Search Results (29,286)

Reconfigurable Intelligent Surface (RIS) has emerged as a promising enabling technology for wireless communications, which significantly enhances system performance through real-time manipulation of electromagnetic wave reflection characteristics. In RIS-assisted communication systems, existing deep learning-based channel state information (CSI) feedback methods often suffer from excessive parameter requirements and high computational complexity. To address this challenge, this paper proposes LwCSI-Net, a lightweight autoencoder network specifically designed for RIS-assisted multiple-input single-output (MISO) systems, aiming to achieve efficient and low-complexity CSI feedback. The core contribution of this work lies in an innovative lightweight feedback architecture that deeply integrates multi-layer convolutional neural networks (CNNs) with attention mechanisms. Specifically, the network employs 1D convolutional operations with unidirectional kernel sliding, which effectively reduces trainable parameters while maintaining robust feature-extraction capabilities. Furthermore, by incorporating an efficient channel attention (ECA) mechanism, the model dynamically allocates weights to different feature channels, thereby enhancing the capture of critical features. This approach not only improves network representational efficiency but also reduces redundant computations, leading to optimized computational complexity. Additionally, the proposed cross-channel residual block (CRBlock) establishes inter-channel information-exchange paths, strengthening feature fusion and ensuring outstanding stability and robustness under high compression ratio (CR) conditions. Our experimental results show that for CRs of 16, 32, and 64, LwCSI-Net significantly improves CSI reconstruction performance while maintaining fewer parameters and lower computational complexity, achieving an average complexity reduction of 35.63% compared to state-of-the-art (SOTA) CSI feedback autoencoder architectures. Full article

The sustainable integration of Distributed Energy Resources (DER) with the next-generation distribution networks requires robust, adaptive, and accurate hosting capacity (HC) forecasting. Dynamic Operating Envelopes (DOE) provide real-time constraints for power import/export to the grid, ensuring dynamic DER integration and efficient network operation. However, conventional HC analysis and forecasting approaches struggle to capture temporal dependencies, the impact of DOE constraints on network operation, and uncertainty in DER output. This study introduces a dynamic optimization framework that leverages the benefits of the sensitivity gate of the Sensitivity-Enhanced Recurrent Neural Network (SERNN) forecasting model, Particle Swarm Optimization (PSO), and Bayesian Optimization (BO) for HC forecasting. The PSO determines the optimal weights and biases, and BO fine-tunes hyperparameters of the SERNN forecasting model to minimize the prediction error. This approach dynamically adjusts the import/export of the DER output to the grid by integrating the DOE constraints into the SG-PSO-BO architecture. Performance evaluation on the IEEE-123 test network and a real Australian distribution network demonstrates superior HC forecasting accuracy, with an $R^2$ score of 0.97 and 0.98, Mean Absolute Error (MAE) of 0.21 and 0.16, and Root Mean Square Error (RMSE) of 0.38 and 0.31, respectively. The study shows that the model effectively captures the non-linear and time-sensitive interactions between network parameters, DER variables, and weather information. This study offers valuable insights into advancing dynamic HC forecasting under real-time DOE constraints in sustainable DER integration, contributing to the global transition towards net-zero emissions. Full article

In order to address the limitations of the number of label samples in practical accurate classification scenarios and the problems of overfitting and an insufficient generalization ability caused by Few-Shot Learning (FSL) in hyperspectral image classification (HSIC), this paper designs and implements a neural architecture search (NAS) for a few-shot HSI classification method that combines meta learning. Firstly, a multi-source domain learning framework was constructed to integrate heterogeneous natural images and homogeneous remote sensing images to improve the information breadth of few-sample learning, enabling the final network to enhance its generalization ability under limited labeled samples by learning the similarity between different data sources. Secondly, by constructing precise and robust search spaces and deploying different units at different locations, the classification accuracy and model transfer robustness of the final network can be improved. This method fully utilizes spatial texture information and rich category information of multi-source data and transfers the learned meta knowledge to the optimal architecture for HSIC execution through precise and robust search space design, achieving HSIC tasks with limited samples. Experimental results have shown that our proposed method achieved an overall accuracy (OA) of 98.57%, 78.39%, and 98.74% for classification on the Pavia Center, Indian Pine, and WHU-Hi-LongKou datasets, respectively. It is fully demonstrated that utilizing spatial texture information and rich category information of multi-source data, and through precise and robust search space design, the learned meta knowledge is fully transmitted to the optimal architecture for HSIC, perfectly achieving classification tasks with few-shot samples. Full article

