Search Results (3,420)

Cross-border equipment manufacturers in Shandong are under growing pressure to maintain supply chain continuity and long-term sustainability amid geopolitical uncertainty and industrial restructuring. Using quarterly data for 149 listed firms from 2001Q1 to 2024Q3, this study develops an interpretable early-warning model for firms’ relative vulnerability. Because firm-level disruption events are not consistently observable, vulnerability is proxied by return-on-assets underperformance relative to the industry median. We compare a multilayer perceptron (MLP) with logistic regression, decision tree, random forest, XGBoost, and LightGBM, and then use Shapley additive explanations (SHAP) to interpret the selected model. Under the study’s F1-oriented early-warning objective, the multilayer perceptron achieves the highest observed F1 score (the harmonic mean of precision and recall) in our evaluation setting, whereas XGBoost performs slightly better on threshold-independent ranking metrics. The interpretation results show that stronger profitability is associated with lower predicted vulnerability, policy-backed export demand with greater stability, and India-related geopolitical risk with higher predicted vulnerability. These findings suggest that interpretable early-warning tools may help support continuity-oriented operations, resilience investment, and sustainability-oriented industrial upgrading in export-dependent manufacturing regions. Full article

As optical access networks continue to evolve toward higher capacity, longer reach, and increased user density, accurately predicting transmission performance has become increasingly complex. Conventional physics-based models often struggle to capture the nonlinear and stochastic behavior of modern passive optical networks (PONs), particularly under diverse operating conditions. In this study, a hybrid deep learning (DL) framework is proposed for the prediction of key performance indicators, including Q-factor, receiver sensitivity, and bit error rate (BER), in asymmetric 160/80 Gbps TWDM-PON systems, which is the target capacity by ITU-T G.989.1 specifications. The proposed approach integrates Gradient Boosting Regression and Multi-Layer Perceptron models within an ensemble learning structure to enhance robustness and predictive accuracy. A synthetic dataset comprising 1000 samples was generated to emulate realistic transmission scenarios with variations in distance, power level, and noise conditions for both upstream and downstream channels. Experimental results demonstrate strong agreement between the proposed DL-based predictions and conventional optical simulation outcomes, while the proposed predictions achieve superior adaptability and reduced computational complexity. High coefficients of determination (R² > 0.94) and low error metrics confirm the effectiveness of the framework, highlighting its potential as a fast and reliable alternative to traditional performance evaluation methods in next-generation optical access networks. Full article

The Internet of Things (IoT) comprises diverse devices connected through heterogeneous communication protocols to deliver a wide range of services. However, the complexity and scale of IoT networks make them difficult to secure. Network intrusion detection systems (NIDSs) have therefore become essential for identifying malicious activities and protecting IoT environments across many applications. Although recent deep learning (DL)-based IDS approaches achieve strong detection performance, they often require substantial computation and storage, which limits their practicality on resource-constrained IoT devices. To balance detection accuracy with computational efficiency, we propose a lightweight deep learning model for IoT intrusion detection. Specifically, our method learns compact, intrusion-relevant representations from traffic features using a two-layer multi-layer perceptron (MLP) embedding backbone, followed by a linear SoftMax classification head for multi-class attack detection. We evaluate the proposed approach on three benchmark datasets, CICIDS2017, NSL-KDD, and CICIoT2023, and the results show strong performance, achieving 99.85%, 99.21%, and 98.45% accuracy, respectively, while significantly reducing model size and computational overhead. The experimental results demonstrate that the proposed method achieves excellent classification performance while maintaining a lightweight design, with fewer parameters and lower FLOPs than existing approaches. Full article

As a crucial component of multimodal sensing in modern AI agents, remote sensing images have attracted significant attention, for which neural representation is a promising direction. Implicit Neural Representations (INRs) using Multi-Layer Perceptrons (MLPs) have the ability to model images by learning an implicit mapping from pixel coordinates to pixel intensities. This paper revisits the ReLU activation function, a widely adopted non-linearity known for its dead region on the negative axis, within the context of MLP-based INRs. We introduce the Dead-Free Linear Unit (DeLU), a novel activation function that leverages a linearly transformed absolute value to eliminate inactive regions. By combining dead-free non-linearity with adaptive linear scaling, DeLU enhances the expressiveness of INR architectures, particularly those employing periodic activations. Extensive experiments across multiple remote sensing datasets, including LandCover.ai, LoveDA, INRIA, UAVid, and ISPRS Potsdam, validate the efficacy of our proposed method. Full article

