Decision support systems

420 Pages·2010·21.429 MB·English

by  edited by Chiang S. Jao.

Decision Support Systems

Decision Support Systems

Edited by
Chiang S. Jao
Intech
IV

Published by Intech

Intech
Olajnica 19/2, 32000 Vukovar, Croatia

Abstracting and non-profit use of the material is permitted with credit to the source. Statements and
opinions expressed in the chapters are these of the individual contributors and not necessarily those of
the editors or publisher. No responsibility is accepted for the accuracy of information contained in the
published articles. Publisher assumes no responsibility liability for any damage or injury to persons or
property arising out of the use of any materials, instructions, methods or ideas contained inside. After
this work has been published by the Intech, authors have the right to republish it, in whole or part, in
any publication of which they are an author or editor, and the make other personal use of the work.

© 2010 Intech
Free online edition of this book you can find under www.sciyo.com
Additional copies can be obtained from:
[email protected]

First published January 2010
Printed in India

Technical Editor: Teodora Smiljanic
Cover designed by Dino Smrekar

Decision Support Systems, Edited by Chiang S. Jao
p. cm.
ISBN 978-953-7619-64-0
Preface

Decision support systems (DSS) have evolved over the past four decades from
theoretical concepts into real world computerized applications. DSS architecture contains
three key components: a knowledge base, a computerized model, and a user interface. DSS
simulate cognitive decision-making functions of humans based on artificial intelligence
methodologies (including expert systems, data mining, machine learning, connectionism,
logistical reasoning, etc.) in order to perform decision support functions. The applications of
DSS cover many domains, ranging from aviation monitoring, transportation safety, clinical
diagnosis, weather forecast, business management, to internet search strategy. By combining
knowledge bases with inference rules, DSS are able to provide suggestions to end users to
improve decisions and outcomes.
At the dawn of the 21st century, more sophisticated applications of computer-based
DSS have been evolved and they have been adopted in diverse areas to assist in decision
making and problem solving. Empirical evidence suggests that the adoption of DSS results
in positive behavioral changes, significant error reduction, and the saving of cost and time.
This book provides an updated view of the state-of-art computerized DSS applications. The
book seeks to identify solutions that address current issues, to explore how feasible
solutions can be obtained from DSS, and to consider the future challenges to adopting DSS.

