Search Results (288)

Hyperspectral imaging (HSI) has potential for forensic entomology, but its practical use is limited by manual region-of-interest (ROI) delineation before spectral extraction. This step is time-consuming, operator-dependent, and difficult to standardize across insect species and developmental stages. Here, we developed an automated individual-level ROI-to-spectrum workflow for HSI analysis of forensically important insects. The dataset included 63 hyperspectral images and 1868 manually annotated insect individuals, covering larvae, pupae, and adults. The proposed Hyperspectral Imaging Fully Convolutional Network (HSI-FCN) segmented insect body regions from three-band pseudo-RGB images, back-projected the predicted masks to the original HSI data cubes, generated individual-level ROIs, and extracted full-band mean spectra. On an independent test set containing 204 insect individuals, HSI-FCN achieved mean Dice and intersection over union (IoU) values of 0.9079 and 0.8328, respectively, and showed the best overall performance among representative segmentation models. All test individuals were successfully matched with their corresponding manual ROIs. Spectra extracted from automated ROIs were highly consistent with manual ROI spectra, with a mean spectral angle mapper of 3.06° and a Pearson correlation coefficient of 0.9956. These results show that the proposed workflow can replace manual ROI delineation with a reproducible preprocessing step for insect HSI analysis, supporting standardized spectral extraction and future applications in forensic entomology. Full article

High-precision flood identification from high-resolution remote sensing images using deep learning network models is challenging. Severe cloud interference, limited receptive fields, insufficient boundary refinement and spatial detail preservation, and difficulty in accurately distinguishing water bodies from ground object shadows constrain the extraction method. Therefore, this study proposes an automatic flood information extraction method that integrates an improved Fully Convolutional Network classification and recognition model (FCN-RAM) with a rough tolerance set. First, a tolerance rough set algorithm was employed for sample data preprocessing. Subsequently, a Residual Attention Module (RAM) was introduced to optimize the U-Net architecture, dynamically adjusting the response intensity of deep features in both the channel and spatial dimensions to construct a deep learning-based FCN-RAM. Finally, comparative analyses were conducted on three high-resolution remote sensing datasets with different resolutions: Global surface water detection in Large-size very-High-resolution satellite imagery (GLH-Water), Gaofen Image Dataset (GID), and Earth Surface Water Dataset (ESWD). The results demonstrated that FCN-RAM consistently and substantially outperformed the baseline U-Net across all three datasets, achieving F1-score improvements of 10.64% (GLH-Water), 9.71% (GID), and 10.64% (ESWD), with corresponding overall accuracy gains of 9.97%, 11.15%, and 10.22%, respectively. Notably, the Intersection-over-Union (IoU) scores were elevated by 17.59% (GLH-Water), 15.66% (GID), and 13.63% (ESWD). The method also surpassed state-of-the-art models including ResNet and Water-SCNet, attaining peak overall accuracies of 98.61% (GLH-Water) and 97.37% (GID). Notably, while the proposed framework exhibits remarkable generalization across the evaluated multi-resolution benchmarks, its current validation is primarily confined to static water body delineation tasks. The model’s transferability to highly heterogeneous geographical regions with scarce training samples, as well as its extendability toward dynamic time-series flood evolution modeling, warrants further systematic investigation. The proposed method significantly improves the accuracy of waterbody information extraction, meets the requirements for high-precision information extraction from high-resolution imagery, and provides technical support for intelligent flood information extraction using high-resolution remote sensing. Full article

Objective pain assessment remains a significant challenge in clinical and research settings due to the subjective nature of self-reported measures. Physiological signals, particularly electrodermal activity (EDA), have emerged as promising indicators of autonomic responses associated with pain. Although recent advances in deep learning have improved the modelling of complex biosignals, many existing approaches remain computationally demanding, limiting their applicability for real-time monitoring in wearable and embedded systems. This paper proposes a fully convolutional network (FCN) for automated pain recognition using EDA signals. The proposed model is designed to efficiently capture temporal patterns in physiological data while maintaining low computational complexity. The approach is evaluated on the AI4Pain dataset for three-class pain classification (No Pain, Low Pain, High Pain). Experimental results show that the proposed FCN achieves an accuracy of 79.23% in offline evaluation. Furthermore, the model enables real-time inference with a latency of 0.47 ms, achieving 73.14% accuracy during real-time operation. These results demonstrate that convolutional architectures can provide an effective balance between predictive performance and computational efficiency, supporting the development of real-time physiological pain monitoring systems using wearable sensing technologies. Full article

