Search Results (178)

Predictive maintenance for marine engines requires forecasts that are both accurate and technically interpretable. This work introduces BEACON, a hybrid architecture that combines a bidirectional long short-term memory encoder with attention pooling, a Kolmogorov Arnold network and a lightweight multilayer perceptron for cylinder-level exhaust gas temperature forecasting, evaluated in both centralized and federated learning settings. On operational data from a bulk carrier, BEACON outperformed strong state-of-the-art baselines, achieving an RMSE of $0.5905$, MAE of $0.4713$ and $R^2$ of approximately 0.95, while producing interpretable response curves and stable SHAP rankings across engine load regimes. A second contribution is the explicit evaluation of explanation stability in a federated learning setting, where BEACON maintained competitive accuracy and attained mean Spearman correlations above $0.8$ between client-specific SHAP rankings, whereas baseline models exhibited substantially lower agreement. These results indicate that the proposed hybrid design provides an accurate and explanation-stable foundation for privacy-aware predictive maintenance of marine engines. Full article

In modern bioinformatics, the analysis of high-dimensional data (genomic, metabolomic, etc.) remains a critical challenge due to the “curse of dimensionality,” where feature redundancy reduces classification efficiency and model interpretability. This study introduces a novel method, AIMarkerFinder (v0.1.0), for analyzing metabolomic data to identify key biomarkers. The method is based on a denoising autoencoder with an attention mechanism (DAE), enabling the extraction of informative features and the elimination of redundancy. Experiments on glioblastoma and adjacent tissue metabolomic data demonstrated that AIMarkerFinder reduces dimensionality from 446 to 4 key features while improving classification accuracy. Using the selected metabolites (Malonyl-CoA, Glycerophosphocholine, SM(d18:1/22:0 OH), GC(18:1/24:1)), the Random Forest and Kolmogorov–Arnold Networks (KAN) models achieved accuracies of 0.904 and 0.937, respectively. The analytical formulas derived by the KAN provide model interpretability, which is critical for biomedical research. The proposed approach is applicable to genomics, transcriptomics, proteomics, and the study of exogenous factors on biological processes. The study’s results open new prospects for personalized medicine and early disease diagnosis. Full article

Due to the large mass, high end load, and long action distance of a mill relining manipulator, gravity effects inevitably lead to a reduction in end effector positioning accuracy. To solve this problem, an online calculation method is proposed to realize real-time end effector deformation prediction. First, a manipulator is simplified into two cantilever beams: the upper arm and the forearm. Second, a reaction force and moment transformation model is established based on the coupling relationship between the forearm and upper arm. Third, finite element (FE) static analysis and simulation are carried out to obtain the end deformation. A total of 3528 discrete joint configurations are selected to cover the entire joint space, and their corresponding FE solutions are used to establish the end deformation offline dataset. Finally, an online deformation calculation algorithm based on Kolmogorov–Arnold networks (KANs) is developed to predict end deformation in any working condition. Visualization analysis and validation experiments are conducted and demonstrate the superiority of the proposed method in reducing gravity effects and improving computational efficiency. In summary, the proposed method provides support for end position compensation, especially for heavy-duty manipulators. Full article

Short-term photovoltaic (PV) power forecasting is pivotal for grid stability and high renewable-energy integration, yet existing hybrid deep-learning models face three unresolved challenges: they fail to balance accuracy, computational efficiency, and interpretability; cannot mitigate iTransformer’s inherent weakness in local feature capture (critical for transient events like minute-level cloud shading); and rely on linear concatenation that mismatches the nonlinear correlations between global multivariate trends and local fluctuations in PV sequences. To address these gaps, this study proposes a novel lightweight hybrid framework—DSC-Chebyshev KAN-iTransformer—for 15-min short-term PV power forecasting. The core novelty lies in the synergistic integration of Depthwise Separable Convolution (DSC) for low-redundancy local temporal pattern extraction, Chebyshev Kolmogorov–Arnold Network (Chebyshev KAN) for adaptive nonlinear fusion and global nonlinear modeling, and iTransformer for efficient capture of cross-variable global dependencies. This design not only compensates for iTransformer’s local feature deficiency but also resolves the linear fusion mismatch issue of traditional hybrid models. Experimental results on real-world PV datasets demonstrate that the proposed model achieves an $R^2$ of 0.996, with root mean square error (RMSE) and mean absolute error (MAE) reduced by 19.6–62.1% compared to state-of-the-art baselines (including iTransformer, BiLSTM, and DSC-CBAM-BiLSTM), while maintaining lightweight characteristics (2.04M parameters, 3.90 GFLOPs) for urban edge deployment. Moreover, Chebyshev polynomial weight visualization enables quantitative interpretation of variable contributions (e.g., solar irradiance dominates via low-order polynomials), enhancing model transparency for engineering applications. This research provides a lightweight, accurate, and interpretable forecasting solution, offering policymakers a data-driven tool to optimize urban PV-infrastructure integration and improve grid resilience amid the global energy transition. Full article

