Search Results (2,041)

This paper proposes a novel image tone-mapping framework that incorporates meta-learning, a psychophysical model, Bayesian optimization, and light-field virtual diffraction. First, we formalize the virtual diffraction process as a mathematical operator defined in the frequency domain to reconstruct high-dynamic-range (HDR) images through phase modulation, enabling the precise control of image details and contrast. In parallel, we apply the Stevens power law to simulate the nonlinear luminance perception of the human visual system, thereby adjusting the overall brightness distribution of the HDR image and improving the visual experience. Unlike existing methods that primarily emphasize structural fidelity, the proposed method strikes a balance between perceptual fidelity and visual naturalness. Secondly, an adaptive parameter tuning system based on Bayesian optimization is developed to conduct optimization of the Tone Mapping Quality Index (TMQI), quantifying uncertainty using probabilistic models to approximate the global optimum with fewer evaluations. Furthermore, we propose a task-distribution-oriented meta-learning framework: a meta-feature space based on image statistics is constructed, and task clustering is combined with a gated meta-learner to rapidly predict initial parameters. This approach significantly enhances the robustness of the algorithm in generalizing to diverse HDR content and effectively mitigates the cold-start problem in the early stage of Bayesian optimization, thereby accelerating the convergence of the overall optimization process. Experimental results demonstrate that the proposed method substantially outperforms state-of-the-art tone-mapping algorithms across multiple benchmark datasets, with an average improvement of up to 27% in naturalness. Furthermore, the meta-learning-guided Bayesian optimization achieves two- to five-fold faster convergence. In the trade-off between computational time and performance, the proposed method consistently dominates the Pareto frontier, achieving high-quality results and efficient convergence with a low computational cost. Full article

We evaluate tactile-first robotic traversal on the Department of Homeland Security (DHS) figure-8 mobility test using a two-way repeated-measures design across various algorithms (three tactile policies—M1 reactive, M2 terrain-weighted, M3 memory-augmented; a monocular camera baseline, CB-V; a tactile histogram baseline, T-VFH; and an optional tactile-informed replanner, T-D* Lite) and lighting conditions (Indoor, Outdoor, and Dark). The platform is the custom-built Eleven robot—a quadruped integrating a joint-mounted tactile tentacle with a tip force-sensitive resistor (FSR; Walfront 9snmyvxw25, China; 0–10 kg range, ≈0.1 N resolution @ 83 Hz) and a woven Galvorn carbon-nanotube (CNT) yarn for proprioceptive bend sensing. Control and sensing are fully wireless via an ESP32-S3, Arduino Nano 33 BLE, Raspberry Pi 400, and a mini VESC controller. Across 660 trials, the tactile stack maintained ∼21 ms (p50) policy latency and mid-80% success across all lighting conditions, including total darkness. The memory-augmented tactile policy (M3) exhibited consistent robustness relative to the camera baseline (CB-V), trailing by only ≈3–4% in Indoor and ≈13–16% in Outdoor and Dark conditions. Pre-specified, two one-sided tests (TOSTs) confirmed no speed equivalence in any M3↔CB-V comparison. Unlike vision-based approaches, tactile-first traversal is invariant to illumination and texture—an essential capability for navigation in darkness, smoke, or texture-poor, confined environments. Overall, these results show that a tactile-first, memory-augmented control stack achieves lighting-independent traversal on DHS benchmarks while maintaining competitive latency and success, trading modest speed for robustness and sensing independence. Full article

To address the challenges of strong nonlinearity, stringent terminal constraints, and the trade-off between computational efficiency and accuracy in the midcourse guidance trajectory optimization problem of aerodynamically controlled interceptors, this paper proposes a variable-discrete-scale sequential convex programming (SCP) method. Firstly, a dynamic model is established by introducing the range domain to replace the traditional time domain, thereby reducing the approximation error of the planned trajectory. Second, to overcome the critical issues of solution space restriction and trajectory divergence caused by terminal equality constraints, a terminal error-proportional relaxation approach is proposed. Subsequently, an improved second-order cone programming (SOCP) formulation is developed through systematic integration of three key techniques: terminal error-proportional relaxation, variable trust region, and path normalization. Finally, an initial trajectory generation algorithm is proposed, upon which a variable-discrete-scale optimization framework is constructed. This framework incorporates a residual-driven discrete-scale adaptation mechanism, which balances discretization errors and computational load. Numerical simulation results indicate that under large discretization scales, the computation time required by the improved SOCP is only about 5.4% of that of GPOPS-II. For small-discretization-scale optimization, the SCP method with the variable discretization framework demonstrates high efficiency, achieving comparable accuracy to GPOPS-II while reducing the computation time to approximately 7.4% of that required by GPOPS-II. Full article