Accurate mortality prediction is essential to actuarial practice as it is directly linked to insurance pricing, reserving, and the management of longevity risk. This study proposes a deep neural network (DNN) model for the mortality rates of multiple populations; it is composed of long short-term memory (LSTM) and convolutional neural network (CNN) components. As mortality trends evolve over long time horizons, and as capturing the complex dependencies among mortality rates across countries or regions with a linear model is challenging, the LSTM and CNN were applied to mortality modeling. The former can automatically learn long-term dependencies of sequential data, whereas the latter can extract local features from grid or sequential data. Formulated as a nonlinear generalization of the Lee–Carter decomposition, the model maps the log-mortality matrix $logM$ to future $logm(x,t)$ end-to-end and generates multi-step forecasts through dynamic recursive prediction. Then, the DNN and baseline models were used to fit mortality data of 21 countries from the Human Mortality Database (HMD), which were divided into training and test sets with the year 2000 as the split point. Extensive numerical experiments from the perspectives of accuracy, stability, and reliability of long-term forecasting revealed that DNN models yield better predictive performance, particularly the LSTM-CNN model. It combines the LSTM, CNN, and fully connected network (FCN) layers and thus exploits each deep neural network to fit nonlinear age, period, and cohort effects as well as their interactive terms to achieve better predictive performance. However, the CNN still outperformed other models for certain groups. In addition, the conclusions hold for remaining life expectancy. Full article

Satellites supporting IoT connectivity may need to serve a large population of LoRa terminals, where collisions among packets using the same spreading factor (SF) can severely degrade uplink reliability. The ALOHA-based access used in LEO-IoT leads to frequent collisions under massive terminal access, which limits system capacity. Conventional signal separation methods that rely on the capture effect typically require a sufficiently large power difference between colliding signals. However, due to the channel characteristics of LEO links, this condition is often difficult to satisfy. We propose ConvLoRa, a collision demodulation method for co-SF LoRa uplink signals in LEO-IoT based on a fully convolutional neural network (FCN). To improve robustness to synchronization deviations, ConvLoRa uses an up-chirp in the preamble as a reference for feature matching, and employs data augmentation to emulate synchronization deviations during training. In addition, a multi-task design is adopted to estimate the payload length with minimal introduction of extra network parameters. Experiments show that ConvLoRa achieves lower demodulation bit error rate (BER) under collision conditions compared with baselines, including CoRa and SIC-based receivers. Under the condition of a two-signal collision with SNR = −9 dB and SF = 8, the BER of the proposed method is 21% that of CoRa and 28% that of the SIC-based method. Full article

Background: Electrocardiography (ECG), particularly the 12-lead configuration, is a crucial method for identifying heart rhythm abnormalities. However, its effectiveness can be reduced by noise contamination. State-of-the-art denoising methods based on neural networks have demonstrated promising performance in denoising complex biosignals like ECG. However, most of these methods have focused on denoising single-lead ECG recordings. Methods: This research aims to leverage the inherent correlation among multi-lead ECG signals. Therefore, a multi-lead convolutional denoising autoencoder (ML-CDAE) model is proposed, to learn more effective representations, leading simultaneously to improved denoising performance and enhanced quality of 12-lead ECG recordings. Results: The findings indicate that ML-CDAE consistently outperforms a single-lead convolutional denoising autoencoder (SL-CDAE) and fully convolutional denoising autoencoder (FCN-DAE) model in denoising ECG signals corrupted by a mixture of physical noises. In particular, the mean squared error ($\mathrm{MSE}$) and signal-to-noise ratio improvement (${\mathrm{SNR}}_{\mathrm{imp}}$) are used as evaluation metrics to assess the performance. Conclusions: The strong correlation among multi-lead ECG signals can be leveraged not only to enhance the denoising performance of the ML-CDAE model but also to simultaneously denoise 12-lead ECG signals more successfully compared to both the SL-CDAE and FCN-DAE models. Full article

Semantic segmentation of metallographic micrographs is a key task for quantitative microstructural analysis in additive manufacturing, yet it remains challenging due to phase heterogeneity, complex morphologies, and the scarcity of annotated data. The MetalDAM dataset, composed of 42 labeled scanning electron microscopy images of steel microstructures, has been widely adopted as a benchmark, with U-Net commonly reported as the strongest supervised baseline. Nevertheless, the encoder–decoder structure of U-Net imposes architectural constraints that hinder the precise delineation of heterogeneous and irregular phase boundaries under severe data limitations. To address this limitation, this paper investigates a Fully Convolutional Network (FCN)-based architecture as an alternative approach for semantic segmentation on the MetalDAM dataset. The FCN is trained and evaluated under the same experimental protocol as the U-Net baseline, enabling a direct and fair comparison. Performance is assessed using multiple evaluation metrics, including Intersection over Union (IoU), precision, recall, and mean Average Precision at an IoU threshold of 0.5. The results show that the FCN achieves comparable overall IoU values (0.75) while delivering substantial improvements at the class level, particularly for minority and morphologically complex phases, with gains of up to 25–30% in class-specific IoU. Additional metrics confirm enhanced robustness, with consistently higher precision, recall, and mAP@0.5 values. These findings demonstrate that FCN-based architectures constitute a competitive and robust alternative to U-Net for metallographic segmentation in additive manufacturing scenarios characterized by limited annotated data. Full article

