Search Results (24)

A coupled multi-stage learning framework is presented for joint bit error rate (BER) prediction and beam angle optimization in massive multiple-input multiple-output (MIMO) systems under a controlled simulation protocol. Unlike purely sequential benchmarking pipelines, the proposed method jointly coordinates BER prediction and beam-angle selection through a shared latent representation, an uncertainty-guided refinement mechanism, a cross-stage consistency loss and alternating optimization. Ten diverse approaches are systematically evaluated across two task-specific stages: Stage 1 examines six classical and adapted methods for BER prediction, including polynomial regression and deep unfolding networks; Stage 2 investigates four machine-learning and generative adversarial network (GAN)-based approaches for angle optimization, including conditional GANs and the proposed Direct-Angle neural network. Stage 3 couples the best-performing methods into a unified hybrid architecture through a shared encoder, explicit consistency regularization and alternating cross-stage updates, thereby producing an integrated beamforming decision strategy rather than an independent cascade. It is shown through the evaluation that the coupled hybrid framework achieves 96.0% overall angle-selection accuracy, a mean BER of $8.0\times {10}^{-5}$ and 100% BER tolerance compliance within $\pm 3$ dB. In this framework, a differentiable BER surrogate initialized from a second-degree polynomial-regression teacher is coupled with the proposed Direct-Angle-NN for angle optimization. Relative to the strongest reimplemented literature baseline under the same controlled simulation assumptions, a 33.3% reduction in mean BER is achieved. Ablation experiments show that the coupling mechanism provides a modest but consistent improvement over the decoupled sequential baseline, increasing angle-selection accuracy from 93.5% to 96.0% and reducing mean BER from $1.05\times {10}^{-4}$ to $8.0\times {10}^{-5}$; the shared encoder accounts for the largest part of this gain while the consistency loss adds 0.6 percentage points. These results indicate that the shared encoder, consistency regularization and uncertainty-guided refinement improve the final beamforming decision, although the gain should be interpreted as incremental rather than as a large architectural breakthrough. A spectral efficiency of 38.0 bps/Hz and an energy efficiency of 0.466 Gbps/W are achieved with a power consumption of only 32.6 W. The theoretical discussion is presented as an analytical characterization of BER sensitivity, complemented by a computational-complexity assessment and empirical convergence diagnostics for the alternating optimization, rather than as a formal optimality proof. The effectiveness of the framework across multiple performance metrics is supported by Monte Carlo simulations, while the limitations of the current setup, including perfect CSI, uncoded QPSK, ideal hardware assumptions and a fixed beam codebook, are explicitly discussed. The complete simulation framework, including code and trained models, can be made available by the corresponding author upon reasonable request to facilitate reproducible research in massive MIMO optimization. Full article

Accurate JIC (Japanese Investigation Committee) classification of osteonecrosis of the femoral head (ONFH) is critical for collapse risk prediction and hip-preserving treatment. However, clinical classification faces challenges: indistinct lesion boundaries, limited annotated medical data, and the black-box inference issue of purely data-driven deep learning models. To address these, a Prior Knowledge-Guided CNN-Swin Transformer Hybrid Network (PGCT-Net) is proposed for high-accuracy classification with interpretable decision support. A cascaded dual-branch structure is adopted: the CNN branch extracts fine-grained local features from MRI images, while the Swin Transformer branch captures multi-scale global semantics and long-range dependencies between necrotic lesions and the acetabular weight-bearing region. A lesion mask-guided learning module injects expert-annotated clinical prior knowledge to focus the model on pathological regions and suppress background interference. Grad-CAM is used to visualize attention distribution for better interpretability. The network is trained end-to-end with a composite loss function combining cross-entropy loss and L1 sparse regularization. On the JLU-ONFH dataset, PGCT-Net achieves 94.38% accuracy, 94.15% F1-score and 93.97% AUC, significantly outperforming mainstream models. Cross-task validation on the BT dataset verifies the architecture’s generalizability. This work provides an effective, interpretable scheme for ONFH JIC classification, with promising clinical auxiliary diagnosis potential. Full article

In clinical CT imaging, high-density metallic implants often induce severe metal artifacts that obscure critical anatomical structures and degrade image quality, thereby hindering accurate diagnosis. Although deep learning has advanced CT metal artifact reduction (CT-MAR), many methods do not effectively use frequency information, which can limit the recovery of both fine details and overall image structure. To address this limitation, we propose a Hybrid-Frequency-Aware Mixture-of-Experts (HFMoE) network for CT-MAR. The proposed method synergizes the spatial-frequency localization of the wavelet transform with the global spectral representation of the Fourier transform to achieve precise multi-scale modeling of artifact characteristics. Specifically, we design a hybrid-frequency interaction encoder with three specialized branches, incorporating wavelet-domain, Fourier-domain, and cascaded wavelet–Fourier modulation, to distinctively refine local details, global structures, and complex cross-domain features. Then, they are fused via channel attention to yield a comprehensive representation. Furthermore, a Frequency-Aware Mixture-of-Experts (MoE) mechanism is introduced to dynamically route features to specific frequency experts based on the degradation severity, thereby adaptively assigning appropriate receptive fields to handle varying metal artifacts. Evaluations on synthetic (DeepLesion) and clinical (SpineWeb, CLINIC-metal) datasets show that HFMoE outperforms existing methods in both quantitative metrics and visual quality. Our method demonstrates the value of explicit frequency-domain adaptation for CT-MAR and could inform the design of other image restoration tasks. Full article