This paper proposes a machine-learning-assisted framework for modal sensitivity analysis of systems with viscoelastic damping elements, including both classical and fractional rheological models. Surrogate models are trained to approximate natural frequencies over a prescribed parameter space using two sampling strategies (Grid and Latin Hypercube) and two regression approaches: multi-layer perceptron (MLP) and Gaussian process regression (GPR). Sensitivities are obtained from the surrogates by finite differences and complemented by model-interpretability measures, namely permutation feature importance (PFI) and Shapley Additive Explanations (SHAP). The surrogate-based results are compared with analytically obtained sensitivities. Local first- and second-order sensitivities of natural frequencies are derived analytically using the direct differentiation method (DDM) for a nonlinear eigenvalue problem formulated in the Laplace domain and further transformed into dimensionless sensitivity measures. The methodology is demonstrated for a single-degree-of-freedom oscillator with classical and fractional Kelvin damper models and a two-story frame equipped with a fractional Kelvin damper. The results show very good agreement between analytical and surrogate-based sensitivities. Feature-importance rankings obtained by PFI and SHAP are consistent with the dimensionless sensitivities and capture changes in parameter influence under varying damping levels. Dispersion studies indicate only minor ranking variations. Full article

As autonomous driving technology advances, the deployment of autonomous vehicles in urban environments is rapidly increasing. Lens flare—an often overlooked optical artifact in object detection research—can lead to increased false positives or missed detections, particularly in the challenging conditions inherent to autonomous driving. Current mitigation methods are often ill-suited for real-time implementation. This work proposes a solution to alleviate the adverse effects of lens flare by utilizing a lightweight lens flare perception network, eliminating the need for additional hardware or complex image pre-processing. Specifically, we propose a reference-free model utilizing a ResNet18 backbone integrated with a lightweight Multi-Layer Perceptron (MLP) to extract and leverage lens flare information. This model is developed via a teacher–student framework, which was distilled from an end-to-end reference-based model optimized using the Learned Perceptual Image Patch Similarity (LPIPS) metric. Our experiments demonstrate that incorporating lens flare information significantly enhances the performance of the baseline object detection network, outperforming previous mitigation methods by a substantial margin. The proposed method can be seamlessly integrated into existing object detectors and requires only an efficient training process, facilitating its deployment in practical autonomous driving tasks. Full article

Due to high specific energy absorption, composite/metal hybrid multi-cell thin-walled tubes hold significant potential in the field of automotive passive safety. However, the material coupling effect enhancing SEA often elevated the initial peak crushing force, reducing crushing force efficiency and compromising occupant protection. To balance SEA and CFE, trigger holes were introduced as an induced deformation mechanism for hybrid tubes to reduce IPCF while preserving SEA, with the optimized perforated configuration yielding higher CFE than the non-perforated counterpart. A high-fidelity finite element model of the hybrid tube was developed and experimentally validated, and the influences of induced structural parameters on SEA and CFE were investigated. Given the strong nonlinear coupling between trigger parameters and crashworthiness, a multilayer perceptron surrogate model was constructed using 200 optimal Latin hypercube sampling samples (20 for validation). A Q-learning enhanced particle swarm optimization (QL-PSO) algorithm was adopted for optimization, with reinforcement learning dynamically adjusting PSO parameters to balance global exploration and local exploitation. Finite element simulations validated that the proposed method achieved a favorable SEA-CFE trade-off, with SEA and CFE improved by 12.02% and 16.39% respectively, outperforming reported configurations. Compared with standard PSO, QL-PSO exhibited superior search efficiency and inverse mapping accuracy, with 22% higher optimization efficiency and full compliance with inverse design performance targets. This study provided valuable guidance for the design of thin-walled energy-absorbing structures in multi-material vehicle bodies. Full article

The rising computational demands of deep learning models have intensified concerns regarding their energy consumption and environmental impact, motivating the development of Green Artificial Intelligence (Green AI) approaches. This paper proposes a multi-objective Green AI optimization framework based on the Grey Wolf Optimizer (GWO) to design efficient multilayer perceptron (MLP) architectures. Unlike conventional strategies that focus solely on maximizing accuracy, the proposed method jointly optimizes validation accuracy, training time, number of trainable parameters, and estimated floating-point operations (FLOPs). Evaluated on the Fashion-MNIST dataset and compared against a baseline MLP and Random Search, the GWO-based approach achieves competitive predictive performance while drastically reducing model size, computational complexity, and training time. Pareto front analysis confirms that GWO consistently identifies non-dominated architectures that offer superior trade-offs between accuracy and efficiency. Additional equal-accuracy evaluations demonstrate improved convergence efficiency and stability despite reduced model complexity. The results provide empirical evidence, within the MLP design setting considered in this study, that bio-inspired multi-objective optimization can support Green AI by identifying more compact and efficient architectures with competitive predictive performance. Full article

