scholarly journals A Multi-Gaussian Fuzzy Membership Function to the Algorithm Fuzzy GrowCut Applied to Segment Lesions in Mammography Images

2018 ◽  
Author(s):  
Filipe R. Cordeiro ◽  
Beatriz Albuquerque ◽  
Valmir Macario
Keyword(s):  
Breast Cancer ◽  
Membership Function ◽  
State Of The Art ◽  
Accurate Diagnosis ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Tumor Segmentation ◽  
Membership Functions ◽  
Low Contrast

Segmentation of masses in mammography images is an important task to aid the accurate diagnosis of breast cancer. Although the quality of segmentation is crucial to avoid misdiagnosis, the segmentation process is a challenging task even for specialists, due to the presence of ill-defined edges and low contrast images. One of the techniques of state of the art for tumor segmentation is the Fuzzy GrowCut algorithm. In this work a study is performed on the behavior of this algorithm when using different membership functions for segmentation. Moreover, this research proposes a new membership function, called Multi-Gaussian, which improves the results of Fuzzy GrowCut with respect to those obtained through the use of classical functions.

scholarly journals Using Artificial Intelligence to Predict Class Loyalty and Plagiarism in Students in an Online Blended Programming Course during the COVID-19 Pandemic

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2203
Author(s):  
Jain-Shing Wu ◽  
Ting-Hsuan Chien ◽  
Li-Ren Chien ◽  
Chin-Yi Yang
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Membership Function ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Membership Functions ◽  
High Class ◽  
Fuzzy Membership Functions ◽  
Novel Method ◽  
Programming Courses

During the COVID-19 epidemic, most programming courses were revised to distance learning. However, many problems occurred, such as students pretending to be actively learning while actually being absent and students engaging in plagiarism. In most existing systems, obtaining status updates on the progress of a student’s learning is hard. In this paper, we first define the term “class loyalty”, which means that a student studies hard and is willing to learn without using any tricks. Then, we propose a novel method combined with the parsing trees of program codes and the fuzzy membership function to detect plagiarism. Additionally, the fuzzy membership functions combined with a convolution neural network (CNN) are used to predict which students obtain high scores and high class loyalty. Two hundred and twenty-six students were involved in the experiments. The dataset was randomly separated into the training datasets and the test datasets for twenty runs. The average accuracies of the experiment in predicting which students obtain high scores using the fuzzy membership function combined with a CNN and using the duration and number of actions are 93.34% and 92.62%. The average accuracies of the experiment in predicting which students have high class loyalty are 95.00% and 92.74%. Both experiments show that our proposed method not only can detect plagiarism but also can be used to detect which students are diligent.

scholarly journals A Novel Approach to Generate Type-1 Fuzzy Triangular and Trapezoidal Membership Functions to Improve the Classification Accuracy

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1932
Author(s):  
Muhammad Hamza Azam ◽  
Mohd Hilmi Hasan ◽  
Saima Hassan ◽  
Said Jadid Abdulkadir
Keyword(s):  
Membership Function ◽  
Clustering Algorithm ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Membership Functions ◽  
Function Type ◽  
Fuzzy C Means ◽  
Fuzzy Membership Functions ◽  
Fuzzy C Means Algorithm

Fuzzy logic is an approach that reflects human thinking and decision making by handling uncertainty and vagueness using fuzzy membership functions. When a human is engaged in the design of a fuzzy system, symmetric properties are naturally preferred. Fuzzy c-means clustering is a clustering algorithm that can cluster datasets to produce membership matrix and cluster centers, which results in generating type-1 fuzzy membership functions. However, fuzzy c-means algorithm has a limitation of producing only a single membership function type, Gaussian MF. Generation of multiple fuzzy membership functions is of immense importance as it provides more efficient and optimal solutions to a problem. Therefore, an approach to generate multiple type-1 fuzzy membership functions through fuzzy c-means is required for the optimal and improved results of classification datasets. Hence, to overcome the limitation of the fuzzy c-means algorithm, an approach for the generation of type-1 fuzzy triangular and trapezoidal membership function through fuzzy c-means is considered in this study. The approach is used to calculate and enhance the accuracy of classification datasets called iris, banknote authentication, blood transfusion, and Haberman’s survival. The proposed approach of generating MFs using FCM produce asymmetric MFs, whose results are compared with the MFs produced from grid partitioning (GP), which are symmetric MFs. The results show that the proposed approach of generating type-1 fuzzy membership function through fuzzy c-means is effective and can be adopted.

scholarly journals K-MEANS SEBAGAI EKSTRAKTOR CIRI PADA KLASIFIKASI DATA DENGAN ALGORITMA SUPPORT VECTOR MACHINE (SVM)

