Proceedings of the Eighth Australian and New Zealand Intelligent Information Systems Conference

These are the full proceedings of the conference.

Modelling the dynamics of genetic algorithms using statistical mechanics

A formalism for modelling the dynamics of Genetic Algorithms (GAs) using methods from statistical mechanics, originally due to Prugel-Bennett and Shapiro, is reviewed, generalized and improved upon. This formalism can be used to predict the averaged trajectory of macroscopic statistics describing the GA's population. These macroscopics are chosen to average well between runs, so that fluctuations from mean behaviour can often be neglected. Where necessary, non-trivial terms are determined by assuming maximum entropy with constraints on known macroscopics. Problems of realistic size are described in compact form and finite population effects are included, often proving to be of fundamental importance. The macroscopics used here are cumulants of an appropriate quantity within the population and the mean correlation (Hamming distance) within the population. Including the correlation as an explicit macroscopic provides a significant improvement over the original formulation. The formalism is applied to a number of simple optimization problems in order to determine its predictive power and to gain insight into GA dynamics. Problems which are most amenable to analysis come from the class where alleles within the genotype contribute additively to the phenotype. This class can be treated with some generality, including problems with inhomogeneous contributions from each site, non-linear or noisy fitness measures, simple diploid representations and temporally varying fitness. The results can also be applied to a simple learning problem, generalization in a binary perceptron, and a limit is identified for which the optimal training batch size can be determined for this problem. The theory is compared to averaged results from a real GA in each case, showing excellent agreement if the maximum entropy principle holds. Some situations where this approximation brakes down are identified. In order to fully test the formalism, an attempt is made on the strong sc np-hard problem of storing random patterns in a binary perceptron. Here, the relationship between the genotype and phenotype (training error) is strongly non-linear. Mutation is modelled under the assumption that perceptron configurations are typical of perceptrons with a given training error. Unfortunately, this assumption does not provide a good approximation in general. It is conjectured that perceptron configurations would have to be constrained by other statistics in order to accurately model mutation for this problem. Issues arising from this study are discussed in conclusion and some possible areas of further research are outlined.

Noisy fitness evaluation in genetic algorithms and the dynamics of learning

A theoretical model is presented which describes selection in a genetic algorithm (GA) under a stochastic fitness measure and correctly accounts for finite population effects. Although this model describes a number of selection schemes, we only consider Boltzmann selection in detail here as results for this form of selection are particularly transparent when fitness is corrupted by additive Gaussian noise. Finite population effects are shown to be of fundamental importance in this case, as the noise has no effect in the infinite population limit. In the limit of weak selection we show how the effects of any Gaussian noise can be removed by increasing the population size appropriately. The theory is tested on two closely related problems: the one-max problem corrupted by Gaussian noise and generalization in a perceptron with binary weights. The averaged dynamics can be accurately modelled for both problems using a formalism which describes the dynamics of the GA using methods from statistical mechanics. The second problem is a simple example of a learning problem and by considering this problem we show how the accurate characterization of noise in the fitness evaluation may be relevant in machine learning. The training error (negative fitness) is the number of misclassified training examples in a batch and can be considered as a noisy version of the generalization error if an independent batch is used for each evaluation. The noise is due to the finite batch size and in the limit of large problem size and weak selection we show how the effect of this noise can be removed by increasing the population size. This allows the optimal batch size to be determined, which minimizes computation time as well as the total number of training examples required.

Accounting information systems as knowledge objects:some effects of objectualization

This paper will outline a research methodology informed by theorists who have contributed to actor network theory (ANT). Research informed from such a perspective recognizes the constitutive role of accounting systems in the achievement of broader social goals. Latour, Knoor Cetina and others argue that the bringing in of non-human actants, through the growth of technology and science, has added immeasurably to the complexity of modern society. The paper ‘sees’ accounting and accounting systems as being constituted by technological ‘black boxes’ and seeks to discuss two questions. One concerns the processes which surround the establishment of ‘facts’, i.e. how ‘black boxes’ are created or accepted (even if temporarily) within society. The second concerns the role of existing ‘black boxes’ within society and organizations. Accounting systems not only promote a particular view of the activities of an organization or a subunit, but in their very implementation and operation ‘mobilize’ other organizational members in a particular direction. The implications of such an interpretation are explored in this paper. Firstly through a discussion of some of the theoretic constructs that have been proposed to frame ANT research. Secondly an attempt is made to relate some of these ideas to aspects of the empirics in a qualitative case study. The case site is in the health sector and involves the implementation of a casemix accounting system. Evidence from the case research is used to exemplify aspects of the theoretical constructs.

