward for concession to other agents contributes to facilitating exploitation. Our cooperation method was examined through experiments on the design of micro satellites and the result showed that it was effective to some extent to facilitate cooperation among agents by letting agents themselves learn the appropriate balance between insistence and concession. The result also suggested the possibility of utilizing the relative magnitude of these rewards as a new control parameter in MAS to control the overall behavior of MAS.

In this paper, an effective method of system modeling and dynamic scheduling to improve operation and control for the Back-End process of semiconductor manufacturing is developed by using Colored Timed Petri-Nets (CTPNs). The simulator of a CTPNs model was utilized to generate a new heuristic scheduling method with genetic algorithm(GA) which enables us to obtain the optimal values of the weighted delay time and standard deviation of lead time.

As telecommunications companies face the rigors of competition, they soon find that their operational support systems play a critical role in providing new services faster, at lower cost and with better quality than their competitors. At TeleManagement Forum, the model for the successful service provider is 'the smooth operator' - a company whose processes and systems fully support its people to provide the best services possible at the lowest cost. Learning the importance of becoming a 'smooth operator' is hard, particularly as it requires giving up the old way of doing things - moving from an internal development environment to one that can take full advantage of 'off-the-shelf' software. The reasons for this shift include a shortage of resources, shortage of time, and the need to do business as part of a greater (and growing) global supply chain. Getting to 'smooth operator' status can be made easier with help from organizations like the TeleManagement Forum. In this paper, a twelve-step method is outlined to give pointers to service providers and their suppliers on how to make the journey successfully.

Internet communication is increasingly becoming an important element in daily life. Keeping this network safe from malicious elements is an urgent task for network management. To maintain the security level networks are generally, monitored for indications of usage with ill-intentions. Such indications are events which need to be collated, correlated and analyzed in real-time to be effective. However, on an average medium to large size network the number of such events are very large. This makes it practically impossible to analyze the information in real-time and provide the necessary security measures. In this paper, we propose a mechanism that keeps the number of events, to be analyzed, low thereby making it possible to provide ample security measures. We discuss a real-time Intrusion Detection System (IDS) for detecting network attacks. The system looks out for TCP ACK/RST packets, which are generally caused by network scans. The system can extract the tendency of network flows in real-time, based on the newly developed time-based clustering and Dynamic Access Tree creation techniques. The algorithm, implemented and deployed on a medium size backbone network using RMON (Remote MONitoring) technology, successfully detected 195 intrusion attempts during a one month period. The results of the pilot deployment are discussed. In this paper, the proposal, implementation and evaluation will be described.

This paper describes the effectiveness of compact semiconductor optical amplifiers (SOAs) in the photonic transport system (PTS). Such amplifiers are small enough to permit high-density packaging. SOAs, having unsaturated signal gain of 10 dB and saturation output power of 10 dBm, can improve the Q-value by 3 over the SOA input power range of 10 dB. Within this range, the signal transport distance can be expanded from 360 km to 600 km by placing SOAs on individual optical channels in a PTS even though the amplified spontaneous emission (ASE) generated by individual SOAs is combined with the optical signals and delivered to the same output fiber. This result indicates that it is useful to employ compact SOAs in the PTS for enlarging the distances between nodes.

The paper argues that a radical shift in the market for communications services is emerging, driven by the mass availability of cheap bandwidth, computing and global mobility combined with the pervasive rise of Internet based data services. At the same time, the Operation Support Systems (OSS's*) that are essential in order to create business value from these technologies are lagging behind market need. The authors argue for a re-think of the humble management system into a complete software wrap-around of the network to deliver a value creation platform - as different from yesterday's OSS as the bakelite telephone is from today's tri-band mobile handsets. This software will be based on product standards, not paper ones and will require a major shift of gears from the position of today. This value creation platform will be built from advanced, component based software delivered through a very different market model to that of today. Much of this technology exists; we simply need critical mass behind a common approach. The discussion in this paper represents the personal views of the authors and does not necessarily represent the views of any organisation.

In this paper, a novel application specific power optimization technique utilizing small instruction ROM which is placed between an instruction cache or a main program memory and CPU core is proposed. Our optimization technique targets embedded systems which assume the following: (i) instruction memories are organized by two on-chip memories, a main program memory and a subprogram memory, (ii) these two memories can be independently powered-up or powered-down by a special instruction of a core processor, and (iii) a compiler optimizes an allocation of object code into these two memories so as to minimize average of read energy consumption. In many application programs, only a few basic blocks are frequently executed. Therefore, allocating these frequently executed basic blocks into low power subprogram memory leads significant energy reduction. Our experiments with actual ROM (Read Only Memory) modules created with 0.5 µm CMOS process technology, and MPEG2 codec program demonstrate significant energy reductions up to more than 50% at best case over the previous approach that applies only divided bit and word lines structure.

