Search Results (27,176)

In grid-deficient environments, residential energy systems face severe carbon emission penalties due to mandatory reliance on diesel standby generators during supply interruptions. In Iraq, summer peak loads routinely exceed grid capacity, triggering prolonged generator operation and dramatically increasing household carbon footprints. This study presents a deep Q-network (DQN) reinforcement learning framework for intelligent battery energy storage system (BESS) scheduling, targeting carbon emissions reduction through strategic peak shaving. The DQN agent learns optimal battery dispatch strategies by internalizing diurnal patterns in load and solar generation through temporal state features, enabling anticipatory control without requiring explicit external forecasting models. The system is trained on one-year operational data from a representative Iraqi residential installation and evaluated over the critical summer period (122 days, 35.5% grid unavailability). The results demonstrate a 54.8% ${\mathrm{CO}}_2$ reduction (306.5 kg versus 677.4 kg baseline), a 25.5% reduction in generator runtime, and a 23.7% reduction in operating costs for the studied configuration. The learned policy approaches 89.6% of perfect-foresight MILP performance while executing 35,000 times faster. A reward function sensitivity analysis across five weighting schemes confirms that the 20:1 carbon-to-cost priority ratio optimally balances environmental and economic objectives. Ablation studies quantify the mechanism contributions: anticipatory pre-charging accounts for 58% of the total improvement, discharge optimization for 44%, and real-time PV coordination for 22%. These findings establish DQN-based BESS optimization as a practically deployable decarbonization approach for residential systems in grid-constrained developing regions. Full article

Neural rendering techniques aim to generate photorealistic images and accurate 3D geometries from multi-view images but often struggle with efficiency and geometric consistency in complex or dynamic scenes. Optimized Neural Radiance Fields (OptiNeRF) addresses these challenges through several innovations. It uses spatially optimized sampling to focus on points near object surfaces, reducing computation while improving precision. Leveraging the pre-trained Marigold model, it generates depth and normal maps as geometric priors. Sampled points are processed through a hybrid network combining an MLP and a multi-resolution feature grid (MRF), capturing fine details and large-scale structures. To handle varying illumination and complex materials, OptiNeRF introduces adaptive volume rendering (AVR), dynamically adjusting light transparency and scattering. A progressive sampling strategy further focuses computation on regions with high geometric complexity. The loss function incorporates RGB, normal, depth, boundary, and lighting optimization losses, with adaptive weight modulation for geometric priors, ensuring both visual fidelity and geometric consistency even with inaccurate depth/normal estimates. Experiments on dynamic scenes show strong performance, with a PSNR of 32.10 dB, SSIM of 0.936, Chamfer distance of $1.28\times {10}^{-3}$, training time of 12 h, and rendering speed of 25 FPS, demonstrating high geometric accuracy, realistic rendering, and computational efficiency over conventional methods. Full article

The increasing penetration of inverter-interfaced photovoltaic (PV) generation in active distribution networks (ADNs) intensifies fast voltage violations and makes real-time Volt-VAR control (VVC) challenging, especially when each inverter has only partial and noisy measurements and communication is limited. Existing local droop-type strategies lack coordination, while fully centralized optimization/learning is often impractical for online deployment. To address these gaps, an attention-enhanced multi-agent deep reinforcement learning (MADRL) framework is developed for inverter-based VVC under the centralized training and decentralized execution (CTDE) paradigm. First, the voltage regulation problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP) to explicitly account for system stochasticity and temporal variability under partial observability. To solve this complex game, an attention-enhanced MADRL architecture is employed, where an agent-level attention mechanism is integrated into the centralized critic. Unlike traditional methods that treat all neighbor information equally, the proposed mechanism enables each inverter agent to dynamically prioritize and selectively focus on the most influential states from other agents, effectively capturing complex intercorrelations while enhancing training stability and learning efficiency. Operating under the CTDE paradigm, the framework realizes coordinated reactive power support using only local measurements, ensuring high scalability and practical implementability in communication-constrained environments. Simulations on the IEEE 33-bus system with six PV inverters show that the proposed method reduces the average voltage deviation on the test set from 0.0117 p.u. (droop control) and 0.0112 p.u. (MADDPG) to 0.0074 p.u., while maintaining millisecond-level execution time comparable to other MADRL baselines. Scalability tests with up to 12 agents further demonstrate robust performance of the proposed method under higher PV penetration. Full article

