Abstract Accurately predicting the hysteretic response of irregular reinforced concrete (RC) shear walls is essential for seismic performance assessment. However, spatial variability in material properties and geometric complexity introduce significant stochasticity, making conventional stochastic finite element (SFEM) methods computationally inefficient due to difficulties in random field assignment and the high cost of nonlinear analyses. This study proposes an efficient deep learning framework that uses a convolutional neural network-Kolmogorov–Arnold network (CNN-KAN) model to predict stochastic hysteresis responses of irregular shear walls with manifold random fields. The random field is constructed using the isometric mapping (isomap) method to accurately represent the spatial variability of material properties in SFEM. Then, hysteresis curves obtained from SFEM analysis are used to train the CNN-KAN model, the CNN-long short-term memory (LSTM) model, and the CNN-multilayer perceptron (MLP) model. While all three models achieve high prediction accuracy, only CNN-KAN successfully preserves the stochastic diversity of structural responses. The traditional CNN-MLP and CNN-LSTM models suffer from an averaging effect, failing to capture the inherent randomness. The trained CNN-KAN model is then used as a surrogate model for Monte Carlo simulation in large-scale sample analysis. The results demonstrated that it can efficiently generate hysteresis curves and energy dissipation distributions to study the influence of spatial correlation on structure stochastic responses. The proposed model significantly enhances computational efficiency, reducing the computing time to only 1/300 of the conventional SFEM analysis. Further, the proposed framework enables efficient uncertainty quantification and is extensible to other complex structural systems involving spatial randomness.
A chitosan hydrogel with tannic acid was obtained by introducing carboxymethylcellulose, which formed a polyelectrolyte complex with the cationic polysaccharide. The combination of electrostatic interactions and hydrogen bonds of the polyphenol with both polysaccharides resulted in dual crosslinking, which led to an almost thousand-fold increase in the mechanical strength of the hydrogel. Furthermore, tannic acid retained pronounced antimicrobial activity, which makes the developed hydrogel promising for biomedical applications such as wound dressings.
High-temperature (HT) stress threatens global rice production, yet the comparative efficacy and synergistic potential of agronomic adaptation strategies remain poorly quantified. Here, we integrated 4044 observations from 106 publications across 11 countries, evaluating the individual effects of cultivar replacement, exogenous application of plant growth regulators (PGRs), fertilization optimization (CF), and sowing-date adjustment (ASD) via multilevel models, and separately conducted a 1980-2024 spatiotemporal analysis across six regions in the Yangtze River Basin. Globally, HT reduced grain yield by 42.3% (lnRR = -0.55; 95% CI: -0.73 to -0.37), driven by a 16-26% decline in seed-setting rate (SSR) depending on type, with field trials showing larger effect than pots (e.g., hybrid rice: -9.98% vs. -1.22% for yield). All four strategies alleviated yield losses, with CF (+48%, lnRR = 0.39; 0.16-0.62) and cultivar replacement (+20%, lnRR = 0.18; 0.12-0.24) showing the strongest effects, whereas the efficacy of exogenous plant growth regulators was unstable (CI crossed zero). Modern hybrid cultivars improved heat tolerance; optimized nitrogen inputs buffered yield penalties by maintaining spikelets and seed-set, whereas excessive nitrogen reversed benefits. In contrast, the Yangtze River Basin reveald that ASD, once an important heat-avoidance measure, has seen its safe window narrowed over the past four decades by warming and anomalies, rendering this strategy increasingly ineffective. Consequently, while global results confirm standalone efficacy, the Yangtze case implies integrated portfolios may be needed. This study provides a robust data-driven framework for informing site- and cultivar-specific adaptation decisions under climate warming.
Accurate battery state-of-health (SOH) estimation in practical battery management systems remains challenging because charging observations are often incomplete, degradation trajectories are heterogeneous, and computational resources are limited. This study proposes a Fragmentation-Aware Masked Multi-Task Network (FA-M2TN) that jointly performs SOH estimation, Voltage Dispersion Rate (VDR) prediction, and masked charging-profile reconstruction within a compact BiLSTM–attention architecture. Evaluated on five open-access lithium-ion battery datasets under a dataset-stratified cell-level split, FA-M2TN achieved an SOH RMSE of 0.0895, MAE of 0.0463, MAPE of 25.73%, and R2 of 0.944, with only 630.1 K trainable parameters and the lowest MAE among the evaluated models. Ablation results indicated that masked reconstruction moderated the multi-task trade-off under joint SOH–VDR learning, reducing SOH RMSE and MAE by 18.7% and 14.0%, respectively, compared with the No-Reconstruction variant. The model also maintained relatively stable performance under high stochastic data-loss ratios and retained low prediction error in the end-of-life regime. Post-hoc analyses further supported the association between VDR and degradation-related charging-profile evolution and the health-state organization of the learned latent space. These results indicate that FA-M2TN provides a compact and fragmentation-aware framework for battery health diagnostics under incomplete charging observations, balancing predictive accuracy, multi-output diagnostic functionality, and computational efficiency.
The Internet of Things (IoT) has become integral to modern society, yet ensuring secure, trustworthy, and accountable communication remains a critical challenge. Non-repudiation is a foundational security service that provides verifiable evidence of origin, receipt, integrity, and action, making it essential for trust establishment, auditability, dispute resolution, and forensic analysis in IoT environments. However, existing reviews have primarily focused on broader IoT security requirements, such as confidentiality, integrity, authentication, privacy, and access control, with limited systematic attention given to non-repudiation mechanisms. This paper presents a systematic literature review of non-repudiation mechanisms in IoT-based systems published between 2015 and 2026. Following PRISMA guidelines and applying rigorous inclusion and exclusion criteria, we identified 41 relevant studies. The reviewed schemes are classified into three main categories: digital signature-based schemes, blockchain-based schemes, and hybrid schemes. Digital signature-based schemes are further divided into classical signature-based mechanisms, including PKI-based, identity-based, certificateless/certificateless aggregate, and signcryption-based schemes, and post-quantum signature-based schemes. Blockchain-based schemes rely on ledger immutability, distributed consensus, and smart-contract execution to preserve tamper-evident evidence, while hybrid schemes combine digital signatures with blockchain-based evidence preservation, including blockchain with classical signature schemes and blockchain with post-quantum signature schemes. The review analyses application domains, security properties, performance evaluation practices, and key trade-offs, including scalability, resource constraints, communication and storage overhead, latency, gas cost, and centralised trust dependencies. The findings show a growing shift from standalone signer-binding mechanisms towards hybrid, auditable, and quantum-resilient evidence-preservation architectures. Future research should prioritise lightweight, formally verified, privacy-preserving, and post-quantum-resilient non-repudiation mechanisms tailored to the resource constraints, trust assumptions, and domain-specific requirements of modern IoT ecosystems.
