Search Results (995)

Cloud storage continues to experience recurring provider-side breaches, raising concerns about the confidentiality and recoverability of user data. This study addresses this challenge by introducing an Artificial Intelligence (AI)-driven hybrid architecture for secure, reconstruction-resistant multi-cloud storage. The system applies telemetry-guided fragmentation, where fragment sizes are dynamically predicted from real-time bandwidth, latency, memory availability and disk I/O, eliminating the predictability of fixed-size fragmentation. All payloads are compressed, encrypted with AES-128 and dispersed across independent cloud providers, while two encrypted fragments are retained within a VeraCrypt-protected local vault to enforce a distributed trust threshold that prevents cloud-only reconstruction. Synthetic telemetry was first used to evaluate model feasibility and scalability, followed by hybrid telemetry integrating real Microsoft system traces and Cisco network metrics to validate generalization under realistic variability. Across all evaluations, XGBoost and Random Forest achieved the highest predictive accuracy, while Neural Network and Linear Regression models provided moderate performance. Security validation confirmed that partial-access and cloud-only attack scenarios cannot yield reconstruction without the local vault fragments and the encryption key. These findings demonstrate that telemetry-driven adaptive fragmentation enhances predictive reliability and establishes a resilient, zero-trust framework for secure multi-cloud storage. Full article

Drinking-water treatment systems must effectively control natural organic matter (NOM), a major precursor of regulated disinfection by-products (DBPs). Specific ultraviolet absorbance (SUVA) is widely used as an operational surrogate for NOM aromaticity and hydrophobicity; however, ozonation and subsequent filtration can disrupt the linear relationship between SUVA and trihalomethane formation potential (THMFP). This study evaluates whether SUVA can reliably predict THMFP under two ozonation configurations frequently applied in drinking-water treatment: pre-ozonation prior to coagulation–filtration and final ozonation following filtration. Experimental data were analyzed using conventional linear regression and artificial neural network (ANN) models, with SUVA employed as the sole predictor variable. Across all treatment configurations, reductions in SUVA were consistently more pronounced than corresponding decreases in THMFP, indicating a decoupling between chromophoric loss and chlorine-reactive precursor dynamics under ozonation-dominated conditions. Linear regression models exhibited only moderate predictive performance (R² = 0.63–0.76), reflecting the limitations of proportional surrogate-based approaches when NOM undergoes oxidative and adsorptive transformation. In contrast, single-parameter ANN models captured the nonlinear SUVA–THMFP relationship with substantially higher accuracy across both pre- and final-ozonation regimes (R² = 0.88–0.99), successfully resolving process-dependent patterns embedded within optically compressed SUVA signals. These findings demonstrate that, although SUVA alone cannot linearly represent the multistep transformation of NOM during ozonation and adsorption, it retains process-relevant structure information on DBP precursor reactivity that can be effectively extracted using nonlinear modelling. The results highlight the potential of integrating ANN-driven tools into advanced monitoring and DBP-control strategies in modern drinking-water treatment systems. Full article

Artificial reefs are an important tool for marine ecological restoration and fishery resource proliferation, and are widely used around the world. Among them, Japan, the United States, China, South Korea, Australia, and the Mediterranean coastal countries have particularly invested in scientific research and practice in this field, and the reefs’ material selection, structural performance, and ecological benefits have attracted much attention. The purpose of this paper is to summarize the preparation methods, characterization methods (such as microstructure analysis and mechanical tests) and mechanical properties (such as compressive strength and durability) of new concrete materials (steel slag-blast furnace slag concrete, oyster shell concrete, sulfoaluminate cement concrete, recycled brick concrete, silica fume concrete, and banana peel filler concrete) that artificial reefs and ceramic artificial reefs developed in recent years, and to explore the resource utilization potential of different waste materials. At the same time, the biostatistical methods (such as species abundance and community diversity) of wood, shipwreck, steel, rock, waste tire, and ordinary concrete artificial reefs and their effects on the marine environment were compared and analyzed. In addition, the potential impact of artificial reef deployment on local fishermen’s income was also assessed. It is found that the use of steel slag, blast furnace slag, sulfoaluminate cement, and silica fume instead of traditional Portland cement can better improve the mechanical properties of concrete artificial reefs (compressive strength can be increased by up to 20%) and reduce the surface pH to neutral, which is more conducive to the adhesion and growth of marine organisms. The compressive strength of oyster shell concrete and banana peel filler concrete artificial reef is not as good as that of traditional Portland cement concrete artificial reef, but it still avoids the waste of a large amount of solid waste resources, provides necessary nutritional support for aquatic organisms, and also improves its chemical erosion resistance. The deployment of artificial reefs of timber, wrecks, steel, rock, waste tires, and ordinary concrete has significantly increased the species richness and biomass in the adjacent waters and effectively promoted the development of fisheries. Cases show that artificial reefs can significantly increase fishermen’s income (such as an increase of about EUR 13 in the value of a unit effort in a certain area), but the long-term benefits depend on effective supervision and community co-management mechanisms. This paper provides a scientific basis for the research and development of artificial reef materials and the optimization of ecological benefits, and promotes the sustainable development of marine ecological restoration technology and fishery economy. Full article