An HPO (Hunter–Prey Optimizer)-optimized Bidirectional LSTM (HPO-BiLSTM) model is introduced to address the challenges in predicting gas concentration within coal mining working faces. This study aims to adaptively adjust the key hyperparameters (such as learning rate and number of hidden layer units) of the BiLSTM network through intelligent optimization algorithms. While the BiLSTM architecture inherently mitigates gradient vanishing and exploding problems through its gating mechanisms, the proposed HPO method focuses on addressing the inefficiency of manual parameter tuning and the risk of trapping in local optima that traditional methods encounter when dealing with nonlinear and non-stationary gas concentration time series. The experiment utilized the actual methane monitoring data from the 15117 working face of Jishazhuang Coal Mine in Jinzhong City, Shanxi Province (with a sampling interval of 2 min). The proposed HPO-BiLSTM model was compared with baseline models such as LSTM, BiLSTM, GA-BiLSTM, and PSO-BiLSTM in terms of performance. This study systematically compares the performance of LSTM, BiLSTM, and BiLSTM models optimized with GA, PSO, and HPO. Results demonstrate that all optimized models outperform the baselines, with HPO-BiLSTM achieving the best overall performance. It attained the lowest RMSE and highest R² across the training, validation, and test sets, showcasing superior fitting and generalization capabilities. Furthermore, HPO-BiLSTM converged to the lowest loss value (0.00062) in only 15 iterations, demonstrating significantly greater efficiency and stability than both GA-BiLSTM (loss 0.00072, 25 iterations) and PSO-BiLSTM (loss 0.00071, 30 iterations). The experiments confirm that the HPO algorithm effectively configures BiLSTM hyperparameters, mitigates overfitting, and provides a more accurate and robust solution for gas concentration prediction in coal mines. Full article

The power-shift system employed in agricultural multi-range continuously variable transmissions (CVTs) features a complex structure and control logic, presenting significant challenges to the reliability of agricultural machinery. To enable timely detection of faults, constructing an intelligent fault diagnosis classifier to monitor the system’s health status is essential. Typically, fault samples utilized for classifier development originate from ideal bench tests, characterized by uniform patterns and limited diversity, thereby hindering the algorithm’s generalization capability. This study addresses this issue by proposing a generative adversarial network (GAN) model, integrated with a triple loss function and a novel generator architecture, to augment the fault dataset under laboratory conditions. The generator architecture comprises a variational autoencoder module and an oil pressure point attention mechanism, enabling the generation of diverse and fluctuating virtual samples. Building on this augmented dataset, a fault classifier based on one-dimensional ConvNeXt was developed. Experimental results indicate that the classifier achieves an accuracy of 99.73%. While classifier accuracy decreases with increasing noise levels, the GAN-generated dataset provides more comprehensive training, resulting in an accuracy approximately 3% higher than that achieved using the original dataset. Full article

Addressing challenges in few-shot image classification, this study introduces the Multi-Dimensional Attention and Composite Loss Former, a meta-learning model built on a Residual Network-12 backbone. The model incorporates multi-dimensional attention mechanisms and is trained with a composite loss function applied across the entire architecture. It enhances feature extraction by dynamically focusing on critical local and global information, while the composite loss optimizes classification accuracy, emphasizes hard samples, suppresses overfitting, and promotes intra-class feature compactness. Comprehensive experiments conducted on the miniImageNet and tieredImageNet datasets demonstrate that the proposed model achieves superior performance in both meta-training and meta-testing stages compared to existing benchmarks, effectively validating its robustness and generalization capabilities in few-shot learning tasks. Full article

