Fuzzy ARTMAP and hybrid evolutionary programming for pattern classification

In this paper, an Evolutionary Artificial Neural Network (EANN) that combines the Fuzzy ARTMAP (FAM) network and a Hybrid Evolutionary Programming (HEP) model is introduced. The proposed FAM-HEP model, which combines the strengths of FAM and HEP, is able to construct its network structure autonomously as well as to perform learning and evolutionary search and adaptation concurrently. The effectiveness of the proposed FAM-HEP network is assessed empirically using several benchmark data sets and a real medical diagnosis problem. The performance of FAM-HEP is analyzed, and the results are compared with those of FAM-EP, FAM, and other classification models. In general, the results of FAM-HEP are better than those of FAM-EP and FAM, and are comparable with those from other classification models. The study also reveals the potential of FAM-HEP as an innovative EANN model for undertaking pattern classification problems in general, and a promising computerized decision support tool for tackling medical diagnosis tasks in particular.

Combination of decisions from a multiple neural network classifier system

In this paper, a study of the effectiveness of a multiple classifier system (MCS) in a medical diagnostic task is described. A hybrid network, based on the integration of a fuzzy ARTMAP and the probabilistic neural network, is employed as the basis of the MCS. Outputs from multiple networks are combined using some decision combination method to reach a final prediction. By using a real medical database, a set of experiments has been conducted to evaluate the performance of the MSC with different network configurations. The experimental results reveal the potential of the MCS as a useful decision support tool in the medical field.

Managing manufacturing technology investments: An intelligent learning system approach

This paper proposes an intelligent decision-support system for managing manufacturing technology investments. The intelligent system is a hybrid integration of two information processing modules: case-based reasoning and fuzzy ARTMAP – a supervised adaptive resonance theory (ART) neural network with a multi-dimensional map. The developed system captures a company's strategic information, provides facilities to quantify qualitative attributes and analyses them alongside the quantitative attributes in an evaluation framework. Through the system, similar cases can be retrieved to enable managers to make effective use of their knowledge and experience of previously delivered technologies and projects as an input to the prioritization of future projects. Other salient features of the system include its ability to adapt and absorb new knowledge and responses pertaining to significant events in the business environment, as well as to extract and elucidate information from the knowledge database for explaining and justifying its analysis. The applicability of the developed system is evaluated using a real case study in collaboration with a pharmaceutical manufacturing firm.

A model to select processes for IT service management improvement

IT organisations are continually seeking improvements in managing IT service management processes. The selection of relevant processes to improve is one of the most crucial initial decisions to make in service improvement projects. In this paper, we focus on developing a process selection decision model using service perception factors from the Service Quality (SERV-QUAL) model and business drivers from the Balanced Scorecard perspectives along with the main objective of service improvement as improvement driver. We use a Design Science Research method to develop the model and then a prototype from our proposed model. We establish an evaluation protocol to determine the effectiveness of the prototype which will be demonstrated in a case organisation. The main contribution of the paper is to provide evidence-based decision support for IT service providers to select the most relevant service processes to improve.

ICT to enhance the triangle of life : the soil, the seed, and the life-giver farmer

This paper reports on the outcomes of an ICT enabled social sustainability project “Green Lanka1” trialled in the Wilgamuwa village, which is situated in the Dambulla district of Sri Lanka. The main goals of the project were focused towards the provision of information about market prices, transportation options, agricultural decision support and modern agriculture practices of the farmer communities to improve their livelihood with the effective use of technologies. The project used Web and Mobile (SMS) enabled systems. The Green Lanka project was sponsored by the Information Communication Technology Agency (ICTA) of Sri Lanka under the Institutional Capacity Building Programme (ICBP) grant scheme which was sponsored by the World Bank. Six hundred families in Wilgamuwa village participated in the project activities. The project was designed, executed and studied through an Action Research approach. The lessons learned through the project activities provide an important understanding of the complex interaction between different stakeholders in the process of implementation of ICT enabled solutions within digitally divided societies. The paper analyses the processes used to reduce the resistance to change and improved involvement of farmer communities in ICT enabled projects. It also analyses the interaction between stakeholders involved in design and implementation of the project activities to improve the chances of project success.

Developing online construction technology resources in tectonic design education

We outline issues of importance in relation to tectonic design within the architectural profession and the relationship to architectural education in Australia. Twelve years of research and curriculum development at Deakin University is discussed, involving the creation of online resources and case studies, digitally-integrated projects relating to building construction and design studio education. The ethos behind the Construction Primer of engaging students as ‘amateur researchers’ in a way that ensures ‘that student research work is worth more than course assessment’ forms the pedagogical foundation of much of this work. A model of Socially Networked Construction Technology education has been developed that integrates social networks and the Internet to engage students in tectonic design within and outside the classroom through authentic curricula. Through the use of Virtual Galleries, Blogs, YouTube and social networks, a culture of peer learning and sharing has been developed. Through shared knowledge facilitated through social networks, great potential lies for expanding the synergies between higher order learning and online resource development for design decision support.