Markov chain Monte Carlo (MCMC) methods are fundamental to Bayesian inference but are often computationally prohibitive for large datasets, as the full likelihood must be evaluated at each iteration. Subsampling-based approximate Metropolis–Hastings (MH) algorithms offer a popular alternative, trading a manageable bias for a significant reduction in per-iteration cost. While this bias–variance trade-off is empirically understood, a formal theoretical framework for its optimization has been lacking. Our work establishes such a framework by bounding the mean squared error (MSE) as a function of the subsample size (m), the data size (n), and the number of epochs (E). This analysis reveals two optimal asymptotic scaling laws: the optimal subsample size is $m^{★}=O\left(E^{1/2}\right)$, leading to a minimal MSE that scales as ${\mathrm{MSE}}^{★}=O\left(E^{-1/2}\right)$. Furthermore, leveraging the large-sample asymptotic properties of the posterior, we show that when augmented with a control variate, the approximate MH algorithm can be asymptotically more efficient than the standard MH method under ideal conditions. Experimentally, we first validate the two optimal asymptotic scaling laws. We then use Bayesian logistic regression and Softmax classification models to highlight a key difference in convergence behavior: the exact algorithm starts with a high MSE that gradually decreases as the number of epochs increases. In contrast, the approximate algorithm with a practical control variate maintains a consistently low MSE that is largely insensitive to the number of epochs. Full article

Previous researches have proved that the synchronized use of inexpensive RGB images, image processing, and machine learning (ML) can accurately identify crop stress. Four Machine Learning Image Modules (MLIMs) were developed to enable the rapid and cost-effective identification of sugar beet stresses caused by water and/or nitrogen deficiencies. RGB images representing stressed and non-stressed crops were used in the analysis. To improve robustness, data augmentation was applied, generating six variations on each image and expanding the dataset from 150 to 900 images for training and testing. Each MLIM was trained and tested using 54 combinations derived from nine canopy and RGB-based input features and six ML algorithms. The most accurate MLIM used RGB bands as inputs to a Multilayer Perceptron, achieving 96.67% accuracy for overall stress detection, and 95.93% and 94.44% for water and nitrogen stress identification, respectively. A Random Forest model, using only the green band, achieved 92.22% accuracy for stress detection while requiring only one-fourth the computation time. For specific stresses, a Random Forest (RF) model using a Scale-Invariant Feature Transform descriptor (SIFT) achieved 93.33% for water stress, while RF with RGB bands and canopy cover reached 85.56% for nitrogen stress. To address the trade-off between accuracy and computational cost, a bargaining theory-based framework was applied. This approach identified optimal MLIMs that balance performance and execution efficiency. Full article

Taxonomies provide essential hierarchical structures for classifying information, enabling effective retrieval and knowledge organization in diverse domains such as e-commerce, academic research, and web search. Traditional taxonomy construction, heavily reliant on manual curation by domain experts, faces significant challenges in scalability, cost, and consistency when dealing with the exponential growth of digital data. Recent advancements in Large Language Models (LLMs) and Natural Language Processing (NLP) present powerful opportunities for automating this complex process. This paper explores the potential of LLMs for automated taxonomy generation, focusing on methodologies incorporating semantic embedding generation, keyword extraction, and machine learning clustering algorithms. We specifically investigate and conduct a comparative analysis of two primary LLM-based approaches using a dataset of eBay product descriptions. The first approach involves fine-tuning a pre-trained LLM using structured hierarchical data derived from chain-of-layer clustering outputs. The second employs prompt-engineering techniques to guide LLMs in generating context-aware hierarchical taxonomies based on clustered keywords without explicit model retraining. Both methodologies are evaluated for their efficacy in constructing organized multi-level hierarchical taxonomies. Evaluation using semantic similarity metrics (BERTScore and Cosine Similarity) against a ground truth reveals that the fine-tuning approach yields higher overall accuracy and consistency (BERTScore F1: 70.91%; Cosine Similarity: 66.40%) compared to the prompt-engineering approach (BERTScore F1: 61.66%; Cosine Similarity: 60.34%). We delve into the inherent trade-offs between these methods concerning semantic fidelity, computational resource requirements, result stability, and scalability. Finally, we outline potential directions for future research aimed at refining LLM-based taxonomy construction systems to handle large dynamic datasets with enhanced accuracy, robustness, and granularity. Full article