A study of business user based information systems development, and modelling success factors

This thesis describes research into business user involvement in the information systems application building process. The main interest of this research is in establishing and testing techniques to quantify the relationships between identified success factors and the outcome effectiveness of 'business user development' (BUD). The availability of a mechanism to measure the levels of the success factors, and quantifiably relate them to outcome effectiveness, is important in that it provides an organisation with the capability to predict and monitor effects on BUD outcome effectiveness. This is particularly important in an era where BUD levels have risen dramatically, user centred information systems development benefits are recognised as significant, and awareness of the risks of uncontrolled BUD activity is becoming more widespread. This research targets the measurement and prediction of BUD success factors and implementation effectiveness for particular business users. A questionnaire instrument and analysis technique has been tested and developed which constitutes a tool for predicting and monitoring BUD outcome effectiveness, and is based on the BUDES (Business User Development Effectiveness and Scope) research model - which is introduced and described in this thesis. The questionnaire instrument is designed for completion by 'business users' - the target community being more explicitly defined as 'people who primarily have a business role within an organisation'. The instrument, named BUD ESP (Business User Development Effectiveness and Scope Predictor), can readily be used with survey participants, and has been shown to give meaningful and representative results.

The Application of Geographic Information Systems to climate change & land evaluation : a study of the effects of climate change upon crop productivity in a sub-tropical environment

This research investigates the contribution that Geographic Information Systems (GIS) can make to the land suitability process used to determine the effects of a climate change scenario. The research is intended to redress the severe under representation of Developing countries within the literature examining the impacts of climatic change upon crop productivity. The methodology adopts some of the Intergovernmental Panel on Climate Change (IPCC) estimates for regional climate variations, based upon General Circulation Model predictions (GCMs) and applies them to a baseline climate for Bangladesh. Utilising the United Nations Food & Agricultural Organisation's Agro-ecological Zones land suitability methodology and crop yield model, the effects of the scenario upon agricultural productivity on 14 crops are determined. A Geographic Information System (IDRISI) is adopted in order to facilitate the methodology, in conjunction with a specially designed spreadsheet, used to determine the yield and suitability rating for each crop. A simple optimisation routine using the GIS is incorporated to provide an indication of the 'maximum theoretical' yield available to the country, should the most calorifically significant crops be cultivated on each land unit both before and after the climate change scenario. This routine will provide an estimate of the theoretical population supporting capacity of the country, both now and in the future, to assist with planning strategies and research. The research evaluates the utility of this alternative GIS based methodology for the land evaluation process and determines the relative changes in crop yields that may result from changes in temperature, photosynthesis and flooding hazard frequency. In summary, the combination of a GIS and a spreadsheet was successful, the yield prediction model indicates that the application of the climate change scenario will have a deleterious effect upon the yields of the study crops. Any yield reductions will have severe implications for agricultural practices. The optimisation routine suggests that the 'theoretical maximum' population supporting capacity is well in excess of current and future population figures. If this agricultural potential could be realised however, it may provide some amelioration from the effects of climate change.

Solving Travelling Salesman Problem in a Simulation of Genetic Algorithms with DNA

In this paper it is explained how to solve a fully connected N-City travelling salesman problem (TSP) using a genetic algorithm. A crossover operator to use in the simulation of a genetic algorithm (GA) with DNA is presented. The aim of the paper is to follow the path of creating a new computational model based on DNA molecules and genetic operations. This paper solves the problem of exponentially size algorithms in DNA computing by using biological methods and techniques. After individual encoding and fitness evaluation, a protocol of the next step in a GA, crossover, is needed. This paper also shows how to make the GA faster via different populations of possible solutions.

DNA Simulation of Genetic Algorithms: Fitness Computation

* This work has been partially supported by Spanish Project TIC2003-9319-c03-03 “Neural Networks and Networks of Evolutionary Processors”.

