This study proposes an integrated decision support framework for evaluating hospital service quality under uncertainty using Interval-Valued Pythagorean Fuzzy (IVPF) information. It combines an improved entropy measure for expert weighting, WENSLO-RANCOM method for criteria weighting, and an IVPF extension of CRADIS method for hospital ranking. The framework is applied to five hospitals in Patna, India, using four experts and eighteen criteria. Public transport, ambulance services, and medication expertise emerge as the most important factors. Hospital-2 ranks first overall. Sensitivity and comparative analyses confirm the robustness of the results, while the framework also supports resource allocation and service improvement planning.
This study proposes a Modified Fuzzy Extended Pivot Pairwise Relative Criteria Importance Assessment (MF PIPRECIA-E) method for determining criteria weights under uncertainty. The proposed extension enables the upper bounds of fuzzy numbers obtained during calculation to remain below, equal to, or slightly above 1. In addition, this study also critically examines the procedure of direct and inverse assignment of the relative importance of the criteria, integrated in the PIPRECIA-E method, with the aim of pointing out some important characteristics of this method, which have not been sufficiently explored in previous research. The proposed approach also addresses consistency assessment and group decision-making. Therefore, the main contribution of this study is development of a modified fuzzy PIPRECIA-E method that provides a more consistent procedure for determining weights of the criteria under uncertainty. Accordingly, proposed approach incorporates both direct and inverse criteria importance assessment, extending the applicability of the PIPRECIA-E method for solving various multiple-criteria decision-making (MCDM) problems.
Forensic handwriting identification plays a pivotal role in criminal investigations and legal proceedings, requiring accurate and reliable techniques for analyzing handwriting samples. Convolutional Neural Networks (CNNs) are effective at feature extraction and classification for handwriting analysis, but their performance is highly sensitive to the choice of architectural hyperparameters, and manually tuned CNNs are prone to overfitting on forensic handwriting data. This study integrates the Chicken Swarm Optimization (CSO) algorithm with a CNN classifier (CSO-CNN) to automatically search the number of convolutional layers, the number and size of filters, and the batch size that minimize overfitting and maximize recognition accuracy. Handwritten samples were collected from staff and students of Ajayi Crowther University, Oyo, Nigeria, and organized into three variants (Original, Disguised, and Forged) with each variant split into training and test sets (72% and 28%, respectively) using a random-sampling hold-out procedure. CSO searched 30 candidate CNN configurations over the number of convolutional layers (1–3), the number of filters, the filter size, and the batch size, using recognition rate as the fitness function; the best-performing configuration used a single convolutional layer with 128 filters of size 3×3 and a batch size of 256. The resulting CSO-CNN model was compared against a standard, non-optimized CNN using accuracy, sensitivity, specificity, precision, false positive rate, and recognition time. CSO-CNN outperformed the standard CNN on every dataset variant: on the original dataset, accuracy improved from 82.14% to 86.43%; on the Disguised dataset, from 85.00% to 87.86%; and on the Forged dataset, from 83.57% to 89.29%, while recognition time was also reduced in all three cases. These results indicate that CSO-based hyperparameter search can meaningfully improve CNN-based forensic handwriting identification without requiring architectural redesign. As the evaluation reported here is based on a single hold-out split, repeated cross-validation and testing on independently collected datasets are recommended as a next step to confirm the statistical robustness and generalizability of these gains.
Against the risks of privacy leakage and quantum computing attacks in smart logistics data trading, this paper proposes a post-quantum privacy-preserving data trading scheme built on consortium blockchain and federated learning. Three orthogonal core innovations are elaborated as follows: (1) A five-layer decoupled smart logistics data trading platform architecture is constructed. Different from existing single-layer blockchain trading frameworks, this work hierarchically divides logistics data workflows into perception, generation, transmission, trading platform and application layers, and introduces a blockchain oracle module to realize consistent synchronization between on-chain transaction records and off-chain IPFS raw cipher storage, solving the cross-layer data inconsistency defect of prior monolithic architectures. (2) A quantitative model parameter quality evaluation algorithm based on cosine similarity, together with a dual-weight dynamic incentive mechanism, is designed. Most existing federated data trading studies lack standardized quantitative quality metrics and static reward allocation rules; our method extracts gradient feature vectors from local FL models, calculates similarity against benchmark parameters to grade data quality, and distributes transaction revenue weighted by both model quality and service participation time to motivate sustained user contribution. (3) A complete lattice-based cryptographic suite including homomorphic proxy re-encryption and aggregate lattice signature is deployed for secure data circulation. Traditional pairing-based privacy schemes are vulnerable to quantum cracking, while standalone lattice encryption works cannot support dynamic cross-buyer ciphertext conversion; our lattice primitive supports homomorphic aggregation and one-time re-encryption transfer, realizing anti-quantum, flexible authorization of federated model trading ciphertexts. Theoretical security proofs and multi-dimensional simulation experiments verify that the proposed scheme achieves post-quantum privacy protection, accurate data quality quantification and high-efficiency dynamic logistics data transactions.
Primary healthcare systems, particularly in low and middle income countries, are caused by insufficient data, constraints on resources, and shifts in the demand for services. The focus of this paper is on a sys- tematic literature review to understand the impact of Generative Adversarial Networks (GANs) in the area of budget and planning in primary healthcare systems. Peer-reviewed literature was used for the analysis, and 35 studies published in the period of 2017 to 2025 were selected and reviewed based on the inclusion criteria of relevance to the area of forecasting, simulation, and decision support in healthcare data. Some of the key variations of GANs that are discussed in the paper involve the use of Conditional GANs, Condi- tional Tabular GANs (CTGANs) and other recurrent or temporal based GANs, which are commonly used for imaging, and electronic health record and time series data in healthcare. The generated findings suggest that, in resource-limited healthcare contexts, the use of GAN- based synthetic data generation improves the flexibility and consistency of predictive models, facilitates resource planning through scenario-based simu- lation, and allows for the controlled sharing of data across collaborating institutions. However, the review findings point to several gaps that include the absence of operational use in primary healthcare budgeting, difficulties in interpretability and governance of models, and no agreed-upon criteria for evaluating the trade-off between the reliability of synthetic data and associated privacy concerns. Therefore, the review demonstrates the possibilities and constraints of GAN-based methods and delineates paths for subsequent research to foster the integration of these methods into primary healthcare budgeting processes.