With the increasing complexity and diversity of network threats, developing high-performance Network Intrusion Detection Systems (NIDSs) has become a critical challenge. A primary obstacle in this domain is the pervasive issue of class imbalance, where the scarcity of minority attack samples and the varying costs of misclassification severely limit the effectiveness of traditional models, often leading to a difficult trade-off between high False Positive Rates (FPRs) and low Recall. To address this challenge, this paper proposes a novel, conditionally symmetric two-stage framework, termed CSCVAE-NID (Conditionally Symmetric Two-Stage CVAE for Network Intrusion Detection). The framework operates in two synergistic stages: Firstly, a Data Augmentation Conditional Variational Autoencoder (DA-CVAE) is introduced to tackle the data imbalance problem at the data level. By conditioning on attack categories, the DA-CVAE generates high-quality and diverse synthetic samples for underrepresented classes, providing a more balanced training dataset. Secondly, the core of our framework, a Cost-Sensitive Multi-Class Classification CVAE (CSMC-CVAE), is proposed. This model innovatively reframes the classification task as a probabilistic distribution matching problem and integrates a cost-sensitive learning strategy at the algorithm level. By incorporating a predefined cost matrix into its loss function, the CSMC-CVAE is compelled to prioritize the correct classification of high-cost, minority attack classes. Comprehensive experiments conducted on the public CICIDS-2017 and UNSW-NB15 datasets demonstrate the superiority of the proposed CSCVAE-NID framework. Compared to several state-of-the-art methods, our approach achieves exceptional performance in both binary and multi-class classification tasks. Notably, the DA-CVAE module is designed to be independent and extensible, allowing the effective data that it generates to support any advanced intrusion detection methodology. Full article

With the continuous growth of global communication demands, the space-ground integrated optical network (SGION), composed of the satellite optical network (SON) and terrestrial optical network (TON), has gradually become a critical component of global communication systems due to its wide coverage, low latency, and large bandwidth. However, although the high directivity of laser communication can significantly enhance the security of data transmission, it still carries the risk of being eavesdropped on during the process of service routing. To resist eavesdropping attacks during service transmission in the SGION, this paper proposes a secure routing scheme named dynamic multipath secure routing (DMSR). In DMSR, a metric called the service eavesdropping ratio (SER) is defined to quantify the service leakage severity. The objective of DMSR is to reduce each service’s SER by switching its routing path proactively. To realize DMSR, heuristic algorithms are developed to sequentially search for optimal routing paths for service path switching in the TON and SGION. Finally, simulation results demonstrate that DMSR can achieve trade-offs between secure service transmission and network performance at different levels by adjusting its system parameters. Furthermore, the DMSR scheme significantly reduces the SER compared to the baseline schemes, while introducing acceptable increases in computation overhead and service latency. Full article

