International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

Today’s datasets are usually very large with many features and making analysis on such datasets is really a tedious task. Especially when performing classification, selecting attributes that are salient for the process is a brainstorming task. It is more difficult when there are many class labels for the target class attribute and hence many researchers have introduced methods to select features for performing classification on multi-class attributes. The process becomes more tedious when the attribute values are imbalanced for which researchers have contributed many methods. But, there is no sufficient research to handle extreme imbalance and feature selection together and hence this paper aims to bridge this gap. Here Particle Swarm Optimization (PSO), an efficient evolutionary algorithm is used to handle imbalanced dataset and feature selection process is also enhanced with the required functionalities. First, Multi-objective Particle Swarm Optimization is used to transform the imbalanced datasets into balanced one and then another version of Multi-objective Particle Swarm Optimization is used to select the significant features. The proposed methodology is applied on eight multi-class extremely imbalanced datasets and the experimental results are found to be better than other existing methods in terms of classification accuracy, G mean, F measure. The results validated by using Friedman test also confirm that the proposed methodology effectively balances the dataset with less number of features than other methods.

Clustering techniques are used to split data into clusters where each cluster contains elements that look more similar to elements in the same cluster than elements in other clusters. Some of these techniques are capable of handling clustering process uncertainty, while other techniques may have stability issues. In this paper, a novel method, called Minimum Information Gain Roughness (MIGR), is proposed to select the clustering attribute based on information entropy with rough set theory. To evaluate its performance, three benchmark UCI datasets are chosen to be clustered by using MIGR. Then, the resulting clusters are compared to those which are resulted from applying Min-Min-Rough (MMR) and information-theoretic dependency roughness (ITDR) algorithms. Both last-mentioned techniques were already compared with a variety of clustering algorithms like k-modes, fuzzy centroids, and fuzzy k-modes. The Global purity, the overall purity, and F-measure are considered here as performance measures to compare the quality of the resulting clusters. The experimental results show that the MIGR algorithm outperforms both MMR and ITDR algorithms for clustering categorical data.

Purpose: During the current pandemic scientists, researchers, and health professionals across the globe are in search of new technological methods for tackling COVID-19. The magnificent performance reported by machine learning and deep learning methods in the previous epidemic has encouraged researchers to develop systems with these methods to diagnose COVID-19.

Methods: In this paper, an ensemble-based multi-level voting model is proposed to diagnose COVID-19 from chest x-rays. The multi-level voting model proposed in this paper is built using four machine learning algorithms namely Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) with a linear kernel, and K-Nearest Neighbor (KNN). These algorithms are trained with features extracted using the ResNet50 deep learning model before merging them to form the voting model. In this work, voting is performed at two levels, at level 1 these four algorithms are grouped into 2 sets consisting of two algorithms each (set 1 — SVM with linear kernel and LR and set 2 — RF and KNN) and intra set hard voting is performed. At level 2 these two sets are merged using hard voting to form the proposed model.

Results: The proposed multilevel voting model outperformed all the machine learning algorithms, pre-trained models, and other proposed works with an accuracy of 100% and specificity of 100%.

Conclusion: The proposed model helps for the faster diagnosis of COVID-19 across the globe.

In the present article, we introduced almost $\lambda$-statistical convergence of complex uncertain sequences in all five aspects of uncertainty viz., almost surely, mean, measure, distribution and uniformly almost surely. Further, with the aid of interesting examples and diagram we investigated some interrelationships among these uncertain complex sequences.

The main intention of this paper is to develop a new intelligent framework for web page classification and re-ranking. The two main phases of the proposed model are (a) classification, and (b) re-ranking-based retrieval. In the classification phase, pre-processing is initially performed, which follows the steps like HTML (Hyper Text Markup Language) tag removal, punctuation marks removal, stop words removal, and stemming. After pre-processing, word to vector formation is done and then, feature extraction is performed by Principle Component Analysis (PCA). From this, optimal feature selection is accomplished, which is the important process for the accurate classification of web pages. Web pages contain several features, which reduces the classification accuracy. Here, the adoption of a new meta-heuristic algorithm termed Opposition based-Tunicate Swarm Algorithm (O-TSA) is employed to perform the optimal feature selection. Finally, the selected features are subjected to the Enhanced Convolutional-Recurrent Neural Network (E-CRNN) for accurate web page classification with enhancement based on O-TSA. The outcome of this phase is the categorization of different web page classes. In the second phase, the re-ranking is involved utilizing the O-TSA, which derives the objective function based on similarity function (correlation) for URL matching, which results in optimal re-ranking of web pages for retrieval. Thus, the proposed method yields better classification and re-ranking performance and reduce space requirements and search time in the web documents compared with the existing methods.

Generally, in every decision-making process under the fuzzy domain, ranking of fuzzy numbers is indispensable. Although such approaches are abundant, yet a universally accepted approach is not apparent. Hence, newer methodologies have been developed since its inception. In many instances, defuzzification techniques are being criticized as these methodologies are based on intuition and the geometry of the fuzzy numbers. Furthermore, in many instances the reasonable properties that a ranking method should follow are not being verified. However, in the current study, a novel defuzzification technique is being developed with the notion of value and multiple of a ambiguity inclusion-exclusion function, $𝜃$, with ambiguity at various decision levels. The current method perfectly obeys the intuition and the geometry of the fuzzy numbers. Adding to this, it should be emphasized that the current methodology follows all the reasonable properties of a ranking method. Furthermore, new properties are stated and proved which illustrate the novelty of the present method. Furthermore, the shortcomings and drawbacks of the existing methods are overcome by the current methodology. Noteworthy, the current method ranks the fuzzy numbers and their corresponding images consistently, which was not evident in most of the existing methods.

In this paper, we propose a method that improves multiplicative consistency based on a fractional programming model to derive the normalized intuitionistic fuzzy priority weight vector from an intuitionistic fuzzy preference relation. To do so, a new definition is formulated that captures previous definitions for multiplicative consistency of intuitionistic fuzzy preference relations. A transformation formula is proposed to convert the normalized intuitionistic fuzzy priority weight vector into a multiplicative consistent intuitionistic fuzzy preference relation. By using the properties of some function, we construct a deviation matrix and prove that the elements in the intuitionistic fuzzy preference relation corresponding to the largest value in the deviation matrix is the most inconsistent. This method not only preserves a lot of the original preference judgments, but also reduce many operations in comparison with previous methods to improve multiplicative inconsistency. Several numerical examples are given to convince the proposed model and method.

In this paper, we have proposed a stochastic Knapsack Problem (KP) based mathematical model for small-scale vegetable sellers in India and solved it by an advanced Genetic Algorithm. The knapsack problem considered here is a bounded one, where vegetables are the objects. In this model, we have assumed that different available vegetables (objects) have different weights (that are available), purchase costs, and profits. The maximum weight of vegetables that can be transported by a seller is limited by the carrying capacity of the vegetable carrier and the business capital of the seller is also limited. The aim of the proposed mathematical model is to maximize the total profit of the loaded/traded items, with a set of predefined constraints on the part of the vegetable seller or retailer. This problem has been solved in a Type-2 fuzzy environment and the Critical Value (CV) reduction method is utilized to defuzzify the objective value. We have projected an improved genetic algorithm based approach, where we have incorporated two features, namely refinement and immigration. We have initially considered benchmark instances and subsequently some redefined cases for experimentation. Moreover, we have solved some randomly generated proposed KP instances in Type-2 fuzzy environment.

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA…