Catálogo de publicaciones - libros

Classification is a kind of basic semantics that people often use to manage versatile contents in daily life. Resource Space Model (RSM) is a semantic model for sharing and managing various resources using normalized classification semantics. Gossip-based peer-to-peer (P2P) techniques are reliable and scalable protocols for information dissemination. Incorporating RSM with gossip-based techniques forms a new decentralized resource sharing mechanism with the improved performance of unstructured P2P systems. Theoretical analysis and experiments validate the feasibility of the mechanism. Such incorporation is a way to synergy normalization and autonomy in managing decentralized large-scale complex resources.

Ubiquitous communications require wireless networking and infrastructure network support. The first step is to look at how the different available technologies will integrate and work with each other. One of the next steps is to seek solutions for connecting “ubiquitous devices” to such “integrated and heterogeneous networks”. These two steps together form the evolutionary approach towards ubiquitous communications. This paper introduces our currently implemented ubiquitous transmission system for “ubiquitous devices/terminals/handset”, called AnyServer with Intelligent Multi-mode Nodes (IMN) for 3G/GSM/WiFi/Internet. AnyServer is an intelligent platform to provide the IMNs with smooth QoS connections/ communications, synchronization and roaming over the heterogeneous networks which is open, scalable, and complaint with IEEE/IETF standards. AnyServr enables IMNs to setup/maintain the real-time video/audio connections among the networks, facing the mobility in the heterogeneous networks.

Analytical models for adaptive routing in multicomputer inter-connection networks with the traditional non-bursty Poisson traffic have been widely reported in the literature. However, traffic loads generated by many real-world parallel applications may exhibit bursty and batch arrival properties, which can significantly affect network performance. This paper develops a new and concise analytical model for hypercubic networks in the presence of bursty and batch arrival traffic modelled by the Compound Poisson Process (CPP) with geometrically distributed batch sizes. The computation complexity of the model is independent of network size. The analytical results are validated through comparison to those obtained from the simulation experiments. The model is used to evaluate the effects of the bursty traffic with batch arrivals on the performance of interconnection networks.

Wireless Sensor Networks (WSNs) have attracted wide interests from both academic and industrial communities due to their diversity of applications. In this paper, we describe the design and implementation of energy-efficient protocols that can be used to improve traffic safety using WSN. Based on these protocols, we implement an intelligent traffic management system. Low-cost wireless sensor nodes are deployed on the roadbed and work collaboratively to detect potential collisions on the road. Experiments have been performed on this system and the results demonstrate the effectiveness of our protocols.

Many approaches have been proposed to improve efficiency of interrupt handling, most of which aim at single processor systems. Traditional model of interrupt management has been used for several decades in parallel computing environment. It can work well in most occasions, even in real-time environments. But it is often incapable to incorporate reliability and the temporal predictability demanded on hard real-time systems. Many solutions, such as In-line interrupt handling and Predictable interrupt management, all have special applying fields. In this paper we propose an algorithm that could schedule interrupts in terms of their deadlines for multiprocessor systems. Hard priorities of IRQs are still left to hardware, we only manager those who can get noticed by the kernel. Each interrupt will be scheduled only before its first execution according to their arrival time and deadlines so that it is called lazy Earliest-Deadline-First algorithm. The scheme tries to make as many as possible ISRs finish their work within the time limit. Finally we did some experiments using task simulation, which proved there was a big improvement in interrupts management.

We investigate the efficient storage of row-sorted 1-variant ( + 1) ×( + 1) matrices,  > , that have the following properties: the rows are sorted in strictly increasing order and the set of elements of each row differs only by one single element from the set of elements of the next row. It has been shown that row-sorted 1-variant matrices are important in several parallel string comparison applications. Due to the large amount of redundancy in the row elements, we investigate efficient data structures to store such matrices. In this paper we propose a representation that stores a row-sorted 1-variant matrix in ( log) space and access time of (log) and can be constructed in ( log) time. We thus seek a representation that constitutes a nice balance between access time, representation construction time, and space requirement.

Data cube has been playing an essential role in OLAP (online analytical processing). The pre-computation of data cubes is critical for improving the response time of OLAP systems. However, as the size of data cube grows, the time it takes to perform this pre-computation becomes a significant performance bottleneck. In a high dimensional OLAP, it might not be practical to build all these cuboids and their indices. In this paper, we propose a parallel hierarchical cubing algorithm, based on an extension of the previous minimal cubing approach. The algorithm has two components: decomposition of the cube space based on multiple dimension attributes, and an efficient OLAP query engine based on a prefix bitmap encoding of the indices. This method partitions the high dimensional data cube into low dimensional cube segments. Such an approach permits a significant reduction of CPU and I/O overhead for many queries by restricting the number of cube segments to be processed for both the fact table and bitmap indices. The proposed data allocation and processing model support parallel I/O and parallel processing, as well as load balancing for disks and processors. Experimental results show that the proposed parallel hierarchical cubing method is significantly more efficient than other existing cubing methods.

A time and interaction coordination model is presented to address the dynamic changes of interaction topology and real-time constraints among autonomous entities in open distributed timing computation. Driven by events, the model distinguishes between three kinds of entities: time coordinators, interaction coordinators and computation entities, which are separated from traditional autonomous entities based on the separation of concerns. A time coordinator is responsible for controlling real-time behaviors; an interaction coordinator is to coordinate interaction and reconfigure interconnection topology among computation entities; a computation entity is only responsible for performing pure computation. An implementation framework is additionally suggested based on Java Message Service and EJB technology. Finally, an application to a vehicle navigation system is presented, including several traffic control centers, a GPS and a navigator. It illustrates how the model and the framework can be used to achieve both the interaction topology and the timing constraints.

For many practical usages or resource-limited environments, it is often desirable to speed up the cryptographic systems without any security lost. Linkable ring signature is a kind of signatures which can simultaneously provide the properties of anonymity, spontaneity as well as linkability. Threshold signature is a useful tool for decentralizing the power to sign a message by distributed computing. The paper presents linkable ring signatures and threshold signatures using -th order characteristic sequences generated by a linear feedback shift register (LFSR). Our schemes enjoy the following attractive features: (i) main computation operations are performed in (); and (ii) security properties rely on the difficulty of solving the state based discrete logarithm problem(S-DLP) and on state based decisional Diffie-Hellman(S-DDH) assumption. Since the complexity of breaking S-DLP(S-DDHP, .) is computationally equivalent to that of solving traditional DLP(DDHP, .) in (), the proposed schemes successfully enhance the security of the system and meanwhile maintain low computational costs. All these make our schemes more flexible.