Behrokh Samadi

Neural network control of communications systems

Neural networks appear well suited to applications in the control of communications systems for two reasons: adaptivity and high speed. This paper describes application of neural networks to two problems, admission control and switch control, which exploit the adaptivity and speed property, respectively. The admission control problem is the selective admission of a set of calls from a number of inhomogeneous call classes, which may have widely differing characteristics as to their rate and variability of traffic, onto a network. It is usually unknown in advance which combinations of calls can be simultaneously accepted so as to ensure satisfactory performance. The approach adopted is that key network performance parameters are observed while carrying various combinations of calls, and their relationship is learned by a neural network structure. The network model chosen has the ability to interpolate or extrapolate from the past results and the ability to adapt to new and changing conditions. The switch control problem is the service policy used by a switch controller in transmitting packets. In a crossbar switch with input queueing, significant loss of throughput can occur when head-of-line service order is employed. A solution can be based on an algorithm which maximizes throughput. However since this solution is typically required in less than one microsecond, software implementation policy is infeasible. We will carry out an analysis of the benefits of such a policy, describe some existing proposed schemes for its implementation, and propose a further scheme that provides this submicrosecond optimization.

Development of a Synthetic Data Set Generator for Building and Testing Information Discovery Systems

Data mining research has yielded many significant and useful results such as discovering consumer-spending habits, detecting credit card fraud, and identifying anomalous social behavior. Information discovery and analysis systems (IDAS) extract information from multiple sources of data and use data mining methodologies to identify potential significant events and relationships. This research designed and developed a tool called IDAS data and scenario generator (IDSG) to facilitate the creation, testing and training of IDAS. IDSG focuses on building a synthetic data generation engine powerful and flexible enough to generate synthetic data based on complex semantic graphs

Generation of synthetic data sets for evaluating the accuracy of knowledge discovery systems

Information Discovery and Analysis Systems (IDAS) are designed to correlate multiple sources of data and use data mining techniques to identify potential significant events. Application domains for IDAS are numerous and include the emerging area of homeland security.Developing test cases for an IDAS requires background data sets into which hypothetical future scenarios can be overlaid. The IDAS can then be measured in terms of false positive and false negative error rates. Obtaining the test data sets can be an obstacle due to both privacy issues and also the time and cost associated with collecting a diverse set of data sources.In this paper, we give an overview of the design and architecture of an IDAS Data Set Generator (IDSG) that enables a fast and comprehensive test of an IDAS. The IDSG generates data using statistical and rule-based algorithms and also semantic graphs that represent interdependencies between attributes. A credit card transaction application is used to illustrate the approach.

TUNEX: a knowledge-based system for performance tuning of the UNIX operating system

TUNEX, an expert system developed for performance tuning of the UNIX operating system, is described. TUNEX was developed on UNIX system V. It uses the properties, commands and utilities of this version. The tuning activities it is concerned with include: (1) adjusting operating system tunable parameters, such as number of disk buffers; (2) running maintenance routines, i.e. reorganizing file systems; (3) developing operation rules, such as off-peak hour runs of backups; and (4) modifying hardware, buying an additional disk drive. The structure of TUNEX is presented and performance analysis modules which provide quantitative information to this tool are briefly described. The overhead in the resource usage introduced by the performance monitoring and tuning tool itself is discussed; the author points to the areas in which additional resources are required by TUNEX. >

VoIP network architectures and QoS strategy

Voice over IP (VoIP) has received much attention in recent years with the promise of lower costs, as well as new revenue-generating services. Cost and services advantages of carrying voice over IP compared to over the current circuit network are made possible by a common high-capacity packet infrastructure for voice, data, and multimedia services. An important requirement of such a packet infrastructure is the ability to provide public-switched telephone network (PSTN) grade quality without excessive over-provisioning. In this paper, we describe an approach to offer AbsoluteQoS™ to voice and other demanding applications over a general-purpose packet network. AbsoluteQoS is defined as the ability to provide an engineered bound on call-blocking and quantitative QoS guarantee that calls-in-progress will receive. The proposed strategy is based on key innovations in architectures and protocols, as well as business models of PSTN and packet networks.

