Editing Fuzzy logic (section)

==Applications==

Fuzzy logic is used in [[control system]]s to allow experts to contribute vague rules such as "if you are close to the destination station and moving fast, increase the train's brake pressure"; these vague rules can then be numerically refined within the system.

Many of the early successful applications of fuzzy logic were implemented in Japan. A first notable application was on the [[Sendai Subway 1000 series]], in which fuzzy logic was able to improve the economy, comfort, and precision of the ride. It has also been used for [[handwriting recognition]] in Sony pocket computers, helicopter flight aids, subway system controls, improving automobile fuel efficiency, single-button washing machine controls, automatic power controls in vacuum cleaners, and early recognition of earthquakes through the Institute of Seismology Bureau of Meteorology, Japan.<ref>{{cite book |last1=Bansod |first1=Nitin A |last2=Kulkarni |first2=Marshall |last3=Patil |first3=S. H. |editor1-last=Bharati Vidyapeeth College of Engineering |title=Soft Computing |date=2005 |publisher=Allied Publishers |isbn=978-81-7764-632-0 |pages=73 |chapter-url=https://books.google.com/books?id=IkajJC9iGxMC&pg=PA73 |access-date=9 November 2018 |chapter=Soft Computing- A Fuzzy Logic Approach}}</ref>

=== Artificial intelligence ===
{{Main|Neuro-fuzzy}}
[[Artificial neural network|Neural networks]] based [[artificial intelligence]] and fuzzy logic are, when analyzed, the same thing—the underlying logic of neural networks is fuzzy. A neural network will take a variety of valued inputs, give them different weights in relation to each other, combine intermediate values a certain number of times, and arrive at a decision with a certain value. Nowhere in that process is there anything like the sequences of either-or decisions which characterize non-fuzzy mathematics, [[computer programming]], and [[digital electronics]]. In the 1980s, researchers were divided about the most effective approach to [[machine learning]]: [[decision tree learning]] or neural networks. The former approach uses binary logic, matching the hardware on which it runs, but despite great efforts it did not result in intelligent systems. Neural networks, by contrast, did result in accurate models of complex situations and soon found their way onto a multitude of electronic devices.<ref>{{cite journal|last1=Elkan|first1=Charles|title=The paradoxical success of fuzzy logic|journal=IEEE Expert|date=1994|volume=9|issue=4|pages=3–49|doi=10.1109/64.336150|citeseerx=10.1.1.100.8402|s2cid=113687}}</ref> They can also now be implemented directly on analog microchips, as opposed to the previous pseudo-analog implementations on digital chips. The greater efficiency of these compensates for the intrinsic lesser accuracy of analog in various use cases.

=== Medical decision making===

Fuzzy logic is an important concept in [[Clinical decision support system|medical decision making]]. Since medical and healthcare data can be subjective or fuzzy, applications in this domain have a great potential to benefit a lot by using fuzzy-logic-based approaches.