Breast cancer (BRCA) remains a significant cause of mortality among women, particularly in developing and underdeveloped regions, where early detection is crucial for effective treatment. This research introduces an innovative hybrid model that combines Improved Grey Wolf Optimizer (IGWO) with the Seagull Optimization Algorithm (SOA), forming the IGWO–SOA technique to enhance BRCA detection accuracy. The hybrid model draws inspiration from the adaptive and strategic behaviors of seagulls, especially their ability to dynamically change attack angles in order to effectively tackle complex global optimization challenges. A deep neural network (DNN) is fine-tuned using this hybrid optimization method to address the challenges of hyperparameter selection and overfitting, which are common in DL approaches for BRCA classification. The proposed IGWO–SOA model demonstrates optimal performance in identifying key attributes that contribute to accurate cancer detection using the CBIS-DDSM dataset. Its effectiveness is validated using performance metrics such as loss, F1-score, precision, accuracy, and recall. Notably, the model achieved an impressive accuracy of 99.4%, outperforming existing methods in the domain. By optimizing both the learning parameters and model structure, this research establishes an advanced deep learning framework built upon the IGWO–SOA approach, presenting a robust and reliable method for early BRCA detection with significant potential to improve diagnostic precision. Full article

Underwater acoustic (UWA) communication supports many critical applications but still faces several physical-layer signal processing challenges. In response, recent advances in machine learning (ML) and deep learning (DL) offer promising solutions to improve signal detection, modulation adaptability, and classification accuracy. These developments highlight the need for a systematic evaluation to compare various ML/DL models and assess their performance across diverse underwater conditions. However, most existing reviews on ML/DL-based UWA communication focus on isolated approaches rather than integrated system-level perspectives, which limits cross-domain insights and reduces their relevance to practical underwater deployments. Consequently, this systematic literature review (SLR) synthesizes 43 studies (2020–2025) on ML and DL approaches for UWA communication, covering channel estimation, adaptive modulation, and modulation recognition across both single- and multi-carrier systems. The findings reveal that models such as convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and generative adversarial networks (GANs) enhance channel estimation performance, achieving error reductions and bit error rate (BER) gains ranging from ${10}^{-3}$ to ${10}^{-6}$. Adaptive modulation techniques incorporating support vector machines (SVMs), CNNs, and reinforcement learning (RL) attain classification accuracies exceeding 98% and throughput improvements of up to 25%. For modulation recognition, architectures like sequence CNNs, residual networks, and hybrid convolutional–recurrent models achieve up to 99.38% accuracy with latency below 10 ms. These performance metrics underscore the viability of ML/DL-based solutions in optimizing physical-layer tasks for real-world UWA deployments. Finally, the SLR identifies key challenges in UWA communication, including high complexity, limited data, fragmented performance metrics, deployment realities, energy constraints and poor scalability. It also outlines future directions like lightweight models, physics-informed learning, advanced RL strategies, intelligent resource allocation, and robust feature fusion to build reliable and intelligent underwater systems. Full article

This study investigates how new R&D institutions mediate policy–market disjunctures to foster integrated innovation and entrepreneurship ecosystems. Employing a longitudinal case analysis (2013–2023) of the Jiangsu Industrial Technology Research Institute (JITRI), we delineate a three-phase evolutionary process: (1) an initial government-dominated phase, stimulating foundational capability development through contract R&D; (2) a subsequent marketization phase, enabling systemic resource integration via co-creation centers and global networks; and (3) a culminating synergy phase, where policy–market alignment facilitates ecosystem optimization through crowdsourced R&D and cross-domain collaboration. Three core mechanisms underpin this adaptation: policy–market coupling (providing external momentum), endogenous capability development (absorption to innovation), and dynamic resource orchestration (acquisition to optimization). JITRI’s hybrid governance model demonstrates that stage-contingent interventions—specifically, policy anchoring in early stages followed by market-responsive resource allocation—effectively transmute inherent tensions into productive synergies. These findings yield implementable frameworks for structuring innovative ecosystems and underscore the necessity for comparative studies to establish broader theoretical generalizability. Full article

