Search Results (952)

The main motivation for this study is to develop a predictive framework that provides high accuracy at lower computational and experimental costs, resulting in better decision-making in the chosen application domain. Artificial neural networks (ANNs) are widely used for prediction, classification, and pattern recognition tasks. However, their performance is sensitive to the selection of architectural and learning parameters. Hence, an important research challenge is the effective selection of architectural and learning parameters. Several hybrid GA–PSO approaches have been proposed, but most of the existing studies simultaneously optimize network architecture and trainable parameters or focus on a single application domain. However, there is still a lack of systematic framework that optimizes these components separately and validates its performance on multiple heterogeneous datasets. To fill this gap, this study proposes a novel hybrid optimization algorithm, called GAPSO, which combines the genetic algorithm (GA) and particle swarm optimization (PSO) for efficient tuning of artificial neural network (ANN) parameters. The proposed framework is evaluated on five benchmark datasets, including AirPassengers, Sunspots, Death and Injury, Earthquake, and Insurance. In the proposed approach, PSO is used for determination of optimal network architecture (number of hidden neurons) and GA is used for optimization of connection weights and threshold values. The experimental results demonstrate that for four out of five datasets, the lowest MAPE values were achieved by GAPSO-ANN, and were competitive compared to ANN, GA-ANN, PSO-ANN, LSTM and XGBoost models. Additionally, the Wilcoxon signed-rank test showed statistically significant performance improvements (p = 0.03125). Full article

Distinguishing between human-made interferences and natural background disturbances is of great significance for the safe operation of terrestrial optical cables because human-caused damage can be halted through timely intervention. To address the problem of small-sample disturbance recognition in distributed acoustic sensing (DAS) systems, this paper proposes a fused CNN–SVM classification model based on hybrid features. A convolutional neural network is employed to extract the high-level spatiotemporal features of disturbance signals, which are subsequently fused with statistical features and fed into a support vector machine for classification. Evaluated on open-source data, the proposed model achieves accuracy improvements of 9.1%, 8.7%, and 2.7% over the conventional CNN, the statistical-feature-based SVM, and the conventional CNN-SVM model, respectively. Furthermore, based on field-measured data, a dataset comprising 5664 samples was constructed, covering four typical disturbance-event types: background noise, drilling, knocking, and digging. The field classification results demonstrate that the three-layer convolutional structure of the model achieves a recognition accuracy of 98.5%. Both the ROC curves and multiple evaluation metrics indicate that the proposed three-layer fused CNN–SVM model delivers better classification performance and more balanced category recognition, offering a feasible reference for similar fiber disturbance engineering tasks. Full article

Accurate waveform classification in noisy environments is an important task in modern communications, radar signal analysis, biomedical signal interpretation, industrial monitoring and other signal processing systems. This paper investigates the performance of three neural network architectures: Multilayer Perceptron (MLP), one-dimensional Convolutional Neural Network (1D-CNN), and Long Short-Term Memory (LSTM) for multiclass waveform classification in the presence of Additive White Gaussian Noise (AWGN). A time series dataset consisting of multiple waveform classes is generated and corrupted with AWGN across a wide range of signal-to-noise ratio (SNR) levels to simulate noisy signal distortion conditions. The three models are trained and evaluated under identical conditions to ensure a fair comparison. Their classification performance is evaluated in terms of accuracy, Confusion Matrix (CM), Receiver Operating Characteristic (ROC) curve and the Area Under the ROC curve (AUC) across varying SNR values. Simulation results demonstrate that the 1D-CNN effectively captures local temporal patterns and achieves superior robustness in classification at moderate and high SNR levels. The LSTM model demonstrates the ability to capture temporal dependencies in sequential waveform data but exhibits sensitivity to waveform variations due to amplitude, phase and frequency changes and noise at lower SNR values. The MLP, although computationally simpler, shows comparatively limited performance in low-SNR conditions due to its lack of temporal feature extraction capability. For the case of multiclass deterministic waveforms, the accuracy of classification for the 1D-CNN and LSTM is nearly 100% at SNR = 5 dB showing their robustness in classification, whereas the accuracy of MLP is approximately 70% that shows poor classification in noisy conditions. When there is random amplitude, frequency and phase variations in the waveforms, the accuracy of the 1D-CNN and MLP increases with SNR, and 1D-CNN superior to MLP. However, the LSTM accuracy fails to improve with SNR, resulting in poor classification performance in such a scenario. The results provide an insight into the suitability of different neural architectures for waveform classification tasks in noisy communication or other time series applications and highlight the advantages of convolutional feature extraction for robust signal recognition. Full article