Tornado occurrence and detection are well established in mesoscale meteorology, yet the application of deep learning (DL) to radar-based tornado detection remains nascent and under-validated. This study benchmarks DL approaches on TorNet, a curated dataset of full-resolution, polarimetric Weather Surveillance Radar-1988 Doppler (WSR-88D) radar volumes. We evaluate three canonical architectures (e.g., CNN, VGG19, and Xception) under five optimizers and assess the effect of replacing conventional MLP heads with Kolmogorov–Arnold Network (KAN) layers. To address severe class imbalance and label noise, we implement radar-aware preprocessing and augmentation, temporal splits, and recall-sensitive training. Models are compared using accuracy, precision, recall, and ROC-AUC. Results show that KAN-augmented variants generally converge faster and deliver higher rare-event sensitivity and discriminative power than their baselines, with Adam and RMSprop providing the most stable training and Lion showing architecture-dependent gains. We contribute (i) a reproducible baseline suite for TorNet, (ii) evidence on the conditions under which KAN integration improves tornado detection, and (iii) practical guidance on optimizer–architecture choices for rare-event forecasting with weather radar. Full article

Crop diseases and pests have a significant impact on planting costs and crop yields and, in severe cases, can threaten food security and farmers’ incomes. Currently, most researchers employ various deep learning methods, such as the YOLO series algorithms and U-Net and its variants, for the detection of agricultural plant diseases. However, the existing algorithms suffer from insufficient interpretability and are limited to linear modeling, which can lead to issues such as trust crises in current technologies, restricted applications and difficulties in tracing and correcting errors. To address these issues, a dual-module Kolmogorov–Arnold Network (U-PKAN) is proposed for agricultural plant disease detection in this paper. A KAN encoder–decoder structure is adopted to construct the network. To ensure the network fully extracts features, two different modules, namely Patchembed-KAN (P-KAN) and Decoder-KAN (D-KAN), are designed. To enhance the network’s feature fusion capability, a KAN-based symmetrical structure for skip connections is designed. The proposed method places learnable activation functions on weights, enabling it to achieve higher accuracy with fewer parameters. Moreover, it can reveal the compositional structure and variable dependencies of synthetic datasets through symbolic formulas, thus exhibiting excellent interpretability. A field corn disease image dataset was collected and constructed. Additionally, the performance of the U-PKAN model was verified using the open plant disease dataset PlantDoc and a gear pitting dataset. To better understand the performance differences between different methods, U-PKAN was compared with U-KAN, U-Net, AttUNet, and U-Net++ models for performance benchmarking. IoU and the Dice coefficient were chosen as evaluation metrics. The experimental results demonstrate that the proposed method achieves faster convergence and higher segmentation accuracy. Overall, the proposed method demonstrates outstanding performance in aspects such as function approximation, global perception, interpretability and computational efficiency. Full article

As a critical energy component in electric vehicles, energy storage systems, and other applications, the accurate estimation of the State of Health (SOH) of lithium-ion batteries is crucial for performance optimization and safety assurance. To this end, this paper proposes a hybrid model named Transformer–KAN, which integrates Transformer architecture with Kolmogorov–Arnold Networks (KANs) for precise SOH estimation of lithium-ion batteries. Initially, five health features (HF1–HF5) strongly correlated with SOH degradation are extracted from the historical charge–discharge data, including constant-voltage charging duration, constant-voltage charging area, constant-current discharging area, temperature peak time, and incremental capacity curve peak. The effectiveness of these features is systematically validated through Pearson correlation analysis. The proposed Transformer–KAN model employs a Transformer encoder to capture long-term dependencies within temporal sequences, while the incorporated KAN enhances the model’s nonlinear mapping capability and intrinsic interpretability. Experimental validation conducted on the NASA lithium-ion battery dataset demonstrates that the proposed model outperforms comparative baseline models, including CNN–LSTM, Transformer, and KAN, in terms of both RMSE and MAE metrics. The results indicate that the Transformer–KAN model achieves superior estimation accuracy while exhibiting enhanced generalization capabilities across different battery instances, indicating its strong potential for practical battery management applications. Full article