In order to achieve better accuracy, modern models have become increasingly large, leading to an exponential increase in computational load, making it challenging to apply them to edge computing. Binary neural networks (BNNs) are models that quantize the filter weights and activations to 1-bit. These models are highly suitable for small chips like advanced RISC machines (ARMs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs) and other edge computing devices. To design a model that is more friendly to edge computing devices, it is crucial to reduce the floating-point operations (FLOPs). Batch normalization (BN) is an essential tool for binary neural networks; however, when convolution layers are quantized to 1-bit, the floating-point computation cost of BN layers becomes significantly high. This paper aims to reduce the floating-point operations by removing the BN layers from the model and introducing the scaled weight standardization convolution (WS-Conv) method to avoid the significant accuracy drop caused by the absence of BN layers, and to enhance the model performance through a series of optimizations, adaptive gradient clipping (AGC) and knowledge distillation (KD). Specifically, our model maintains a competitive computational cost and accuracy, even without BN layers. Furthermore, by incorporating a series of training methods, the model’s accuracy on CIFAR-100 is 0.6% higher than the baseline model, fractional activation BNN (FracBNN), while the total computational load is only 46% of the baseline model. With unchanged binary operations (BOPs), the FLOPs are reduced to nearly zero, making it more suitable for embedded platforms like FPGAs or other edge computers. Full article

Real-time visual inference on resource-constrained hardware remains a core challenge for edge computing and embedded artificial intelligence systems. Recent deep learning architectures, particularly Vision Transformers (ViTs) and Detection Transformers (DETRs), achieve high detection accuracy but impose substantial computational and memory demands that limit their deployment on low-power edge platforms such as NVIDIA Jetson and Raspberry Pi devices. This paper presents a systematic review of model compression and optimization strategies—specifically quantization, pruning, and knowledge distillation—applied to lightweight object detection architectures for edge deployment. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, peer-reviewed studies were analyzed from Scopus, IEEE Xplore, and ScienceDirect to examine the evolution of efficient detectors from convolutional neural networks to transformer-based models. The synthesis highlights a growing focus on real-time transformer variants, including Real-Time DETR (RT-DETR) and low-bit quantized approaches such as Q-DETR, alongside optimized YOLO-based architectures. While quantization enables substantial theoretical acceleration (e.g., up to 16× operation reduction), aggressive low-bit precision introduces accuracy degradation, particularly in transformer attention mechanisms, highlighting a critical efficiency-accuracy tradeoff. The review further shows that Quantization-Aware Training (QAT) consistently outperforms Post-Training Quantization (PTQ) in preserving performance under low-precision constraints. Finally, this review identifies critical open research challenges, emphasizing the efficiency–accuracy tradeoff and the high computational demands imposed by Transformer architectures. Future directions are proposed, including hardware-aware optimization, robustness to imbalanced datasets, and multimodal sensing integration, to ensure reliable real-time inference in practical agricultural edge computing environments. Full article