Synthetic Data Generation Capabilties for Testing Data Mining Tools

Recently, due to commercial success of data mining tools, there has been much attention to extracting hidden information from large databases to predict security problems and terrorist threats. The security applications are somewhat more complicated than commercial applications due to (i) lack of sufficient specific knowledge on what to look for, (ii) R&D labs developing these tools are not able to easily obtain sensitive information due to security, privacy or cost issues. Tools developed for security applications require substantially more testing and revisions in order to prevent costly errors. This paper describes a platform for the generation of realistic synthetic data that can facilitate the development and testing of data mining tools. The original applications for this platform were people information and credit card transaction data sets. In this paper, we introduce a new shipping container application that can support the testing of data mining tools developed for port security

Adaptive play-out algorithms for voice packets

We study the delay characteristics of voice packets that share a transmission medium with bursty data traffic. In order to model the data traffic accurately, we used real data traffic traces upon which we superimposed simulated voice sources generating real time traffic at a constant rate. Our simulation environment allows us to easily develop and compare different adaptive algorithms for the play-out delay of voice streams. We motivate and compare the performance of three algorithms based on exponential smoothing techniques. We test the algorithms in the context of a shared 10 Mbps Ethernet LAN, using the CSMA/CD protocol.

The Operations Assistant: A new manufacturing resource management tool

Abstract The Operations Assistant (OA) is an on-line, interactive decision support system designed to help users with the management of a manufacturing facility. It provides information on the current state of the facility and products, along with projections on the fature states of the facility and progress of products. It generates a graphical view of data and the necessary information to make decisions on product entry sequence, work-in-process reduction schemes, labor/ machine/shift assignments, machine maintenance schedules, and capacity/utilization issues. It contains a number of modules which have the capability of suggesting decisions, and these can be exchanged or supplemented for a particular application. The present OA prototype provides two graphical views; the Product View and the Process View. The operating strategy of the line can be modified interactively, and the consequences of the proposed change (as projected by simulation) seen immediately on these views. The user can also ask for suggestions in making operating decisions, using one of several optimization or heuristic algorithms. OA is highly modular and not specific to any one algorithm—other resource management algorithms can be easily added.

QoS with an Edge-Based Call Admission Control in IP Networks

Central to the viability of providing traditional services over IP networks is the capability to deliver some level of end-to-end Quality of Service (QoS) to the applications and users. IP networks continue to struggle to migrate from a cost effective best effort data service solution to revenue generating solutions for QoS-sensitive applications such as voice and real-time video. For the case of a network of Media Gateways controlled by SoftSwitches, we propose the use of a measurement based call admission control algorithm at the edge of the network as an approach to provide a cost effective QoS solution. The proposed method utilizes statistical prediction techniques based on available performance measurements without complex QoS management of the packet network. Simulation analysis shows that significant gains in QoS can be achieved with such an edge-to-edge measurement based approach.

Model for location mobility area design

The mobility model described in the paper is used in GLAD which is a tool developed for the design of location areas in GSM networks. The objective of the design is to balance the load on different system resources, including processors, in order to maximize the capacity of the system. In this paper we give a general overview of GLAD, but the focus is on the mobility model which constitutes a critical element of this tool although the model can be applied to any type of wireless networks that uses the location area concept. The proposed mobility model allows us to approximate the number of mobiles crossing the boundary between two neighbouring cells. This information is needed to calculate the number of location updates. The calculation of the mobile flows between the neighbouring cells is based on total number of handovers in cells (measured or assumed) and information available from the network design stage such as cell coverage, road and subscriber density maps. The proposed mathematical model for calculation of the mobile flows between the neighbouring cells is based on the best fit approach. The influence of the location area design on the network resource utilization is illustrated using a realistic example.