J. Douglas Birdwell

University of Tennessee at Knoxville | UTK · Department of Electrical Engineering and Computer Science

This document provides a partial survey of relatively recent research efforts reported in the literature in the area of automated source code generation (ASCG) using methods from artificial intelligence (AI) in general and machine learning (ML) in particular. The work was motivated by the fact that the Army has “identified the need to reduce costs...

This paper discusses selected publications that relate cyber-security to artificial intelligence (AI) in general and to machine learning (ML) specifically. The focus is cyber-security in the context of software development and life-cycle environments (SDLE) and their products. Because of the large volume of publications in this area, the survey inc...

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine lea...

We discuss a neuroscience-inspired dynamic architecture (NIDA) and associated design method based on evolutionary optimization. NIDA networks designed to perform anomaly detection tasks and control tasks have been shown to be successful in previous work. In particular, NIDA networks perform well on tasks that have a temporal component. We present m...

The present invention provides a method of predicting whether an unknown biological specimen originates from a member of a particular family. The method compares DNA profiles from at least one unknown biological specimen to DNA profiles of more than one family member, which significantly increases the methods' predictive ability. In particular, the...

We present the design-scheme and physical implementation for a Dynamic Adaptive Neural Network Array (DANNA) based upon the work by Schuman and Birdwell [1,2] and using a programmable array of elements constructed with a Field Programmable Gate Array (FPGA). The aim of this paper is to demonstrate how a single programmable neuromorphic element can...

Three methods of predicting whether an unknown biological specimen of a missing person originates from a member of a particular family comprise an initial automated decision support (ADS) algorithm for determining a list of relatives of the missing person for DNA typing and which typing technologies of available technologies to use for a listed rel...

Method and apparatus for predicting properties of a target object comprise application of a search manager for analyzing parameters of a plurality of databases for a plurality of objects, the databases comprising an electrical, electromagnetic, acoustic spectral database (ESD), a micro-body assemblage database (MAD) and a database of image data whe...

Neuroscience-inspired computational elements and architectures are one of the most popular ideas for replacing the von Neumann architecture. In this work, we propose a neuroscience-inspired dynamic architecture (NIDA) and discuss a method for automatically designing NIDA networks to accomplish tasks. We discuss the reasons we chose evolutionary opt...

Analysis of DNA is critical to many applications including identifying perpetrators of crimes based on genetic evidence left at crime scenes. An initial step to analyzing DNA data is detection, identification, and quantization of allele peaks in the DNA data. The invention provides a method and apparatus for accurately and expeditiously performing...

Artificial neural networks (ANNs) are processors that are trained to perform particular tasks. We couple a computational ANN with a simulated affective system in order to explore the interaction between the two. In particular, we design a simple affective system that adjusts the threshold values in the neurons of our ANN. The aim of this paper is t...

We introduce a discrete-event artificial neural network structure inspired by biological neural networks. It includes dynamic components and has variable structure. The network’s topology and its dynamic components are modifiable and trainable for different applications. Such adaptation in the network’s parameters, structure, and dynamic components...

Identifying multiple enzyme targets for metabolic engineering is very critical for redirecting cellular metabolism to achieve desirable phenotypes, e.g., overproduction of a target chemical. The challenge is to determine which enzymes and how much of these enzymes should be manipulated by adding, deleting, under-, and/or over-expressing associated...

Method and apparatus for determining a metric for use in predicting properties of an unknown specimen belonging to a group of reference specimen electrical devices comprises application of a network analyzer for collecting impedance spectra for the reference specimens and determining centroids and thresholds for the group of reference specimens so...

A deterministic dynamic linear time-delay model is presented to model load balancing in a cluster of nodes used for parallel computations. The model is analyzed for stability in terms of the delays in the transfer of information between nodes and the gains in the load balancing algorithm.

In this paper, we present a new dynamic, and adaptive distributed load balancing algorithm. This algorithm is able to handle the loss of some computational nodes, the connectivity of the network, and the variations in tasks and transfer delays. An experimental veriflcation of the algorithm is presented using PlanetLab. Copyright c ∞2005 IFAC

Early in 2004, as part of the planning process for celebrating the IEEE Control Systems Society (CSS) 50th anniversary, I decided to assemble a collection of photographs from Society events. The collection is not intended to have any profound meaning, but it is simply a way for our members to indulge in their—and others'—memories of past events and...

A novel preferential image segmentation method is proposed that performs image segmentation and object recognition using mathematical morphologies. The method preferentially segments objects that have intensities and boundaries similar to those of objects in a database of prior images. A tree of shapes is utilized to represent the content distribut...

This paper provides the Banach duality theory structure of the optimal two-block H∞ problem. Alignment conditions are obtained and show that the optimal solution is flat or allpass in general, and is unique in the single-input single-output case. The optimal solution is shown to satisfy an extremal identity, which gives a necessary and sufficient c...

