Which component of a decision support system enables the DSS to perform analysis?

III.A. DSS Forerunners

One way to appreciate the characteristics of a DSS is to compare and contrast them with traits of two other major types of business computing systems: data processing systems and management information systems [MIS]. Both predate the advent of computer-based decision support systems. All three share the trait of being concerned with record keeping. On the other hand, the three kinds of business computing systems differ in various ways, because each serves a different purpose in the management of an organization's knowledge resources

In the 1950s and 1960s, data processing [DP] systems dominated the field of business computing. Their main purpose was and is to automate the handling of large numbers of transactions. At the heart of a DP system lies a body of descriptive knowledge [i.e., data], which is a computerized record of what is known as a result of various transactions having happened. In addition, a DP system endows the computer with two major abilities related to this stored data: record keeping and transaction generation. The first enables the computer to keep the records up to date in light of incoming transactions. The second ability is concerned with the computerized production of outgoing transactions based on the stored descriptive knowledge, transmitted to such targets as customers, suppliers, employees, or governmental regulators. Administrators of a DP system are responsible for seeing that record keeping and transaction generation abilities are activated at proper times.

Unlike a DP system, the central purpose of MIS was and is to provide managers with periodic reports that recap certain predetermined aspects of an organization's past operations. Giving managers regular snapshots of what has been happening in the organization helps them in controlling their operations. Whereas DP is concerned with transforming transactions into records and generating transactions from records, the MIS concern with record keeping focuses on using this stored descriptive knowledge as a base for generating recurring standard reports. An MIS department typically is responsible for development, operation, and administration of DP systems and the MIS.

Information contained in standard reports from an MIS certainly can be factored into decision-making activities. When this is the case, an MIS could be fairly regarded as a kind of DSS. However, the nature of support it provides is very limited due to several factors: its reports are predefined, they tend to be issued periodically, and they are based only on descriptive knowledge. The situation surrounding a decision maker can be very dynamic. Except for the most structured kinds of decisions, information needs can arise unexpectedly and change more rapidly than an MIS can be built or revised by the MIS department.

Even when some needed information exists in a stack of reports accumulated from an MIS, it may be buried within other information held by a report, scattered across several reports, not presented in a fashion that is most helpful to the decision maker, or in need of further processing. Report generation by an MIS typically follows a set schedule. However, decisions that are not fully structured tend to be required at irregular intervals or unanticipated times. Knowledge needed for these decisions should be available on an ad hoc, spur-of-the-moment, basis. Another limit on an MIS's ability to support decisions stems from its exclusive focus on managing descriptive knowledge. Decision makers frequently need to manage procedural and/or reasoning knowledge as well. They need to integrate the use of these kinds of knowledge with ordinary descriptive knowledge.

2 Mathematical Methods and Decision Support Systems

If people demonstrate imperfect reasoning or decision making then it would presumably be desirable to support them with techniques that avoid errors and comply with rational rules. There is a vast amount of research on decision support systems that are designed to help people overcome their biases and limitations, and make decisions more knowledgeably and effectively. If we are to engineer computer systems to take decisions, it would seem clear that we should build those systems around theories that give us some appropriate guarantees of rationality. In a standard text on rational decision making, Lindley summarizes the ‘correct’ way to take decisions as follows:

… there is essentially only one way to reach a decision sensibly. First, the uncertainties present in the situation must be quantified in terms of values called probabilities. Second, the consequences of the courses of actions must be similarly described in terms of utilities. Third, that decision must be taken which is expected on the basis of the calculated probabilities to give the greatest utility. The force of ‘must’ used in three places is simply that any deviation from the precepts is liable to lead the decision maker to procedures which are demonstrably absurd. [Lindley 1985, p. vii]

The above viewpoint leads naturally to Expected Utility Theory [EUT] which is well established and very well understood mathematically. If its assumptions are satisfied and the expected utilities of alternative options are properly calculated, it can be argued that the procedure will reliably select the best decision. If people made more use of EUT in their work, it is said, this would result in more effective decision making. Doctors, for example, would make more accurate diagnoses, choose better treatments, and make better use of resources. Similar claims are made about the decision making of managers, politicians, and even juries in courts of law.