Spiking neural networks (SNNs) are well suited for modeling temporally evolving information due to their event-driven and dynamic neuronal mechanisms. Nevertheless, the majority of existing SNN topologies are constructed through algorithmic procedures rather than guided by constraints from biological brain connectivity, which weakens their biological plausibility. In our earlier work, we developed a spiking neural network (SNN) by incorporating topological information from functional brain networks extracted from functional magnetic resonance imaging (fMRI) data of healthy individuals, and named the resulting model fMRISNN. Nevertheless, the fMRI data used in previous work were resting-state fMRI. Compared with resting-state fMRI, task-state fMRI can capture brain-region coordination patterns induced by specific task stimuli, and the resulting functional brain network is therefore more closely related to the corresponding task. Motivated by this advantage, this study replaces the resting-state topology used in previous fMRISNN studies with a task-state, number/digit-related fMRI topology and validates the resulting Task-fMRISNN on handwritten digit recognition. The experimental results demonstrate that the proposed Task-fMRISNN outperforms the Rest-fMRISNN in terms of recognition accuracy, lesion robustness, and noise robustness. In addition, the Task-fMRISNN achieves significantly better performance than several baseline models constructed using algorithmically generated topologies. While deep convolutional neural networks (CNNs) may deliver superior absolute recognition performance, the proposed fMRISNN provides a more compact model structure and shows potential resource-efficiency advantages due to its sparse and event-driven computational characteristics. Full article

Background/Objectives: Advancements in neuroscience and machine learning have increasingly enabled brain pattern recognition based on bio-signal measurements, such as electroencephalography (EEG). These developments support next-generation technologies, including brain–computer interfaces (BCIs) and AI-assisted systems. However, volume conduction (VC) effects remain a major source of contamination in EEG recordings, affecting both univariate analyses and functional connectivity estimation. Methods: In this work, we propose a VC mitigation method that explicitly models and suppresses VC components in the observed functional networks. Specifically, the observed functional network is decomposed into a matrix capturing only VC-related components (i.e., components attributed to volume conduction) and a residual matrix, where the residual is regarded as a proxy for a VC-mitigated functional network that better reflects the underlying functional interactions. The VC component matrix is modeled using a decay function parameterized by the inter-electrode distance matrix, capturing the dominant spatial bias induced by VC. To estimate these parameters, we introduce supervised channel importance, quantified as the mutual information between experimental labels and channel signals, as a proxy for task-relevant neural activity. The parameters are optimized such that the unsupervised node importance derived from the VC-mitigated functional network, defined as the average node strength, aligns with the supervised channel importance. Results: Evaluation results using a deep-learning framework demonstrate that, compared with the observed functional network, the VC-mitigated functional network improves classification performance in brain pattern recognition tasks. Full article

Electromyographic (EMG) signals are increasingly used in wearable cyber–physical systems (CPS), where reliable movement recognition must be achieved under limited computational resources. In this study, we present a compact EMG processing framework that integrates signal acquisition, preprocessing, segmentation, and movement classification within a unified pipeline designed for embedded-oriented applications. The proposed approach combines a multi-channel EMG acquisition system with a lightweight one-dimensional convolutional neural network (1D CNN) developed according to TinyML principles, withprocessing input windows of size 32 × 3 and low computational complexity and memory requirements. Experimental evaluation was conducted on a dataset collected from 15 participants performing squat, walking, and running activities under realistic acquisition conditions. The proposed model achieved an accuracy of 0.9135, an F1-score of 0.9124, and a ROC AUC of approximately 0.96, demonstrating reliable classification performance. Following 8-bit quantization, the model size was reduced to approximately 2 KB, supporting deployment on resource-constrained embedded platforms. The results show that compact CNN architectures can effectively classify EMG-based movement patterns while maintaining a small computational footprint, providing a practical foundation for future wearable CPS and TinyML-enabled applications. Full article