The rapid proliferation of electric vehicles (EVs) demands lightweight yet efficient battery thermal management systems (BTMS). The fin-embedded phase-change material energy storage tube (PCM-EST) offers significant potential due to its high thermal energy density and passive operation, but conventional designs face a critical trade-off: enhancing heat transfer typically increases mass, conflicting with EV lightweight requirements. To resolve this conflict, this study proposes a multi-objective surrogate optimization framework integrating computational fluid dynamics (CFD) and Kriging modeling. Fin geometric parameters—number, height, and tube length—were rigorously analyzed via ANSYS (2020 R1) Fluent simulations to quantify their coupled effects on PCM melting/solidification dynamics and structural mass. The results reveal that fin configurations dominate both thermal behavior and weight. An enhanced multi-objective particle swarm optimization (MOPSO) algorithm was then deployed to simultaneously maximize heat transfer and minimize mass, generating a Pareto-optimal solution. The optimized design achieves 8.7% enhancement in heat exchange capability and 0.732 kg mass reduction—outperforming conventional single-parameter designs by 37% in weight savings. This work establishes a systematic methodology for synergistic thermal-structural optimization, advancing high-performance BTMS for sustainable EVs. Full article

Floods are among the most destructive natural hazards, with damages expected to intensify under climate change and socio-economic pressures. Effective reservoir operation remains a critical yet challenging strategy for mitigating downstream impacts, as operators must navigate nonlinear system dynamics, uncertain inflow forecasts, and trade-offs between competing objectives. This study proposes a novel end-to-end data-driven framework that integrates process-based hydraulic simulations, a Transformer-based surrogate model for flood damage prediction, and reinforcement learning (RL) for reservoir gate operation optimization. The framework is demonstrated using the Coralville Reservoir (Iowa, USA) and two major historical flood events (2008 and 2013). Hydraulic and impact simulations with HEC-RAS and HEC-FIA were used to generate training data, enabling the development of a Transformer model that accurately predicts time-varying flood damages. This surrogate is coupled with a Transformer-enhanced Deep Q-Network (DQN) to derive adaptive gate operation strategies. Results show that the RL-derived optimal policy reduces both peak and time-integrated damages compared to expert and zero-opening benchmarks, while maintaining smooth and feasible operations. Comparative analysis with a genetic algorithm (GA) highlights the robustness of the RL framework, particularly its ability to generalize across uncertain inflows and varying initial storage conditions. Importantly, the adaptive RL policy trained on perturbed synthetic inflows transferred effectively to the hydrologically distinct 2013 event, and fine-tuning achieved near-identical performance to the event-specific optimal policy. These findings highlight the capability of the proposed framework to provide adaptive, transferable, and computationally efficient tools for flood-resilient reservoir operation. Full article

The global transition toward carbon neutrality has accelerated the adoption of electric vehicles (EVs), prompting the need for smarter infrastructure planning in urban environments. This study presents a novel framework that integrates machine learning–based EV adoption forecasting with multi-objective optimization (MOO) using the NSGA-II algorithm. The forecasting component leverages neural networks to predict the percentage of EV sales relative to total vehicle sales, which is then used to derive infrastructure demand, energy consumption, and traffic congestion. These derived forecasts inform the optimization model, which balances conflicting objectives—namely infrastructure costs, energy usage, and traffic congestion—to support data-driven decision-making for smart city planners. A comprehensive dataset covering EV metrics from 2011 to 2024 is used to validate the framework. Experimental results demonstrate strong predictive performance for EV adoption, while downstream derivations highlight expected patterns in infrastructure cost and energy usage, and greater variability in traffic congestion. The NSGA-II algorithm successfully identifies Pareto-optimal trade-offs, offering urban planners flexible strategies to align infrastructure development with sustainability goals. This research underscores the benefits of integrating adoption forecasting with optimization in dynamic, real-world planning contexts. These results can significantly inform future smart city planning and optimization of EV infrastructure deployment in rapidly urbanizing regions. Full article

This article presents a novel strategy for the design of planar phased arrays using Fibonacci-based partitioning combined with a random multi-objective search. This approach intends to minimize the number of phase shifters used by the system while maintaining the radiation characteristics required for Ku-band user terminals in Low Earth Orbit (LEO) satellite communications. This methodology efficiently tessellates a $16\times 16$ antenna array, reducing the solution search space size and improving algorithmic computational time. From a total of 409,600 possible configurations, an optimal candidate solution was obtained in 2 h. This configuration achieves a balanced trade-off between radiation performance metrics, including side lobe level (SLL), first null beamwidth (FNBW), and the number of phase shifters. This optimal design maintains a value of SLL below $-15$ dB across all the azimuth scanning angles, with a beam steering capability of $\theta =-{40}^{\circ }$ and $0^{\circ }\le \varphi \le {360}^{\circ }$. These results demonstrate the suitability of this novel approach regarding Ku-band satellite communications, providing efficient and practical solutions for high-demand internet services via LEO satellite systems. Full article