Hyperspectral anomaly detection (HAD) remains a critical challenge in remote sensing, aiming to precisely separate sparse, unknown anomalies from complex, high-proportion backgrounds. Although deep learning architectures, particularly the Transformer, dominate HAD, their effectiveness is constrained by two fundamental deficiencies: the architectural flaw of “uniform processing” across feature tokens and the microscopic reliance on fixed non-linear activation functions, which are mathematically insufficient for modeling the complex HSI spectral features. To address this dual challenge, this paper introduces the Synergistic Kolmogorov–Arnold Network and Fidelity-Gated Transformer (KANGT) framework. This novel framework integrates two synergistic innovations: the Fidelity-Gated Context-Aware Transformer (GCAT), which employs a reconstruction fidelity-based gating module named the Contextual Feature Matching Module (CFMM) to explicitly and dynamically separate background and anomaly processing streams, and the KAN-MLP module, which replaces traditional Feed-Forward Networks (FFNs) with learnable, spline-based functions, enabling superior adaptive non-linear feature approximation. Extensive experiments on challenging real-world HSI datasets consistently demonstrate KANGT’s superior performance compared to existing methods, and the average AUC reached 0.9921 on eight datasets. This work establishes a robust new paradigm for HAD, with future efforts aimed at optimizing the computational efficiency of KANs to meet real-time application demands. Full article

To address the core challenges of multivariate nonlinear coupling and long-term temporal dependency in 4D UAV trajectory prediction, this study proposes an innovative model named KAN-Former. On a 21-dimensional multimodal UAV dataset, KAN-Former achieves statistically significant improvements over all baseline models, reducing the mean squared error (MSE) by 8.96% compared to the standard Transformer and by 2.66% compared to the strongest physics-informed baseline (PITA), while decreasing the mean absolute error (MAE) by 7.43% relative to TimeMixer/PatchTST. The model adopts a collaborative architecture with two key components: first, a “vertical–horizontal” cross-dimensional attention mechanism—where the vertical branch models physical correlations among multivariate variables using hierarchical clustering priors, and the horizontal branch employs a blockwise dimensionality reduction strategy to efficiently capture long-term temporal dynamics; second, it represents the first application of Kolmogorov–Arnold decomposition in trajectory prediction, replacing traditional feedforward networks with learnable combinations of B-spline basis functions to approximate high-dimensional nonlinear mappings. Ablation studies verify the effectiveness of each module, with the KAN module alone reducing MSE by 6.59%. Moreover, the model’s feature clustering results align closely with UAV physical characteristics, significantly improving interpretability. The demonstrated improvements in accuracy, interpretability, and computational efficiency make KAN-Former highly suitable for real-world applications such as real-time flight control and air traffic management, providing reliable trajectory forecasts for decision-making systems. This work offers a new paradigm for trajectory prediction in complex dynamic systems, successfully integrating theoretical innovation with practical value. Full article

An on-load tap changer (OLTC) is a critical component of power transformers, and the vibration signals generated during its operation provide valuable information for forecasting equipment conditions and anomalies. In this study, we propose a novel mixture-of-experts-based Kolmogorov–Arnold network (KAN) model, referred to as MoEKAN, to enhance the accuracy of time series forecasting for the vibration signals of the OLTC. The proposed MoEKAN incorporates reversible instance normalization (RevIN) to flexibly adapt to changes in data distribution and employs a transformer-based gating mechanism to dynamically integrate forecasts from various KAN expert models. In addition, multi-scale signal processing is performed to effectively capture the complex periodicity and patterns present in the vibration data. Experiments using real OLTC operational data demonstrate that the MoEKAN model achieves superior forecasting performance, recording forecasting errors with MSE, MAE, and MAPE values of 133.4579, 7.2801, and 4.4272, respectively, outperforming all comparison models. These results validate the practicality and contribution of the proposed model and confirm its potential as a highly reliable diagnostic tool for condition monitoring and predictive maintenance of OLTCs. Full article

Focusing on the mechanical characteristics of robotic dexterous hand tea-picking, this paper takes the harvesting of the premium tea Huangshan Maofeng as an example and proposes an adaptive impedance control method for tea-picking dexterous hands based on the Whale Optimization Algorithm (WOA) and Kolmogorov–Arnold Network (KAN). Firstly, within the impedance control framework, a KAN neural network with cubic B-spline functions as activation functions is introduced. Subsequently, the WOA is applied to optimize the B-splines, enhancing the network´s nonlinear fitting and global optimization capabilities, thereby achieving dynamic mapping and real-time adjustment of impedance parameters to improve the accuracy of tea bud contact force-tracking. Finally, simulation results show that under working conditions such as stiffness mutation and dynamic changes in desired force, the proposed method reduces the overshoot by 14.2% compared to traditional fixed-parameter impedance control, while the steady-state error is reduced by 99.89%. Experiments on tea-picking using a dexterous hand equipped with tactile sensors show that at a 50Hz control frequency, the maximum overshoot is about 6%, further verifying the effectiveness of the proposed control algorithm. Full article