In current mobile networks, users’ identity privacy is threatened by long-term observation attacks. To resist such attacks, identity-anonymity technology has been proposed. However, existing anonymity schemes cannot adapt to diverse, dynamic business scenarios because of their rigid anonymity strategies. This leads to wasted computing and communication resources in low-risk scenarios or privacy leaks in high-risk scenarios. To address this problem, we propose an Adaptive Dynamic Anonymity and Traceability scheme based on privacy-aware random forest and local differential privacy in a Trusted Execution Environment. We first construct a convex optimization model to seek the optimal balance between privacy risk and performance cost. Subsequently, we train a privacy-aware random forest model to intelligently predict the optimal Time-To-Live of the anonymous identifier based on the real-time context. Lastly, to resist long-term observation attacks, our scheme uses a lightweight symmetric encryption algorithm to generate pseudo-random, anonymous identifiers and applies truncated local differential privacy to ensure the indistinguishability of the timing patterns of anonymous identifier updates. We formally prove that our scheme can resist long-term observation attacks. Experimental results show that, compared with fixed Time-To-Live schemes, our scheme significantly reduces the comprehensive cost while maintaining the same level of security. Furthermore, compared with traditional public-key schemes, it greatly improves the generation speed of anonymous identifiers and reduces communication costs. Full article

Reservoir management, flood control, and operational planning are the benefits of dam inflow forecasting. Decomposition algorithms can decompose complex inflow data into intrinsic components and reduce noise and fluctuations, while quantum machine learning models use features such as superposition and entanglement to manage large datasets and capture nonlinear hydrological behaviors. This study used three models: random forest (RF) as a classical benchmark, hybrid quantum neural network (HQNN) as a quantum approach, and sequential variational mode decomposition with HQNN (SVMD-HQNN) that integrates decomposition and quantum learning. The modeling was applied to forecast the inflow to Khoda Afarin Dam over 16 years (2009–2024) in two scenarios that included hydrological parameters (precipitation and evaporation) and reservoir parameters (water level, volume, and surface area). The data was divided into training and testing sets in a ratio of 70:30. The results showed that SVMD-HQNN achieved higher accuracy than the other two models with RMSE = 34.51, R² = 0.93, NSE = 0.91, MAPE = 11.48%, and KGE = 0.89 in scenario (i) and RMSE = 25.74, R² = 0.95, NSE = 0.94, MAPE = 8.98%, and KGE = 0.93 in scenario (ii). In the first scenario, this approach increased the prediction accuracy by 43.71%, and in the second scenario, it increased the prediction accuracy by 45.47% compared to the HQNN model. The proposed SVMD-HQNN framework is particularly effective under climate change conditions, where inflow fluctuations and instability are significant, and provides robust and generalizable predictions for reservoirs in similar environments. Full article

This article presents a scalable IoT-based architecture for continuous and passive monitoring of human behavior in home environments, designed as a technical foundation for future dementia risk assessment systems. The architecture addresses three fundamental challenges: achieving room-level spatial localization without privacy-invasive methods, balancing temporal resolution with bandwidth efficiency in continuous data streams, and enabling multi-institutional model development under GDPR constraints. The system integrates (1) wearable BLE sensors with infrared room-level localization; (2) edge computing gateways with local preprocessing and machine learning; (3) a three-channel data architecture that simultaneously achieves full 1 s temporal resolution for machine learning training, low-latency real-time visualization, and 41.2% network bandwidth reduction; and (4) a federated learning framework enabling collaborative model development without data sharing between institutions. Technical validation in two apartments (three participants, 7 days) demonstrated: 97.6% room-level localization accuracy using infrared beacons; less than 7 s end-to-end latency for 99.5% of critical events; and 98.5% deduplication accuracy in multi-gateway configurations. Federated learning simulation demonstrates algorithmic convergence (84.3% IID, 79.8% non-IID) and workflow feasibility, establishing a foundation for future production deployment. Cost analysis shows approximately €490 for initial implementation and approximately €55 monthly operation, representing substantially lower costs than existing research systems. The work establishes architectural and technical feasibility, as well as system-level economic viability, of continuous home monitoring for behavioral analysis within the evaluated residential scenarios. Clinical validation of diagnostic capabilities through longitudinal studies with validated cognitive assessments and patients with mild cognitive impairment remains to be studied in future work. Full article

