An associative memory approach to medical decision support systems

Classification is one of the key issues in medical diagnosis. In this paper, a novel approach to perform pattern classification tasks is presented. This model is called Associative Memory based Classifier (AMBC). Throughout the experimental phase, the proposed algorithm is applied to help diagnose diseases; particularly, it is applied in the diagnosis of seven different problems in the medical field. The performance of the proposed model is validated by comparing classification accuracy of AMBC against the performance achieved by other twenty well known algorithms. Experimental results have shown that AMBC achieved the best performance in three of the seven pattern classification problems in the medical field. Similarly, it should be noted that our proposal achieved the best classification accuracy averaged over all datasets.     

A new approach to water quality modelling and environmental decision support systems

The concepts and technology of environmental decision support systems (EDSS) have developed considerably over recent decades, although core concepts such as flexibility and adaptability within a changing decision environment remain paramount. Much recent EDSS theory has focussed on model integration and re-use in decision support system (DSS) tools and for design and construction of ‘DSS generators’. Many current specific DSS have architectures, tools, models and operational characteristics that are either fixed or difficult to change in the face of changing management needs. This paper reports on development and deployment of an EDSS that encompasses a new approach to DSS tools, generators and specific DSS applications. The system, named E2, is built upon a conceptualisation of terrestrial and aquatic environmental systems that has resulted in a robust and flexible system architecture. The architecture provides a set of base classes to represent fundamental concepts, and which can be instantiated and combined to form DSS generators of varying complexity. A DSS generator is described within which system users are able to select and link models, data, analysis tools and reporting tools to create specific DSS for particular problems, and for which new models and tools can be created and, through software reflection (introspection), discovered to provide expanded capability where required. This system offers a new approach within which environmental systems can be described in the form of specific DSS at a scale and level of complexity suited to the problems and needs of decision makers.     

A decision support system for fisheries management using operations research and systems science approach

In this paper, we present a general framework, using a systems science approach, for developing a decision support system (DSS) for fisheries management. Decision support systems are quantitative tools for managers to evaluate outcomes of their policies prior to implementation. Our fishery model considers multiple stocks and fisheries simultaneously in balancing catch among targeted and protected fish abundances. Since in the Northeastern US multispecies fishery the distribution of abundance, catch-per-unit-effort and bycatch vary geographically, we focus on a spatial management approach to address their spatial variability. The core component of this DSS applies operations research techniques of simulation and optimization to determine the optimal inter-annual and intra-annual fishing plans in terms of fishing efforts in each sub-area and the time period. The result is the recommended amount to catch from each fish species at each sub-area at any time period so that while management objectives for sustainability of fish stocks are satisfied, the value of landings is maximized. The graphical user interface of the proposed DSS helps users to define inputs, to set constraints and sub-area boundaries, and to visualize the outcomes.     

A group decision support approach to evaluating journals

One of the most important decisions made in academic institutions, research organizations, and government agencies is the grading or ranking of journals for their academic values. Current methods for evaluating journals use either a subjective (e.g., experts’ judgments on journals) or objective approach (e.g., impact factors of journals), or an informal mix of the two. This paper presents a formal procedure that integrates objective and subjective judgments to provide a comprehensive method. The procedure is based on a fuzzy set approach that deals with the imprecise and missing information inherent in the evaluation process. The system was tested in Hong Kong in an assessment of faculty research productivity. Similar assessments exist in the UK, Singapore, and other countries. The proposed model can also be used for similar decisions that involve subjective and objective information.     

Integration of decision support systems to improve decision support performance

Decision support system (DSS) is a well-established research and development area. Traditional isolated, stand-alone DSS has been recently facing new challenges. In order to improve the performance of DSS to meet the challenges, research has been actively carried out to develop integrated decision support systems (IDSS). This paper reviews the current research efforts with regard to the development of IDSS. The focus of the paper is on the integration aspect for IDSS through multiple perspectives, and the technologies that support this integration. More than 100 papers and software systems are discussed. Current research efforts and the development status of IDSS are explained, compared and classified. In addition, future trends and challenges in integration are outlined. The paper concludes that by addressing integration, better support will be provided to decision makers, with the expectation of both better decisions and improved decision making processes.     

Cloud-based decision support systems and availability context: the probability of successful decision outcomes

In an age of cloud computing, mobile users, and wireless networks, the availability of decision support related computing resources can no longer guarantee five-nines (99.999%) availability. Since the dependence on decision support systems is ever increasing, obtaining accurate deterministic advice from these systems will become critical. This study proposes a probabilistic model that maps decision resource availability to correct decision outcomes. Grounded in system reliability theory, the probability functions are given and developed. The model is evaluated with a simulated decision opportunity and the outcome of the experimentation is quantified using a goodness of fit measure and ANOVA testing.     