A DNA Codification for Genetic Algorithms Simulation

In this paper we propose a model of encoding data into DNA strands so that this data can be used in the simulation of a genetic algorithm based on molecular operations. DNA computing is an impressive computational model that needs algorithms to work properly and efficiently. The first problem when trying to apply an algorithm in DNA computing must be how to codify the data that the algorithm will use. In a genetic algorithm the first objective must be to codify the genes, which are the main data. A concrete encoding of the genes in a single DNA strand is presented and we discuss what this codification is suitable for. Previous work on DNA coding defined bond-free languages which several properties assuring the stability of any DNA word of such a language. We prove that a bond-free language is necessary but not sufficient to codify a gene giving the correct codification.

Implementation of Genetic Algorithms for Transit Points Arrangement

The problem of transit points arrangement is presented in the paper. This issue is connected with accuracy of tariff distance calculation and it is the urgent problem at present. Was showed that standard method of tariff distance discovering is not optimal. The Genetic Algorithms are used in optimization problem resolution. The UML application class diagram and class content are showed. In the end the example of transit points arrangement is represented.

Social construction of Geographic Information Systems. (Volumes I and II)

Geographic Information Systems (GIS) is an emerging information technology (IT) which promises to have large scale influences in how spatially distributed resources are managed. It has had applications in the management of issues as diverse as recovering from the disaster of Hurricane Andrew to aiding military operations in Desert Storm. Implementation of GIS systems is an important issue because there are high cost and time involvement in setting them up. An important component of the implementation problem is the "meaning" different groups of people who are influencing the implementation give to the technology. The research was based on the theory of (theoretical stance to the problem was based on the) "Social Construction of Knowledge" systems which assumes knowledge systems are subject to sociological analysis both in usage and in content. An interpretive research approach was adopted to inductively derive a model which explains how the "meanings" of a GIS are socially constructed. The research design entailed a comparative case analysis over two county sites which were using the same GIS for a variety of purposes. A total of 75 in-depth interviews were conducted to elicit interpretations of GIS. Results indicate that differences in how geographers and data-processors view the technology lead to different implementation patterns in the two sites.

Consequences of interorganizational information systems: An empirical investigation of the effects of EDI use on interorganizational relationships in the retail industry

This dissertation examines the consequences of Electronic Data Interchange (EDI) use on interorganizational relations (IR) in the retail industry. EDI is a type of interorganizational information system that facilitates the exchange of business documents in structured, machine processable form. The research model links EDI use and three IR dimensions--structural, behavioral, and outcome. Based on relevant literature from organizational theory and marketing channels, fourteen hypotheses were proposed for the relationships among EDI use and the three IR dimensions.^ Data were collected through self-administered questionnaires from key informants in 97 retail companies (19% response rate). The hypotheses were tested using multiple regression analysis. The analysis supports the following hypothesis: (a) EDI use is positively related to information intensity and formalization, (b) formalization is positively related to cooperation, (c) information intensity is positively related to cooperation, (d) conflict is negatively related to performance and satisfaction, (e) cooperation is positively related to performance, and (f) performance is positively related to satisfaction. The results support the general premise of the model that the relationship between EDI use and satisfaction among channel members has to be viewed within an interorganizational context.^ Research on EDI is still in a nascent stage. By identifying and testing relevant interorganizational variables, this study offers insights for practitioners managing boundary-spanning activities in organizations using or planning to use EDI. Further, the thesis provides avenues for future research aimed at understanding the consequences of this interorganizational information technology. ^

Understanding the dynamics of information technology implementation: The case of clinical information systems