Abstract

Decision Support Systems [DSS] play a significant role in several fields that assist professionals in their decision-making process, either in short-term or mid/long term. The advent of Big Data, Big Data Streams, and Cloud computing ecosystems enables new, faster, and more effective forms of decision-making, therefore laying the basis for a new generation of DSS. Knowledge base and Rule base systems play an important role in the development of DSS. This chapter illustrates different types of Decision Support Systems and their application in healthcare, the barriers they encounter, implementation strategies, challenges, and outlook for the future vision of DSS.

Spatial decision support systems [SDSS] are computer-based systems that combine the geographic storage, search, and retrieval capabilities of geographic information systems with the decision models and optimizing algorithms used to support decision-making about spatial problems. Examples are political redistricting, selection of routes, facility location, and planning land uses. SDSS are used increasingly in both business and public sectors today. These systems allow decision makers to use ‘multiple spatial criteria’ in making locational choices by exploring alternatives in the spatial and the attribute solution space. In some SDSS, the user generates these spaces interactively. The capabilities of the SDSS then consist of the tools for manipulating the geographic information, and reporting the characteristic attributes of the outcomes. In other cases, instead of modeling the choices of individuals, the user of the SDSS directly participates in the choice evaluation process. Some SDSS incorporate methods for reconciling different views. In many situations, the assistance required by users of an SDSS lies in the knowledge of experts who are not available in person. Much of current research in SDSS entails capturing the knowledge of experts and incorporating it in the SDSS. The typical characteristics and functionalities of SDSS are becoming incorporated in social science theories and models that explain spatial decisions.

Decision support systems [DSS]

Decision support systems are sometimes confused with management information systems, but they are quite distinct. Whereas the latter provide predefined information to the manager, decision support systems [DSS] are used by the manager to predict actions based on a formal model of the organisation. There are various definitions in the literature. Indeed, the literature of the mid-1980s tended to use the terms ‘management information system’ and ‘decision support system’ interchangeably. Here the distinction between the terms is taken to be that whereas management information systems provide information, the manager uses a decision support system to manipulate information. Spreadsheet packages are typical decision support tools in a library environment, used to explore ‘what if scenarios, for example, ‘If the library cuts its printed serials budget by 10% over the next year, what would be the likely effect on document delivery services?’

Decision support systems are less structured than management information systems, and are based on a more or less formal model of the organisation and its relationship with its environment. The model may be a simple ‘what if spreadsheet analysis of a budget or a more sophisticated model such as resource scheduling. Whereas data for a management information system are drawn mainly from internal sources [typically a data processing or ‘transaction-oriented’ system], a decision support system will draw its data from internal sources, such as data processing systems or management information systems, but also from external sources, such as user surveys.

2.20.3 Decision Support System [DSS] for Land Use and Planning

A decision support system is a computer-based information system that supports government, business or organizational decision-making activities, typically resulting in ranking, sorting, or choosing from among alternatives. DSSs serve the management, operations, and planning levels of an organization [usually mid and higher management] and help people make decisions about problems that may be rapidly changing and not easily specified in advance—i.e., unstructured and semistructured decision problems [Cabrerizo et al., 2015]. Decision support systems can be fully computerized, human-powered, or a combination of both computerized and human-powered. As a tool that is intended to support the analysis involved in decision-making processes, i.e., DSS, not to replace the human involvement, is used to support the process from technical implementation details, allowing the users to focus on the fundamental value judgments [Ferrández et al., 2015].

II.C. Decision Support Systems for Prescriptive Knowledge Management

Decision support systems [DSS] help managers make decisions in situations where human judgment is an important contributor to the problem-solving process, but where limitations in human information processing impede decision making. The goal of a DSS is to amplify the power of the decision makers without usurping their right to use human judgment and make choices. They attempt to bring together the intellectual flexibility and imagination of humans with the speed, accuracy, and tirelessness of the computer.

