Web-based decision support systems, using intelligent agents in electronic commerce Management Science, MIS Quarterly, Decision Support Systems, and. Decision Support Systems and Intelligent Systems 7th Edition Free eBook Download - Free download as PDF File .pdf), Text File .txt) or read online for free. INTERNATIONAL EDITION. Decision. Support Systems and. Intelligent Systems. Seventh Edition. Efraim Turban Jay E. Aronson Ting-Peng Liang.
|Language:||English, Spanish, Japanese|
|Genre:||Fiction & Literature|
|Distribution:||Free* [*Register to download]|
Decision Support and Business Intelligence Systems 9th Edition by Efraim Turban, Ramesh Sharda & Dursen medical-site.info Decision Support Systems and. Intelligent Systems. 6th edition. Prentice Hall, Upper Saddle River, NJ, 2. CHAPTER 1. Management Support Systems. 3. PDF | Decision making is a fundamental human activity at the center of our interaction with the world. This chapter reviews research in decision making and the.
So, a man ager should be well. To be succe ssful in. Lack of information the ma nager. Therefore, it is clear that only managerial skills do. Again think that a manager has accurate, timely an d pl enty of informa tion, but. Though having all the resources information and skills , the. T herefore, ha ving informa tion. Therefore, infor mation should be gathere d in structured forms or systems so that. Here, the role of information. Information systems are those systems that deal w ith i nformation.
Information systems can be defined as interrelated components working together. Information systems con tain infor mation about significant p eople,. An i deal infor mation system u sually collect an d input of data resources,. All these activities helps. These systems are often termed as management information sys tems or MIS. Through an informa tion system, s tructured information are collected , proc essed.
Thus, the managers are updated with. Such system just plays a. It state s the current situatio n and updates an d. Managers are responsible to use them properly with their skills and.
So, such i nformation system or MIS, whatever is called, is a too l to decision. I t does not ensure the proper decision if t he manager s fail to use th eir.
For example, a production ma nager can easily know the. Though the organization is providing sufficient,. It is v ery usual that though managers are. But what will happen, if. It is prove n that machines ca n calculate, estimate. Just think. It does not mean. But once human sets some logic and algorithms, machines work almo st w ithout.
So, if i nformation system can p rovide decisions with the help of ar tificial. So , some computer. T hus the thin king about decision support system introduced.
Decision support system or DSS is such an informa tion or computer system that. This system jus t use the rea soning capabilities of human, in. No doubt that DSS is a totally computerized sys tem, especially software, opera ted. Decision support system ca n be defined a s information system at the management. Decision supp ort systems couple the intellectu al resources of individuals with the.
It is a computer-. The DSS is under user control from early inception to final implementation and. DSS are linked closely to exi sting corporate i nformation flows.
Of ten,. In simplest terms, DSS is such a mechanism that integrate s information and. Question is how it works? How does a calculator work? One i nputs digits and gives algorithmic direc tions,. V ery simple to say, but what occurs at the. That mac hine is well pre-pro grammed with logics and algorithms a long.
W hen a person just puts a ccurate data a nd.
Ju st in that way, DSS wo rks. Here, obvio usly som e ar tificial intelligence analyzing. DSS assist managers of different levels and functional areas in such decision. They a ddress problems w here the procedu re to get the solution may not. It is very clear that DSS hav e much more analytical capabili ties than any other.
They are built explicitly with a variety of models to analyze. Decision support systems can be classified into two c ategories; model-driven DS S. Mode l driven DSS are primari ly stand-alone systems tha t use. Information of va rious categories; e. Though they have all necessary. Da ta-driven DSS is s uch a syste m that enables de cision ma kers to.
It may be an indexi ng system or search en gine that. Such DSS only help i n finding t he. But the story of model-. Through the model-driven DSS, the de cision makers are allowed to use different. Users arrange the nece ssary. Thus, the model-. American airline s use such model-driven DSS to set price and. They have the informa tion about the pressure of.
T hey use the information in DSS wi th relativ e mode ls, and get the most. Researchers remind us that a comprehensive understanding of decision making is needed. Adam AI attempts to mimic human decision making in some capacity, and adv ances. This chapter will revie w research in. An excellent summary of research on human decision making is provided by Pomerol and.
They posit that reasoning and recognition are key poles in decision making that. Many types of reasoning can be represented by analytical techniques and, as such, can be. Not all decisions are analytical, of course.
At the other pole, recognition. However , some progress has been made in understanding responses or. Interesting research on. In such cases, decision support, if it is used, should supply relevant. Physiologically, the capacity to mak e decisions is known to reside in the prefrontal lobe of.