Deploying artificial intelligence models on low-cost edge devices requires balancing predictive accuracy with strict constraints on computational resources, such as inference latency and memory footprint. Despite growing interest in TinyML systems, limited empirical evidence exists on how these factors interact across different embedded hardware platforms. This study presents a systematic multi-objective evaluation of three lightweight AI architectures—multinomial logistic regression (MLR), multilayer perceptron (MLP), and a reduced convolutional neural network (CNN)—implemented natively on three representative platforms: ESP32-S3, Raspberry Pi Pico, and Raspberry Pi Zero W. The models were evaluated on three image classification datasets of increasing complexity (Synthetic Geometric Figures, MNIST, and Fashion-MNIST), measuring classification accuracy, inference latency, and peak memory footprint under real execution conditions. Pareto-front analysis was used to identify efficient model–platform configurations and characterize the trade-offs between predictive performance and computational resources. The results provide quantitative insight into accuracy–resource trade-offs and establish a reproducible framework for evaluating lightweight AI models on resource-constrained edge devices, supporting informed design decisions in TinyML applications. Full article

Background: Gambling disorders are an escalating public health issue, with notable increases across age groups, particularly among adolescents and young adults. This study examines the role of coping strategies in gambling behaviors among university students aged 17–48 years and explores the prediction potential of artificial neural networks. Methods: The sample included 218 participants (M = 21.89, SD = 5.57). Results: A multilayer perceptron neural network was implemented to classify gambling risk based on coping strategies. Significant correlations between specific coping strategies and higher levels of gambling disorders were revealed. The neural network model demonstrated an 85% accuracy in predicting gambling risk, with the most influential factors identified as autonomy, negative urgency, gender, denial, and lack of perseverance. Conclusions: These findings highlight the effectiveness of neural networks in identifying individuals most at risk for GDs. Full article

Phosphorus (P) deficiency severely limits maize growth and yield, yet early detection remains challenging, as visible symptoms appear only after prolonged starvation. This study evaluated the capability of hyperspectral imaging (HSI) combined with machine learning to detect P deficiency in maize seedlings at both symptomatic and pre-symptomatic stages. Two greenhouse experiments were conducted: a long-term pot system under high and low P conditions and a short-term hydroponic experiment with three P concentrations of 500, 100, and 0 μmol/L phosphate (Pi). After long-term P deficiency, significant reductions in shoot biomass and Pi content were observed, while root biomass increased and nutrient profiles were altered. Hyperspectral signatures revealed distinct wavelength-specific differences across visible, red-edge, and near-infrared (NIR) regions, with P-deficient leaves showing lower reflectance in green and NIR regions but higher reflectance in the red band. A multilayer perceptron machine learning model achieved 99.65% accuracy in discriminating between P treatments. In the short-term experiment, P deficiency significantly reduced tissue Pi content within one week without affecting pigment composition or photosynthetic parameters. Despite the absence of visible symptoms, hyperspectral measurements detected subtle spectral changes, particularly in older leaves, enabling classification accuracies of 80.71–84.56% in the first week and 85.88–90.98% in the second week of P treatment. Conventional vegetation indices showed weak correlations with Pi content and failed to detect early P deficiency. These findings demonstrate that HSI combined with machine learning can effectively detect P deficiency before visible symptoms emerge, offering a non-destructive, rapid diagnostic tool for precision nutrient management in maize production systems. Full article

As a significant source of global carbon emissions, the construction industry (CI) urgently needs to promote green transformation with the help of digital twin (DT) against the backdrop of human–machine collaboration and sustainable development advocated by CI 5.0. However, there is still a lack of systematic research on its specific driving mechanism and carbon reduction path. This study uses a systematic literature review (SLR) to explore how five key DT-enabled capabilities, namely, resource management (RM), process optimization (PO), real-time monitoring (R-Tm), sustainable design (SD), and predictive maintenance (PM), influence three performance indicators: efficiency improvement (EI), energy optimization (EO), and cost control (CC). Data from 490 companies were analyzed using partial least squares structural equation modeling (PLS-SEM) and a multilayer perceptron (MLP) with Shapley additive explanation (SHAP). The results show that the PLS-SEM and MLP models showed consistent patterns, with EO exhibiting the strongest predictive performance (Q² = 0.372; R² = 0.3666), followed by EI (Q² = 0.307; R² = 0.3109) and CC (Q² = 0.305; R² = 0.2609); the SHAP results further indicated that RM contributed most to EI (0.242), while PO was the most important driver for both EO (0.304) and CC (0.259). Academically, it introduces a quantitative approach combining PLS-SEM and machine learning. Practically, it highlights the priority of key technologies with cross-dimensional effects and offers guidance for governments to optimize digital resource allocation and carbon performance evaluation, as well as for enterprises to apply DT more effectively. Full article

