Search Results (1,445)

Neural networks (NNs) achieve breakthroughs in computer vision and natural language processing, yet their “black box” nature persists. Traditional methods prioritise parameter optimisation and loss design, overlooking NNs’ fundamental structure as topologically organised nonlinear computational systems. This work proposes a complex network theory framework decoding structure–function coupling by mapping convolutional layers, fully connected layers, and Dropout modules into graph representations. To overcome limitations of heuristic compression techniques, we develop a topology-sensitive adaptive pruning algorithm that evaluates critical paths via node strength centrality, preserving structural–functional integrity. On CIFAR-10, our method achieves 55.5% parameter reduction with only 7.8% accuracy degradation—significantly outperforming traditional approaches. Crucially, retrained pruned networks exceed original model accuracy by up to 2.63%, demonstrating that topology optimisation unlocks latent model potential. This research establishes a paradigm shift from empirical to topologically rationalised neural architecture design, providing theoretical foundations for deep learning optimisation dynamics. Full article

This paper presents a flight control framework based on neural network Model Predictive Control (NN-MPC) to tackle the challenges of acceleration command tracking for supersonic vehicles (SVs) in complex flight environments, addressing the shortcomings of traditional methods in managing nonlinearity, random disturbances, and real-time performance requirements. Initially, a dynamic model is developed through a comprehensive analysis of the vehicle’s dynamic characteristics, incorporating strong cross-coupling effects and disturbance influences. Subsequently, a predictive mechanism is employed to forecast future states and generate virtual control commands, effectively resolving the issue of sluggish responses under rapidly changing commands. Furthermore, the approximation capability of neural networks is leveraged to optimize the control strategy in real time, ensuring that rudder deflection commands adapt to disturbance variations, thus overcoming the robustness limitations inherent in fixed-parameter control approaches. Within the proposed framework, the ultimate uniform bounded stability of the control system is rigorously established using the Lyapunov method. Simulation results demonstrate that the method exhibits exceptional performance under conditions of system state uncertainty and unknown external disturbances, confirming its effectiveness and reliability. Full article

Unmanned aerial vehicles (UAVs) are widely used in surveillance and combat for their efficiency and autonomy, whilst complex, dynamic environments challenge the modeling of inter-agent relations and information transmission. This research proposes a novel UAV tactical choice-making algorithm utilizing graph neural networks to tackle these challenges. The proposed algorithm employs a graph neural network to process the observed state information, the convolved output of which is then fed into a reconstructed critic network incorporating a Laplacian convolution kernel. This research first enhances the accuracy of obtaining unstable state information in hostile environments. The proposed algorithm uses this information to train a more precise critic network. In turn, this improved critic network guides the actor network to make decisions that better meet the needs of the battlefield. Coupled with a policy transfer mechanism, this architecture significantly enhances the decision-making efficiency and environmental adaptability within the multi-agent system. Results from the experiments show that the average effectiveness of the proposed algorithm across the six planned scenarios is 97.4%, surpassing the baseline by 23.4%. In addition, the integration of transfer learning makes the network convergence speed three times faster than that of the baseline algorithm. This algorithm effectively improves the information transmission efficiency between the environment and the UAV and provides strong support for UAV formation combat. Full article