Damage to this area results in irrational decisions and. Decision making is also. Recent research in IDSS has demonstrated the ability to model affective characteristics such.
Pomerol and Adam also. Models of human decision making underpin systems that have been proposed for DSS and. An early model of decision making was offered by Savage and is sometimes.
Model or In essence,. Intelligent Decision Support Systems 3. Rationality in which decision makers are limited by the information they possess,. During the Intelligence phase the decision maker develops an understanding of the problem,.
The Design phase is characterized by identifying variables important to the decision problem,. During the Choice phase the decision maker evaluates alternati ves and selects a decision. Review is the phase in which the decision maker considers the consequences of the decision,.
The phases. A model similar to that of Simon often referenced by defense researchers in decision. During the Observe phase the pilot could see their adversary earlier. As decision makers, US pilots were able to. Decision making, then, in volves possible contradictory criteria and. Research has sho wn that humans will use strategies such as. Such sub-optimal strategies can lead to cognitive bias, with sev eral well-known errors. Anchoring is disproportionate weight.
Status quo is an effort to maintain the current state. Figure 1. The framing phenomenon is a selection of an alternative depending on the way. Intelligent Decision Support Systems 5. Estimating and forecasting occurs when decision makers overestimate their. Finally ,. Intelligent decision support systems help overcome human cognitive limitations and biases. Systems DSS refer to a broad range of interactive computer systems that.
The decision maker is part. DSS can also be designed for one or multiple decision makers, and can. V arious. Output Choice. Group or Collaborative DSS are in the early dev elopment stage since. Similarly , DSS. A schematic of the basic structure of a DSS is shown in Figure 1. Input includes a database, knowledge base and model. The database contains data relevant to the decision problem while the kno wledge base. The model base holds formal. Processing in volves using. Feedback from processing can provide additional inputs that may be updated in.
Output may generate forecasts and explanations to. Results are provided to the decision maker who. More recently, the term decision support has been broadened to include other decision. AI features are often used.
They offer powerful ne w tools to solve highly complex problems. Problem knowledge. Output Feedback. AI tools such as Fuzzy Logic,. Intelligent Decision Support Systems 7. T able 1. Lam et al. Warehouse cross-border deliv ery activities, such as. Lao et al. Quality control of food inventories in the warehouse. Kung et al. Saed et al.
Lei and Ghorbani Neural networks Detection of fraud and network intrusion. Santos et al. Neural network Rapid and successful detection of a face in an image. Tradeoff between fuel cost economic and emission. Kamami et al. One way of looking at intelligence is that it is primarily concerned with rational action,. IDSS are emerging as useful for practical and important applications as seen in T able. Applications range from healthcare support to.
W e will discuss. NN were inspired by the way that the brain processes information and are. The advantage of NN is their. The basic unit of a NN is the neuron or node. Each neuron receives an input x i as a. W eights may be positive or negati ve, i. The neuron computes the weighted sum of all inputs to the neuron, i.
Information can. The weights w i are critical to learning in the NN since. T ypically the NN is exposed iteratively. T wo generic topologies of NN are feedforward and recurrent, or feedbackward, networks.
For example, Figure 1. Feedforward NN ha ve. Intelligent Decision Support Systems 9. Feedbackward NN can have signals. Their fundamental advantage is that they can. NN offer decision. On the other hand, NN are not suitable. Unsupervised learning. The goal is to. In supervised learning, the NN is given inputs. Howev er, in many practical situations, detailed input-output n -tuples.
Reinforcement learning is used to deal with this situation and provide some. When training a. Since the computation is distributed over sev eral. Decision makers often. For example, the weather may. By comparison, Boolean logic is a system. Fuzzy logic enables a representation. There is no inherent structure in fuzzy logic,.
As new. Fuzzy logic provides a way to represent rule-. Fuzzy logic can. For example, input variables might be described with three values such as a maximum,.
These are natural language descriptions that enhance the. Fuzzy logic neural networks are a category of decision models that can provide.
Aggregative neurons accomplish AN-OR logic while referential neurons support predicate-. Fuzzy logic NN help address some of the shortcomings of NN regarding transparency. System ES is a computer system that attempts to solve problems that would. Often the term ES is used to describe.
The system. Components of an ES are shown in Figure 1. It shows a domain expert who pro vides. That kno wledge is encoded in the. Knowledge Base, usually as part of the development process. The user or decision maker.