Artificial Intelligence (AI) is rapidly transforming engineering fields, from robotics to aerospace, with applications in control systems for UAVs and satellites. This work builds on a previously developed AI attitude controller for the InnoCube 3U nanosatellite. Deploying complex Neural Networks (NNs) on resource-limited microcontrollers presents a significant challenge. To overcome this, we propose distilling a Multi-Layer Perceptron (MLP) trained with Deep Reinforcement Learning (DRL) for attitude control into a Kolmogorov–Arnold Network (KAN). We convert this numeric KAN into a symbolic KAN, where each edge represents a learnable mathematical function, and finally extract a concise symbolic formula. This symbolic representation dramatically reduces memory usage and computational complexity, making it ideal for pico- and nanosatellites. We evaluate and demonstrate the feasibility of this approach for inertial pointing with reaction wheels in simulation using a realistic model of the InnoCube satellite. Our results show that the highly compressed KANs successfully solve the attitude control problem, while reducing the required memory footprint and inference time on the InnoCube ADCS hardware by over an order of magnitude. Beyond attitude control, we believe symbolic KANs hold great potential in aerospace for neural network compression and interpretable, data-driven modeling and system identification in future space missions. Full article

Cybersecurity remains a key challenge in the development of intelligent telecommunications systems and the Internet of Things (IoT). The growing destructive impact of the digital environment, coupled with high-performance computing (HPC), requires the development of effective countermeasures to ensure the security of the digital space. Traditional approaches to detecting destructive content are primarily limited to static text analysis, which ignores the temporal dynamics and evolution of destructive impact scenarios. This is critical for monitoring tasks in the digital environment, where threats rapidly evolve. To overcome this limitation, this study proposes a hybrid architecture, Hyb-TKAN, based on adaptive algorithms that account for the temporal component and nonlinear dependencies. This approach enables not only the classification of destructive messages but also the analysis of their development and transformation over time. Unlike existing studies, which focus on individual aspects of aggressive content, the model utilizes multilayered data analysis to identify hidden relationships and nonlinear patterns in destructive messages. The integration of these components ensures high adaptability and accuracy of text processing. The presented approach was implemented in a multi-class classification task with evaluation based on real text data. The obtained results demonstrate improved classification accuracy. In the Experimental Analysis Section, the results are compared with the closest modern analogs, confirming the relevance and competitiveness of the proposed hybrid neural network. Full article

Accurate and robust power load forecasting is a cornerstone for efficent energy management and the sustainable integration of renewable energy. However, the practical application of current deep learning methods is hindered by two critical challenges: the rigidity of fixed-length prediction horizons and the difficulty in capturing the complex, heterogeneous temporal patterns found in real-world load data. To address these limitations, this paper proposes the multi-scale adaptive forecasting with multi-expert collaboration (MAFMC) framework. MAFMC’s primary contribution is a novel architecture that utilizes a collaborative ensemble of specialized expert predictors, enabling it to dynamically adapt to complex and non-linear load dynamics with superior accuracy. Furthermore, it introduces an innovative iterative learning strategy that allows for highly flexible, variable-length forecasting without the need for costly and time-consuming retraining. This capability significantly enhances operational efficiency in dynamic energy environments. Extensive evaluations on three benchmark datasets demonstrate that MAFMC achieves state-of-the-art performance, consistently outperforming leading baseline methods and establishing a new standard for power load forecasting. Full article

The tunneling face poses a significant risk for gas disaster in coal mining due to the complex interplay of geological conditions, ventilation strategies, and construction techniques, resulting in nonlinear and spatiotemporal dynamics in gas concentration distribution. Accurate prediction of gas levels is crucial for ensuring the safety of coal mining operations. This study introduces a novel approach for gas concentration forecasting at the tunneling face by integrating the Kolmogorov–Arnold Network (KAN) with an enhanced iTransformer model, leveraging multi-source sensor data for enhanced predictive capabilities. KAN improves the feature extraction ability due to flexible mapping kernel function that is capable of capturing complicated nonlinearities between gas emission volume and environmental variables. iTransformer, with concentrated attention mechanism and sparsity pattern, can further model very long-term sequence dependencies and learn to capture multi-scale features. As a whole, they address the problem of gradient vanishing and insufficient feature extraction in the temporal sequential prediction models based on deep learning methods with long sequences input, leading to significant improvements in prediction accuracy and model stability. Experiments on site monitoring datasets demonstrate that the proposed KAN + iTransformer model achieved better fitting and generalization capacity than two baseline models (iTransformer, Transformer) for gas concentration prediction. Full article