Red mud (RM), an industrial byproduct generated during bauxite refining, has accumulated to more than 5 billion tons worldwide, posing serious environmental challenges. In response, substantial research over recent decades has focused on the sustainable utilization of RM, particularly in the field of construction materials. This review first summarizes the generation process and chemical composition of RM, and then systematically examines its potential applications in the production of artificial aggregates, partial replacement of cementitious materials, and synthesis of geopolymers. Existing studies demonstrate that RM exhibits considerable potential in construction applications: when used as an aggregate, it can reduce concrete porosity, enhance compressive strength, and improve overall mechanical performance. Moreover, RM can partially substitute cement or serve as a geopolymer precursor, contributing to the immobilization of toxic elements such as Pb and Cr while simultaneously improving the mechanical properties of both cementitious systems and geopolymers. The reactivity and performance of RM-based materials can be further enhanced through carbonation curing and other modification techniques. Finally, this review highlights the significant sustainability and economic benefits of RM-based concrete, supported by life-cycle assessment and cost–benefit analyses. Full article

To investigate the shear behavior of rock mass joint surfaces with varying roughness and lithology, this study introduces a novel experimental framework that combines high-precision 3D printing and direct shear testing. Ten artificial joint surfaces were fabricated using Barton standard profiles with different joint roughness coefficients (JRC) and were cast using two representative rock-like materials simulating soft and hard rocks. The 3D printing technique employed significantly reduced the staircase effect and ensured high geometric fidelity of the joint morphology. Shear tests revealed that peak shear strength increases with JRC, but the underlying failure mechanisms vary depending on the lithology. Experimental results were further used to back-calculate JRC values and validate the empirical JRC–JCS (joint wall compressive strength) model. Numerical simulations using FLAC3D captured the shear stress–displacement evolution for different lithologies, revealing that rock strength primarily influences peak shear strength and fluctuation characteristics during failure. Notably, despite distinct lithologies, the post-peak degradation behavior tends to converge, suggesting universal residual shear mechanisms across rock types. These findings highlight the critical role of lithology in joint shear behavior and demonstrate the effectiveness of 3D-printing-assisted model tests in advancing rock joint characterization. Full article

The pharmaceutical industry faces a broken drug development pipeline, characterized by high costs, slow timelines and is prone to high failure rates. The convergence of Artificial Intelligence (AI) and quantum technologies is poised to fundamentally transform this landscape. AI excels in interpreting complex data, optimizing processes and designing drug candidates, while quantum systems enable unprecedented molecular simulation, ultra-sensitive sensing and precise physical control. This convergence establishes an integrated, self-learning ecosystem for the discovery, development, and delivery of therapeutics. This framework co-designs strategies from molecular targeting to formulation stability, compressing timelines and enhancing precision, which may enable safer, faster, and more adaptive medicines. Full article

The fusion of Artificial Intelligence and the Internet of Things (AI-IoT, also widely referred to as AIoT) offers transformative potential for smart cities, yet presents a critical challenge: how to process heterogeneous data streams from intelligent sensing—particularly crowd sensing data derived from citizen interactions like text, voice, and system logs—into reliable intelligence for sustainable urban governance. To address this challenge, we introduce the Intelligent Multimodal Ticket Processing System (IMTPS), a novel AI-IoT smart system. Unlike ad hoc solutions, the novelty of IMTPS resides in its theoretically grounded architecture, which orchestrates Information Theory and Game Theory for efficient, verifiable extraction, and employs Causal Inference and Meta-Learning for robust reasoning, thereby synergistically converting noisy, heterogeneous data streams into reliable governance intelligence. This principled design endows IMTPS with four foundational capabilities essential for modern smart city applications: Sustainable and Efficient AI-IoT Operations: Guided by Information Theory, the IMTPS compression module achieves provably efficient semantic-preserving compression, drastically reducing data storage and energy costs. Trustworthy Data Extraction: A Game Theory-based adversarial verification network ensures high reliability in extracting critical information, mitigating the risk of model hallucination in high-stakes citizen services. Robust Multimodal Fusion: The fusion engine leverages Causal Inference to distinguish true causality from spurious correlations, enabling trustworthy integration of complex, multi-source urban data. Adaptive Intelligent System: A Meta-Learning-based retrieval mechanism allows the system to rapidly adapt to new and evolving query patterns, ensuring long-term effectiveness in dynamic urban environments. We validate IMTPS on a large-scale, publicly released benchmark dataset of 14,230 multimodal records. IMTPS demonstrates state-of-the-art performance, achieving a 96.9% reduction in storage footprint and a 47% decrease in critical data extraction errors. By open-sourcing our implementation, we aim to provide a replicable blueprint for building the next generation of trustworthy and sustainable AI-IoT systems for citizen-centric smart cities. Full article