Overview and Guide to Use This Book

This book is written as a textbook so that it can be used in formal courses examining
decision support systems. It may be used by both undergraduate and graduate students
from diverse computer-related fields. It will also be of value to established professionals as a
text for self-study or for reference. Our goals in writing this text were to introduce the basic
concepts of DSS and to illustrate their use in a variety of fields.
Chapter 1 first discusses the motivational framework that highlights the significance of
motivational factor, a psychological construct, in explaining and facilitating the
comprehension of DSS use and decision performance. The motivational framework
translates several user-related factors (task motivation, user perception of a DSS, motivation
to use DSS, DSS adoption, and decision performance) to the driving force in using DSS to
improve task processing effectively and efficiently. To understand thoroughly the
motivation framework will assist system designers and end users in reducing the barriers of
system design and adoption.
VI
Chapters 2 and 3 introduce complicated decision support processes. Chapter 2 explores
how to apply intelligent multi-agent paradigm architecture in DSS for the distributed
environment. Intelligent multi-agent technology is adopted to develop DSS in enhancing the
system operation in a dynamic environment and in supporting the adaptability of the
system under complicated system requirements. An intelligent agent is capable to adapt
DSS on the new situation through effective learning and reasoning. Employing multi-agents
will simplify the complex decision making process and expedite the operation more
efficiently.
Chapter 3 applies a hybrid decision model using generic algorithm and fuzzy logic
theory to provide decision makers the ability to formulate nearly optimal sets of knowledge
base and to improve the efficiency of warehouse management. This model incorporates
error measurement to reduce the complexity of process change during the development and
selection of the best warehouse design for a given application.
Chapter 4 reviews connectionist models of decision support in a clinical environment.
These models connect the implementation and the adoption of DSS to establish effective
medical management, maintenance and quality assurance and to predict potential clinical
errors. These models aim to provide clinicians effective drug prescribing actions and to
ensure prescription safety. The implementation of DSS accompanies the advantages of staff
education and training to promote user acceptance and system performance.
Chapter 5 integrates DSS with data mining (DM) methodology for customer
relationship management (CRM) and global system for mobile communication (GSM) for
the business service requirements. Data mining is appropriate for analyzing massive data to
uncover hypothetical patterns in the data. A data mining DSS (DMDSS) offers an easy-to-
use tool to enable business users to exploit data with fundamental knowledge, and assists
users in decision making and continual data analysis.
Chapter 6 highlights the importance of DSS evaluation using various testing methods.
Integrating several testing methods would help detect primary errors generally found in the
DSS adoption. A gold standard knowledge source is critical in choosing DSS testing
methods. Correct use of these testing methods can detect significant errors in DSS. At this
point, you are able to understand how to design and evaluate DSS for general purposes.
Chapter 7 adopts artificial neural network (ANN) model in developing DSS for
pharmaceutical formulation development. The use of ANNs provides the predictive “black-
box” model function that supports the decision difficult to explain and justify because
numerous system parameters are under consideration. Integrating DSS with ANNs applies
data mining methodology and fuzzy logic algorithm, mentioned in Chapter 3, for decision
making under multiple influential factors after performing statistical sensitivity analysis on
feasible decision making mechanisms. The ANN in DSS is especially useful in improving
drug substance original characteristics for optimized pharmaceutical formulation.
Chapters 8 and 9 introduce the application of DSS in the clinical domain. Chapter 8
investigates the characteristics of clinical DSS (CDSS) and illustrates the architecture of a
CDSS. An example of embedding CDSS implementation within computerized physician
order entry (CPOE) and electronic medical record (EMR) is demonstrated. A CDSS aims to
assist clinicians making clinical errors visible, augmenting medical error prevention and
promoting patient safety.
Chapter 9 introduces the importance of knowledge bases that provide useful contents
for clinical decision support in drug prescribing. Knowledge bases are critical for any DSS in
VII
providing the contents. Knowledge bases aim to fulfill and be tailored timely to meet
specific needs of end users. Standards are vital to communicate knowledge bases across
different DSS so that different EMRs can share and exchange patient data on different
clinical settings. Knowledge bases and CDSS have been proved to be helpful in daily
decision making process for clinicians when instituting and evaluating the drug therapy of a
patient.
Chapters 10 and 11 introduce the concepts of spatial DSS. Chapter 10 introduces the
framework of a web service-based spatial DSS (SDSS) that assists decision makers to
generate and evaluate alternative solutions to semi-structured spatial problems through
integrating analytical models, spatial data and geo-processing resources. This framework
aims to provide an environment of resource sharing and interoperability technically through
web services and standard interfaces so as to alleviate duplication problems remotely and to
reduce related costs.
Chapter 11 introduces another SDSS for banking industry by use of geographic
information systems (GIS) and expert systems (ES) to decide the best place for locating a
new commence unit in the banking industry. This SDSS aims to improve the decision
making process in solving issues of choosing a new commence location for the banking
industry, expanding possibilities through spatial analysis, and assisting domain experts in
managing subjective tasks.
Chapters 12 and 13 introduce DSS adoption in monitoring the environment. Chapter 12
introduces a web-based DSS for monitoring and reducing carbon dioxide (CO) emissions to
2
the environment using an intelligent data management and analysis model to incorporate