Optical networks serve as the backbone of modern communication, requiring statistical analysis and modeling to optimize performance, reliability, and scalability. This review paper explores statistical methodologies for analyzing network characteristics, dimensioning, parameter estimation, and cost prediction of optical networks, and provides a generalized framework based on the idea of convex areas, and link length and shortest path length distributions. Accurate dimensioning and cost estimation are crucial for optical network planning, especially during early-stage design, network upgrades, and optimization. However, detailed information is often unavailable or too complex to compute. Basic parameters like coverage area and node count, along with statistical insights such as distribution patterns and moments, aid in determining the appropriate modulation schemes, compensation techniques, repeater placement, and in estimating the fiber length. Statistical models also help predict link lengths and shortest path lengths, ensuring efficiency in design. Probability distributions, stochastic processes, and machine learning improve network optimization and fault prediction. Metrics like bit error rate, quality of service, and spectral efficiency can be statistically assessed to enhance data transmission. This paper provides a review on statistical analysis and modeling of optical networks, which supports intelligent optical network management, dimensioning of optical networks, performance prediction, and estimation of important optical network parameters with partial information. Full article

Auxin (IAA), a key natural signaling molecule, plays a pivotal role in regulating plant growth, development, and stress responses. Understanding its signal transduction mechanisms is crucial for improving crop yields. In this study, we conducted a comparative transcriptome analysis of wheat leaf and root tissues treated with different concentrations of IAA (0, 1, and 50 μM). Functional enrichment analysis revealed that differentially expressed genes (DEGs) exhibited tissue-specific regulatory patterns in response to auxin. Weighted Gene Co-expression Network Analysis (WGCNA) identified receptor-like kinase genes within the MEgreen module as highly correlated with auxin response, suggesting their involvement in both root and leaf regulation. Among them, TaPBL7-2B, a receptor-like kinase gene significantly upregulated under 50 μM IAA treatment, was selected for functional validation. Ectopic overexpression of TaPBL7-2B in Arabidopsis thaliana (Col-0) enhanced auxin sensitivity and inhibited plant growth by suppressing root development and leaf expansion. In contrast, knockout of the Arabidopsis homolog AtPBL7 reduced auxin sensitivity and promoted both root and leaf growth. Transcriptome analysis of Col-0, the TaPBL7-2B overexpression line, and the pbl7 mutant indicated that TaPBL7-2B primarily functions through the MAPK signaling pathway and plant hormone signal transduction pathway. Furthermore, qRT-PCR analysis of wheat varieties with differing auxin sensitivities confirmed a positive correlation between TaPBL7-2B expression and auxin response. In conclusion, TaPBL7-2B acts as a negative regulator of plant growth, affecting root development and leaf expansion in both Arabidopsis and wheat. These findings enhance our understanding of auxin signaling and provide new insights for optimizing crop architecture and productivity. Full article

Accurate and rapid prediction of structural responses to seismic loading is critical for ensuring structural safety. Recently, there has been active research focusing on the application of deep learning techniques, including Physics-Informed Neural Networks (PINNs) and Long Short-Term Memory (LSTM) networks, to predict the dynamic behavior of structures. While these methods have shown promise, each comes with distinct limitations. PINNs offer physical consistency but struggle with capturing long-term temporal dependencies in nonlinear systems, while LSTMs excel in learning sequential data but lack physical interpretability. To address these complementary limitations, this study proposes a hybrid LSTM-PINN model, combining the temporal learning ability of LSTMs with the physics-based constraints of PINNs. This hybrid approach allows the model to capture both nonlinear, time-dependent behaviors and maintain physical consistency. The proposed model is evaluated on both single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) structural systems subjected to the El-Centro ground motion. For validation, the 1940 El-Centro NS earthquake record was used, and the ground acceleration data were normalized and discretized for numerical simulation. The proposed LSTM-PINN is trained under the same conditions as the conventional PINN models (e.g., same optimizer, learning rate, and loss structure), but with fewer training epochs, to evaluate learning efficiency. Prediction accuracy is quantitatively assessed using mean error and mean squared error (MSE) for displacement, velocity, and acceleration, and results are compared with PINN-only models (PINN-1, PINN-2). The results show that LSTM-PINN consistently achieves the most stable and precise predictions across the entire time domain. Notably, it outperforms the baseline PINNs even with fewer training epochs. Specifically, it achieved up to 50% lower MSE with only 10,000 epochs, compared to the PINN’s 50,000 epochs, demonstrating improved generalization through temporal sequence learning. This study empirically validates the potential of physics-guided time-series AI models for dynamic structural response prediction. The proposed approach is expected to contribute to future applications such as real-time response estimation, structural health monitoring, and seismic performance evaluation. Full article

