Informatica

Credit card fraud (CCF) poses a growing threat to the global economy, with payment card fraud losses reaching approximately USD 33.8 billion in 2023. While deep learning approaches such as CNNs, autoencoders, and Transformer-based models have improved detection accuracy, their “black box” nature restricts adoption in high-stakes financial domains where transparent and auditable reasoning is essential for trust and regulatory compliance. To address this challenge, we propose MTLFraudDetect, a multi-task framework that combines fraud detection with complementary model-analysis techniques. The model combines fraud classification with two auxiliary tasks—data reconstruction and amount prediction—while employing curriculum learning and PCGrad to stabilize multi-task optimization. For model analysis, the framework combines reconstruction-based anomaly-sensitivity signals with SHAP-based decision attribution. Reconstruction errors indicate transaction-level and feature-wise deviations from patterns learned by the reconstruction branch, whereas SHAP examines how the classifier’s shared latent representation and transaction amount contribute to its final prediction. Under an explicitly separated development-test protocol with training-fold-only preprocessing and out-of-fold hyperparameter selection, MTLFraudDetect achieves competitive F1-score and AUC-PR performance while providing complementary evidence at the levels of global anomaly detection, feature-wise error localization, and post-hoc decision attribution. These results do not by themselves establish formal explanatory faithfulness or complete interpretability.

Calculating motion features frame by frame and organizing them into a 3D matrix is a typical CNN-based solution for human action recognition (HAR). With the widespread use of consumer electronics, reducing computational costs and enabling efficient edge-side action recognition have become a research hotspot. In this paper, we extract action key frames via a well-designed algorithm to reduce computational overhead, so that the proposed method can be deployed on mobile electronic devices. Then we construct local and global motion features from these key frames and feed them into a cascade neural network for action recognition. The primary contributions include three aspects. First, the strategic adoption of key frames is introduced to greatly reduce the number of input parameters. The number of key frames can be adjusted to adapt to the temporal scales of different actions. Second, multiple origin points are adopted to construct motion matrices with larger dimensions than those constructed using a single origin point. Thus, deeper neural networks can be employed to achieve higher recognition accuracy. Third, a cascade neural network is proposed for action prediction, which leverages global and local information to achieve better efficiency and accuracy. Experimental results on UTKinect-Action3D, Florence-3D and our self-built HanYue-3D datasets demonstrate that our method achieves accuracy and efficiency competitive with state-of-the-art (SOTA) approaches. Moreover, the flexibility of the proposed method enables users to readily balance effectiveness and efficiency, making it well-suited for resource-constrained mobile devices.

Multimodal sentiment analysis, due to its comprehensive ability to capture user sentiment, has significant application value in areas such as public opinion analysis. Existing research, however, falls short in several aspects: (1) it inadequately models the global structural information of the image, and (2) it overlooks the potential noise impact within each modality. These limitations hinder the accurate extraction of sentiment cues from individual modalities. To address these issues, we propose a Frequency Domain Decoupling and Semantic Filtering Network for Multimodal Sentiment Analysis. This network primarily integrates frequency-domain decoupling with semantic filtering to process high- and low-frequency image information separately, thereby enhancing model performance. Specifically, we designed a Dynamic Frequency Domain Decoupling Module that applies discrete wavelet transforms for differentiated image processing. This module, combined with a Dual-Domain Loss Function, constrains consistency between the text semantic space and the frequency distribution of the optimized image features, preventing sentiment information loss from excessive filtering. The module also incorporates two key components: a Global Semantic Sentiment Component (GSSC) and a High-Frequency Filtering Component (HFFC). In the GSSC component, we designed a Hybrid Mamba to leverage text in capturing global semantic information from low-frequency image data. Furthermore, our HFFC component generates a dynamic weight matrix guided by text, enabling quantitative noise suppression. Additionally, we developed a Multi-Grained Semantic Purification Module to filter noise at the word, phrase, and sentence levels. Experimental findings from publicly accessible datasets indicate that our proposed model achieves competitive performance compared with existing methods on multimodal sentiment analysis under the adopted experimental settings and sarcasm detection tasks, validating the effectiveness of our noise-suppression method in cross-modal sentiment analysis. A key limitation of the model is its use of DWT: downsampling-related resolution loss in low-frequency subbands and independent subband partitioning compromise the capture of large-scale global structural correlations and local-global feature modelling, which advanced transform techniques can alleviate.

The research introduces a credible decision-support tool for dealing with uncertainty for supplier selection in the aerated concrete industry. The developed framework includes criteria selection, determination of expert and criterion weights, and alternative ranking within a hyperbolic fuzzy environment. Criteria selection is done via the Laplacian score. Expert weights are methodically determined via entropy measure. Criteria are weighted using the LOPCOW and RANCOM methods, and alternatives are ranked using the hyperbolic extension of the DEPART method. The model is employed to solve a circular supplier selection problem in the aerated concrete industry. Comprehensive sensitivity and comparison checks are conducted.

