Showing papers in "Applied Soft Computing in 2023"

TL;DR: In this article , an explainable medical recommender system that uses graph concepts to provide an interpretable approach to medical data has been developed, which is based on community detection algorithms.

TL;DR: In this article , a triangle-filter convolution neural network (TFCNN) was proposed to solve the problems of fuel reloading optimization for block-type HTGRs.

TL;DR: Wang et al. as discussed by the authors proposed an anomaly detection method based on fuzzy-rough density, which takes into account both the density and fuzziness of the samples, and the experimental results show that the proposed method achieves better performance on three types of datasets.

TL;DR: In this paper , the authors define some solid mathematical concepts to model and resolve the stated problem named complex picture fuzzy soft relations (CPFSRs) which is defined by the Cartesian product (CP) of two Complex Picture Fuzzy Soft Sets (CPFSSs) and provide modeling methodologies based on CPFSRs which are used for the analysis of electing the best GAN for effective working.

TL;DR: In this paper , the authors provide a state-of-the-art review of ML in geotechnical reliability analysis applications, including multisensor data fusion, time-variant reliability analysis, three-dimensional reliability analysis of practical cases, and ML model selection and optimization.

TL;DR: In this article , a novel linguistic assessment model, namely rough fuzzy integrated clouds (RFICs), is developed to handle uncertain information by integrating rough fuzzy numbers with cloud model theory, and a significant decision support model for the analysis of failure modes is constructed based on RFICs, hybrid weighting method and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method.

TL;DR: Wang et al. as discussed by the authors proposed a modified gray wolf optimization algorithm for feature selection of high-dimensional data, which introduces ReliefF algorithm and Coupla entropy in the initialization process, which effectively improves the quality of the initial population.

TL;DR: An improved queuing search optimization (QSO) algorithm dependent on the differential evolution (DE) technique and bound-constraint amendment procedure, which is called IQSODE, has been presented to efficiently extract the PV parameter values for various PV models as discussed by the authors .

TL;DR: In this paper , the authors extended the fuzzy weighted with zero inconsistency (FWZIC) method with interval-valued Pythagorean fuzzy rough set (IVPFRS) and integrated it with the evaluation based on distance from average solution (EDAS) method to rank I4.0-in-a-CE-and-SPs applications.

TL;DR: In this article , an efficient anomaly detection method in real-time sensor is identified through markov and LSTM based network and the outliers in the data is clearly removed through the proposed approach.

TL;DR: In this article , a deep learning framework using fine-grained facial action unit detection was proposed to identify facial activity, behavior, and mood and recognize a person's emotions based on these individual patterns.

TL;DR: In this paper , the authors proposed an Agri4SC benchmarking framework for improving data analytics capabilities and achieving sustainable performance based on an extension of the proposed Fermatean probabilistic hesitant fuzzy sets (FPHFSs) and MCDM methods.

TL;DR: In this article , an evolutionary computation-based multitask learning network named EEG-DEMTL is proposed to evaluate railway passenger comfort from EEG signals, which fully exploits the relationship between subtasks such as passenger emotion and the main task, which is passenger overall comfort.

TL;DR: In this paper , an ant colony optimization algorithm with destory and repair strategies (ACO-DR) is proposed on the basis of ACO, which designs a random transition rule with direction to improve the probability of the algorithm to search the target and to enhance the global search ability.

TL;DR: Wang et al. as discussed by the authors proposed a novel three-way decisions model based on cumulative prospect theory and outranking relations, which reduces decision risk by constructing an outranked set for each alternative and a hybrid multi-criteria decision-making matrix.

TL;DR: Wang et al. as mentioned in this paper proposed Multiple Information Spatial-Temporal Attention based Graph Convolution Networks (MISTAGCN), which consists of two parts, the first part utilizes combinations of different inputs and graph structures to compute the corresponding latent variables, and the second part is comprehensively integrated and deeply mined.

TL;DR: In this paper , the authors present two significant techniques for group decision-making by considering dominance and subordination between alternatives relying on the prime concepts of concordance, discordance and indifferent sets.

TL;DR: The authors proposed a novel machine learning based framework, i.e., BERT-based back-translation Text and Entire-image multimodal model with Contrastive learning (TTEC).

TL;DR: Zhang et al. as mentioned in this paper proposed an evolutionary graph neural network (EGNN) approach to improve defense against adversarial attacks and enhance GNN performance by learning a graph structure that conforms to the ground truth.

TL;DR: In this paper , a hybrid decision-making framework was proposed to select an optimal transportation route in multimodal supply chains, which integrates the fuzzy risk assessment model (FRAM), best-worst method (BWM), and measurement of alternatives and ranking according to the compromise solution (MARCOS).

TL;DR: In this article , an engineering project about excavation construction was provided to illustrate the potentials of TOPSIS-based MCDM modelling. But the applicationability and robustness of the top three high-risk factors in high risk factors' target was performed through sensitivity and comparative analysis.

TL;DR: In this paper , a novel Dense Swin Transformer Network (DST-Net) is proposed for audio-visual deep-fakes detection, which consists of an input block, feature extraction block, and output block.

TL;DR: In this paper , the authors implemented weighted agreement measures as evaluation metrics for ordinal classifiers and evaluated the applicability of agreement and mainstream performance metrics to various practice fields under challenging data compositions.

TL;DR: Wang et al. as discussed by the authors proposed an automated spatio-temporal information fusion neural network (ASTIF-Net) for urban hotspot forecasting, where normal convolution and graph convolution operations are adopted to capture spatial geographic neighborhood dependencies and spatial semantic neighborhood dependencies.

TL;DR: In this article , the authors proposed three interval-valued intuitionistic hesitant fuzzy (IISFG) operators to capture the interrelation of fuzzy input variables, including an IISFG weighted BM operator, a simplified IGSFG BM operator and a simplified SIVIHFWBM operator.

TL;DR: In this article , the q-rung orthopair fuzzy distance measure based triangle orthocenter is given, and a q-ROF score function (SF) based distance measure is proposed for disposing of comparison issue.