In the context of intelligent coal mine safety monitoring, an integrated prediction and early-warning method named MTGNN-Bayesian-IF-DBSCAN (Multi-Task Graph Neural Network–Bayesian Optimization–Isolation Forest–Density-Based Spatial Clustering of Applications with Noise) is proposed to address the challenges of gas concentration prediction and anomaly detection in coal mining faces. The MTGNN (Multi-Task Graph Neural Network) is first employed to model the spatiotemporal coupling characteristics of gas concentration and wind speed data. By constructing a graph structure based on sensor spatial dependencies and utilizing temporal convolutional layers to capture long short-term time-series features, the high-precision dynamic prediction of gas concentrations is achieved via the MTGNN. Experimental results indicate that the MTGNN outperforms comparative algorithms, such as CrossGNN and FourierGNN, in prediction accuracy, with the mean absolute error (MAE) being as low as 0.00237 and the root mean square error (RMSE) maintained below 0.0203 across different sensor locations (T0, T1, T2). For anomaly detection, a Bayesian optimization framework is introduced to adaptively optimize the fusion weights of IF (Isolation Forest) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). Through defining the objective function as the F1 score and employing Gaussian process surrogate models, the optimal weight combination (w_if = 0.43, w_dbscan = 0.52) is determined, achieving an F1 score of 1.0. By integrating original concentration data and residual features, gas anomalies are effectively identified by the proposed method, with the detection rate reaching a range of 93–96% and the false alarm rate controlled below 5%. Multidimensional analysis diagrams (e.g., residual distribution, 45° diagonal error plot, and boxplots) further validate the model’s robustness in different spatial locations, particularly in capturing abrupt changes and low-concentration anomalies. This study provides a new technical pathway for intelligent gas warning in coal mines, integrating spatiotemporal modeling, multi-algorithm fusion, and statistical optimization. The proposed framework not only enhances the accuracy and reliability of gas prediction and anomaly detection but also demonstrates potential for generalization to other industrial sensor networks. Full article

The reliability of unmanned aerial vehicle (UAV) energy storage battery systems is critical for ensuring their safe operation and efficient mission execution, and has the potential to significantly advance applications in logistics, monitoring, and emergency response. This paper reviews theoretical and technical advancements in UAV battery reliability, covering definitions and metrics, modeling approaches, state estimation, fault diagnosis, and battery management system (BMS) technologies. Based on international standards, reliability encompasses performance stability, environmental adaptability, and safety redundancy, encompassing metrics such as the capacity retention rate, mean time between failures (MTBF), and thermal runaway warning time. Modeling methods for reliability include mathematical, data-driven, and hybrid models, which are evaluated for accuracy and efficiency under dynamic conditions. State estimation focuses on five key battery parameters and compares neural network, regression, and optimization algorithms in complex flight scenarios. Fault diagnosis involves feature extraction, time-series modeling, and probabilistic inference, with multimodal fusion strategies being proposed for faults like overcharge and thermal runaway. BMS technologies include state monitoring, protection, and optimization, and balancing strategies and the potential of intelligent algorithms are being explored. Challenges in this field include non-unified standards, limited model generalization, and complexity in diagnosing concurrent faults. Future research should prioritize multi-physics-coupled modeling, AI-driven predictive techniques, and cybersecurity to enhance the reliability and intelligence of battery systems in order to support the sustainable development of unmanned systems. Full article

Forecasting the energy consumption of different consumers became an important procedure with the creation of the European Electricity Market. This study presents a methodology for 24-hour ahead prediction of the energy consumption, which is suitable for application in animal husbandry facilities, such as pig farms. To achieve this, 24 individual models are trained using artificial neural networks that forecast the energy production 1 to 24 h ahead. The selected features include power consumption over the last 72 h, time-based data, average, minimum, and maximum daily temperatures, relative humidities, and wind speeds. The models’ Normalized mean absolute error (NMAE), Normalized root mean square error (NRMSE), and Mean absolute percentage error (MAPE) vary between 16.59% and 19.00%, 22.19% and 24.73%, and 9.49% and 11.49%, respectively. Furthermore, the case studies showed that in most situations, the forecasting error does not exceed 10% with several cases up to 25%. The proposed methodology can be useful for energy managers of animal farm facilities, and help them provide a better prognosis of their energy consumption for the Energy Market. The proposed methodology could be improved by selecting additional features, such as the variation of the controlled meteorological parameters over the last couple of days and the schedule of technological processes. Full article

