Evangelos Zervas

Using recurrent neural networks for adaptive communication channel equalization

Nonlinear adaptive filters based on a variety of neural network models have been used successfully for system identification and noise-cancellation in a wide class of applications. An important problem in data communications is that of channel equalization, i.e., the removal of interferences introduced by linear or nonlinear message corrupting mechanisms, so that the originally transmitted symbols can be recovered correctly at the receiver. In this paper we introduce an adaptive recurrent neural network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed channel equalization. We propose RNN based structures for both trained adaptation and blind equalization, and we evaluate their performance via extensive simulations for a variety of signal modulations and communication channel models. It is shown that the RNN equalizers have comparable performance with traditional linear filter based equalizers when the channel interferences are relatively mild, and that they outperform them by several orders of magnitude when either the channels transfer function has spectral nulls or severe nonlinear distortion is present. In addition, the small-size RNN equalizers, being essentially generalized IIR filters, are shown to outperform multilayer perceptron equalizers of larger computational complexity in linear and nonlinear channel equalization cases.

An efficient RSVP-mobile IP interworking scheme

During the past years, several attempts have been made to develop functionality for mobility management support and QoS provision in the realm of the IP networks. Since IP was not designed to support such functionality, new protocols have been specified and implemented to tackle these issues. Mobile IP is currently the dominant protocol that allows users to retain connectivity while roaming in IP networks. RSVP (Resource reSerVation Protocol) is a well established protocol for reserving network resources to support QoS requirements. These protocols, when deployed separately, can work quite efficiently. However, if their functionality is combined, several inefficiencies arise in terms of QoS deterioration and misuse of the network resources. To minimize these inefficiencies, we propose a new approach that limits mobility and QoS related network modifications inside the domain, in which a user moves. The deployment of our scheme enhances the network resource usage efficiency, while minimizing the duration of the QoS deterioration experienced after a terminal movement. To quantify the advantages of our proposal, we have developed an analytical and a simulation model that we also present in this paper.

A 'quantized' channel approach to blind equalization

A blind identification algorithm for unknown linear channels is proposed. The algorithm operates over a grid in the channel space that is made finer by using the maximum likelihood criterion to confine the estimated channel in the neighborhood of the original unknown channel. The nature of the algorithm leads to efficient parallel implementation, and its storage requirements are only those of the Viterbi algorithm. Simulation examples have shown that identification of the channels considered is possible within 500 symbols and often within 50-100 symbols. The algorithm can be used as a start-up technique in conjunction with other identification methods. Implementation of the algorithm with a varying quantizing step is also possible.<<ETX>>

An efficient QoS scheme for mobile hosts

Mobile hosts utilize Mobile IP to retain connectivity, while roaming in various networks, and acquire new IP addresses through the mechanisms that Mobile IP supports. One of todays most demanding application requirements is QoS support. RSVP (resource reservation protocol), the protocol implementation of the IETF integrated services architecture (IntServ), cannot handle hosts that change their IP addresses during a connection lifetime, and thus, must re-establish any given reservation states. To overcome this limitation, we propose the adoption of a mobility management scheme, that maintains a single contact IP address throughout the mobility session. Furthermore, we introduce RSVP mobility proxy, an enhanced RSVP enabled border router to deal with QoS signaling at any mobility related network topology modification.

Electron beam lithography simulation for high resolution and high-density patterns

Abstract A fast simulator for electron beam lithography, called SELID TM , is applied for the simulation and prediction of the resist profile of high-resolution patterns in the case of homogeneous and multilayer substrates. For exposure simulation, an analytical solution based on the Boltzmann transport equation (where all important scattering phenomena have been taken into account) for a wide range of e-beam energies is used. The case of substrates consisting of more than one layer (multilayer) is considered in depth as it is of great importance in e-beam patterning. By combining the energy deposition data from simulation with analytical functions describing the resist development (for the conventional positive-resist PMMA), complete simulation of dense layouts in the sub-quarter-micron range has been carried out. Additionally, the simulation results are compared with experimental ones for dense patterns in the sub-quarter-micron region. By using SELID TM , forecast of resist profile with considerable accuracy for a wide range of resists, substrates and energies is possible, reducing in that way the cost of process development. Additionally, proximity effect parameters are extracted easily for use in any proximity correction package.

Information Dissemination between Mobile Nodes for Collaborative Context Awareness

In our everyday life, we frequently experience cases where persons group together. In those cases, context-aware systems capture and process identical context. Therefore, the need to collaboratively address Context Awareness (CA) emerges. In the considered setting, ad hoc networking between mobile nodes enables the exchange of information, thus, CA is facilitated. The synergy between mobile nodes materializes the Collaborative CA (CCA) paradigm. We advance the general CCA concept by performing communication between nodes probabilistically in a way similar to virus (epidemic) spreading. Nodes feature a hierarchical information model, which can be exploited by an information diffusion process. Multiple pieces of information, exchanged as epidemics, can complete the information present at a certain node, which in turn infers and spreads new information. We study this novel scheme extensively through an information model for context and an analytical framework (Markov process) with simulations. Our findings show that the information spreading large benefits from the mobility of nodes and semantic processing of the information model.

A Multi-level Data Fusion Approach for Early Fire Detection

Wireless Sensor Networks (WSN) allows large scale deployments for environmental monitoring applications especially in the Wild land Urban Interface (WUI) (i.e. in areas where forests and rural lands interface with homes, other buildings and infrastructures). In such areas early fire detection is of great importance as the consequences of a fire are catastrophic. Towards this direction the SCIER project envisages the deployment of Wireless Sensor Networks at the WUI using a multi-level scheme of data fusion to enhance the performance of the early fire detection process.

Location management in wireless ATM customer premises networks

This paper introduces a new location management protocol, called LAMPS (Location Agents and Mobile PNNI Scheme), that is suitable for wireless ATM customer premises networks. LAMPS takes advantage of the PNNI routing functionality to advertise the movement of mobile terminals within pre-defined areas. Furthermore, it uses specialized entities to store and retrieve the current location area of the mobile terminals. These entities are located within mobility enhanced switches, that provide to mobile terminals connectivity with the rest of the network and supervise the execution of all mobility related procedures. In this paper, we compare LAMPS with similar mechanisms and we present the advantages that arise from its application. The efficiency of the protocol is demonstrated by the results of an analytical model.

Using recurrent neural networks for blind equalization of linear and nonlinear communications channels

A recurrent neural network (RNN) equalizer for blind equalization of linear and nonlinear communication channels is proposed. RNNs have the ability to learn dynamical mappings of arbitrary complexity and therefore present a natural choice for implementing equalizers for communication channels. In several cases the nonlinear nature of a communication channel is too severe to ignore, and at the same time no nonlinear channel model can account sufficiently for the nonlinearities that are inherently present in the channel. In those cases a neural network equalizer is preferable over a conventional one. The real-time recurrent learning (RTRL) algorithm is used to train an RNN, and its performance is compared with that of a conventional equalizer based on the constant-modulus algorithm.<<ETX>>

A generic adaptation layer for differentiated services and improved performance in wireless networks

The paper focuses on the integration of Internet and wireless LANs (WLANs) and proposes a novel technique that supports seamless and efficient integration. This technique is based on a generic adaptation layer, referred to as wireless adaptation layer (WAL), which is introduced between the IP layer and the WLAN link layer. WAL is designed to: (i) cope dynamically with wireless channel impairments; (ii) provide QoS interworking between the IP infrastructure and the WLAN; (iii) be independent of the WLAN technology. These characteristics account for the advantages of WAL, namely, improved performance, wide applicability and provisioning of differentiated services.