1
Decision Making Using Fuzzy Logic Using Multicriteria

Panem Charanarur1, Srinivasa Rao Gundu2* and J.Vijaylaxmi3

1Department of Cyber Security and Digital Forensics, National Forensic Sciences University, Tripura Campus, Tripura, India

2Department of Computer Science, Government Degree College-Sitaphalmandi, Hyderabad, Telangana, India

3PVKK Degree & PG College, Anantapur, Andhra Pradesh, India

Abstract

Fuzzy set theory and multicriteria decision making were initially introduced in the early 1970s. As a consequence, a wide variety of innovative solutions have been tried and confirmed through the use of fuzzy multicriteria decision making. The following section provides a quick overview of fuzzy multicriteria decision-making categories, as well as some of their earliest and most recent uses. Uncertainty and ambiguity are synonyms for the adjective "fuzzy." Since there are numerous instances in real life when we are not able to discern whether a given condition is true or untrue, the flexibility that fuzzy logic gives is quite helpful when making decisions. There will always be some degree of inaccuracy and unpredictability to every circumstance. The development of fuzzy set theory and the rise of decision making are closely linked. It was necessary to highlight the groundbreaking applications of fuzzy multicriteria decision making (MCDM) in order to encourage more research in this field. Many real-world Malaysian cases are used to demonstrate the broad range of applications that may be pulled from the various approaches described in this study. Some cutting-edge intelligent methods to MCDM are intended to help spread the news about fuzzy MCDM.

Keywords: Fuzzy, fuzzy set, multicriteria decision making (MCDM), decision theory, logical thinking

1.1 Introduction

Determining what to do is an NP-complete issue, and it has applications in a wide range of domains. There were a lot of researchers that looked into the subject in the mid-20th century. Through his work on the lens model, Brunswick pioneered the use of mathematical or statistical models to capture individual variances in decision-making procedures in 1947, paving the way for future research.

It is possible to analyze many different decision-making circumstances using policy capture, according to the researchers. Sequences of judgment stimuli that have been produced using controlled signals are shown to participants in order to capture and model the participants' subsequent judgments, according to this approach. Changing environmental signals in a systematic way addresses interactions with the environment, whereas the deployment of expert decision-making systems addresses interactions with extraneous validity. Brehmer and Brehmer followed up on their research into this method by conducting an analysis into the amount to which individuals utilize various decision policies and the extent to which they are aware of the processes they apply when making judgments.

In today's fast-paced climate, enterprises, industries, and the government all require competent, rational decision-making, and they all need it urgently. It is needed that it must be chosen between one or more options while making a decision. In the framework of cognitive brain processes, it is possible to come up with a wide range of options for making a choice. A final choice is reached at the end of every decision-making process. Decisions may be made in terms of action or opinion depending on the outcome. Long-term or short-term planning, working at the highest or lowest levels of management, having the ability to make sound decisions is a need. Using the advanced decision-making tools offered by Decision Theory [1], the Decision Maker can make better choices when confronted with tough choices.

The following is an example of a wide definition of Decision Theory:

One must pick the action that is most likely to achieve one's objectives, as established by the decision maker, from among the numerous possibilities when provided with a list of options. Before making a decision, a person who wants to choose the best possible course of action must evaluate all of the potential consequences and outcomes associated with each option. The selection problem is subjected to logical and quantitative investigation.

To better comprehend or prescribe actions to strengthen the coherence between various alternatives offered by the scenario and the aims and value systems of the agents participating in the decision process, there are a variety of ways for modeling decision scenarios. Building a relational or functional model is the basis for mathematical decision analysis [2].

Many different methodologies have been used to study the decision-making process of humans. Experts recommend that while evaluating a person's options, they take into account their psychological needs, preferences, and desired values. From a cognitive standpoint, it is essential to perceive decision-making as a continuous process that is linked to one's immediate environment. It is necessary to examine the logic and rationality of decision-making and the consistency of the choice that results from it from a normative perspective to understand the process. Another way to look about it is as a process that leads to the discovery of an appropriate solution to a problem that has been addressed. There are two kinds of assumptions that may influence a decision: explicit and implicit [3]. An emotional or intellectual choice may also lead to a decision.

Logical thinking is required for technical decision-making in which experts draw on their expertise to make well-informed judgments about the present situation. A study employing natural techniques found that professionals rely more on intuitive Decision Making than organized approaches when faced with tighter deadlines, higher stakes, or more uncertainty. A recognition-primed decision approach is used in order to fit a collection of indicators into the expert's competence and swiftly arrive at an acceptable plan of action [4]. There have been several recent efforts that have formalized the incorporation of uncertainty into decision making. Several studies have underlined the importance of human judgment and the inherent flaws in decision making as essential components in the assessment of human performance. Psychologists have been working on mathematical and computer models for many years to better understand how humans make choices. They may be used to a broad variety of tasks and circumstances in a wide range of organizations and settings. AI research has concentrated on how intelligent beings interact with their environment and make decisions, rather than how they think.

Scientists study how individuals interact with their environment and try to mimic their decision-making processes in order to learn more about these people. Most of the time, public policy is at issue in these kinds of operations. All of the decision making problems often include the concept of ambiguity or vagueness. Many psychologists turn to probability theory for help when presented with this problem. When using probabilistic models instead of statistical models, there are two key limitations: It should be highlighted that certain natural sources of uncertainty may not exist in a form that can be explained by a universally agreed probability model [5]. Many cognitive processes exhibit an unpredictability that defies the predictions of probability theory and randomness, and this uncertainty may be difficult to explain. Since Lotfi Zadeh got his start in fuzzy sets theory, the latter field has grown to include soft computing, which incorporates techniques, such as fuzzy systems with neural networks and genetic algorithms.

As per Lotfi Zadeh the fuzzy sets and fuzzy logic, which are mathematical systems that directly translate into natural language, may be used in combination with other mathematical systems to represent the intricate interactions between variables that occur in everyday language. Model-free estimators or universal approximations, reasoning imprecision, and fuzzy rule representations are all part of the fuzzy system method to simulating human judgment and decision making [6].

Fuzzy logic is becoming an increasingly vital instrument to have on hand whether we work in construction engineering or management research. As a consequence of the lack of comprehensive data sets for modeling, fuzzy logic may be used to reflect the subjective uncertainty in the construction sector. There are several ways to develop a hybrid system, such as using fuzzy logic, evolutionary algorithms, and artificial neural networks, but the most important is to mix these methods with each other. Additionally, unique applications in planning and scheduling, estimation, bidding, productivity; project control; structuring projects; process improvement; and risk analysis will be discussed in this session. With a focus on fuzzy logic and fuzzy hybrid techniques, we could conduct a detailed examination and provide recommendations on how to adapt them for construction applications in particular [7].

Image processing, analysis, indexing, and retrieval are becoming more important due to the increasing availability on the Internet of enormous picture datasets. Using low-level content-based qualities, content-based image retrieval (CBIR) is able to give results that are quite consistent. "Semantic gap" has long been a problem in CBIR due to the challenges in precisely describing images at the lowest feasible level and having that description be...