Amid China’s shift from a model of urban “incremental expansion” to one focused on “stock optimization”, the renewal of streetscapes has taken center stage as a critical approach to improving the human experience within urban environments. However, empirical insight into how visual interventions affect aesthetic perception across different road types remains notably limited. This study addresses that gap through a spatiotemporal investigation of Zhengzhou’s streetscape transformations between 2017 and 2022. Major roads were categorized into four functional types—freeway, under-freeway, regular road, and tunnel—to better capture perceptual variation. Leveraging a Fully Convolutional Network (FCN), we extracted nine visual components from historical street views and paired them with crowd-sourced “beauty” ratings from the MIT Place Pulse 2.0 dataset. Statistical analyses, including paired t-tests and Kernel Density Estimation (KDE), indicated marked improvements in perceived beauty following renewal, with the exception of tunnel segments. Through Random Forest (RF) regression and SHapley Additive exPlanations (SHAP) interpretation, greening emerged as the most influential driver of aesthetic enhancement—most prominently on regular roads (SHAP = 2.246). The impact of renewal was found to be context-specific: green belts were most effective in under-freeway areas (SHAP = +0.8), while improvements to pavement (SHAP = +0.97) and street vitality were key for regular roads. Notably, SHAP analysis revealed non-linear relationships, such as diminishing perceptual returns when green coverage exceeded certain thresholds. These findings inform a “visual renewal–perceptual response” framework, offering data-driven guidance for adaptive, human-centered upgrades in high-density urban settings. Full article

To solve the difficulty of autonomous decision-making caused by the complex driving environment and changeable weather conditions, an end-to-end autonomous decision-making method based on residual network (ResNet), convolutional block attention module (CBAM) and bidirectional long short-term memory network (BiLSTM) is proposed for intelligent vehicles. Firstly, ResNet is used to extract spatial feature information contained in driving scene images. Then, CBAM is adopted to assign weights to each network channel and dynamically focus on important spatial regions in the image. Finally, BiLSTM is constructed to process the contextual features of continuous scenes, and the autonomous decision-making of intelligent vehicles is achieved through the fusion of spatial features and temporal information. On this basis, the proposed network model is trained using a real-world driving dataset and fully tested in various scenarios. Moreover, ablation experiments are conducted to verify the contribution of each module to the overall performance. The results show that the proposed method has better accuracy and stability compared with multiple existing methods, including PilotNet, FCN-LSTM, and DBNet, and its accuracy reaches 90.16% under clear weather conditions, as well as 81.29% under nighttime and snowy weather conditions. Full article

Background/Objectives: The difficulties caused by breast cancer have been addressed in a number of ways. Since it is said to be the second most common cause of death from cancer among women, early intervention is crucial. Early detection is difficult because of the existing detection tools’ shortcomings in objectivity and accuracy. Quadra Sense, a fusion of deep learning (DL) classifiers for mitosis detection in breast cancer histopathology, is proposed to address the shortcomings of current approaches. It demonstrates a greater capacity to produce more accurate results. Methods: Initially, the raw dataset is preprocessed by using a normalization by means of color channel normalization (zero-mean normalization) and stain normalization (Macenko Stain Normalization), and the artifact can be removed via median filtering and contrast enhancement using histogram equalization; ROI identification is performed using modified Fully Convolutional Networks (FCNs) followed by the feature extraction (FE) with Modified InceptionV4 (M-IV4), by which the deep features are retrieved and the feature are selected by means of a Self-Improved Seagull Optimization Algorithm (SA-SOA), and finally, classification is performed using Mito-Quartet. Results: Ultimately, using a performance evaluation, the suggested approach achieved a higher accuracy of 99.2% in comparison with the current methods. Conclusions: From the outcomes, the recommended technique performs well. Full article

Electric motor drives with a wide variety of applications are usually derived with inverters, where the inverter switches are always prone to different types of faults. Short circuit faults can rapidly shut down systems, and open-circuit ones can lead to secondary damage if they are not detected and tolerated in time. Due to this fact, in this paper, a novel data-driven fault detection and diagnosis (FDD) method has been proposed to detect and locate all types of inverter switch faults. Three deep learning algorithms, including fully connected neural networks (FCNs), convolutional neural networks (CNNs), and bidirectional long short-term memory (BiLSTM), have been implemented and compared. The BiLSTM network with 98.45% accuracy outperforms the others and can detect all types of faults in less than half a fundamental period under different and variable speeds with the existence of noise. The results show that the proposed method is highly effective and is a great candidate for real-time applications. Full article