High-energy solid propellants are multiphase engineering materials, whose mechanical behavior is predominantly governed by the characteristics of embedded crystalline particles. While microstructural influences have been extensively examined, quantitative correlations between microstructure and macroscopic mechanical properties remain underexplored. This work develops a cohesive finite element method (CFEM) framework to quantify the thermomechanical response of high-energy solid propellants at the microstructural scale. The analysis focuses on impact loading at strain rates ranging from 10³ to 10⁴ s⁻¹, accounting for large deformation, thermomechanical coupling, and microcrack-induced failure. Damage evolution under impact conditions was evaluated using a combined neural network-based inverse identification method and a three-dimensional cohesive finite element model to determine temperature-dependent bilinear-polynomial cohesive parameters. Results demonstrate a strong dependence of the propellant’s mechanical behavior on both strain rate and temperature. Validation against experimental data confirms that the proposed temperature-sensitive CFEM accurately predicts both damage progression and macroscopic mechanical responses. Full article

The rapid evolution of deep learning (DL) has fundamentally transformed the paradigm for detecting special components in agricultural products, addressing critical challenges in food safety, quality control, and precision agriculture. This comprehensive review systematically analyzes many seminal studies to evaluate cutting-edge DL applications across three core domains: contaminant surveillance (heavy metals, pesticides, and mycotoxins), nutritional component quantification (soluble solids, polyphenols, and pigments), and structural/biomarker assessment (disease symptoms, gel properties, and physiological traits). Emerging hybrid architectures—including attention-enhanced convolutional neural networks (CNNs) for lesion localization, wavelet-coupled autoencoders for spectral denoising, and multi-task learning frameworks for joint parameter prediction—demonstrate unprecedented accuracy in decoding complex agricultural matrices. Particularly noteworthy are sensor fusion strategies integrating hyperspectral imaging (HSI), Raman spectroscopy, and microwave detection with deep feature extraction, achieving industrial-grade performance ($RPD$ > 3.0) while reducing detection time by 30–100× versus conventional methods. Nevertheless, persistent barriers in the “black-box” nature of complex models, severe lack of standardized data and protocols, computational inefficiency, and poor field robustness hinder the reliable deployment and adoption of DL for detecting special components in agricultural products. This review provides an essential foundation and roadmap for future research to bridge the gap between laboratory DL models and their effective, trusted application in real-world agricultural settings. Full article

Breast cancer detection through non-invasive and accurate techniques remains a critical challenge in medical diagnostics. This study introduces a deep learning-based framework that leverages a microwave radar system equipped with an arc-shaped array of six antennas to estimate key tumor parameters, including position, size, and depth. This research begins with the evolutionary design of an ultra-wideband octagram ring patch antenna optimized for enhanced tumor detection sensitivity in directional near-field coupling scenarios. The antenna is fabricated and experimentally evaluated, with its performance validated through S-parameter measurements, far-field radiation characterization, and efficiency analysis to ensure effective signal propagation and interaction with breast tissue. Specific Absorption Rate (SAR) distributions within breast tissues are comprehensively assessed, and power adjustment strategies are implemented to comply with electromagnetic exposure safety limits. The dataset for the deep learning model comprises simulated self and mutual S-parameters capturing tumor-induced variations over a broad frequency spectrum. A core innovation of this work is the development of the Attention-Based Feature Separation (ABFS) model, which dynamically identifies optimal frequency sub-bands and disentangles discriminative features tailored to each tumor parameter. A multi-branch neural network processes these features to achieve precise tumor localization and size estimation. Compared to conventional attention mechanisms, the proposed ABFS architecture demonstrates superior prediction accuracy and interpretability. The proposed approach achieves high estimation accuracy and computational efficiency in simulation studies, underscoring the promise of integrating deep learning with conformal microwave imaging for safe, effective, and non-invasive breast cancer detection. Full article

