International Journal of Computational Intelligence Research

Abstract With the rapid development of the civil aviation industry, the demand for secure sharing of civil aviation data is increasing. As a global platform for secure sharing of civil aviation data, the security of the System Wide Information Management (SWIM) system is of great concern. SWIM adopts a service-oriented architecture and realizes the interaction of civil aviation data through a publish-subscribe model. To protect the service privacy while enabling subscribers to subscribe to the service quickly and securely, this paper proposes an efficient Circular Shift and Coalesce-Cuckoo Filter (CSC-CF)-based service Keyword Search (CCKS) scheme assisted by blockchain. This scheme uses the Symmetric-key Hidden Vector Encryption (SHVE) algorithm to encrypt and match service indexes and trapdoors to protect service privacy; the CSC-CF structure is applied to keyword search, which can effectively improve the efficiency of SWIM user subscription service. To improve search accuracy and space utilization, we propose the improved CCKS (ICCKS) scheme by optimizing the query algorithm of CSC-CF and setting a threshold for the number of keyword query failures. ICCKS improves search accuracy by 5–20% compared to CCKS when the filter’s space utilization is between 60 and 90%. Additionally, the scheme stores service topic indexes and registry on the blockchain and implements a smart contract to match indexes and subscription trapdoors, ensuring the integrity and trustworthiness of service topics and registry. Security analysis and experimental simulations demonstrate that the scheme is effective and secure in the SWIM system.

Abstract A critical aspect of simulation models used in cost-effectiveness analysis lies in accurately representing the natural history of diseases, requiring parameters such as probabilities and disease burden rates. While most of these parameters can be sourced from scientific literature, they often require calibration to align with the model’s expected outcomes. Traditional optimization methods can be time-consuming and computationally expensive, as they often rely on simplistic heuristics that may not ensure feasible solutions. In this study, we explore using Bayesian optimization to enhance the calibration process by leveraging domain-specific knowledge and exploiting structural properties within the solution space. Specifically, we investigate the impact of additive kernel decomposition and a stepwise approach, which capitalizes on the sequential block structure inherent in simulation models. This approach breaks down large optimization problems into smaller ones without compromising solution quality. In some instances, parameters obtained using this methodology may exhibit less error than those derived from naive calibration techniques. We compare this approach with two state-of-the-art high-dimensional Bayesian Optimization techniques: SAASBO and BAxUS. Our findings demonstrate that Bayesian optimization significantly enhances the calibration process, resulting in faster convergence and improved solutions, particularly for larger simulation models. This improvement is most pronounced when combined with a stepwise calibration methodology.

Abstract This paper presents FORSEER (Forecasting by Selective Ensemble Estimation and Reconstruction), a novel methodology designed to address temperature forecasting under the challenges inherent to climate change. FORSEER integrates decomposition, forecasting, and ensemble methods within a modular framework. This methodology decomposes the time series into trend, seasonal, and residual components. Subsequently, multiple optimized forecast models are applied to each component. These component models are then carefully weighted and combined through an ensemble process to generate a final robust forecast. Experimental results demonstrate that FORSEER is an efficient computational forecasting methodology for complex climate time series. Furthermore, we show that FORSEER has an equivalent forecasting performance to the M4 competition champion SMYL method for temperature series. Besides, the proposed methodology has less computational complexity than SMYL, making it a more accessible and scalable option. FORSEER's modular architecture also allows flexibility when substituting techniques depending on the context of the problem, facilitating the parallel execution of independent tasks and resulting in a strategy adaptable to multiple contexts.

Abstract This study endeavors to enhance the macro-ergonomics of pharmaceutical supply chains by introducing an innovative hybrid AI methodology, incorporating fuzzy data envelopment analysis (FDEA). A comprehensive case study is conducted to evaluate the efficiency of the pharmaceutical supply chain, focusing on macro-ergonomic work system assessment. This evaluation aims to identify design flaws contributing to communication delays between physicians and patients. The proposed integrated approach utilizes a hybrid AI framework, specifically FDEA, to accurately measure macro-ergonomic influences on the healthcare supply chain under uncertain conditions. The case study involves a prominent urban outpatient medical facility with 20 clinics, selecting 20 Decision-Making Units for a holistic perspective. Results uncover factors causing delays, emphasizing weak or absent feedback structures as critical elements affecting the healthcare supply chain’s effectiveness. In conclusion, the study recommends modifications to optimize the pharmaceutical supply chain, enhancing overall healthcare efficiency. The findings provide valuable insights for healthcare management, underscoring the crucial role of advanced AI methodologies in addressing complex challenges within healthcare supply chains.