Decision support systems may contain a number of subsystems, each with a specific task [Fig. 3]. The first, and most important, is the subsystem composed of the decision maker[s]. Decision makers are consciously diagrammed as part of the DSS because without their guidance, there is no DSS. The group negotiation management subsystem helps decision makers organize their ideas, formulate relationships surrounding issues and arguments, and refine their understanding of the problem and their own value systems. Examples of group negotiation tools include: the active response Geographic Information System [AR/GIS] and the issue-based information system [IBIS]. Group negotiation tools are used to construct issue-based argument structures to clarify the values and preferences of group members in the attempt to reach group consensus. For example, IBIS uses formal argument logic [the logic of questions and answers] as a way to diagram and elucidate argumentative thinking. By asking and answering crucial questions, you can begin to better understand the problem and its solution set. Decision support systems should specifically employ mechanisms by which the biological realities guide and, if appropriate, constrain the desires of the stakeholders. For example, compromise is not acceptable for some issues. If the productive capacity of an ecosystem is fixed yet key stakeholders all want to extract a product from that ecosystem at a higher level, a compromise midway between the levels will be unsustainable.

The next major subsystem, spatial and non-spatial data management, organizes the available descriptions of the ecological and management components of natural resource management. Data must be available to support choices among alternative management scenarios and to forecast consequences of management activities on the landscape. There is a trade-off between the increasing number of goals that decision makers and stakeholders value and the high cost of obtaining data and understanding relationships that support these choices. Monitoring both natural and anthropogenic disturbance activities and disturbance-free dynamics of managed forest ecosystems are also extremely important if a DSS is to accurately portray the decision choices and their consequences. Barring blind luck, the quality of the decision cannot be better than the quality of the knowledge behind it. Poor data can lead to poor decisions. It is difficult to conceive of prudent natural resource management without an adequate biophysical description of the land base in question.

The next three subsystems—hypertext, knowledge-base, and simulation model management—deal with effectively managing knowledge in the many diverse forms in which it is stored, represented, or coded. These systems have been covered in more detail in the preceding sections. The simulation model management subsystem of the DSS is designed to provide a consistent framework into which models of many different origins and styles can be placed so the decision makers can use them to analyze, forecast, and understand elements of the decision process. The knowledge management subsystem of the DSS is designed to organize all available knowledge-based models in a uniform framework to support the decision-making process. The software subsystems of a DSS described so far help decision makers organize the decision problem, formulate alternatives, and analyze their future consequences. The decision methods management subsystem [Fig. 3] provides tools and guidance for choosing among the alternatives, for performing sensitivity analysis to identify the power of specific variables to change the ranking of alternatives, and for recording the decisions made and their rationale.

There are many facets or dimensions that influence the decision-making process. The rational/technical dimension, which concerns itself with the mathematical formulation of the methods of choice and their uses, is the one most often encountered in the decision science literature. But there are others including the political/power dimension and the value/ethical dimension.

Decision makers might find themselves at any point along the political/power dimension bounded by a dictatorship [one person decides] on the one extreme and by anarchy [no one can decide] on the other. Intermediate positions are democracy [majority decides], republicanism [selected representatives decide], and technocracy/aristocracy [experts or members of a ruling class decide]. Currently three approaches seem to be in use at multiple-societal temporal and spatial scales: management by experts [technocracy], management by legal prescription [republicanism], and management by collaboration [democracy]. No one approach predominates. In fact, the sharing of power between these three approaches creates tensions which help make natural resource management a very difficult problem. In the context of natural resource management, the value/ethical dimension might be defined on the one extreme by the preservationist ethic [reduce consumption and let nature take its course] and on the other by the exploitation ethic [maximum yield now and let future generations take care of themselves]. Various forms of the conservation ethic [use resources, but use them wisely] could be defined between these two extremes. The rational/technological dimension is defined by the normative/rational methods on the one hand and the expert/intuitive methods on the other. Numerous intermediate methods also have been described and used. The formal relationships between these dimensions affecting the decision process have not been worked out.

Informally, it is easy to observe decision-making situations where the political/power or value/ethical dimensions dominate the rational/technical dimension. Choosing an appropriate decision-making method is itself a formidable task that influences both the design of alternatives and the final choice. Many DSSs do not offer a decision methods subsystem due to the complexity and sensitivity of the subject matter. Unfortunately, providing no formal support in DSSs for choosing among alternatives simply places all the burden on the users and may make them more vulnerable to challenges of their process and choice mechanisms.