There is a lack of systematic research on the behavioral design of charging decision-making for Shared Autonomous Electric Vehicles (ASEVs), and the thresholds of “when to charge and where to charge” have not been clarified. Therefore, this paper investigates the optimization of charging decisions of SAEVs and the impact of different decision-making objectives to provide theoretical support and practical guidance for intelligent operation. A multi-agent simulation model (which accurately simulates complex interaction systems) is constructed to simulate the operation and charging behavior of SAEVs. Four charging decision optimization objective functions are defined, and a weighted multi-objective optimization method is adopted. A comprehensive solution process combining the multi-agent simulation model and genetic algorithm (efficiently solving complex objective optimization problems) is applied to approximate the global optimal solution among 35 scenarios through 100 iterative runs. In this paper, factors such as passenger demand (e.g., average remaining battery power, demand response time) and operator demand (e.g., empty vehicle mileage, charging cost) are considered, and the impacts of different objectives and decision variables are analyzed. The optimization results show that (1) when a single optimization objective is selected, minimizing the total charging cost effectively balances the overall fleet operation; (2) there are trade-offs between different objectives, such as the conflict between the remaining battery power and charging cost, and the balance between the demand response time and the empty vehicle mileage; and (3) in order to satisfy the operational requirements, the weight distribution, charging probability, stopping probability, and recommended battery power should be adjusted. In conclusion, this study provides optimal charging decision strategies for the intelligent operation of SAEVs in different scenarios, which can optimize target weights and charging parameters, and achieve dynamic, balanced fleet management. Full article

We present a compact hybrid imaging system operating in the 3–5 μm spectral band that combines refractive optics with a dispersion-engineered metasurface to overcome the longstanding trade-off between wide field of view (FOV), system size, and thermal stability. The system achieves an ultra-wide 178° FOV within a total track length of only 28.25 mm, employing just three refractive lenses and one metasurface. Through co-optimization of material selection and system architecture, it maintains the modulation transfer function (MTF) exceeding 0.54 at 33 lp/mm and the geometric (GEO) radius below 15 μm across an extended operational temperature range from –40 °C to 60 °C. The metasurface is designed using a propagation phase approach with cylindrical unit cells to ensure polarization-insensitive behavior, and its broadband dispersion-free phase profile is optimized via a particle swarm algorithm. The results indicate that phase-matching errors remain small at all wavelengths, with a mean value of 0.11068. This design provides an environmentally resilient solution for lightweight applications, including automotive infrared night vision and unmanned aerial vehicle remote sensing. Full article

Blockchain-based cryptocurrency markets present unique analytical challenges due to their decentralized nature, continuous operation, and extreme volatility. Traditional price prediction models often struggle with the binary trade execution problem in these markets. This study introduces a confidence-based classification framework that separates directional prediction from execution decisions in cryptocurrency trading. We develop a neural network system that processes multi-scale market data, combining daily macroeconomic indicators with a high-frequency order book microstructure. The model trains exclusively on directional movements (up versus down) and uses prediction confidence levels to determine trade execution. We evaluate the framework across 11 major cryptocurrency pairs over 12 months. Experimental results demonstrate 82.68% direction accuracy on executed trades with 151.11-basis point average net profit per trade at 11.99% market coverage. Order book features dominate predictive importance (81.3% of selected features), validating the critical role of blockchain microstructure data for short-term price prediction. The confidence-based execution strategy achieves superior risk-adjusted returns compared to traditional classification approaches while providing natural risk management capabilities through selective trade execution. These findings contribute to blockchain technology applications in financial markets by demonstrating how a decentralized market microstructure can be leveraged for systematic trading strategies. The methodology offers practical implementation guidelines for cryptocurrency algorithmic trading while advancing the understanding of machine learning applications in blockchain-based financial systems. Full article