Major depressive disorder (MDD) was long framed as a single clinical entity arising from a linear stress–monoamine–hypothalamic–pituitary–adrenal (HPA) axis cascade. This view was shaped by forced swim and learned helplessness tests in animals and by short-term symptom-based trials using scales such as the Hamilton Depression Rating Scale (HAM-D) and the Montgomery–Åsberg Depression Rating Scale (MADRS). This “unitary cascade” view has been dismantled by advances in neuroimaging, immune–metabolic profiling, sleep phenotyping, and plasticity markers, which reveal divergent circuit-level, inflammatory, and chronobiological patterns across anxiety-linked, pain-burdened, and cognitively weighted depressive presentations, all characterized by high rates of non-response and relapse. Translationally, face-valid rodent assays that equated immobility with despair have yielded limited bedside benefit, whereas cross-species bridges—electroencephalography (EEG) motifs, rapid eye movement (REM) architecture, effort-based reward tasks, and inflammatory/metabolic panels—are beginning to provide mechanistically grounded, clinically actionable readouts. In current practice, depression care is shifting toward systems psychiatry: inflammation-high and metabolic-high archetypes, anhedonia- and circadian-dominant subgroups, formal treatment-resistant depression (TRD) staging, connectivity-guided neuromodulation, esketamine, selected pharmacogenomic panels, and early digital phenotyping, as endpoints broaden to functioning and durability. A central gap is that heterogeneity is acknowledged but rarely built into trial design or implementation. This perspective advances a plasticity-centered systems psychiatry in which a testable prediction is that manipulating defined prefrontal–striatal and prefrontal–limbic circuits in sex-balanced, chronic-stress models will reproduce human network-defined biotypes and treatment response, and proposes hybrid effectiveness–implementation platforms that embed immune–metabolic and sleep panels, circuit-sensitive tasks, and digital monitoring under a shared, preregistered data standard. Full article

Geographic object-based image analysis (GEOBIA) has demonstrated substantial utility in remote sensing tasks. However, its integration with deep learning remains largely confined to image-level classification. This is primarily due to the irregular shapes and fragmented boundaries of segmented objects, which limit its applicability in semantic segmentation. While convolutional neural networks (CNNs) excel at local feature extraction, they inherently struggle to capture long-range dependencies. In contrast, Transformer-based models are well suited for global context modeling but often lack fine-grained local detail. To overcome these limitations, we propose GOFENet (Geo-Object Feature Enhanced Network)—a hybrid semantic segmentation architecture that effectively fuses object-level priors into deep feature representations. GOFENet employs a dual-encoder design combining CNN and Swin Transformer architectures, enabling multi-scale feature fusion through skip connections to preserve both local and global semantics. An auxiliary branch incorporating cascaded atrous convolutions is introduced to inject information of segmented objects into the learning process. Furthermore, we develop a cross-channel selection module (CSM) for refined channel-wise attention, a feature enhancement module (FEM) to merge global and local representations, and a shallow–deep feature fusion module (SDFM) to integrate pixel- and object-level cues across scales. Experimental results on the GID and LoveDA datasets demonstrate that GOFENet achieves superior segmentation performance, with 66.02% mIoU and 51.92% mIoU, respectively. The model exhibits strong capability in delineating large-scale land cover features, producing sharper object boundaries and reducing classification noise, while preserving the integrity and discriminability of land cover categories. Full article

Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. It plays a crucial role in applications such as medical imaging, surveillance, and remote sensing. However, due to the ill-posed nature of the task and the inherent limitations of imaging sensors, obtaining accurate HR images remains challenging. While numerous methods have been proposed, the traditional approaches suffer from oversmoothing and limited generalization; CNN-based models lack the ability to capture long-range dependencies; and Transformer-based solutions, although effective in modeling global context, are computationally intensive and prone to texture loss. To address these issues, we propose a hybrid CNN–Transformer architecture that cascades a pixel-wise self-attention non-local means module (PSNLM) and an adaptive dual-path multi-scale fusion block (ADMFB). The PSNLM is inspired by the non-local means (NLM) algorithm. We use weighted patches to estimate the similarity between pixels centered at each patch while limiting the search region and constructing a communication mechanism across ranges. The ADMFB enhances texture reconstruction by adaptively aggregating multi-scale features through dual attention paths. The experimental results demonstrate that our method achieves superior performance on multiple benchmarks. For instance, in challenging ×4 super-resolution, our method outperforms the second-best method by 0.0201 regarding the Structural Similarity Index (SSIM) on the BSD100 dataset. On the texture-rich Urban100 dataset, our method achieves a 26.56 dB Peak Signal-to-Noise Ratio (PSNR) and 0.8133 SSIM. Full article