Fuzzy logic can be used in many different aspects within the medical decision making framework. Such aspects include<ref>{{cite journal |author1= Lin, K. P.|author2= Chang, H. F.|author3= Chen, T. L.|author4= Lu, Y. M.|author5 = Wang, C. H. | title = Intuitionistic fuzzy C-regression by using least squares support vector regression. | journal = Expert Systems with Applications | date = 2016 | volume = 64 |pages=296–304| doi = 10.1016/j.eswa.2016.07.040 }}</ref><ref>{{cite journal |author1= Deng, H.|author2= Deng, W.|author3= Sun, X.|author4= Ye, C.|author5= Zhou, X.| title = Adaptive intuitionistic fuzzy enhancement of brain tumor MR images | journal = Scientific Reports | date = 2016 | volume=6 | pages=35760 | doi=10.1038/srep35760 | pmid = 27786240 | pmc = 5082372 | doi-access=free| bibcode = 2016NatSR...635760D }}</ref><ref>{{cite journal |author=Vlachos, I. K.|author2= Sergiadis, G. D.| title = Intuitionistic fuzzy information–applications to pattern recognition. | journal = Pattern Recognition Letters | date = 2007 | volume= 28 | issue = 2 | pages= 197–206| doi = 10.1016/j.patrec.2006.07.004 | bibcode = 2007PaReL..28..197V }}</ref>{{clarify|reason=please summarise these refs- several are on a subscription basis|date=February 2022}} in [[medical image analysis]], biomedical signal analysis, [[image segmentation|segmentation of images]]<ref name=wounds>{{Cite book|last1=Gonzalez-Hidalgo|first1=Manuel|last2=Munar|first2=Marc|last3=Bibiloni|first3=Pedro|last4=Moya-Alcover|first4=Gabriel|last5=Craus-Miguel|first5=Andrea|last6=Segura-Sampedro|first6=Juan Jose|title=2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) |chapter=Detection of infected wounds in abdominal surgery images using fuzzy logic and fuzzy sets |date=October 2019|location=Barcelona, Spain|publisher=IEEE|pages=99–106|doi=10.1109/WiMOB.2019.8923289|isbn=978-1-7281-3316-4|s2cid=208880793}}</ref> or signals, and [[feature extraction]] / selection of images<ref name=wounds/> or signals.<ref>{{cite journal | author = Das, S.|author2= Guha, D.|author3= Dutta, B.| title = Medical diagnosis with the aid of using fuzzy logic and intuitionistic fuzzy logic. | journal = Applied Intelligence | date = 2016 | volume= 45 | issue = 3 | pages= 850–867| doi = 10.1007/s10489-016-0792-0 | s2cid = 14590409 }}</ref>

The biggest question in this application area is how much useful information can be derived when using fuzzy logic. A major challenge is how to derive the required fuzzy data. This is even more challenging when one has to elicit such data from humans (usually, patients). As has been said {{blockquote|text="The envelope of what can be achieved and what cannot be achieved in medical diagnosis, ironically, is itself a fuzzy one" |source=Seven Challenges, 2019.<ref name=YT/>}} How to elicit fuzzy data, and how to validate the accuracy of the data is still an ongoing effort, strongly related to the application of fuzzy logic. The problem of assessing the quality of fuzzy data is a difficult one. This is why fuzzy logic is a highly promising possibility within the medical decision making application area but still requires more research to achieve its full potential.<ref name=YT>{{Cite journal|last1=Yanase|first1=Juri|last2=Triantaphyllou|first2=Evangelos|date=2019|title=The Seven Key Challenges for the Future of Computer-Aided Diagnosis in Medicine|journal=International Journal of Medical Informatics|volume=129|pages=413–422|doi=10.1016/j.ijmedinf.2019.06.017|pmid=31445285|s2cid=198287435}}</ref> 

==== Image-based computer-aided diagnosis ====
One of the common application areas of fuzzy logic is image-based [[computer-aided diagnosis]] in medicine.<ref>{{Cite journal|last1=Yanase|first1=Juri|last2=Triantaphyllou|first2=Evangelos|date=2019|title=A Systematic Survey of Computer-Aided Diagnosis in Medicine: Past and Present Developments|journal=Expert Systems with Applications|volume=138|pages=112821|doi=10.1016/j.eswa.2019.112821|s2cid=199019309}}</ref> Computer-aided diagnosis is a computerized set of inter-related tools that can be used to aid physicians in their diagnostic decision-making.

=== Fuzzy databases ===
Once fuzzy relations are defined, it is possible to develop fuzzy [[relational database]]s. The first fuzzy relational database, FRDB, appeared in [[Maria Zemankova]]'s dissertation (1983). Later, some other models arose like the Buckles-Petry model, the Prade-Testemale Model, the Umano-Fukami model or the GEFRED model by J. M. Medina, M. A. Vila et al.

Fuzzy querying languages have been defined, such as the [[SQLf]] by P. Bosc et al. and the [[FSQL]] by J. Galindo et al. These languages define some structures in order to include fuzzy aspects in the SQL statements, like fuzzy conditions, fuzzy comparators, fuzzy constants, fuzzy constraints, fuzzy thresholds, linguistic labels etc.