BURA Collection:

Policy Brief: Delivering accessible AI for everyone in public services

2026-08-03T00:00:00Z

Title: Policy Brief: Delivering accessible AI for everyone in public services Authors: Spyridonis, Fotios Abstract: Policy Context: The UK Government’s AI Opportunities Action Plan aims to accelerate AI adoption across public services to improve productivity and service delivery. Public bodies also have legal responsibilities to provide accessible digital services. As AI increasingly shapes how citizens access public services, current policy provides little guidance on ensuring AI-enabled services remain accessible and inclusive. Key Findings: AI-enabled accessibility is most effective when it incorporates contextual human knowledge and recognises diverse user needs. Policy Advice: As AI becomes increasingly embedded within public services, accessibility should be recognised as a core principle of AI governance. Accessibility guidance for AI-enabled public services should be updated, procurement and evaluation practices should be strengthened, and human-informed approaches to AI-enabled accessibility should be supported.

Multi-Objective Optimization Framework for Reliable Safety Stock Decisions With Intermittent Demand Forecasting

2026-08-21T00:00:00Z

Title: Multi-Objective Optimization Framework for Reliable Safety Stock Decisions With Intermittent Demand Forecasting Authors: Zhang, Jia; Zhang, Yake; Mao, Wentao; Luo, Tiejun; Wang, Zidong Abstract: Safety stock (SS), encompassing reorder point (RP) and maximum stock (MS), is designed to minimize inventory cost while maintaining maintenance safety for manufacturing enterprises. In recent years, advanced computational techniques have been applied to forecast spare parts demand (SPD), enabling dynamic updates to SS settings. However, existing methods have often failed to produce reliable SS decisions when confronted with significant demand volatility and random failures. The reliability of SS decisions remains an open problem and is still in its early stages of investigation. To address this issue, in this paper, a reliable SS model with uncertainty evaluation of SPD is proposed in this paper. Initially, a basic setting of RP and MS is derived on a three-level warehousing architecture by simultaneously minimizing excess inventory cost and shortage cost. Building upon this foundation, a novel SS reliability metric is introduced by integrating static information (inventory coverage and emergency replenishment rate) with dynamic information (decision compactness ratio). To enhance the decision compactness ratio, a multivariate intermittent time series forecasting method based on an improved graph neural network is developed. Accurate forecasting with a confidence interval is achieved through bootstrap resampling. Finally, a reliable RP and MS configuration is obtained by incorporating the forecasting interval into the basic stock setting. Validation is conducted using an actual spare parts dataset from a large rail transit manufacturing enterprise in China. The experimental results demonstrate that the proposed model not only achieves higher SPD prediction accuracy but also improves inventory turnover and coverage while significantly enhancing reliability.

Sparsity-Aware Sensor Selection for Privacy-Preserving Zonotopic Fusion Filtering in Cloud-Based Vehicle Tracking Systems

2026-08-25T00:00:00Z

Title: Sparsity-Aware Sensor Selection for Privacy-Preserving Zonotopic Fusion Filtering in Cloud-Based Vehicle Tracking Systems Authors: Zhu, Kaiqun; Wang, Zidong; Zheng, Xinhu; Li, Zhenning; Li, Keqiang Abstract: This article investigates the zonotopic filtering problem for cloud-based vehicle tracking systems under joint privacy and communication bandwidth constraints. Cloud-side tracking platforms improve vehicle state estimation accuracy by fusing multisource measurements collected from roadside nodes. However, during roadside-to-cloud data transmission, the system is confronted with coupled challenges arising from privacy leakage risks and the communication burden induced by concurrent data uploads from large-scale sensor deployments. To address these challenges, a zonotopic fusion filtering framework incorporating privacy-preserving mechanisms and sparsity-aware sensor selection strategies is proposed to achieve a balanced tradeoff among privacy protection, communication efficiency, and estimation accuracy. First, a novel secret-sharing-based zonotopic fusion filtering method is developed, which embeds a dynamic-encoding-based secret sharing mechanism into the multisensor fusion process to protect both transmitted data and estimation results. Furthermore, to reduce redundant communications, a sparsity-promoting sensor selection scheme is constructed by introducing a sparsity penalty into the filter parameter optimization problem, enabling transmission only from sensors that effectively contribute to the current estimation accuracy. The resulting optimization problem is solved using convex relaxation and the alternating direction method of multipliers, yielding analytical update expressions for the filter parameters. In addition, the boundedness of the vehicle state estimation error is rigorously analyzed, and a sufficient condition ensuring that the estimation error remains bounded is established. Finally, simulation experiments demonstrate the effectiveness of the proposed algorithm in achieving accurate, communication-efficient, and privacy-preserving state estimation.

Nonfragile Distributed Fusion Filtering for Time-Varying Systems With Sensor Saturations: A Decode-and-Forward Relay-Aided Approach

2026-08-25T00:00:00Z

Title: Nonfragile Distributed Fusion Filtering for Time-Varying Systems With Sensor Saturations: A Decode-and-Forward Relay-Aided Approach Authors: Meng, Xueyang; Wang, Zidong; Wang, Fan; Chen, Yun Abstract: In this article, the problem of distributed fusion filtering (DFF) has been studied for discrete-time, time-varying systems affected by sensor saturations, packet losses, and stochastic gain perturbations. The transmission process between sensors and remote filters is carried out via relay channels subject to packet losses. To enhance communication quality and ensure transmission reliability, a decode-and-forward (DaF) relay-aided mechanism is introduced. Random perturbations in the local filter gains are incorporated to model potential implementation uncertainties and parameter fluctuations. The objective of this work is to design an appropriate distributed fusion filter that ensures specific performance constraints are satisfied for both local and global filtering error systems. For each sensor node, a sufficient condition, derived from stochastic analysis theory, is first established to guarantee the existence of a desired local H∞ filter. The associated filter gains are then computed by solving a set of coupled difference equations. Building on these local designs, a distributed fusion filter is constructed, and the corresponding fusion parameters are determined through the solution of a convex optimization problem. Finally, the effectiveness of the proposed fusion filtering framework is demonstrated through a numerical example.