China
Africa
Explore chapters and articles related to this topic
Fuzzy Linear Programming
Published in Anindya Ghosh, Prithwiraj Mal, Abhijit Majumdar, Advanced Optimization and Decision-Making Techniques in Textile Manufacturing, 2019
Anindya Ghosh, Prithwiraj Mal, Abhijit Majumdar
The word fuzzy means “vagueness” or “ambiguity.” In the real world, problems often turn out to be complex due to uncertainty that arises mainly due to partial information about the problems, inherent ambiguity in the language, conflicting information from multiple sources, or information that is not fully trustworthy. In such cases, fuzzy set theory is an excellent tool to handle such uncertainty arising due to vagueness or ambiguity. The concept of fuzzy logic was propounded by Lotfi A. Zadeh (1965). Since then, a lot of theoretical developments have taken place, which are explained in many standard books authored by Zimmerman (1996), Cox (1998), Hung and Walker (1999), Berkan and Trubatch (2000), and Kartalopoulos (2000). To understand an FLP algorithm, the reader should initially comprehend the concept of crisp set, fuzzy set, and membership function.
Structure function in analysis of multi-state system availability
Published in Stein Haugen, Anne Barros, Coen van Gulijk, Trond Kongsvik, Jan Erik Vinnem, Safety and Reliability – Safe Societies in a Changing World, 2018
M. Kvassay, V. Levashenko, J. Rabcan, P. Rusnak, E. Zaitseva
The interpretation of the MSS structure function as classifier allows us to use methods for induction of classifiers based on incompletely specified data. Such methods are well known in Data Mining. One of them is induction of a decision tree. For example, the decision tree can be inducted by algorithm ID3/C4.5 developed by Quinlan (1987). This algorithm can be used for incompletely specified data that has crisp values. But initial data for reliability analysis is collected as expert data often. This data is latent or uncertain. There are different factors that cause uncertainty of data collected for reliability analysis (Aven 2010, Ley 2011). In this paper two of them are considered. The first is incompleteness of data. The second is ambiguity and vagueness of initial data.
Knowledge–Based Tuning
Published in Clarence W. de Silva, Intelligent Control, 2018
In knowledge-based control the control signals are generated by an appropriate inference mechanism, and employing a control knowledge base which is typically expressed as a set of rules. Unlike hard-algorithmic control, knowledge-based control does not primarily depend on analytic control algorithms or on accurate models of the plant. Clearly, knowledge-based control is particularly attractive when considerable knowledge, expertise (or specialized knowledge), and experience are available in controlling a particular plant, and when the plant is rather incompletely known or complex to be accurately modeled. Fuzzy control, which is based on the fuzzy logic of Zadeh (1965), is a class of knowledge-based control that incorporates control knowledge in the form of a set of linguistic rules. These rules may contain fuzzy, noncrisp or soft terms such as “rather high”, “slightly lower”, “very slow”, and “accurate”. It should be noted that vagueness, ambiguity, generality, imprecision, and uncertainty are not exactly synonymous with fuzziness. Examples of the first five situations are given by the following statements: “I will read the paper some day”, “I may or may not read the paper”, “I will read x papers in y months”, “I will read the paper within the next twenty-four hours”, and “There is a 50 percent probability that I will read the paper within the next twenty-four hours”. Instead, the statement, “I will read the paper soon” is fuzzy, as it contains the fuzzy term “soon”. There are numerous practical implementations of fuzzy logic control. In Japan, in particular, consumer products and utilities such as washing machines, vacuum cleaners, toasters, hand-jitter-compensated video cameras, television sets which can automatically adjust brightness and volume depending on room conditions, and subway trains that use this method of control are already commercially available.
Mental workload measurement, the case of stock market traders
Published in Theoretical Issues in Ergonomics Science, 2021
Finally, we note that results of our study may be for interest to both stockbrokers and their superiors. In fact, apprehending origins of mental workload could help stockbroker control it and avoid being overloaded. Moreover, our study gives him the opportunity to build new strategies of mental workload management based on coping and locus of control. He could also be awarded of the importance of developing new emotional skills that could moderate the interaction between mental workload and several job strains, miss-efficacy, burnout and turnover. Employers and especially human resources departments could also take advantage of this study to provide a favourable range of working environment, to enhance stockbroker’s operational autonomy, to encourage a real social support that could improve stockbroker’s self-efficacy and then organization performance. Regarding role ambiguity, managers must reconsider prevailing procedures in order to clarify every task as part of protocol to be applied systematically. Moreover, a real effort of coaching and training is important in order to help stockbrokers manage mental workload by using coping strategies, internal locus of control and by developing a resilience capability to confront efficiently mental effort and to manage emotional dissonance.