Traffic flow prediction (TFP) is a fundamental component of intelligent transportation systems (ITS) that supports traffic management, congestion mitigation, and route planning. Although recent advances in deep learning have demonstrated strong capability in modeling non-linear spatio-temporal correlations, most existing approaches rely on centralized training paradigms, which incur substantial communication costs, high computational overhead, and significant data privacy risks. Federated Learning (FL) has emerged as a promising alternative by enabling decentralized model training across distributed clients while reducing privacy risks and communication overhead. However, existing FL-based TFP frameworks often employ local models with limited capacity to capture complex spatio-temporal dependencies, and their reliance on the conventional FedAvg aggregation approach restricts robustness under heterogeneous traffic data distributions. To address these challenges, this study proposes the FedASTAM framework, which integrates FL with the Adaptive Spatio-Temporal Attention-based Multi-Model (ASTAM) to effectively model complex and non-linear spatio-temporal traffic correlations in a data-local FL setting. Within FedASTAM, the road network is divided into sub-regions using spectral clustering, allowing each sub-region to train a local ASTAM model tailored to localized and heterogeneous traffic patterns. At the central server, locally trained models are aggregated using seven aggregation schemes, including the classical FedAvg, to optimize global model updates while preserving data locality. Extensive experiments conducted on two real-world benchmark datasets, PeMS04 and PeMS08, demonstrate that FedASTAM achieved strong and stable predictive performance while keeping raw data localized throughout the federated training process. The results further indicate that the aggregation approaches used in the proposed FedASTAM framework generally outperform classical FedAvg under heterogeneous traffic conditions, highlighting FedASTAM as an effective approach for traffic flow prediction in complex, distributed ITS environments. Full article

The accelerated discovery of high-performance lead-free piezoelectric ceramics is hindered by the vast compositional space and the limited interpretability of conventional machine learning (ML) models. Here, we propose a physics-informed and interpretable ML framework with integrated uncertainty quantification to predict and understand the piezoelectric coefficient d₃₃ of (K_0.5Na_0.5) NbO₃ (KNN)-based ceramics. A curated dataset of 1113 experimental samples is used to construct 65 descriptors by decoupling A-site and B-site ionic contributions. Pearson correlation analysis reduces these to an optimized 11-dimensional feature set for training deep neural networks, Wide & Deep networks, and residual networks. A Bayesian neural network further provides predictive uncertainty, which quantitatively reflects the confidence of machine-learning-based d₃₃ predictions rather than experimental measurement uncertainty. To achieve physical interpretability, SHapley Additive exPlanations (SHAP) are combined with the Sure Independence Screening and Sparsifying Operator (SISSO) to derive a compact analytical descriptor revealing that sintering temperature, B-site electronic anisotropy, and A-site ionic displacement jointly govern d₃₃. The proposed framework achieves high accuracy (R² ≈ 0.81) while offering transparent design rules for next-generation lead-free piezoelectrics. Full article

The multi-depot vehicle routing problem with soft time windows (MDVRPSTW) has long been a focus in both academic and industrial circles. This paper proposes a deep reinforcement learning framework designed to enhance the efficiency and quality of MDVRPSTW solutions, addressing the limitations of traditional heuristic algorithms in large-scale complex scenarios. The framework first transforms the mathematical model into a sequential decision-making problem through a Markov decision process, then extracts path selection strategies using an encoder–decoder architecture based on attention mechanisms and graph neural networks, and employs unsupervised reinforcement learning for model training. Test results on the Solomon benchmark dataset demonstrate that for small-scale problems (N = 20), our method reduces solving time by over 96% compared to comparative algorithms, with the objective value difference from the generalized variable neighborhood search (GVNS) being less than 9%. For medium-to-large scale problems (N = 50/100), our method achieves a 27.7 to 96.3 percent improvement over GVNS, maintaining stable solution times within 3 to 10 s. Compared to exact algorithms and meta-heuristic methods, our approach reduces computational costs by 2–3 orders of magnitude while demonstrating strong adaptability to variations in the number of depots and vehicles. In summary, this method significantly outperforms baseline models in both solution quality and computational efficiency, providing an efficient end-to-end solution for MDVRPSTW in complex scenarios. Full article

