Fuzzy Logic Theory and Applications in Uncertainty Management of Linguistic Evaluations for Students

Fuzzy logic can deal with information arising from perception and cognition that is uncertain, imprecise, vague, partially true, or without sharp boundaries. Fuzzy logic can be used for assigning linguistic grades and for decision making and data mining with those linguistic grades by teachers, instructors, and professors. Many aspects of fuzzy logic including fuzzy sets, linguistic variables, fuzzy rules, fuzzy math, fuzzy database queries, computational theory of perceptions, and computing with words are useful in uncertainty management of linguistic evaluations for students. This chapter provides many examples of this after describing the theory of fuzzy logic.

Fuzzy database for medical diagnosis.

A challenge of working with traditional database systems with large amounts of data is that decision making requires numerous comparisons. Health-related database systems are examples of such databases, which contain millions of data entries and require fast data processing to examine related information to make complex decisions. In this thesis, a fuzzy database system is developed by integration of fuzzy inference system (FIS) and fuzzy schema design, and implementing it by SQL in three different health-care contexts; the assessments of heart disease, diabetes mellitus, and liver disorders. The fuzzy database system is implemented with the potential of having any form of data and tested with different types of data value, including crisp, linguistic, and null (i.e., missing) data. The developed system can explore crisp and linguistic data with loosely defined boundary conditions for decision-making. FIS and neural network-based solutions are implemented in MATLAB for the mentioned contexts for the comparison and validation with the dataset used in published works.

Fuzzy database for medical diagnosis.

A challenge of working with traditional database systems with large amounts of data is that decision making requires numerous comparisons. Health-related database systems are examples of such databases, which contain millions of data entries and require fast data processing to examine related information to make complex decisions. In this thesis, a fuzzy database system is developed by integration of fuzzy inference system (FIS) and fuzzy schema design, and implementing it by SQL in three different health-care contexts; the assessments of heart disease, diabetes mellitus, and liver disorders. The fuzzy database system is implemented with the potential of having any form of data and tested with different types of data value, including crisp, linguistic, and null (i.e., missing) data. The developed system can explore crisp and linguistic data with loosely defined boundary conditions for decision-making. FIS and neural network-based solutions are implemented in MATLAB for the mentioned contexts for the comparison and validation with the dataset used in published works.

Breast cancer disease classification using fuzzy-ID3 algorithm with FUZZYDBD method: automatic fuzzy database definition

Breast cancer becomes the second major cause of death among women cancer patients worldwide. Based on research conducted in 2019, there are approximately 250,000 women across the United States diagnosed with invasive breast cancer each year. The prevention of breast cancer remains a challenge in the current world as the growth of breast cancer cells is a multistep process that involves multiple cell types. Early diagnosis and detection of breast cancer are among the greatest approaches to preventing cancer from spreading and increasing the survival rate. For more accurate and fast detection of breast cancer disease, automatic diagnostic methods are applied to conduct the breast cancer diagnosis. This paper proposed the fuzzy-ID3 (FID3) algorithm, a fuzzy decision tree as the classification method in breast cancer detection. This study aims to resolve the limitation of an existing method, ID3 algorithm that unable to classify the continuous-valued data and increase the classification accuracy of the decision tree. FID3 algorithm combined the fuzzy system and decision tree techniques with ID3 algorithm as the decision tree learning. FUZZYDBD method, an automatic fuzzy database definition method, would be used to design the fuzzy database for fuzzification of data in the FID3 algorithm. It was used to generate a predefined fuzzy database before the generation of the fuzzy rule base. The fuzzified dataset was applied in FID3 algorithm, which is the fuzzy version of the ID3 algorithm. The inference system of FID3 algorithm is simple with direct extraction of rules from generated tree to determine the classes for the new input instances. This study also analysed the results using three breast cancer datasets: WBCD (Original), WDBC (Diagnostic) and Coimbra. Furthermore, the comparison of FID3 algorithm with the existing methods is conducted to verify the proposed method’s capability and performance. This study identified that the combination of FID3 algorithm with FUZZYDBD method is reliable, robust and managed to perform well in breast cancer classification.

From Classical to Fuzzy Databases in a Production Enterprise

This article presents the evolution of databases from classical relational databases to distributed databases and data warehouses to fuzzy databases used in a production enterprise. This paper discusses characteristics of this kind of enterprise. The authors precisely define centralized and distributed databases, data warehouses and fuzzy databases. In the modern global world, many companies change their management strategy from the one based on a centralized database to an approach based on distributed database systems. Growing expectations regarding business intelligence encourage companies to deploy data warehouses. New solutions are sought as the demand for engineers' expertise continues to rise. The requested knowledge can be certain or uncertain. Certain knowledge does not any problems and is easy to obtain. However, uncertain knowledge requires new ways of obtaining, including the use of fuzzy logic. It is from where the fuzzy database approach takes its beginning. The above-mentioned strategies of a production enterprise were described herein as a case of special interest.

Analisis Penilaian Kinerja Dosen Mengajar Menggunakan Logika Fuzzy

Kualitas sebuah lembaga pendidikan sangat dipengaruhi oleh kemampuan dari tenaga pengajar mereka dalam memberikan materi pembelajaran. Semakin baik kualitas kinerja dari tenaga pengajar biasanya akan berbanding lurus dengan kualitas lulusan dari lembaga pendidikan tersebut. Pada penelitian ini, dibangun sebuah sistem fuzzy database yang bertujuan untuk melakukan manipulasi data- data keberhasilan dosen yang mengajar yang bersifat ambigu. Model fuzzy database tahani digunakan untuk keperluan tersebut. Variabel yang digunakan adalah angket mahasiswa dengan jumlah angket lima belas . Bentuk pilihan di Implementasikan menggunakan himpunan fuzzy dengan kurva naik, kurva turun dan kurva segitiga. Himpunan Fuzzy Nilai angket diberikan secara pilihan yaitu tidak pernah, kurang, cukup, baik dan baik sekali. Dengan adanya sistem fuzzy database ini, dapat mengetahui penilaian dosen dengan target ouputnya supaya meningkatnya kualitas dosen mengajar.