2018 ◽  
Vol 9 (2) ◽  
pp. 889-896
Author(s):  
Nurul Chamidah
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Heart Disease ◽  
Membership Function ◽  
Cross Validation ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Support Vector ◽  
Fold Cross Validation

Besarnya dimensi pada ciri merupakan masalah pada komputasi untuk mengklasifikasi data sehingga diperlukan suatu proses ekstraksi ciri agar dimensinya berkurang dengan cara mengambil hanya informasi yang penting dari ciri. Penelitian ini menggunakan algoritma K-Means untuk mengekstraksi ciri dengan menemukan pola tersembunyi dari setiap kelas kemudian direkonstruksi dengan fuzzy membership function dan mendapatkan pola baru. Pola baru yang terbentuk digunakan sebagai  ciri abstrak dan dibagi kedalam data latih dan data uji. Pelatihan dilakukan dengan memanfaatkan algoritma Support Vector Machine (SVM) untuk mendapatkan model klasifikasi. Model klasifikasi SVM yang diperoleh kemudian di uji dengan menggunakan data uji untuk memperoleh performa klasifikasi berupa akurasi dan waktu komputasi. Dengan 5-fold cross validation, metode ini memberikan akurasi yang baik pada dataset Liver, Breast Cancer dan Heart Disease yang diperoleh dari UCI Machine Learning Repository. Penelitian ini menunjukkan kemampuan K-Means untuk mengekstraksi ciri dari dataset. Hasil penelitian ini menujukkan bahwa K-Means sebagai ekstraktor ciri dapat mengurangi waktu komputasi.

MAMMOGRAM SCREENING USING MULTIRESOLUTION-BASED IMAGE SEGMENTATION

1993 ◽  
Vol 07 (06) ◽  
pp. 1437-1460 ◽  
Author(s):  
D. BRZAKOVIC ◽  
M. NESKOVIC
Keyword(s):  
Image Segmentation ◽  
Membership Function ◽  
Region Growing ◽  
Fine Tuning ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Low Contrast ◽  
Mammogram Images ◽  
Multiresolution Image ◽  
Selection Of

This paper describes the design, implementation, and testing of an adaptive digital image segmentation method that detects cancerous changes in mammograms and can potentially aid medical experts in establishing the diagnosis. The essence of the method is hierarchical region growing that uses pyramidal multiresolution image representation. The relationships between pixels at different resolution levels are established using a fuzzy membership function, thus enabling detection of very small and/or low contrast objects in a highly textured background. The selection of the parameters of the fuzzy membership function allows for fine-tuning the method to specific segmentation objectives. This paper discusses two versions of the method: the first is aimed at the detection of microcalcifications and the second at the detection of benign and malignant nodules. The two versions are fully automated and differ in the procedure applied to automatically select the appropriate parameters of the fuzzy membership function. Both versions were evaluated in two ways: (i) using synthetically generated objects superimposed on normal mammograms and (ii) using mammogram images for which the corresponding truth images were generated by human experts. The objective of the first evaluation was to precisely determine the method’s capabilities and its sensitivity to object size, shape, and contrast. The objective of the second evaluation was to establish the method’s usefulness in helping medical experts to establish the diagnosis.

A Different Approach for Solving the Shortest Path Problem Under Mixed Fuzzy Environment

2020 ◽  
Vol 9 (2) ◽  
pp. 132-161 ◽  
Author(s):  
Ranjan Kumar ◽  
Sripati Jha ◽  
Ramayan Singh
Keyword(s):  
Linear Programming ◽  
Shortest Path ◽  
Path Length ◽  
Real Life ◽  
Shortest Path Problem ◽  
Fuzzy Linear Programming ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Membership Functions ◽  
Fuzzy Environment

The authors present a new algorithm for solving the shortest path problem (SPP) in a mixed fuzzy environment. With this algorithm, the authors can solve the problems with different sets of fuzzy numbers e.g., normal, trapezoidal, triangular, and LR-flat fuzzy membership functions. Moreover, the authors can solve the fuzzy shortest path problem (FSPP) with two different membership functions such as normal and a fuzzy membership function under real-life situations. The transformation of the fuzzy linear programming (FLP) model into a crisp linear programming model by using a score function is also investigated. Furthermore, the shortcomings of some existing methods are discussed and compared with the algorithm. The objective of the proposed method is to find the fuzzy shortest path (FSP) for the given network; however, this is also capable of predicting the fuzzy shortest path length (FSPL) and crisp shortest path length (CSPL). Finally, some numerical experiments are given to show the effectiveness and robustness of the new model. Numerical results show that this method is superior to the existing methods.

Sign in / Sign up

Export Citation Format

Share Document