Crowdfunding platforms like Kickstarter have reshaped early-stage financing by allowing entrepreneurs to connect directly with potential supporters. As a fast-expanding part of digital commerce, crowdfunding offers significant opportunities but also substantial risks for both entrepreneurs and platform operators, making predictive analytics an essential capability. Although crowdfunding shares some operational features with traditional e-commerce, its mix of financial uncertainty, emotionally charged storytelling, and fast-evolving social interactions makes it a distinct and more challenging forecasting problem. Accurately predicting campaign outcomes is especially difficult because of the high-dimensionality and diversity of the underlying textual and behavioral data. These factors highlight the need for scalable, intelligent data science methods that can jointly exploit structured and unstructured information. To address these issues, this study proposes a novel AI-based predictive framework that integrates a Convolutional Block Attention Module (CBAM)-enhanced symmetric autoencoder for compressing high-dimensional Generative AI (GenAI) BERT embeddings with meta-heuristic feature selection and advanced classification models. The framework systematically couples attention-driven feature compression with optimization techniques—Genetic Algorithm (GA), Jaya, and Artificial Rabbit Optimization (ARO)—and then applies Long Short-Term Memory (LSTM) and Gradient Boosting Machine (GBM) classifiers. Experiments on a large-scale Kickstarter dataset demonstrate that the proposed approach attains 77.8% accuracy while reducing feature dimensionality by more than 95%, surpassing standard baseline methods. In addition to its technical merits, the study yields practical insights for platform managers and campaign creators, enabling more informed choices in campaign design, promotional tactics, and backer targeting. Overall, this work illustrates how advanced AI methodologies can strengthen predictive analytics in digital commerce, thereby enhancing the strategic impact and long-term sustainability of crowdfunding ecosystems. Full article

The explosive growth of artificial intelligence (AI) services has led to massive scaling of GPU computing clusters, causing sharp rises in power consumption and carbon emissions. Although hardware-level accelerator enhancements and deep neural network (DNN) model compression techniques can improve power efficiency, they often encounter deployment barriers and risks of accuracy loss in practice. To address these issues without altering hardware or model architectures, we propose a novel Carbon-Aware Resource Management (CA-RM) framework for GPU clusters. In order to minimize the carbon emission, the CA-RM framework dynamically adjusts energy usage by combining real-time GPU core frequency scaling with intelligent workload placement, aligning computation with the temporal availability of renewable generation. We introduce a new metric, performance-per-carbon (PPC), and develop three optimization formulations: carbon-constrained, performance-constrained, and PPC-driven objectives that simultaneously respect DNN model training deadlines, inference latency requirements, and carbon emission budgets. Through extensive simulations using real-world renewable energy traces and profiling data collected from NVIDIA RTX4090 GPU running representative DNN workloads, we show that the CA-RM framework substantially reduces carbon emission while satisfying service-level agreement (SLA) targets across a wide range of workload characteristics. Through experimental evaluation, we verify that the proposed CA-RM framework achieves approximately 35% carbon reduction on average, compared to competing approaches, while still ensuring acceptable processing performance across diverse workload behaviors. Full article

In customized production environments featuring multi-task parallelism, the efficient adaptability of edge intelligent models is essential for ensuring the stable operation of production lines. However, rapidly generating deployable lightweight models under conditions of frequent task changes and constrained hardware resources remains a major challenge for current edge intelligence applications. This paper proposes an adaptive lightweight artificial intelligence (AI) model compression method for edge nodes in customized production lines to overcome the limited transferability and insufficient flexibility of traditional static compression approaches. First, a task requirement analysis model is constructed based on accuracy, latency, and power-consumption demands associated with different production tasks. Then, the hardware information of edge nodes is structurally characterized. Subsequently, a compression-strategy candidate pool is established, and an adaptive decision engine integrating ensemble reinforcement learning (RL) and Bayesian optimization (BO) is introduced. Finally, through an iterative optimization mechanism, compression ratios are dynamically adjusted using real-time feedback of inference latency, memory usage, and recognition accuracy, thereby continuously enhancing model performance in edge environments. Experimental results demonstrate that, in typical object-recognition tasks, the lightweight models generated by the proposed method significantly improve inference efficiency while maintaining high accuracy, outperforming conventional fixed compression strategies and validating the effectiveness of the proposed approach in adaptive capability and edge-deployment performance. Full article