An effective heuristic for stockyard planning and machinery scheduling at a coal handling facility

Coal handling is a complex process involving different correlated and highly dependent operations such as selecting appropriate product types, planning stockpiles, scheduling stacking and reclaiming activities and managing train loads. Planning these operations manually is time consuming and can result in non-optimized schedules as future impact of decisions may not be appropriately considered. This paper addresses the operational scheduling of the continuous coal handling problem with multiple conflicting objectives. As the problem is NP-hard in nature, an effective heuristic is presented for planning stockpiles and scheduling resources to minimize delays in production and the coal age in the stockyard. A model of stockyard operations within a coal mine is described and the problem is formulated as a Bi- Objective Optimization Problem (BOOP). The algorithm efficacy is demonstrated on different real-life data scenarios. Computational results show that the solution algorithm is effective and the coal throughput is substantially impacted by the conflicting objectives. Together, the model and the proposed heuristic, can act as a decision support system for the stockyard planner to explore the effects of alternative decisions, such as balancing age and volume of stockpiles, and minimizing conflicts due to stacker and reclaimer movements.

Supporting athlete selection and strategic planning in track cycling omnium: A statistical and machine learning approach

This article describes the implementation of machine learning techniques that assist cycling experts in the crucial decision-making processes for athlete selection and strategic planning in the track cycling omnium. The omnium is a multi-event competition that was included in the Olympic Games for the first time in 2012. Presently, selectors and cycling coaches make decisions based on experience and opinion. They rarely have access to knowledge that helps predict athletic performances. The omnium presents a unique and complex decision-making challenge as it is not clear what type of athlete is best suited to the omnium (e.g., sprint or endurance specialist) and tactical decisions made by the coach and athlete during the event will have significant effects on the overall performance of the athlete. In the present work, a variety of machine learning techniques were used to analyze omnium competition data from the World Championships since 2007. The analysis indicates that sprint events have slightly more influence in determining the medalists, than endurance-based events. Using a probabilistic analysis, we created a model of performance prediction that provides an unprecedented level of supporting information that assists coaches with strategic and tactical decisions during the omnium.

A discrete simulation approach to spatial allocation of commodity production for revenue optimisation over a local region

A simulation approach is described for the spatial allocation of crops across a region in order to maximise total revenue. The model uses inputs from GIS-based land suitability analysis to provide data on yields for a range of commodities, where the land suitability for the crops can be determined by either biophysical models or multi-criteria analysis. The objective of the study was to gain some indication of the magnitude of improvement possible in revenue, based on the convergence results for the optimisation (subject to estimated production quantities and market prices). The basic structure of the model allows for scaling up to larger problems with additional inputs and finer cell resolution. The software produces a visualisation of crop spatial allocation across the region and is compatible with statistical uncertainty analysis. The results of model simulations revealed a significant increase in revenue is possible using this approach and, when projected over the full region, suggests the possibility of significant economic benefits.

Classification of healthcare data using genetic fuzzy logic system and wavelets

Healthcare plays an important role in promoting the general health and well-being of people around the world. The difficulty in healthcare data classification arises from the uncertainty and the high-dimensional nature of the medical data collected. This paper proposes an integration of fuzzy standard additive model (SAM) with genetic algorithm (GA), called GSAM, to deal with uncertainty and computational challenges. GSAM learning process comprises three continual steps: rule initialization by unsupervised learning using the adaptive vector quantization clustering, evolutionary rule optimization by GA and parameter tuning by the gradient descent supervised learning. Wavelet transformation is employed to extract discriminative features for high-dimensional datasets. GSAM becomes highly capable when deployed with small number of wavelet features as its computational burden is remarkably reduced. The proposed method is evaluated using two frequently-used medical datasets: the Wisconsin breast cancer and Cleveland heart disease from the UCI Repository for machine learning. Experiments are organized with a five-fold cross validation and performance of classification techniques are measured by a number of important metrics: accuracy, F-measure, mutual information and area under the receiver operating characteristic curve. Results demonstrate the superiority of the GSAM compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. The proposed approach is thus helpful as a decision support system for medical practitioners in the healthcare practice.

Interventions to reduce medication errors in pediatric intensive care

To systematically examine the research literature to identify which interventions reduce medication errors in pediatric intensive care units.