A group decision support approach to evaluating journals

One of the most important decisions made in academic institutions, research organizations, and government agencies is the grading or ranking of journals for their academic values. Current methods for evaluating journals use either a subjective (e.g., experts’ judgments on journals) or objective approach (e.g., impact factors of journals), or an informal mix of the two. This paper presents a formal procedure that integrates objective and subjective judgments to provide a comprehensive method. The procedure is based on a fuzzy set approach that deals with the imprecise and missing information inherent in the evaluation process. The system was tested in Hong Kong in an assessment of faculty research productivity. Similar assessments exist in the UK, Singapore, and other countries. The proposed model can also be used for similar decisions that involve subjective and objective information.     

维修智能决策支持系统及其可视化实现

阐速了一种维修智能决策支持系统的可视化实现,讨论了决策支持可视化的涵义,介绍了可视化维修智能决策支持系统的体系结构及关键技术。该系统支持自动获取维修数据信息,实现了维修故障诊断过程和智能决策的可视化,提高了装备维修保障水平。     

A Bayesian approach to model dispersal for decision support

In agricultural and environmental sciences dispersal models are often used for risk assessment to predict the risk associated with a given configuration and also to test scenarios that are likely to minimise those risks. Like any biological process, dispersal is subject to biological, climatic and environmental variability and its prediction relies on models and parameter values which can only approximate the real processes. In this paper, we present a Bayesian method to model dispersal using spatial configuration and climatic data (distances between emitters and receptors; main wind direction) while accounting for uncertainty, with an application to the prediction of adventitious presence rate of genetically modified maize (GM) in a non-GM field. This method includes the design of candidate models, their calibration, selection and evaluation on an independent dataset. A group of models was identified that is sufficiently robust to be used for prediction purpose. The group of models allows to include local information and it reflects reliably enough the observed variability in the data so that probabilistic model predictions can be performed and used to quantify risk under different scenarios or derive optimal sampling schemes.     

Production decision support system for computerized manufacturing systems

The introduction of Computerized Manufacturing Systems (CMS) into the mid-volume manufacturing industry has been an important new step in the development of automated manufacturing. CMS's are computer-integrated systems which incorporate Direct Numerical Control (DNC) capabilities with automatic material handling to manufacture parts. Due to its complex nature, the task of production control in an CMS cannot rely on human effort alone. It is essential to develop a software package in the form of a Production Decision Support System (PDSS) to assist the production decision maker in operating this complex manufacturing facility.     

A decision support system for usability evaluation of web-based information systems

In this study, a decision support system (DSS) for usability assessment and design of web-based information systems (WIS) is proposed. It employs three machine learning methods (support vector machines, neural networks, and decision trees) and a statistical technique (multiple linear regression) to reveal the underlying relationships between the overall WIS usability and its determinative factors. A sensitivity analysis on the predictive models is performed and a new metric, criticality index, is devised to identify the importance ranking of the determinative factors. Checklist items with the highest and the lowest contribution to the usability performance of the WIS are specified by means of the criticality index. The most important usability problems for the WIS are determined with the help of a pseudo-Pareto analysis. A case study through a student information system at Fatih University is carried out to validate the proposed DSS. The proposed DSS can be used to decide which usability problems to focus on so as to improve the usability and quality of WIS.     

A decision support system for the diagnosis of melanoma: A comparative approach

Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The extirpation in early phases implies a high degree of survival so it is fundamental to diagnose it as soon as possible. In this paper we present a clinical decision support system for melanoma diagnosis using as input an image set of the skin lesion to be diagnosed. The system analyses the image sequence to extract the affected area, determinates the characteristics which indicate the degree of damage and, according to them, it makes a decision. Several methods of classification are proposed: a multilayered perceptron, a Bayesian classifier and the algorithm of the K nearest neighbours. These methods work independently and also in combination making a collaborative decision support system. The classification rates obtained are around 87%.     

Adaptive decision support systems

The effectiveness of decision support systems (DSS) is enhanced through dynamic adaptation of support to the needs of the decision maker, to the problem, and to the decision context. We define this enhanced DSS as adaptive decision support systems (ADSS) and propose its architecture. In an ADSS, the decision maker controls the decision process. However, the system monitors the process to match support to the needs. The proposed architecture evolves from the traditional DSS models and includes an additional intelligent‘Adaptation’ component. The ‘Adaptation’ component workd with the data, model, and interface components to provide adaptive support. The architecture also integrates enhancements proposed in the past research. In this paper, we have illustrated the proposed architecture with two examples, a prototype system, and results from a preliminary empirical investigations     

A framework for systems analysis for decision support systems

Comprehensive and elaborate systems analysis techniques have been developed in the past of routine and operational information systems. Developing support systems for organizational decision-making requires new tools and methodologies. We present a new framework for data collection and decision analysis which is useful for developing decision support systems. This task analysis methodology encompasses (1) event analysis, (2) participant analysis, and (3) decision content analysis. With a proper coding manual, it provides a framework for collecting relevant and detailed information required for decision support design and implementation. Further research is suggested for application and evaluation of the methodology in real-life DSS environments.     