2.1.2 Machine learning algorithms for wheat yield prediction

Decision support system [DSS]: A DSS is a system that provides information and maintains the administrative activities of a business or organization. A DSS addresses organizational administration, operations, and development levels to help in making the decisions about quickly changing issues that may not be easily identified in advance. A DSS can be fully automatic, human-powered, or a combination of each. A DSS has inputs, such as factors, numbers, and characteristics for analyzing user information and proficiency. Users need to analyze the inputs and outputs manually. Transformed data produces a DSS “decision.” Outcomes produced by DSS are built on specific criteria. DSSs that bring out certain cognitive decision-making functions are assembled with artificial intelligence [AI] or intelligent agent technology and known as intelligent DSS. The DSS for harvesting high superiority wheat holds the idea of the united method in making multidisciplinary DSSs. This DSS is taken into account and provides selection provision for all key elements of the production chain, from strategic selection to tactical operations [Rossi et al., 2010].

Regression method: Regression evaluation is a hard and fast statistical technique for estimating the relationships among a based variable and one or more independent variables. If there is no reasonable dependency among variables, one can attempt mathematical equations in order to find a link between them [Niedbała, 2018]. The maximum common regression evaluation is linear regression in which a researcher reveals the line that most intently fits the statistics in step with a precise mathematical criterion. Regression evaluation is normally used for two conceptual functions. Initially, regression evaluation is broadly used for predicting and forecasting, where its use has considerable overlap with the field of ML. Then, in some conditions, regression analysis can be used to conclude a fundamental relationship between the independent and dependent variables.

Random forest [RF]: Random decision forest is a collaborative learning method that works by constructing a huge number of decision trees during training and outputting classes that are the modes of sorting and grouping or mean prediction [regression], for classification, regression, and other tasks. RF corrects the tendency of overfitting a training set of decision trees. The RF classifier is a collective method that trains numerous decision trees similar with bootstrap, which is collectively called bagging, and subsequent aggregation. RF is an effective and flexible ML technique for crop yield predictions on both a regional and a global scale for its excessive accuracy and exactness, accessibility, and effectiveness in facts analysis. For classification and regression purpose, RF can be used, and when needed, it can be used as regression model also [Jeong et al., 2016].

Support vector machine [SVM]: SVM is a set of ML rules developed by way of Vapnik and is primarily based at the principles of statistical learning theory. SVM uses an introduced feature of structural and experimental threat reduction. It has the capability to do the mapping of the functions in high dimensional space though translating the difficult problems to a linearly separable event [Kumar et al., 2019]. The determination of the SVM algorithm is to find that the RF classifier [i.e., ensemble method] that trains numerous decision trees in parallel with bootstrap. If you have a set of training samples, each one is marked as association to one of two groupings and the SVM algorithm generates a model that allocates the new example to one of the groups and a nonstochastic binary linear classification. The SVM model represents the examples as points in space, that is, it maps the individual categories into the widest possible gaps. The new examples are then mapped to that identical area and expected to fit to a group primarily built on the aspect of the distance on which they fall.

Neural network: A neural network includes neurons, organized in layers, which translate an input vector into an output vector. Input is taken at each unit after applying numerous features on it, and at that moment passes output to the next layer. Artificial neural networks [ANNs] are extraordinarily crude electronic networks of neurons created on the basis of neural structure of the brain. They learn by analyzing the records one by one and comparing the record’s classification with the identified actual classification of the document. The faults from the preliminary class of the first record is fed lower back into the network and conditioned to adjust to the network’s set of rules. A group of input values [xi] and related weights [wi] and a characteristic function [g] does the summation of weights and draws the result to the output [y]. A neural community includes neurons organized in layers and transforms an enter vector into several outputs. Every unit proceeds with an input, puts a function to it, and passes its output to the succeeding layer [Training an Artificial Neural Network, 2020].

Multilayer perceptron neural network [MLP]: MLP is a category of feed-forward ANN, or networks consist of several layers of perceptron. MLP are as often colloquially known as “vanilla” neural networks, specifically when they are having a hidden layer. An MLP contains an input layer, a hidden layer, and an output layer. Through the exclusion of input nodes, every node is a neuron that uses a nonlinear activation function. The input layer gets the parameters to control the neurons of the hidden layer[s] and the output layer method and the weighted indicators from the neurons of its preceding layer and calculate an output cost, making use of an activation feature [Kross et al., 2018]. MLP makes use of a supervised learning method referred to as backpropagation [BP] for training. It is a combination of layers and nonlinear activation that differentiate MLP from a linear perceptron and can make a distinction of data that is not linearly separable.