Under the background of urban stock renewal, the quality improvement of public spaces in aged residential areas is confronted with challenges such as inefficient data collection, disconnection between subjective and objective evaluations, and insufficient dynamic adaptability. To address these issues, this study develops and applies a data-driven framework to achieve an objective, precise, and diagnostically powerful evaluation. Focusing on the Zhongshan Road Sub-district of Qingdao and based on 46 typical public space samples, we utilize a Fully Convolutional Network (FCN) for the semantic segmentation of panoramic images, deriving nine objective spatial indicators. We then combine morphological classification and Principal Component Analysis (PCA) to uncover latent correlations and use K-means clustering to pinpoint framework blind spots and heterogeneous spatial types. The results not only diagnose the specific vitality deficits of different spatial types but also demonstrate the method’s capacity to support targeted renewal strategies. This data-driven approach provides a reference framework for achieving precise and objective assessment in urban renewal, moving beyond subjective assumptions to offer a robust theoretical and empirical foundation for governance. Full article

Recently, deep learning models such as convolutional neural networks (CNNs), convolutional autoencoders (CAEs), CNN-based support vector machines (SVMs), YOLO, fully convolutional networks (FCNs), fully convolutional data descriptions (FCDDs) and so on have been applied to defect detections and anomaly detections of various kinds of industrial products, materials and systems. In those models, downsampled images, including target features, are used for training and testing. On the other hand, although various types of anomaly detection systems based on time series data such as sounds and vibrations are also applied to manufacturing processes, complicated conversions to the frequency domain are basically needed in conventional approaches. This paper addresses an important industrial problem for detecting anomalies in machine tools at low cost using audio data. Intelligent anomaly diagnosis systems for computer numerical control (CNC) machine tools are considered and proposed, in which raw time-series data without the need of conversion to the frequency domain can be directly used for training and testing. As for the NN models for comparison, conventional shallow NN, RNN and 1D CNN are designed and trained using the nine kinds of mechanical sounds. Classification results of test sound block (SB) data by the three models are shown. Then, an autoencoder (AE) is designed and considered for the identifier by training it using only normal SB data of a machine tool. One of the technical needs in dealing with time-series data such as SB data by NNs is how to clearly visualize and understand anomalous regions in concurrence with identification. Finally, we propose the SB data-based FCDD model to meet this need. Basic performance of the SB data-based FCDD model is evaluated in terms of anomaly detection and concurrent visualization of understanding. Full article

Tailings storage facilities (TSFs) have experienced numerous global failures, many linked to active deposition on tailings beaches. Understanding these processes is vital for effective management. As deposition alters surface elevation, developing an explainable model to predict the changes can enhance insight into deposition dynamics and support proactive TSF management. This study applies deep learning (DL) to predict surface elevation changes in tailings storage facilities (TSFs) from high-resolution digital elevation models (DEMs) generated from UAV photogrammetry. Three DL architectures, including multilayer perceptron (MLP), fully convolutional network (FCN), and residual network (ResNet), were evaluated across spatial patch sizes of 64 × 64, 128 × 128, and 256 × 256 pixels. The results show that incorporating broader spatial contexts improves predictive accuracy, with ResNet achieving an $R2$ of 0.886 at the 256 × 256 scale, explaining nearly 89% of the variance in observed deposition patterns. To enhance interpretability, SHapley Additive exPlanations (SHAP) were applied, revealing that spatial coordinates and curvature exert the strongest influence, linking deposition patterns to discharge distance and microtopographic variability. By prioritizing predictive performance while providing mechanistic insight, this framework offers a practical and quantitative tool for reliable TSF monitoring and management. Full article

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing automatic depth gate calculation using derivative analysis and eliminated the need for manual parameter tuning. Even though this method demonstrates robust flaw indication, it faces difficulties for automatic defect detection in highly noisy data or in cases with large pore zones. Considering this, multiple DL architectures—including fully connected networks, convolutional neural networks, and a novel Convolutional Attention Temporal Transformer for Sequences—are developed and trained on diverse datasets comprising simulated CIVA data and real-world data files from welded and composite specimens. Experimental results show that while the FCN architecture is limited in its ability to model dependencies, the CNN achieves a strong performance with a test accuracy of 94.9%, effectively capturing local features from PAUT signals. The CATT-S model, which integrates a convolutional feature extractor with a self-attention mechanism, consistently outperforms the other baselines by effectively modeling both fine-grained signal morphology and long-range inter-beam dependencies. Achieving a remarkable accuracy of 99.4% and a strong F1-score of 0.905 on experimental data, this integrated approach demonstrates significant practical potential for improving the reliability and efficiency of NDT in complex, heterogeneous materials. Full article