A framework for decision support systems evaluation

In this paper, we present a framework for the Decision Support Systems evaluation problem. Using the Gorry-Scott Morton's framework for information systems, we develop several evaluation methods that structure the evaluation process. The framework determines the best methods of evaluation that are suitable to the characteristics of the Decision Support System concerned. Finally, we use the framework to evaluate two widely used Decision Support Systems.     

基于RCM的雷达装备维修决策支持系统研究

针对传统RCM(reliability centered maintenance)分析存在的信息利用不充分、缺乏模型支持及实施过程不够完整等不足,提出了雷达装备RCM分析的信息化改进思路。在分析了改进的RCM过程模型基础上,设计出雷达装备维修决策支持系统。以数据的充分利用和模型的合理支持为核心,描述了系统的逻辑全貌。基于分布式网络技术和面向服务软件技术构建了开放式、智能化的系统应用体系构架。原型系统开发结果表明,该方案能充分利用各类有用信息,在相关模型支持下,实现更规范、更快捷、更准确的装备维修分析与决策。     

A structured modeling based methodology to design decision support systems

Many Decision Support Systems (DSS) support the decision making process through the use of mathematical models and data. DSS design involves modeling data as well as mathematical relationships in a domain. The process of model formulation and subsequent integration of model with data in a DSS is a complex and ill-structured process. This paper proposes a methodology based on Structured Modeling (SM), originally introduced by Geoffrion together with the modeling language SML, to model and design the DSS. The methodology includes rigorous and step by step procedures to design and integrate data and modelbases. The main contribution of our approach lies in the integration of research in database design, and mathematical model formulation within the structured modeling framework. The resultant procedures can be easily automated and taught to students in DSS courses. The motivation for our research stemmed from our constant frustrations in teaching DSS courses over the last five years. In the last two years, when we used our methodology, the performance of the students improved significantly. The average score in the DSS project went up to 85 from 60. Our positive experience in using our methodology in classes over the past two years suggests that the methodology imposes structure into the analysis of decision problems, and as a result students produce better DSS designs for classroom cases.     

Planned approach to systems support

System support is an essential task and whether it is done inhouse or by a third party, best results will be obtained with a planned approach to quality, cost control and staffing. The article describes the basic steps in a system support process: system audit, testing modifications, error correction, controlling costs, and motivating staff.     

A decision support approach to automatic timetabling in higher education institutions

At a time when the need to reduce costs has become part of the day-to-day reality of all educational institutions, it is unthinkable to continue to manually perform those tasks (i.e., the creation of timetables) that can be automated and optimized. The automatic creation of timetables for educational institutions is one of the most studied problems by the scientific community. However, almost all studies have been based on very simplified models of reality that have no practical application. A realistic model of the problem, robust algorithms that are able to find valid solutions in highly restricted environments, and optimization methods that are able to quickly provide quality results are key factors to consider when attempting to solve this (real) problem faced by educational institutions. This paper presents a summary of the work performed by Bullet Solutions over the last few years, from the first stage of understanding and modelling the problem to the final analysis of the results obtained using the developed software under real conditions.     

A transaction cost view of decision support systems

Abstract

Research and practice in decision support systems have often been said to focus too much on individual decision-making, when decisions actually are made by groups. Another shortfall of current research is the absence of any established theory or framework on which to base it. A third shortfall is the lack of connections between theory and actual implementation in terms of information technology. The first two problems in particular are addressed in this study. Decision-making is considered to be a group activity— rather than an individual activity—in which as a matter of fact a contract between the decision-makers is established. The contracts incur transaction costs, which may or may not be covered by the extra value gained by the contract. Transaction costs in the contract formulation phase should be eliminated, and information technology in its various forms is a principal means by which to achieve this end. Different kinds of technologies support different kinds of contracts. This is why decision-makers should understand the nature of their decision-making situation and select the information technology tools most suitable for the situation. The different factors causing transaction costs in decision-making— contracting—are identified, and the means to eliminate them by information technology are presented. This study is based on a transaction cost perspective of organizations. Information technology is seen as a primary means to lower transaction costs. Thus, the necessary theoretical framework so often missing in information technology research is provided. The results of the study stem from empirical research, the aim of which was to investigate and to understand information technology from the viewpoint of transaction costs.