Crop yield estimation, particularly early-season yield prediction, is highly important for global food security and disaster mitigation. In this study, we utilized deep learning models combined with remote sensing data to develop in-season crop yield estimation models, enabling immediate yield prediction. We employed a convolutional neural network (CNN) for spatial feature extraction and a long short-term memory network (LSTM) for temporal patterns, complemented by Gaussian process regression (GP) that introduced geographical coordinates. Three groups of in-season yield prediction experiments were designed, utilizing four-phase, two-phase, and single-phase data, respectively. The results indicated that under the two-phase training scheme, the LSTM_GP model achieved the highest performance in the sixth period, with an $R^2$ value of 0.61 and a root mean square error ($RMSE$) value of 983.38 kg/ha. When trained on single-phase data at the twelfth phase (approximately mid-to-late July), the LSTM_GP model also performed best, attaining an $R^2$ value of 0.62 and an $RMSE$ value of 969.06 kg/ha. The single-phase prediction model outperformed time-series models in yield prediction accuracy. The periods from mid-to-late July to early-to-mid August represent critical crop growth stages were essential for accurate yield prediction. From our research, we found that adding GP can improve the prediction accuracy, especially for LSTM. Moreover, the proposed single-phase prediction model realized reliable crop yield prediction as well as the silking to early grain-filling stage (mid-to-late July), providing a critical lead time of approximately 2–2.5 months before harvest to support pre-harvest agricultural decision-making. Full article

Existing hyperspectral denoising networks typically rely on large amounts of high-quality paired noisy–clean images for training, which are often unavailable. Moreover, the noise distribution in real hyperspectral images (HSIs) is complex and variable, making it challenging for existing networks to handle noise distributions not present in the training dataset, resulting in poor generalization. To address these issues, this paper proposes an unsupervised Hyperspectral image Denoising approach exploiting the spectral learning preference of neural networks with an adaptive early stopping strategy (termed HyDePre). Inspired by the Deep Image Prior, which reveals that neural networks tend to capture natural image structures before fitting noise, we observe that deep neural networks exhibit a similar learning preference in the spectral domain. Specifically, as training progresses, the network first fits smooth spectral feature curves and only later adapts to Gaussian noise and complex impulse noise. This observation provides an opportunity to use an early stopping strategy, allowing the network to fit only the clean spectral signals and thus achieve denoising. Our method does not require clean images for training, but instead optimizes network parameters to automatically learn prior spectral information from a single noisy image, modeling the intrinsic structure of the input data to uncover its underlying patterns.However, finding the optimal stopping point is challenging without access to clean images as sources of prior information. To tackle this challenge, we introduce an adaptive early stopping strategy based on the average spectral maximum variation of the reconstructed image, effectively preventing overfitting. The experimental results demonstrate that HyDePre outperforms existing methods in terms of both visual quality and quantitative metrics. Full article

With the increasing availability of satellite imagery and the shortening revisit intervals, efficiently processing satellite hyperspectral images has become a critical task. However, in practice, a large portion of satellite hyperspectral data remains unlabeled, making it difficult to achieve satisfactory classification performance using satellite data alone. Meanwhile, UAV-based platforms offer acquisition flexibility, which facilitates the collection of rich and detailed information. To address these challenges, this paper proposes a method called Sharpness-Aware Minimization with Local-to-Global Feature Enhancement (SAMLFE), which uses UAV hyperspectral images for training to enhance the fine-grained classification performance of satellite hyperspectral images in large scenes. Specifically, a spectral dimension mapping model is first employed to unify UAV and satellite images into a common spectral dimension, thereby mitigating the impact of inconsistent feature representations. Next, a local-to-global feature extraction network is constructed to capture both local details and global semantics. Few-shot learning is applied to extract discriminative features from both the source and target domains within the shared feature space, thereby enhancing the model’s ability to utilize limited labeled data efficiently. Furthermore, a conditional adversarial domain adaptation strategy is adopted to align the feature distributions of the source and target domains, thereby alleviating spectral shift. Meanwhile, the integration of an improved Sharpness-Aware Minimization (ISAM) enhances the model’s robustness across domains. Finally, the K-Nearest Neighbor algorithm is employed to perform accurate classification. Experimental results on multiple datasets demonstrate that the proposed method achieves superior generalization and classification performance in cross-domain hyperspectral image classification. It also outperforms existing methods in terms of feature distribution alignment, robustness of feature extraction, and adaptability to small-sample scenarios. Full article