Background: Anhedonia, defined as the diminished capacity to experience pleasure, represents a core negative symptom in first-episode psychosis (FEP) with profound implications for functional outcomes and long-term prognosis. Despite its clinical significance, comprehensive understanding of anhedonia prevalence, underlying mechanisms, and optimal intervention strategies in early psychosis remains limited. Objectives: To systematically examine the prevalence and characteristics of anhedonia in FEP patients, explore neurobiological mechanisms, identify clinical correlates and predictive factors, and evaluate intervention efficacy. Methods: Following PRISMA 2020 guidelines, we conducted comprehensive searches across PubMed, Embase, PsycINFO, and Web of Science databases from January 1990 to June 2025. Studies examining anhedonia and negative symptoms in FEP patients (≤24 months from onset) using validated assessment instruments were included. Quality assessment was performed using appropriate tools for study design. Results: Twenty-one studies comprising 3847 FEP patients met inclusion criteria. Anhedonia prevalence ranged from 30% at 10-year follow-up to 53% during acute phases, demonstrating persistent motivational deficits across illness trajectory. Factor analytic studies consistently supported five-factor negative symptom models with anhedonia as a discrete dimension. Neuroimaging investigations revealed consistent alterations in reward processing circuits, including ventral striatum hypofunction and altered network connectivity patterns. Social anhedonia demonstrated stronger associations with functional outcomes compared to other domains. Epigenetic mechanisms involving oxytocin receptor methylation showed gender-specific associations with anhedonia severity. Conventional antipsychotic treatments showed limited efficacy for anhedonia improvement, while targeted psychosocial interventions demonstrated preliminary promise. Conclusions: Anhedonia showed high prevalence (30–53%) across FEP populations with substantial clinical burden (13-fold increased odds vs. general population). Meta-analysis revealed large effect sizes for anhedonia severity in FEP vs. controls (d = 0.83) and strong negative correlations with functional outcomes (r =·−0.82). Neuroimaging demonstrated consistent ventral striatum dysfunction and altered network connectivity. Social anhedonia emerged as the strongest predictor of functional outcomes, with independent suicide risk associations. Conventional antipsychotics showed limited efficacy, while behavioral activation approaches demonstrated preliminary promise. These findings support anhedonia as a distinct treatment target requiring specialized assessment and intervention protocols in early psychosis care. Full article

Broadcasting in Mobile Ad Hoc Networks (MANETs) is significantly challenged by dynamic network topologies. Traditional fuzzy logic-based schemes that often rely on static fuzzy tables and fixed membership functions are limiting their ability to adapt to evolving network conditions. To address these limitations, in this paper, we conduct a comparative study of two innovative broadcasting schemes that enhance adaptability through dynamic fuzzy logic membership functions for the broadcasting problem. The first approach (Model A) dynamically adjusts membership functions based on changing network parameters and fine-tunes the broadcast (BC) versus do-not-broadcast (DNB) ratio. Model B, on the other hand, introduces a multi-profile switching mechanism that selects among distinct fuzzy parameter sets optimized for various macro-level scenarios, such as energy constraints or node density, without altering the broadcasting ratio. Reinforcement learning (RL) is employed in both models: in Model A for BC/DNB ratio optimization, and in Model B for action decisions within selected profiles. Unlike prior fuzzy logic or reinforcement learning approaches that rely on fixed profiles or static parameter sets, our work introduces adaptability at both the membership function and profile selection levels, significantly improving broadcasting efficiency and flexibility across diverse MANET conditions. Comprehensive simulations demonstrate that both proposed schemes significantly reduce redundant broadcasts and collisions, leading to lower network overhead and improved message delivery reliability compared to traditional static methods. Specifically, our models achieve consistent packet delivery ratios (PDRs), reduce end-to-end Delay by approximately 23–27%, and lower Redundancy and Overhead by 40–60% and 40–50%, respectively, in high-density and high-mobility scenarios. Furthermore, this comparative analysis highlights the strengths and trade-offs between reinforcement learning-driven broadcasting ratio optimization (Model A) and parameter-based dynamic membership function adaptation (Model B), providing valuable insights for optimizing broadcasting strategies. Full article