Acoustic gait recognition is an emerging passive biometric modality that identifies individuals by unique walking sound patterns. This work presents a reproducible benchmarking framework for convolutional neural network (CNN)-based acoustic gait recognition, providing a systematic evaluation methodology across varying identity pool sizes. Raw footstep recordings from the AFPILD dataset were converted into 128-bin mel-spectrograms and used to train a compact CNN across identity pool sizes from 10 to 40 subjects. To ensure statistical reliability, a three-times-repeated five-fold stratified cross-validation protocol was implemented. Experimental results demonstrate strong discriminative capability, with validation accuracy reaching 94.92% and Equal Error Rate (EER) of 1.31% for the 40-subject configuration. A multi-seed subset validation experiment across five independent random subject draws per pool size confirmed that the observed scaling trend is consistent across subset compositions rather than an artifact of a single subject selection. Additional analysis confirmed the framework’s resilience to moderate environmental noise and its superiority over classical Mel-Frequency Cepstral Coefficients paired with a Support Vector Machine (MFCC-SVM) and Convolutional Recurrent Neural Network (CRNN) baselines, supporting the feasibility of acoustic gait recognition as a passive biometric modality. Full article

Radar signal sorting (RSS) and radar emitter recognition (RER) constitute foundational yet challenging operations in electronic reconnaissance, where RSS aims to accurately segregate interleaved radar pulse streams and RER aims to recognize their originating emitters. Existing methods typically address RSS and RER as separate processes within a sequential streaming framework, which neglect the inherent interdependence and collaborative potential between them, thereby resulting in error accumulation and performance bottleneck. In this paper, we redefine the radar signal sorting and recognition (RSSR) problem from an integrated modeling perspective, decomposing it into three sub-problems, i.e., signal pattern detection, signal pattern extraction, and detection result integration. In order to effectively solve these problems, we propose a novel Unified Framework inspired by Object Detection (UFiOD). Firstly, an end-to-end neural network is constructed to simultaneously optimize the regression of signal temporal occurrence regions and the recognition of signal categories. Then, a template matching algorithm is designed to extract corresponding pulses from the regions based on the signal categories. Finally, an integration algorithm based on temporal correlation and direction of arrival (DOA) fuses the detection results to generate object-level sorting and recognition conclusions. We extensively validate the effectiveness of the proposed method on simulation datasets. It demonstrates robust performance under various interleaving scenarios, including the interleaving of homogeneous radar emitters. Notably, it exhibits impressive capability for handling unknown signals, further highlighting its practical utility. Full article

Regularization plans, acceleration mechanisms, and optimization strategies all have a significant impact on the convergence behavior of neural network training algorithms. A thorough analysis of a batch gradient method (BGM) improved with momentum and penalty terms for training wavelet feedforward neural networks (WFNNs) is presented in this research. In nonlinear function approximation challenges, the suggested approach seeks to enhance convergence speed, stability, and generalization performance. To prove the monotonicity, weak convergence, and strong convergence of the training process under the combined influence of momentum regularization and penalty, a rigorous mathematical framework is created. While the momentum term speeds up convergence by reducing oscillations in the gradient trajectory, the penalty term suppresses weight overgrowth and overfitting. The algorithm is applied to the Peaks function, Sinc function, and 5-bit parity problem to support these theoretical findings. The findings show that in terms of quicker convergence, lower mean squared error (MSE), and smaller gradient norms, the suggested BGM with penalty and momentum performs better than traditional BGM with L₂ regularization. Smoother optimization dynamics and improved generalization are revealed by the training convergence and gradient norm evolution curves. The suggested method offers a cohesive viewpoint on integrating momentum acceleration, regularization, and penalty into gradient-based optimization for WFNNs. It is a promising technique for function approximation, pattern recognition, and control system applications since it provides both theoretical convergence guarantees and real-world increases in learning efficiency. Full article