In this paper, we propose a preemptive priority handoff scheme for integrated voice/data cellular mobile systems. In our scheme, calls are divided into three different classes: handoff voice calls, originating voice calls, and data calls. In each cell of the system there is a queue only for data calls. Priority is given to handoff voice calls over the other two kinds of calls. That is, the right to preempt the service of data is given to a handoff voice call if on arrival it finds no idle channels. The interrupted data call returns to the queue. The system is modeled by a two-dimensional Markov chain. We apply the Successive Over-Relaxation (SOR) method to obtain the equilibrium state probabilities. Blocking and forced termination probabilities for voice calls are obtained. Moreover, average queue length and average transmission delay of data calls are evaluated. The results are compared with another handoff scheme for integrated voice/data cellular mobile systems where some numbers of channels are reserved for voice handoff calls. It is shown that, when the data traffic is not very light, the new scheme can provide lower blocking probability for originating voice calls, lower forced termination probability for ongoing voice calls, and shorter average queue length and less average transmission delay for data calls.

Recently, it is widely known that the partial response maximum-likelihood (PRML) system has attracted much attention as one of indispensable signal processing technique for achieving high density digital magnetic recording. But, the performance of PRML system is degraded by many undesirable causes in recording channel. For improving the performance, it is desirable to use any high order PRML system or high rate code. Our proposed two-track recording method increases the coding rate over 1, and contributes to decrease these degradation effects. The recording code in our system adopts a turbo code which provides a substantial near-ML performance by the suboptimum iterative decoding algorithm. In this paper, the turbo coded class four partial response (PR4) systems using the rate 4/6, 8/10 and 16/18 codes for high density two track digital magnetic recording are proposed. The error rate performance of the proposed system is obtained by computer simulation taking account of the partial erasure, which is one of nonlinear distortions at high densities. The performance of our system is compared with that of the conventional NRZ coded PR4ML system. The result shows that the proposed system is hardly affected by partial erasure and keeps good performance in high density recording. In especial, the proposed system using the rate 16/18 turbo code can achieve a bit error rate of 10-4 with SNR of approximately 12.2 dB less than the conventional NRZ coded PR4ML systems at a normalized linear density of 3.

Experiment is reported of enhanced backscattering of light in binary and ternary suspensions of rutile and/or alumina particles. With a conventional CCD camera system for observing the phenomena, the angular line shape and the enhancement factor were agreed with the theoretically predicted curve and value. Observation of the angular distribution scattered at the backscattered direction supported the hypothesis proposed by Pine et al. , in which the transport mean free path of the polydisperse mixture can be expressed in terms of summing its reciprocal values weighted over the particle sizes.

We propose a traffic measurement system which uses trap and polling methods. To obtain its performance we consider a queueing model with a single server and evaluate a packet delay. In our multi-cast traffic, packets are modeled as a batch with a batch size distribution {gk}. The batch arrival process is observed as two processes on the basis of batch size. For a batch whose size is more than or equal to a threshold L, the batch will be trapped by our traffic measurement system (in queueing model, it will enter a queue immediately after its arrival). For a batch whose size is less than L, it will be observed at a polling cycle T (in queueing model, it will be temporarily stored in a buffer and all these small batches will be cyclically noticed with a cycle T). We analyze this queueing model by a diffusion approximation and compare the packet delay observed by our traffic measurement system with the L=1 original batch arrival model. Evaluating the results of the diffusion approximation, we illustrate that our traffic measurement system has functions not only to give an accurate estimation of the mean waiting time but also reduce the number of measurements by choosing appropriate parameters L and T.

This paper presents a new number representation called the Signed-Weight (SW) number system, which is useful for designing configurable counter-tree architectures for digital signal processing applications. The SW number system allows the unified manipulation of positive and negative numbers in arithmetic circuits by adjusting the signs assigned to individual digit positions. This makes possible the construction of highly regular arithmetic circuits without introducing irregular arithmetic operations, such as negation and sign extension in the two's complement representation. This paper also presents the design of a Field-Programmable Digital Filter (FPDF) architecture--a special-purpose FPGA architecture for high-speed FIR filtering--using the proposed SW arithmetic system.

This paper proposes applications of a code-division multiplexing technique to VLSI systems free from interconnection problems. We employ a pseudo-random orthogonal m-sequence carrier as a multiplexable information carrier to achieve efficient data transmission. Using orthogonal property of m-sequences, we can multiplex several computational activities into a single circuit, and execute in parallel using multiplexed data transmission with reduced interconnection. Also, randomness of m-sequences offers the high tolerance to interference (jamming), and suppression of dynamic range of signals while maintaining a sufficient signal-to-noise ratio (SNR). We demonstrate application examples of multiplex computing circuits, neural networks, and spread-spectrum image processing to show the advantages.

The aim of this contribution is to take a further step in the study of the impact of chaos-based techniques on classical DS-CDMA systems. The problem addressed here is the sequence phase acquisition and tracking which is needed to synchronize the spreading and despreading sequences of each link. An acquisition mechanism is considered and analyzed in depth to identify analytical expressions of suitable system performance parameters, namely outage probability, link startup delay and expected time to service. Special chaotic maps are considered to show that the choice of spreading sequences can be optimized to accelerate and improve the spreading codes acquisition phase.