HPMC, regulating slurry properties, is widely used in cement-based materials. Research on the application of HPMC in gangue slurry is still in its early stages. Moreover, the interactive effects of various factors on gangue slurry performance have not been thoroughly investigated. The work examined the effects of slurry concentration (X₁), maximum gangue particle size (X₂), and HPMC dosage (X₃) on slurry performance using response surface methodology (RSM). The microstructure of the slurry was characterized via scanning electron microscopy (SEM) and polarized light microscopy (PLM), while low-field nuclear magnetic resonance (LF-NMR) was employed to analyze water distribution. Additionally, industrial field tests were conducted. The results are presented below. (1) X₁ and X₃ exhibited a negative correlation with layering degree and slump flow, while X₂ showed a positive correlation. Slurry concentration had the greatest impact on slurry performance, followed by maximum particle size and HPMC dosage. HPMC significantly improved slurry stability, imposing the minimum negative influence on fluidity. Interaction terms X₁X₂ and X₁X₃ significantly affected layering degree and slump flow, while X₂X₃ significantly affected layering degree instead of slump flow. (2) Derived from the RSM, the statistical models for layering degree and slump flow define the optimal slurry mix proportions. The gangue gradation index ranged from 0.40 to 0.428, with different gradations requiring specific slurry concentration and HPMC dosages. (3) HPMC promoted the formation of a 3D floc network structure of fine particles through adsorption-bridging effects. The spatial supporting effect of the floc network inhibited the sedimentation of coarse particles, which enhanced the stability of the slurry. Meanwhile, HPMC only converted a small amount of free water into floc water, which had a minimal impact on fluidity. HPMC addition achieved the synergistic optimization of slurry stability and fluidity. (4) Field industrial trials confirmed that HPMC-optimized gangue slurry demonstrated significant improvements in both stability and flowability. The optimized slurry achieved blockage-free pipeline transportation, with a maximum spreading radius exceeding 60 m in the goaf and a maximum single-borehole backfilling volume of 2200 m³. Full article

With the increasing integration of renewable energy, the secure operation of distribution networks faces significant challenges, such as voltage limit violations and increased power losses. To address the issue of reactive power and voltage security under renewable generation uncertainty, this paper proposes a graph-based security reinforcement learning method. First, a graph-enhanced neural network is designed, to extract both topological and node-level features from the distribution network. Then, a primal-dual approach is introduced to incorporate voltage security constraints into the agent’s critic network, by constructing a cost critic to guide safe policy learning. Finally, a dual-critic framework is adopted to train the actor network and derive an optimal policy. Experiments conducted on real load profiles demonstrated that the proposed method reduced the voltage violation rate to 0%, compared to 4.92% with the Deep Deterministic Policy Gradient (DDPG) algorithm and 5.14% with the Twin Delayed DDPG (TD3) algorithm. Moreover, the average node voltage deviation was effectively controlled within 0.0073 per unit. Full article

The performance of the UAVs while executing various mission profiles greatly depends on the selection of planning algorithms. Reinforcement learning (RL) algorithms can effectively be utilized for robot path planning. Due to random action selection in case of action ties, the traditional Q-learning algorithm and its other variants face the issues of slow convergence and suboptimal path planning in high-dimensional navigational environments. To solve these problems, we propose an improved deep Q-network (DQN), incorporating an efficient tie-breaking mechanism, prioritized experience replay (PER), and L2-regularization. The adopted tie-breaking mechanism improves the action selection and ultimately helps in generating an optimal trajectory for the UAV in a 3D cluttered environment. To improve the convergence speed of the traditional Q-algorithm, prioritized experience replay is used, which learns from experiences with high temporal difference (TD) error and avoids uniform sampling of stored transitions during training. This also allows the prioritization of high-reward experiences (e.g., reaching a goal), which helps the agent to rediscover these valuable states and improve learning. Moreover, L2-regularization is adopted that encourages smaller weights for more stable and smoother Q-values to reduce the erratic action selections and promote smoother UAV flight paths. Finally, the performance of the proposed method is presented and thoroughly compared against the traditional DQN, demonstrating its superior effectiveness. Full article

Speaker profiling systems are often evaluated on a single corpus, which complicates reliable comparison. We present a fully reproducible evaluation pipeline that trains Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM) models independently on three speech corpora representing distinct recording conditions—studio-quality TIMIT, crowdsourced Mozilla Common Voice, and in-the-wild VoxCeleb1. All models share the same architecture, optimizer, and data preprocessing; no corpus-specific hyperparameter tuning is applied. We perform a detailed preprocessing and feature extraction procedure, evaluating multiple configurations and validating their applicability and effectiveness in improving the obtained results. A feature analysis shows that Mel spectrograms benefit CNNs, whereas Mel Frequency Cepstral Coefficients (MFCCs) suit LSTMs, and that the optimal Mel-bin count grows with corpus Signal Noise Rate (SNR). With this fixed recipe, EfficientNet achieves 99.82% gender accuracy on Common Voice (+1.25 pp over the previous best) and 98.86% on VoxCeleb1 (+0.57 pp). MobileNet attains 99.86% age-group accuracy on Common Voice (+2.86 pp) and a 5.35-year MAE for age estimation on TIMIT using a lightweight configuration. The consistent, near-state-of-the-art results across three acoustically diverse datasets substantiate the robustness and versatility of the proposed pipeline. Code and pre-trained weights are released to facilitate downstream research. Full article