This study proposes an integrated AI-driven quantum spherical fuzzy decision framework for multi-criteria evaluation under uncertainty. The model combines AI-based decision-maker weighting, quantum spherical fuzzy Bayesian networks for criteria weighting, and WASPAS for ranking. Decision makers are clustered using k-means to reduce bias, while interdependencies and uncertainty are captured probabilistically. The framework is applied to assess renewable energy investment competencies in G7 economies. Results highlight the importance of customer-centric expectations and real-time financial performance. The model offers a flexible, robust, and scalable approach, improving reliability, transparency, and decision quality in complex environments.

Multi-Criteria Decision-Making (MCDM) is a vital tool for handling complex decision problems under uncertainty. Fuzzy set theory and its extensions, such as Single-Valued Neutrosophic Sets (SVNS), enhance decision-making by addressing ambiguity, indeterminacy, and partial information. Among MCDM techniques, TOPSIS has gained prominence for ranking alternatives, and its integration with some MCDM approaches has been widely applied. However, no prior study has combined the Analytic Hierarchy Process (AHP) with Neutrosophic-TOPSIS. This study proposes a hybrid AHP-SVNS-TOPSIS framework, where AHP determines the weights of evaluation criteria, and Neutrosophic-TOPSIS ranks alternatives under uncertain conditions. The model is applied to assess hydropower plant (HPP) performance, considering impacts from urbanization, climate change, and machine failures. The generator’s efficiency is the most important parameter, based on the results of the suggested model. Existing research validates the outcomes of the suggested model.

The purpose of this study is to evaluate the significant dimensions of customer-centric innovation in renewable energy projects. We construct a novel fuzzy decision-making model to address this objective. In the first stage, significant indicators are identified using balanced scorecard-based determinants and weighted through the multi-step wise weight assessment ratio analysis (M-SWARA) method integrated with quantum spherical fuzzy sets. In the second stage, the energy efficiency of renewable energy alternatives is assessed for customer-centric innovation performance via technique for order preference by similarity to ideal solution (TOPSIS). We offer priority strategies for green energy investors to enhance customer-centric innovation with more reasonable costs. Methodologically, the proposed model provides important advantages by effectively handling uncertainty through quantum spherical fuzzy structures, incorporating the golden ratio in degree calculations, and capturing interdependencies among criteria through the improved M-SWARA approach. The findings reveal that customization is the most critical indicator for improving customer-centric innovation performance, followed by efficiency, while optimization and innovation have relatively lower importance. The ranking results indicate that solar energy projects demonstrate the highest performance in managing customer-centric innovation, followed by wind and geothermal energy alternatives.

Taking into account the irrational elements and regret aversion of decision makers (DMs) during the decision-making process, regret theory (RT) and the TODIM methods have been integrated into a decision-making framework to develop an enhanced multi-attribute decision-making (MADM) method (PDHL-RT-TODIM) within probabilistic double hierarchy linguistic (PDHL) environment. Specifically, extending the perceived utility function in RT to determine the regret and joy values of the overall advantage flow of alternatives calculated by TODIM method in PDHL environment. Then, a correlation coefficient (CC) and standard deviation (SD) integral (CCSD) method was created using the probabilistic double hierarchy linguistic set (PDHLTS) distance metric and PDHL weight arithmetic operator to establish the objective weights of attributes. Additionally, the effectiveness of this proposed method was illustrated through numerical examples for information system investment project selection, and its stability, efficiency, and benefits were further confirmed through sensitivity analysis and comparisons with existing methods.

Quality Function Deployment (QFD) is a technique used to collect Customer Requirements (CRs) for the product to be designed before the start of the manufacturing processes, and also used to determine whether CRs will be met with correlated or uncorrelated Design Requirements (DRs). In QFD technique, customers tend to explain their expectations from the product by using linguistic expressions instead of using exact numbers. Vagueness and impreciseness in linguistic expressions can be captured perfectly using fuzzy set theory. Pythagorean fuzzy (PF) sets as one of the extensions of ordinary fuzzy sets offer the decision maker a larger membership and non-membership assignment region than ordinary intuitionistic fuzzy sets. In this paper, customer requirements in QFD analysis are prioritized by Best-Worst Method (BWM), which has become a very popular optimization-based weighting method in recent years. In the proposed BWM and QFD methodology, interval-valued Pythagorean fuzzy (IVPF) sets are used for the first time in order to handle the uncertainties in the linguistic judgments. In the application, the two-phase IVPF methodology is proposed to a real life e-scooter design problem addressing 12 customer & 12 design requirements. The proposed PF methodology could determine the weights of customer requirements, and identify which of the design requirements is stronger, and make a competitive analysis to reveal the position of our company in the market under fuzzy environment. Besides, the sensitivity and comparative analyses have demonstrated the dominance of our company over the other competitors.