This brief documents experimental results using a deterministic dynamic nonlinear system for load balancing, previously reported by Tang et al. in a cluster of computer nodes used for parallel computations in the presence of time delays and resource constraints. While previous publications by the authors have provided theoretical analysis of this l...

Load balancing for parallel computations is modeled as a deterministic dynamic nonlinear time-delay system. This model accounts for the trade-off between using processor time/network bandwidth and the advantage of distributing the load evenly between the nodes to reduce overall processing time. A distributed closed-loop controller is presented to b...

Curve evolution implementations of the Mumford-Shah functional are of broad interest in image segmentation. These implementations, however, have initialization problems. A mathematical analysis of the initialization problem for the Chan-Vese implementation is provided in this paper. The initialization problem is a result of the non-convexity of the...

Interpreting mixture short tandem repeat DNA data is often a laborious process, involving trying different genotype combinations mixed at assumed DNA mass proportions, and assessing whether the resultant is supported well by the relative peak-height information of the mixture sample. If a clear pattern of major-minor alleles is apparent, it is feas...

This paper develops a hybrid optimal control technique and resulting experimental data using a previously reported deterministic dynamic nonlinear system model for load balancing in a cluster of computer nodes used for parallel computations in the presence of time delays and resource constraints. The model accounts for the trade-off between using p...

Curve evolution implementations of the Mumford-Shah functional are of broad interest in image segmentation. These implementations, however, have initialization problems. A mathematical analysis of the initialization problem for the bi-modal Chan-Vese model is provided in this paper. The initialization problem is a result of the non-convexity of the...

Efficient implementation methods are proposed for Chan-Vese models. The proposed methods do not require solutions of PDEs and are therefore fast. The advantages of level set methods, such as automatic handling of topological changes, are preserved. These methods utilize region information to guide the evolution of initial curves. Gaussian smoothing...

The topic of this workshop is Distributed Intelligent Networks and Systems (DINS). The workshop aims to help develop a strategy to build a better “home” for the research areas and technologies within the scope of DINS. These research areas and technologies cut across the traditional boundaries of many IEEE technical societies, and a more coordinate...

The critical features of the load balancing problem are the delayed receipt of information and transferred load. Load distribution and task processing contend for the same resources on each computational element. This paper documents experimental results using a previously reported deterministic dynamic nonlinear system for load balancing in a clus...

In many distributed computing systems that are prone to either induced or spontaneous node failures, the number of available computing resources is dynamically changing in a random fashion. A load-balancing (LB) policy for such systems should therefore be robust, in terms of workload re-allocation and effectiveness in task completion, with respect...

In this paper, a new model is proposed for image segmentation that integrates the curve evolution and anisotropic diffusion methods. The curve evolution method, utilizing both gradient and region information, segments an image into multiple regions. During the evolution of the curve, anisotropic diffusion is adaptively applied to the image to remov...

This paper generalizes the methods in a previous paper in Pan, Y. et al, (2006) in two ways. First, a more comprehensive analysis of the initialization problem of the Chan-Vese models is given. Second, the image segmentation method proposed in Pan, Y. et al. (2006) is improved by applying bimodal curve evolution with region competition. The improve...

A deterministic dynamic nonlinear time-delay system is developed to model load balancing in a cluster of computer nodes used for parallel computations. The model is shown to be self consistent in that the queue lengths cannot go negative and the total number of tasks in all the queues and the network are conserved (i.e., load balancing can neither...

The proliferation of computational resources and data networks has enabled the conception and solution of information management problems of an unprecedented scale. These technologies expose vulnerabilities that may be exploited through happenstance or design. The engineering problems encountered in the design of networked data systems and software...

Thesis. 1978. Ph.D.--Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. Includes bibliographical references. Ph.D.

Load balancing for parallel computations is modeled as a deterministic dynamic nonlinear time-delay system. This model accounts for the trade-off between using processor time/network bandwidth and the advantage of distributing the load evenly between the nodes to reduce overall processing time. A distributed closed-loop controller is presented to b...

This paper provides the duality structure of the optimal two-block H^∞ problem. The dual description leads naturally to a numerical solution based on convex programming for LTI (including infinite dimensional) systems. Alignment conditions are obtained and show that the optimal solution is flat in general, and unique in the SISO case. It...

In this paper, experimental evaluation of the load balancing algorithm in real environments is presented. We emphasize the effects of delays on the exchange of information among nodes, and the constraints these effects impose on the design of a load balancing strategy. Two testbeds in two different real environments have been built; the first imple...

A deterministic dynamic nonlinear time-delay system is developed to model load balancing in a cluster of computer nodes used for parallel computations. This model refines a model previously proposed by the authors to account for the fact that the load balancing operation involves processor time which cannot be used to process tasks. Consequently, t...

Presents the President's message for this issue of the publication.