In space gravitational wave detection, various physical effects in the spacecraft, such as self-gravity, electricity, and magnetism, will introduce undesirable parasitic stiffness. The coupling noise between stiffness and the motion states of the test mass critically affects the performance of scientific detection, making accurate stiffness identification crucial. In response to the question, this paper proposes a method to optimize the test mass motion state for enhancing stiffness identification performance. First, the dynamics of the test mass are studied and a recursive least squares algorithm is applied for the implementation of on-orbit stiffness identification. Then, the motion state of the test mass is parametrically characterized by multi-frequency sinusoidal signals as the variable to be optimized, with the optimization objectives and constraints of stiffness identification defined based on convergence time, convergence accuracy, and engineering requirements. To tackle the dual-objective, computationally expensive nature of the problem, a multigranularity surrogate-assisted evolutionary algorithm with individual progressive constraints (MGSAEA-IPC) is proposed. A fuzzy radial basis function neural network PID (FRBF-PID) controller is also designed to address complex control needs under varying motion states. Numerical simulations demonstrate that the convergence time after optimization is less than 2 min, and the convergence accuracy is less than 1.5 × 10⁻¹⁰ s⁻². This study can provide ideas and design references for subsequent related identification and control missions. Full article

Computational Fluid Dynamics (CFD) is regarded as an important tool for analyzing the flow field, thermal environment, and air quality around the built environment. However, for built environment applications, the high computational cost of CFD hinders large-scale scenario simulation and efficient design optimization. In the field of built environment research, surrogate modeling has become a key technology to connect the needs of high-fidelity CFD simulation and rapid prediction, whereas the low-dimensional nature of traditional surrogate models is unable to match the physical complexity and prediction needs of built flow fields. Therefore, combining machine learning (ML) with CFD to predict flow fields in built environments offers a promising way to increase simulation speed while maintaining reasonable accuracy. This review briefly reviews traditional surrogate models and focuses on ML-based surrogate models, especially the specific application of neural network architectures in rapidly predicting flow fields in the built environment. The review indicates that ML accelerates the three core aspects of CFD, namely mesh preprocessing, numerical solving, and post-processing visualization, in order to achieve efficient coupled CFD simulation. Although ML surrogate models still face challenges such as data availability, multi-physics field coupling, and generalization capability, the emergence of physical information-driven data enhancement techniques effectively alleviates the above problems. Meanwhile, the integration of traditional methods with ML can further enhance the comprehensive performance of surrogate models. Notably, the online ministry of trained ML models using transfer learning strategies deserves further research. These advances will provide an important basis for advancing efficient and accurate operational solutions in sustainable building design and operation. Full article

Urban expansion will squeeze the green space system and cause ecological fragmentation. The question of how to expand cities more scientifically and build eco-cities has become an important topic of sustainable urban construction. This paper takes Shanghai as a research case. A deep neural network combined with an attention mechanism model measures the comprehensive level of the built environment and green space pattern of urbanization and quantitatively analyzes the coordinated relationship between the two using the coupled degree of coordination model. Subsequently, the K-Means clustering model was used for spatial clustering to determine the governance and construction directions for different spatial areas and was, finally, combined with the LightGBM model plus SHAP to analyze the importance and threshold effect of the indicators on the degree of coupled coordination. The results of the study show that (1) the core area of the city shows a high state of coordination, indicating that Shanghai has a better green space construction in the central city, but the periphery shows different imbalances; (2) three different kinds of areas are identified, and different governance measures as well as the direction of urbanization are proposed according to the characteristics of the different areas; and (3) this study finds that the structural indicators of the built environment, such as Average Compactness, Weighted Average Height, and Land Use Diversity, have a significant influence on the coupling coordination degree and have different response thresholds. The results of the study provide theoretical support for regional governance and suggestions for the direction of urban expansion for sustainable urbanization. Full article