The ultimate intent of this dissertation was to broaden and strengthen our understanding of IT implementation by emphasizing research efforts on the dynamic nature of the implementation process. More specifically, efforts were directed toward opening the "black box" and providing the story that explains how and why contextual conditions and implementation tactics interact to produce project outcomes. In pursuit of this objective, the dissertation was aimed at theory building and adopted a case study methodology combining qualitative and quantitative evidence. Precisely, it examined the implementation process, use and consequences of three clinical information systems at Jackson Memorial Hospital, a large tertiary care teaching hospital.^ As a preliminary step toward the development of a more realistic model of system implementation, the study proposes a new set of research propositions reflecting the dynamic nature of the implementation process.^ Findings clearly reveal that successful implementation projects are likely to be those where key actors envision end goals, anticipate challenges ahead, and recognize the presence of and seize opportunities. It was also found that IT implementation is characterized by the systems theory of equifinality, that is, there are likely several equally effective ways to achieve a given end goal. The selection of a particular implementation strategy appears to be a rational process where actions and decisions are largely influenced by the degree to which key actors recognize the mediating role of each tactic and are motivated to action. The nature of the implementation process is also characterized by the concept of "duality of structure," that is, context and actions mutually influence each other. Another key finding suggests that there is no underlying program that regulates the process of change and moves it form one given point toward a subsequent and already prefigured end. For this reason, the implementation process cannot be thought of as a series of activities performed in a sequential manner such as conceived in stage models. Finally, it was found that IT implementation is punctuated by a certain indeterminacy. Results suggest that only when substantial efforts are focused on what to look for and think about, it is less likely that unfavorable and undesirable consequences will occur. ^

Managing conflict in user-oriented development environments: Effects on information systems success

Today, many organizations are turning to new approaches to building and maintaining information systems (I/S) to cope with a highly competitive business environment. Current anecdotal evidence indicates that the approaches being used improve the effectiveness of software development by encouraging active user participation throughout the development process. Unfortunately, very little is known about how the use of such approaches enhances the ability of team members to develop I/S that are responsive to changing business conditions.^ Drawing from predominant theories of organizational conflict, this study develops and tests a model of conflict among members of a development team. The model proposes that development approaches provide the relevant context conditioning the management and resolution of conflict in software development which, in turn, are crucial for the success of the development process.^ Empirical testing of the model was conducted using data collected through a combination of interviews with I/S executives and surveys of team members and business users at nine organizations. Results of path analysis provide support for the model's main prediction that integrative conflict management and distributive conflict management can contribute to I/S success by influencing differently the manifestation and resolution of conflict in software development. Further, analyses of variance indicate that object-oriented development, when compared to rapid and structured development, appears to produce the lowest levels of conflict management, conflict resolution, and I/S success.^ The proposed model and findings suggest academic implications for understanding the effects of different conflict management behaviors on software development outcomes, and practical implications for better managing the software development process, especially in user-oriented development environments. ^

Optimization of adaptive traffic signal control with transit signal priority at isolated intersections using parallel genetic algorithms

Optimization of adaptive traffic signal timing is one of the most complex problems in traffic control systems. This dissertation presents a new method that applies the parallel genetic algorithm (PGA) to optimize adaptive traffic signal control in the presence of transit signal priority (TSP). The method can optimize the phase plan, cycle length, and green splits at isolated intersections with consideration for the performance of both the transit and the general vehicles. Unlike the simple genetic algorithm (GA), PGA can provide better and faster solutions needed for real-time optimization of adaptive traffic signal control. ^ An important component in the proposed method involves the development of a microscopic delay estimation model that was designed specifically to optimize adaptive traffic signal with TSP. Macroscopic delay models such as the Highway Capacity Manual (HCM) delay model are unable to accurately consider the effect of phase combination and phase sequence in delay calculations. In addition, because the number of phases and the phase sequence of adaptive traffic signal may vary from cycle to cycle, the phase splits cannot be optimized when the phase sequence is also a decision variable. A "flex-phase" concept was introduced in the proposed microscopic delay estimation model to overcome these limitations. ^ The performance of PGA was first evaluated against the simple GA. The results show that PGA achieved both faster convergence and lower delay for both under- or over-saturated traffic conditions. A VISSIM simulation testbed was then developed to evaluate the performance of the proposed PGA-based adaptive traffic signal control with TSP. The simulation results show that the PGA-based optimizer for adaptive TSP outperformed the fully actuated NEMA control in all test cases. The results also show that the PGA-based optimizer was able to produce TSP timing plans that benefit the transit vehicles while minimizing the impact of TSP on the general vehicles. The VISSIM testbed developed in this research provides a powerful tool to design and evaluate different TSP strategies under both actuated and adaptive signal control. ^