Background/Objectives: Leishmaniasis is a group of diseases caused by obligate intracellular parasites of the Leishmania genus and is classified by the World Health Organization as a category I neglected tropical disease. Leishmania infantum predominantly affects children under five years of age and shows an increasing incidence of cutaneous and visceral forms. The development of new therapeutic alternatives remains challenging, making in silico approaches valuable for accelerating antileishmanial drug discovery. This study aimed to identify new compounds with potential activity against Leishmania infantum amastigotes using artificial intelligence-based classification models. Methods: A curated database of compounds with reported biological activity was constructed. Molecular representation employed zero- to two-dimensional descriptors calculated with Dragon software (v 7.0.10). Unsupervised k-means cluster analysis was applied to define training and external prediction sets. Supervised models were developed on the WEKA platform using IBk, J48, multilayer perceptron, and sequential minimal optimization algorithms. Model performance was assessed through internal cross-validation and external validation procedures. Results: All models achieved classification accuracies above eighty percent for both training and prediction sets, indicating consistent predictive performance and good generalization ability. The validated models were applied to virtual screening of the DrugBank database and a collection of synthetic compounds. This screening campaign enabled the identification of one hundred twenty compounds with potential activity against the amastigote form of Leishmania infantum. Conclusions: Artificial intelligence-based QSAR models proved to be useful tools for prioritizing antileishmanial candidates. The integration of molecular descriptors, machine learning, and virtual screening offers an efficient strategy for drug discovery. Full article

Traditional intrusion detection systems for IoT networks achieve high classification accuracy but lack interpretability and actionable incident-response capabilities, limiting their operational value in security-critical environments. This paper presents a graph-based multi-agent framework that integrates ensemble machine learning with Large Language Model (LLM)-powered incident report generation via Retrieval-Augmented Generation (RAG). The system employs a three-phase architecture: (1) a lightweight Random Forest binary pre-detection, achieving 99.49% accuracy with a 6 MB model size for edge deployment; (2) ensemble classification combining Multi-Layer Perceptron, Random Forest, and XGBoost with soft voting and SHAP-based feature attribution for explainability; and (3) a ReAct-based summary agent that synthesizes classification results with external threat intelligence from Web search and scholarly databases to generate evidence-grounded incident reports. To address the challenge of evaluating non-deterministic LLM outputs, we introduce custom RAG evaluation metrics—faithfulness and groundedness implemented via the LLM-as-Judge framework. Experimental validation on the ACI IoT Network Dataset 2023 demonstrates ensemble accuracy exceeding 99.8% across 11 attack classes; perfect groundedness scores (1.0), indicating all generated claims derive from the retrieved context; and moderate faithfulness (0.64), reflecting appropriate analytical synthesis. The ensemble approach mitigates individual model weaknesses, improving the UDP Flood F1 score from 48% (MLP alone) to 95% through soft voting. This work bridges the gap between high-accuracy detection and trustworthy, actionable security analysis for automated incident-response systems. Full article

Modern automotive paints have a thin undercoat and color coat layer protected by a thick clear coat layer. All too often, only the clear coat layer of the automotive paint is recovered at the crime scene of a vehicle-related fatality. Searches for motor vehicle paint databases of clear coats using commercial software typically generate large hitlists that are difficult for a forensic paint examiner to work through unless additional information is provided for the search. To address this problem, deep learning has been applied to the infrared spectra of automotive clear coats to identify patterns in their spectra indicative of the motor vehicle manufacturer. An in-house automotive paint library of 2796 clear coat infrared spectra from six automotive manufacturers and 100 assembly plants was partitioned into training, validation, and prediction sets. Each spectrum has 1880 measurements over the spectral range of 4000 cm⁻¹ to 376 cm⁻¹. Several multilayer perceptron neural network models, each with three hidden layers, were developed that achieved high classification success rates for the training, validation, and prediction sets. The addition of convolutional layers to the deep learning neural network models did not improve the performance of these models. Full article