To address the issues of low perception accuracy and poor robustness in traditional motion recognition methods within complex walking environments for visually impaired individuals, this study utilizes multi-modal data, including ECG, PPG, and IMU, for classification. Regarding the low filtering efficiency of multi-modal data, an improved wavelet filtering algorithm based on LSTM is proposed. To further enhance classification accuracy, this paper introduces a motion recognition method for the blindfolded mobility simulation based on an Attention-based Two-Stream Deep Fusion Convolutional Neural Network (ATS-DFCNN). The proposed method constructs a two-stream heterogeneous feature extraction architecture by synchronously collecting tri-axial motion signals and physiological signals from subjects. A 1D-CNN is employed to capture the spatial geometric features of limb movements, while a hybrid CNN-GRU network is utilized to mine the temporal evolution patterns of physiological stress. Furthermore, an attention mechanism is introduced to achieve dynamic weighted fusion at the feature level, which strengthens critical motion features and suppresses environmental noise. Experiments were conducted with 10 subjects simulating the movements of visually impaired individuals, covering typical actions such as walking, standing, climbing stairs, descending stairs, and falling. The results demonstrate that the proposed adaptive filtering algorithm achieves an AUC of 0.942, significantly improving feature distinctiveness compared to traditional algorithms. The ATS-DFCNN model achieved an average recognition accuracy of 92.2% across five activity categories, representing a 4.8% performance increase over single IMU modal classification. Particularly in fall detection, the model effectively reduces false alarms through physiological feedback and accurately infers motion intentions, providing reliable technical support for the safety monitoring of intelligent walking-aid systems. Full article

Plant recognition plays a vital role in agriculture and biodiversity monitoring, and deep learning, particularly convolutional neural networks (CNNs), has gained increased attention for automating this task. However, CNNs have a limitation in their ability to handle complex patterns due to the difficulty in capturing global contextual information. Furthermore, plant datasets are often created in laboratory environments that minimize discrimination challenges, enabling the analysis of model performance. This study proposes a hybrid deep learning model, HDL-PlantNet, for real-world plant recognition on the primary dataset, the Cyprus Seasonal Flora Image Dataset (CSFID), comprising 27 plant species. The HDL-PlantNet model integrates an EfficientNetV2-S convolutional backbone with a Transformer encoder to capture both spatial contextual and long-range dependencies. Additionally, the Swedish Leaf Dataset is used as a supplementary dataset to analyze the consistency of the HDL-PlantNet under controlled environments. Five benchmark CNN models are used for comparative evaluation, and statistical tests and an ablation study are conducted to assess the results. The proposed model achieved the highest observed Macro-F1 and Macro-AUC scores among the evaluated models, reaching 90.06% and 99.59%, respectively. The results demonstrate that combining convolutional and Transformer architectures yields computationally effective performance in fine-grained plant classification while maintaining a compact model size suitable for further research. This study contributes to real-time plant identification studies and supports informed ecological decision-making. Full article

The intermittent nature of renewable energy sources such as solar and wind power poses significant challenges for grid stability and energy management. Accurate forecasting is crucial for mitigating these challenges, as traditional models such as Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) often fail to capture the non-linear relationships between weather patterns and energy generation. To address this limitation, this research proposes a machine learning framework leveraging Convolutional Neural Networks (CNNs) for spatial pattern recognition and Recurrent Neural Networks (RNNs) for time-series forecasting. By integrating system design parameters with meteorological data, the framework aims to enhance prediction accuracy. The potential outcomes of this framework are not just improved grid stability, optimized energy storage utilization, and reduced operational costs, but also a significant step towards the efficient integration of renewable energy into the power system, fostering a sense of optimism for the future of renewable energy forecasting. Full article