The user may then directly access the Knowledge. Base for past cases, or the Inference Engine to infer from past cases to a new case.
ES thus serves to capture, collect and infer knowledge from a domain expert and pass that. AI techniques attempt to mimic these qualities of adapting. Algorithms GA are among the most utilized for decision problems. After the population is initialized, succeeding generations interact, communicate, and. Each individual is evaluated with respect to the.
Intelligent Decision Support Systems W eak individuals may also become parents. T wo techniques are. Crossover requires selected indi viduals. Mutation causes small alternations in some. Of the various AI techniques, Agents IA, a class that includes agents have had.
This intrinsic capability of autonomous action is the human-like characteristic. The literature makes a distinction between an agent and an intelligent agent with the. Weak agenc y. Strong agenc y adds to these abilities more advanced characteristics such as.
Autonomy is the ability. Agents that display reactivity and adaptiveness. Decision Sciences, , doi In fact, Yager uses the linguistic symbolic model based on ordinal scales and max-min operators presented in the previous section to solve multiobjective decision problems where not only the information about each alternative is given using linguistic terms but also where the importance of each objective is evaluated linguistically.
It was later revisited and extended in R. Group Decision and Negotiation, 2 1 —93, doi Buckey also studied decision making problems in a linguistic context in which the best alternative from a feasible set has to be selected by an analyst according the the opinions of several judges which supply information about the alternatives for a set of different criteria: J. Buckley states several reasons for using the ordinal scale instead of other exact, ratio or interval scales, e.
To resolve these problems the author discusses the three main issues that have to be faced to obtain the final ranking of the alternatives: when to pool, or average, the judges; how to pool, or average, the judges; and how to compute the final weight for each alternative. In this work the linguistic symbolic computational model based on ordinal scales and max-min operators presented in the previous section is used with some variations of the median, max and min operators to aggregate the linguistic information.
Finally, two short contributions published in dealt with multicriteria optimization problems and selection of models. Shendrik and B. Automatic Control and Computer Sciences, 19 6 , The authors extend a multicriteria optimization algorithm to accept fuzzy linguistic variables and thus, they convert it into a fuzzy linguistic algorithm. In particular they use different linguistic term sets to evaluate the degree to which a decision maker is satisfied with a particular solution and to control the rate of change between different criteria.
Silov and D. Soviet Journal of Automation and Information Sciences English translation of Avtomatyka , 18 4 , The authors make use of a linguistic model to characterize the preferences of the decision maker in form of rules that take linguistic variables as parameters.
Both works use a linguistic computational model based on membership functions. Recent Applications of CW in Decision Making In this section we present some of the recent applications published in the specialized literature in and based on a CW approach: Resource management and transfer Papers Sustainable energy management H. Doukas, B. Andreas, J. Multi-criteria decision aid for the formulation of sustainable technological energy priorities using linguistic variables.
European Journal of Operational Research 2 doi Expert Systems with Applications 34 1 doi Yang, M. Chen, C. Multiple attribute decision-making methods for the dynamic operator allocation problem.
Mathematics and Computers in Simulation 73 5 doi Sun, J. Ma, Z. Fan, J. Tai, C. A new evaluation model for intellectual capital based on computing with linguistic variable. Expert Systems With Applications 36 2 doi Wang, J. Fuzzy linguistic PERT. Lu, G.
Zhang, D. Intelligent multi-criteria fuzzy group decision-making for situation assessments. Soft Computing 12 3 doi Chang, R. Wang, S. Applying a direct multi-granularity linguistic and strategy-oriented aggregation approach on the assessment of supply performance. Yamaguchi, M. A grey-based decision-making approach to the supplier selection problem.
Mathematical and Computer Modelling 46 doi Chou, C. Hsu, M. A fuzzy multi-criteria decision model for international tourist hotels location selection. International Journal of Hospitality Management 27 2 doi Onut, S.
Waste Management 28 9 doi Doukas, J. Expert Systems with Applications 35 4 doi Lin, P. Hsu, G. A fuzzy-based decision-making procedure for data warehouse system selection. Expert Systems with Applications 32 3 doi Evaluating the flexibility in a manufacturing system using fuzzy multi-attribute group decision-making with multi-granularity linguistic information.
International Journal of Advanced Manufacturing Technology 32 doi downloadukozkan, D. Evaluation of software development projects using a fuzzy multi-criteria decision approach. Mathematics and Computers in Simulation 77 doi Martinez, J. Liu, D. Dealing with heterogeneous information in engineering evaluation processes. Information Sciences 7 doi Zou, X.