International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

Uncertainties are pervasive in ever-increasing more practical evaluation and decision making environments. Numerical information with uncertainty losses more or less credibility, which makes it possible to use bi-polar preference based weights allocation method to attach differing importance to different information granules in evaluation. However, there lacks effective methodologies and techniques to simultaneously consider various categories of involved bi-polar preferences, not merely the magnitude of main data which ordered weighted averaging aggregation can well handle. This work proposes some types and categories of bi-polar preference possibly involved in preference and uncertain evaluation environment, discusses some methods and techniques to elicit the preference strengths from practical backgrounds, and suggests several techniques to generate corresponding weight vectors for performing bi-polar preference based information fusion. Detailed decision making procedure and numerical example with management background are also presented. This work also presents some practical approaches to apply preferences and uncertainties involved aggregation techniques in decision making.

Autism spectrum disease is one of the severe neuro developmental disorders that are currently present worldwide (ASD). It is a chronic disorder that has an impact on a person’s behaviour and communication abilities. The world health organization’s 2019 study states that an increasing number of people are being diagnosed with ASD, which poses a risk because it is comparable to high medical expenses. Early detection can significantly lessen the impact. Traditional techniques are costly and time-consuming. This paper offers a Novel Deep Recurrent Neural Network (NDRNN) algorithm for the detection of the level of autism to address the aforementioned problems. The deep recurrent neural network is developed with several hidden recurrent network layers with Long-Short Term Memory (LSTM) units. In this work, Artificial Algae Algorithm (AAA) is used as a feature extraction algorithm, to obtain the best optimal features among the listed feature set. An Intelligent Water Droplet (IWD) algorithm is used for obtaining optimal weight and bias value for the recurrent neural network. The algorithm was evaluated for the dataset obtained by the Indian scale for assessment of autism. Experimental results shows that this proposed model produces the 91% of classification accuracy and 92% of sensitivity and reduces the cost.

This paper intends to develop a novel framework for text document clustering with the aid of a new improved meta-heuristic algorithm. Initially, the features are selected from the text document by subjecting each word under Term Frequency-Inverse Document Frequency (TF-IDF) computation. Subsequently, centroid selection plays a vital role in cluster formation, which is done using a new Improved Lion Algorithm (LA) termed as Cross over probability-based LA model (CP-LA). As a novelty, this paper introduced a new inter and intracluster similarity model. Moreover, this centroid selection is made in such a way that the proposed adaptive weighted similarity should be minimal. Based on the characteristics of the document, the weights are automatically adapted with the similarity measure. The proposed adaptive weighted similarity function involves the inter-cluster, and intra-cluster similarity of both ordered and unordered documents. Finally, the superiority of the proposed over other models is proved under different performance measures.

This research article illustrates the notion of strong and complete Pythagorean fuzzy soft graphs (PFSGs). Different operations on PFSGs including union of two PFSGs, join of two PFSGs, lexicographic product of two PFSGs, strong product of two PFSGs, Cartesian product of two PFSGs, composition of two PFSGs are also analysed here. Some properties related to these products are discussed here. The idea of complememt of a PFSG is also eloborated here. Moreover, we establish the application of PFSG in the decision making (DM) problem.

In real life, multiple attribute decision problems (MADM) can be applied in different areas and numerous related extensions and methodologies have been proposed by researchers. Combining three-way TOPSIS decision ideas with MADM is a feasible and meaningful research direction. In light of this, this paper generalizes the classical TOPSIS method with the help of mean and standard deviation and proposes the so-called modified three-way TOPSIS. First, using a pair of thresholds which is derived by mean and standard deviation, we divide decision alternatives into three segments, and then a preliminary rank results of decision alternatives can be obtained. Furthermore, in each decision region, we use two ranking regulations (one-way TOPSIS or modified two-way TOPSIS method) to rank decision alternatives. A practical example of urban expressway route selection illustrates the feasibility of the proposed method. Finally, we test the feasibility and validity of the modified three-way TOPSIS method by comparing with some existing method.

This paper is intended to investigate fuzzy variational problems of several dependent variables. Firstly, we establish both necessary and sufficient optimality conditions for fundamental fuzzy variational problems and fuzzy variational problems with natural boundary conditions. Then, the necessary and sufficient optimality conditions for fuzzy variational problems with isoperimetric constraints and holonomic constraints are discussed. Some examples are given to illustrate our results.

This paper deals with fuzzy multi-depot bus scheduling (FMDBS) problem in which the objective function and constraints are defined with fuzzy attributes. Credibility relation is used to formulate the problem as an integer multicommodity flow problem. A novel combination of branch-and-price and heuristic algorithms, is proposed to efficiently solve FMDBS problem. In the proposed algorithm, the heuristic algorithm is applied to generate initial columns for the column generation method. Also, a heuristic algorithm is used to improve the generated solutions in each node of the branch-and-price tree. Two sets of benchmark examples are applied to demonstrate the efficiency of the proposed algorithm for large-scale instances. Also, the algorithm is applied to solve the classical multi-depot bus scheduling problem. The results show that the proposed algorithm decreases integrality gap and computational time in comparison with the state-of-the-art algorithms and normal branch-and-price algorithm. Finally, as a case study, the bus schedules in Tehran BRT network are generated.