human expert heuristics and captured CO emission data. Using object-linking and
2
embedding (OLE) technology, this DSS aims to automatically filter and process massive raw
data in reducing significant operating time.
Chapter 13 illustrates case studies of Canadian environmental DSS (EDSS). The EDSS
makes informed resource management decisions available to users after integrating
scientific data, information, models and knowledge across multimedia, multiple-disciplines
and diverse landscapes. The EDSS is also using GIS mentioned in Chapter 11 to deal with
temporal and spatial consistency among different component models. The EDSS can solve
complex environmental issues by providing informed resource and perform data analysis
effectively. The schematic EDSS concepts of an EDSS can assist in developing a good EDSS
with required functions to achieve the goals of environmental monitoring.
Chapters 14 to 21 illustrate several examples of DSS adoption in diverse areas
(including business partnership, internet search, wine management, agribusiness, internet
data dependencies, customer order enquiry, construction industry, and disaster
management) to solve problems in the current world.
Chapter 14 presents a set of different DSS that extend the decision support process
outside a single company. An automatic speech synthesis interface is adopted in the web-
based DSS for the operational management of virtual organizations. Incorporating different
business partners can provide decision support in multiple useful scenarios and extend the
interoperability in a centralized cooperative and distributed environment. This trend is very
useful to meet decision support requirements for global business in the 21st century.
Chapter 15 introduces a DSS for analyzing prominent ranking auction markets for
internet search services. This strategy has been broadly adopted by the internet search
service provider like Google. This DSS aims to analyze ranking auction by the bidding
VIII
behavior of a set of business firms to display the searched information based on the ranking
by bids strategy. You will be able to understand how the searching information being
displayed on the internet by the searching engine, just like what you have seen by using
Google Search.
Chapter 16 introduces a DSS for evaluating and diagnosing unstructured wine
management in the wine industry. This DSS offers effective performance assessment of a
given winery and ranks the resource at the different levels of aggregation using statistical
data. It aims in improved resource utilization and significant operational cost and time
reduction. Fuzzy logic theory is adopted in the decision support process to compute a give
winery performance in term of several dependent factors.
Chapter 17 introduces a DSS adopted in agribusiness (hop industry) concerning issues
related to personnel safety, environmental protection and energy saving. This DSS aims to
monitor all functions of an agricultural process and to satisfy specific performance criteria
and restrictions. Automation Agents DSS (AADSS) is adopted to support decision making in
the range of the agribusiness operation, production, marketing and education. The AADSS
facilitates the support to farmers in e-commence activities and benefits effective labor and
time management, environmental protection, better exploitation of natural sources and
energy saving.
Chapter 18 introduces a framework for automating the building of diagnostic Bayesian
Network (BN) model from online data sources using numerical probabilities. An example of
a web-based online data analysis tool is demonstrated that allows users to analyze data
obtained from the World Wide Web (WWW) for multivariate probabilistic dependencies
and to infer certain type of causal dependencies from the data. You will be able to
understand the concept in designing the user interface of DSS.
Chapter 19 introduces a DSS based on knowledge management framework to process
customer order enquiry. This DSS is provided for enquiry management to minimize cost,
achieve quality assurance and enhance product development time to the market. Effective
and robust knowledge management is vital to support decision making at the customer
order enquiry stage during product development. This DSS highlights the influence of
negotiation on customer due dates in order to achieve forward or backward planning to
maximize the profit.
Chapter 20 introduces a web-based DSS for tendering processes in construction
industry. This DSS is used to benefit the security of tender documents and to reduce
administrative workload and paperwork so as to enhance productivity and efficiency in
daily responsibilities. This DSS is used in reducing the possibility of tender collusion.
Chapter 21 introduces the concept of DSS used in disaster management based on
principles derived from ecology, including preservation of ecological balance, biodiversity,
reduction of natural pollution in air, soil and water, and exploitation of natural resources.
This DSS provides complex environment management and public dissemination of
environment-related information.
The book concludes in Chapter 22 with the introduction of a theoretical DSS framework
to secure a computer system. This CDSS framework adopts an accurate game-theoretic
model to identify security primitives of a given network and assesses its security
enhancement. Through the set-up of a game matrix, the DSS provides the capability of
analysis, optimization and prediction of potential network vulnerability for security
assessment. Five examples are provided to assist you in comprehending the concept of how
to construct networks with optimal security settings for your computer system.
IX
It is exciting to work in the development of DSS that is increasingly maturing and
benefits our society to some degree. There is still ample opportunity remaining for
performance enhancement and user acceptance as new computer technologies evolve and
more modern problems in the current world are being faced. In light of the increasing
sophistication and specialization required in decision support, it is no doubt that the
development of practical DSS needs to integrate multi-disciplined knowledge and expertise
in diverse areas. This book is dedicated to providing useful DSS resources that produce
useful application tools in decision making, problem solving, outcome improvement, and
error reduction. The ultimate goals aim to promote the safety of beneficial subjects.

Editor
Chiang S. Jao
National Library of Medicine
United States