Studying surface energy and permeability offers insights into the relationship between temporary polymers and the oral environment. Variations in contact angle and surface free energy may signify modifications in surface polarity and tendency for plaque buildup, staining, or microcrack formation. Objectives: The present study aims to evaluate the influence of simulated salivary and chemical aging conditions on the surface and mechanical properties of 3D-printed PMMA provisional materials. Methods: Two 3D-printed polymethyl methacrylate (PMMA) resins were investigated, namely Anycubic White (Anycubic, Shenzhen, China) and NextDent Creo (NextDent, 3D Systems, Soesterberg, The Netherlands), using two aging protocols. Protocol A consisted of chemical aging in an alcohol-based mouthwash, while Protocol B involved thermal aging in artificial saliva. After aging, surface properties (wettability and SFE) and compressive behaviour were analyzed. Statistical analysis was conducted to assess the influence of temperature, immersion duration, and aging medium, with significance established at p < 0.05. Results: In Protocol A, mechanical properties showed a time-dependent decrease, with material-specific stabilization trends. In Protocol B, thermal aging resulted in elastic modulus reductions ranging from 35% to 46% relative to the reference. The yield strength exhibited similar tendencies. In Protocol A, X samples exhibited a consistent decline, while C samples stabilized after 14 days. For Protocol B, the fitted model produced residuals under 2%, confirming temperature as the primary variable. Conclusions: Chemical and thermal aging influence the physical and mechanical properties of the analyzed 3D-printed PMMA. Among the two protocols, thermal aging in artificial saliva resulted in more pronounced material degradation. After chemical aging in mouthwash, the surface free energy remained almost constant. After thermal aging, all samples demonstrated a gradual rise in SFE with prolonged immersion duration. The current study offers valuable insights into the environmental stability of printed PMMA; however, it is an in vitro evaluation. The findings indicate that temperature exposure and prolonged contact with oral hygiene products may affect the mechanical reliability of 3D-printed provisional restorations, which must be considered during material selection for longer temporary usage. Additionally, spectroscopic and microscopic analyses might better clarify the molecular-level chemical alterations linked to aging. Full article

We introduce AHA–SCA, a compact hybrid optimiser that alternates the wave-based exploration of the Sine–Cosine Algorithm (SCA) with the exploitation skills of the Artificial Hummingbird Algorithm (AHA) within a single population. Even iterations perform SCA moves with a linearly decaying sinusoidal amplitude to explore widely around the current best solution, while odd iterations invoke guided and territorial hummingbird flights using axial, diagonal, and omnidirectional patterns to intensify the search in promising regions. This simple interleaving yields an explicit and tunable balance between exploration and exploitation and incurs negligible overhead beyond evaluating candidate solutions. The proposed approach is evaluated on the CEC2014, CEC2017, and CEC2022 benchmark suites and on several constrained engineering design problems, including welded beam, pressure vessel, tension/compression spring, speed reducer, and cantilever beam designs. Across these diverse tasks, AHA–SCA demonstrates competitive or superior performance relative to stand-alone SCA, AHA, and a broad panel of recent metaheuristics, delivering faster early-phase convergence and robust final solutions. Statistical analyses using non-parametric tests confirm that improvements are significant on many functions, and the method respects problem constraints without parameter tuning. The results suggest that alternating wave-driven exploration with hummingbird-inspired refinement is a promising general strategy for continuous engineering optimisation. Full article

Absorption systems offer a practical alternative to traditional compression systems, especially when low-grade heat sources are available. Their applications range from vaccine preservation to space conditioning, making performance optimization essential. This study employed a multivariate inverse artificial neural network with multiple parameters (ANNim-mp) to simultaneously enhance the cooling load and coefficient of performance in an experimental single-effect ammonia–water absorption cooling system. Optimization was carried out using particle swarm optimization. The results showed significant performance improvements: up to 100% in cooling load and 97% in COP when optimizing two variables. With four-variable optimization, improvements reached 98.7% and 106.7%, respectively. These results demonstrate the strong potential of the ANNim-mp approach in enhancing the efficiency of absorption cooling systems. Full article