In this paper, a new geometric snake model is proposed, based upon techniques of curve evolution and the utilization of gradient information and region information simultane-ously. This model successfully solves the boundary leakage problem. With the help of a hierarchical approach, it can handle complicated cases, such as triple junctions. Further...

A probabilistic active contour model is formulated, in which curve evolution is viewed as state estimation for a nonlinear dynamical system. The method is implemented using particle filters in a Bayesian framework. Level set methods are utilized and enable the proposed model to handle topological changes. Experimental results show that the proposed...

As part of the planning process for the IEEE Control Systems Society's 50th anniversary celebration, a collection of photographs from Society events are assembled. The collection is not intended to have any profound meaning but is simply a way for the members to indulge in their individual and collective memories of past events and people, to impar...

The objective of parallel processing is to reduce wall-clock time and increase the size of solvable problems by dividing the code into multiple fragments that can be executed simultaneously on each of a set of computational elements (CE) interconnected via a high bandwidth network. A common parallel computer architecture is the cluster of otherwise...

Distributing the total computational load across available processors is referred to as load balancing in the literature. A typical distributed system consists of a cluster of physically or virtually distant and independent computational elements (CEs), which are linked to one another by some communication medium. The workload has to be distributed...

Presents the President's message for this issue of the publication.

Presents the President's message for this issue of the publication.

Presents the President's message for this issue of the publication.

Presents the President's message for this issue of the publication.

Deterministic dynamic nonlinear time-delay systems are developed to model load balancing in a cluster of computer nodes used for parallel computations. The model is shown to be self consistent in that the queue lengths cannot go negative and the total number of tasks in all the queues are conserved (i.e., load balancing can neither create nor lose...

In large-scale distributed computing systems, in which the computational elements are physically or virtually distant from each other, there are communication-related delays that can significantly alter the expected performance of load-balancing policies that do not account for such delays. This is a particularly significant problem in systems for...

Parallel computer architectures utilize a set of computational elements (CE) to achieve performance that is not attainable on a single processor, or CE, computer. A common architecture is the cluster of otherwise independent computers communicating through a shared network. To make use of parallel computing resources, problems must be broken down i...

Previous data mining activities have mostly focused on mining a centralized database. One big problem with a centralized database is its limited scalability. Because of the distributed nature of many businesses and the exponentially in- creasing amount of data generated from numerous sources, a distributed database becomes an attractive alternative...

A deterministic dynamic nonlinear time-delay systems has been recently developed to model load balancing in a cluster of computer nodes used for parallel computations. Further, it was shown that using the proposed load balancing algorithms, the system is stable independent of the feeback gains. However, the performance of the system is dependent on...

A linear time-delay system is proposed to model load balancing in a cluster of computer nodes used for parallel computations. The linear model is analysed for stability in terms of the delays in the transfer of information between nodes and the gains in the load balancing algorithm. This model is compared with an experimental implementation of the...

Fielding and managing the dynamic, complex information systems infrastructure necessary for defense operations presents significant opportunities for revolutionary improvements in capabilities. An example of this technology trend is the creation and validation of the Joint Battlespace Infosphere (JBI) being developed by the Air Force Research Lab....

Not Available

The ramifications of a condensed signal technology and the application of Markov chain methods to system modeling and control are explored. Condensed object-oriented signals are constructed from raw measurement data. Finite impulse response hybrid systems are proposed for process models based upon these object-oriented signals

This paper describes a method to automatically design autotuners for control systems using simulated annealing and decision trees. Simulated annealing is used to select a set of tuning rules that optimize an objective function defined by a set of system performance criteria over the controller's parameters. Simulated annealing updates its intellige...

Not Available

Wireless sensors which utilize low power spread spectrum data transmission have significant potential in industrial environments due to low cabling and installation costs. In addition, this technology imposes fewer constraints upon placement due to cable routing, allowing sensors to be installed in areas with poor access. Limitations are imposed on...

This paper deals with processing and storage methods for large volume industrial process data measurements which enable the utilization of historical data for process understanding. In the context of hybrid systems, the focus is upon the steps commonly lumped under the category of analog to digital conversion (ADC), which is the interface between t...

This paper presents the fuzzy-PID controller model, which encodes different control strategies for use under different circumstances in a fuzzy rule-base. The fuzzy-PID controller is able to implement any PID controller with additional flexibility, and substantial opportunities for improved performance exist. Conditions which guarantee stability of...

This paper presents a new controller model, the fuzzy-PID controller, which merges PID control and fuzzy control in order to improve system performance especially when nonlinearity, uncertainty and complexity are involved. The proposed model provides a mechanism to achieve PID control selftuning and encodes different control strategies for use unde...

A method to automatically design a fuzzy logic autotuner (FLA) for PID regulators is described. The autotuner evaluates a fuzzy logic rule base obtained by application of simulated annealing (SA) optimization procedures to a set of chosen initial controllers for a system. Both autotuner and the SA procedures optimize an objective function defined b...