Some chemical reactors exhibit coupled dynamics with multiple equilibrium points and strong nonlinearities. The accurate modeling of these dynamics is crucial to optimal control and increasing the reactor’s economic performance. While neural networks can effectively handle complex nonlinearities, they sacrifice interpretability. Alternatively, block-oriented Hammerstein–Wiener models and Koopman operator-based linear predictors combine nonlinear representation with linear dynamics, offering a gray-box identification approach. This paper comprehensively reviews recent advancements in both the Hammerstein–Wiener and Koopman operator methods and benchmarks their accuracy against neural network-based approaches to modeling a large-scale industrial Fluid Catalytic Cracking fractionator. Furthermore, Monte Carlo simulations are employed to validate performance under varying signal-to-noise ratios. The results demonstrate that the Koopman bilinear model significantly outperforms the other methods in terms of accuracy and robustness. Full article

Human-Robot Collaboration (HRC) is pivotal for flexible, worker-centric manufacturing in Industry 5.0, yet dynamic task allocation remains difficult because operator states—fatigue and skill—fluctuate abruptly. I address this gap with a hybrid framework that couples real-time perception and double-estimating reinforcement learning. A Convolutional Neural Network (CNN) classifies nine fatigue–skill combinations from synthetic physiological cues (heart-rate, blink rate, posture, wrist acceleration); its outputs feed a Double Deep Q-Network (DDQN) whose state vector also includes task-queue and robot-status features. The DDQN optimises a multi-objective reward balancing throughput, workload and safety and executes at 10 Hz within a closed-loop pipeline implemented in MATLAB R2025a and RoboDK v5.9. Benchmarking on a 1000-episode HRC dataset (2500 allocations·episode⁻¹) shows the hybrid CNN+DDQN controller raises throughput to 60.48 ± 0.08 tasks·min⁻¹ (+21% vs. rule-based, +12% vs. SARSA, +8% vs. Dueling DQN, +5% vs. PPO), trims operator fatigue by 7% and sustains 99.9% collision-free operation (one-way ANOVA, p < 0.05; post-hoc power 1 − β = 0.87). Visual analyses confirm responsive task reallocation as fatigue rises or skill varies. The approach outperforms strong baselines (PPO, A3C, Dueling DQN) by mitigating Q-value over-estimation through double learning, providing robust policies under stochastic human states and offering a reproducible blueprint for multi-robot, Industry 5.0 factories. Future work will validate the controller on a physical Doosan H2017 cell and incorporate fairness constraints to avoid workload bias across multiple operators. Full article

Weighted belief propagation (WBP) for the decoding of linear block codes is considered. In WBP, the Tanner graph of the code is unrolled with respect to the iterations of the belief propagation decoder. Then, weights are assigned to the edges of the resulting recurrent network and optimized offline using a training dataset. The main contribution of this paper is an adaptive WBP where the weights of the decoder are determined for each received word. Two variants of this decoder are investigated. In the parallel WBP decoders, the weights take values in a discrete set. A number of WBP decoders are run in parallel to search for the best sequence- of weights in real time. In the two-stage decoder, a small neural network is used to dynamically determine the weights of the WBP decoder for each received word. The proposed adaptive decoders demonstrate significant improvements over the static counterparts in two applications. In the first application, Bose–Chaudhuri–Hocquenghem, polar and quasi-cyclic low-density parity-check (QC-LDPC) codes are used over an additive white Gaussian noise channel. The results indicate that the adaptive WBP achieves bit error rates (BERs) up to an order of magnitude less than the BERs of the static WBP at about the same decoding complexity, depending on the code, its rate, and the signal-to-noise ratio. The second application is a concatenated code designed for a long-haul nonlinear optical fiber channel where the inner code is a QC-LDPC code and the outer code is a spatially coupled LDPC code. In this case, the inner code is decoded using an adaptive WBP, while the outer code is decoded using the sliding window decoder and static belief propagation. The results show that the adaptive WBP provides a coding gain of 0.8 dB compared to the neural normalized min-sum decoder, with about the same computational complexity and decoding latency. Full article