The recent rapid growth of deep learning has significantly reshaped the landscape of computer vision, establishing itself as the preferred paradigm for various tasks. Deep learning methods have demonstrated superior performance compared to previous state-of-the-art machine learning techniques across various fields. This review provides a concise overview of artificial neural networks (ANNs) and some of the most significant deep learning architectures, such as recurrent neural networks (RNNs), generative adversarial networks (GANs) and radial basis function networks (RBFNs). This review not only outlines the historical context and structures of these architectures but also provides a sophisticated understanding of their applications across different computer vision domains. A rigorous and comprehensive overview of these architectures is discussed throughout this review, and an essential systematic comparative analysis based on specific benchmarking criteria is provided. While individual deep learning frameworks excel in distinct domains, selecting the optimal architecture requires a balanced trade-off between algorithmic complexity, computational overhead, data dependencies, and structural interpretability. An intuitive and holistic benchmarking process synthesizes the core characteristics, technical configurations, operational constraints, and developmental pathways toward Explainable AI (XAI) and Green AI sustainability for the examined architectures (ANNs, RNNs, LSTMs, GANs, and RBFNs). Additionally, in this work the advantages and limitations of these architectures are discussed. Furthermore, an investigation of their applications in diverse computer vision tasks is carried out. Full article

Extracting relational triples from unstructured text is essential for information extraction and knowledge graph construction, but it remains challenging in complex scenarios involving overlapping entities and diverse relational patterns. To address this issue, this paper proposes an Information-Enhanced Multi-Scale Fusion Convolutional Neural Network (EnInfo-Mulscal FCNN) for joint entity–relation extraction. The model uses BERT to obtain contextual representations, predicts candidate relations through multi-label classification, incorporates relation-aware features into entity recognition, and introduces a multi-scale fusion convolutional module and an attention-based entity filtering mechanism to enhance subject–object correspondence modeling. Experiments on the NYT-star and WebNLG datasets demonstrate the effectiveness of the proposed method. Experiments show that EnInfo-Mulscal FCNN achieves precision, recall, and F1-score values of 87.2%, 75.1%, and 80.7% on NYT-star and 86.3%, 88.3%, and 87.3% on WebNLG, respectively. Compared with ETL-span, our model improves the F1-score by 2.7% on NYT-star and 4.2% on WebNLG. Compared with PRE-span, our model improves the F1-score by 4.3%, demonstrating its effectiveness in relational triple extraction. These results indicate that the proposed method improves relational triple extraction by enhancing information in the relation identification, entity recognition, and entity filtering stages, thereby improving triple generation in complex text scenarios. Full article

Driven by the energy transition and carbon-neutrality targets, global demand for critical minerals is increasing rapidly, while the discovery of new mineral deposits has become increasingly challenging because easily detectable outcropping deposits are being depleted, and exploration is shifting toward concealed ore systems. In this context, data-driven approaches based on machine learning (ML) and deep learning (DL) are increasingly complementing conventional geological, geochemical, geophysical, and remote-sensing methods. This review provides a structured synthesis of AI-based mineral exploration studies published over the past decade, focusing on four key aspects: theoretical foundations; applications to diverse exploration datasets, including remote sensing, geochemistry, geophysics, and drill-core imagery; advances in mineral prospectivity mapping (MPM); and emerging trends and challenges, such as limited labeled data, uncertainty quantification, geological consistency, explainability, physics-informed neural networks (PINNs), and the adaptation of foundation models to geoscience data. Convolutional neural networks, autoencoders, generative adversarial networks, Transformers, and graph neural networks show strong potential for improving pattern recognition, data integration, and workflow automation. Overall, AI-based exploration is expected to play an increasingly important role in detecting concealed mineral deposits and strengthening resilient critical-mineral supply chains. Full article