Adaptive network-based fuzzy inference system [ANFIS]: ANFIS refers to synthetic neural community based on the Takagi-Sugeno fuzzy inference device. By integrating neural networks in addition with fuzzy logic principles, it is possible to combine the advantages of both into a particular framework. The inference system supports a series of fuzzy IF-THEN rules with a learning function that approximates nonlinear functions. One can identify two parts of the network structure: the premise and consequence. In detail, the architecture consists of five layers. The first layer contains input fuzzy rules, the second layer contains input membership functions, the third layer contains fuzzy neurons, the fourth layer contains output membership functions, and the fifth layer contains a summation of all operations [Rusgiyono, 2019].

Self-organizing map [SOM]: A SOM is a form of ANN that uses unsupervised learning to provide a two-dimensional discretized view of the input space of a training sample called a map, and it is a way to reduce dimensions. Unlike other synthetic neural networks, SOMs follow competitive learning rather than error-correcting learning, so we have experience using neighborhood features to hold topological assets in the input space. It is common to think of this type of network structure associated to a feed-forward network in which the nodes are imagined as connected, but this kind of structure varies in arrangement and motivation. The SOM models involve input nodes demonstrating the principle features in wheat crop manufacturing, including biomass signs, organic carbon [OC], pH, Mg, Total N, Ca, cation exchange capacity, moisture content [MC], and the output weights characterized the class labels similar to the anticipated wheat yield [Pantazi et al., 2014].

Supervised Kohonen networks [SKNs]: SKN models are supervised neural networks, rising from SOMs used for sorting and grouping. In the case of SKNs, the SOM and output layers are amassed collectively to provide a joint layer trained in keeping within the regime of SOMs. In the SKN network, the input map Xmap and the output map Ymap are “combined” to form the joint input/output map [XYmap] as a result of the unsupervised Kohonen network training scheme. [Melssen et al., 2006] [Table 3].

Table 3. Wheat yield prediction summary by machine learning algorithms.

DSS

Regression method

RF

SVM

Neural network

MLP

Regression model

SVM

RF

Neural network

ANN

Multilayer perceptron

ANFIS

Used to simulate the hydration properties of wheat grain

Supervised SOM and crop sensors

Were used to predict soil properties for yield prediction

Abstract

Decision support systems must provide the tools for effective problem management thus improving the whole decision process, from problem conception to solution implementation. However, model creation heavily depends on the modeler’s expertise and the problem conception. This work focuses on automating the problem modeling and creating semantically enriched models. As a result, the modeler is supported in the modeling process. An automated modeling platform is developed, which encompasses mathematical models, their formal representation and the semantic model of the represented system. In addition, intelligent agents are designed in order to provide additional reasoning capabilities and create case rules for model creation, problem application storage and usage. A case study is performed using a scheduling modeling and solution example. Specifically, a systematic approach to scheduling model selection and solution implementation is achieved, thus enabling the bridge between theoretical developments and industrial practice.

1 Introduction

Decision Support Systems [DSS] are directly or indirectly related to manufacturing indicators, like economic efficiency, product quality, flexibility, reliability, etc. Global competition has made essential for the viability of the enterprise the use of such DSS, and the need for development of new tools to integrate the different time and scale levels involved have been highlighted. The first requirement to achieve such integration is to define standardized information structures and more sophisticated information tools to exploit them, in order to improve the availability and communication of data between different decision levels and also the models behind the corresponding decision support tools. In this framework, the role of infrastructures that continuously and coherently support fast and reliable decision-making activities related to the production process is now of paramount importance [Venkatasubramanian et al., 2006]. The use of an ontology is proposed, as a formal specification, that is a body of formally represented knowledge based on conceptualizations, which are abstract, simplified views of the physical or procedural elements. The ontology elements should be part of the model intended to represent a system for some purpose, managing the relationships that hold among the elements of the model, allowing this model to be usable [Gruber, 2008]. On the other hand, reusing ontologies is far from being an automated process. It requires not only consideration of the ontology, but also of the tasks for which it is intended. The key for the presented ontology reusability is that it lies on the basis of the standard ANSI/ISA 88 [International Society for Measurement and Control, 2001]. In general, this standard should facilitate building larger, better and cheaper systems. It should also lead to a greater dissemination of these systems.