COVID-19 was one of the most serious global public health emergencies in recent years, and its extremely fast spreading speed had a profound negative impact on society. A comprehensive analysis and prediction of COVID-19 could lay a theoretical foundation for monitoring and early warning systems. Since the outbreak of COVID-19, there has been an influx of research on predictive modelling, with artificial intelligence (AI) techniques, particularly machine learning (ML) methods, becoming the dominant research direction due to their superior capability in processing multidimensional datasets and capturing complex nonlinear transmission patterns. We systematically reviewed COVID-19 ML prediction models developed under the background of the epidemic using the PRISMA method. We used the selected keywords to screen the relevant literature of COVID-19 prediction using ML technology from 2020 to 2023 in the Web of Science, Springer and Elsevier databases. Based on predetermined inclusion and exclusion criteria, 136 eligible studies were ultimately selected from 5731 preliminarily screened publications, and the datasets, data preprocessing, ML models, and evaluation metrics used in these studies were assessed. By establishing a multi-level classification framework that included traditional statistical models (such as ARIMA), ML models (such as SVM), deep learning (DL) models (such as CNN, LSTM), ensemble learning methods (such as AdaBoost), and hybrid models (such as the fusion architecture of intelligent optimization algorithms and neural networks), it revealed that the hybrid modelling strategy effectively improved the prediction accuracy of the model through feature combination optimization and model cascade integration. In addition, we compared the performance of ML models with other models in the COVID-19 prediction task. The results showed that the propagation of COVID-19 is affected by multiple factors, including meteorological and socio-economic conditions. Compared to traditional methods, ML methods demonstrated significant advantages in COVID-19 prediction, especially hybrid modelling strategies, which showed great potential in optimizing accuracy. However, these techniques face challenges and limitations despite their strong performance. By reviewing existing research on COVID-19 prediction, this study provided systematic theoretical support for AI applications in infectious disease prediction and promoted technological innovation in public health. Full article

Applying deep learning algorithms in the construction industry holds tremendous potential for enhancing site management, safety, and efficiency. The development of such algorithms necessitates a comprehensive and diverse image dataset. This study introduces the Aerial Image Dataset for Construction (AIDCON), a novel aerial image collection containing 9563 construction machines across nine categories annotated at the pixel level, carrying critical value for researchers and professionals seeking to develop and refine object detection and segmentation algorithms across various construction projects. The study highlights the benefits of utilizing UAV-captured images by evaluating the performance of five cutting-edge deep learning algorithms—Mask R-CNN, Cascade Mask R-CNN, Mask Scoring R-CNN, Hybrid Task Cascade, and Pointrend—on the AIDCON dataset. It underscores the significance of clustering strategies for generating reliable and robust outcomes. The AIDCON dataset’s unique aerial perspective aids in reducing occlusions and provides comprehensive site overviews, facilitating better object positioning and segmentation. The findings presented in this paper have far-reaching implications for the construction industry, as they enhance construction site efficiency while setting the stage for future advancements in construction site monitoring and management utilizing remote sensing technologies. Full article

Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors. Full article

Blueberry fruit phenotypes are crucial agronomic trait indicators in blueberry breeding, and the number of fruits within the cluster, maturity, and compactness are important for evaluating blueberry harvesting methods and yield. However, the existing instance segmentation model cannot extract all these features. And due to the complex field environment and aggregated growth of blueberry fruits, the model is difficult to meet the demand for accurate segmentation and automatic phenotype extraction in the field environment. To solve the above problems, a high-precision phenotype extraction model based on hybrid task cascade (HTC) is proposed in this paper. ConvNeXt is used as the backbone network, and three Mask RCNN networks are cascaded to construct the model, rich feature learning through multi-scale training, and customized algorithms for phenotype extraction combined with contour detection techniques. Accurate segmentation of blueberry fruits and automatic extraction of fruit number, ripeness, and compactness under severe occlusion were successfully realized. Following experimental validation, the average precision for both bounding boxes (bbox) and masks stood at 0.974 and 0.975, respectively, with an intersection over union (IOU) threshold of 0.5. The linear regression of the extracted value of the fruit number against the true value showed that the coefficient of determination (R²) was 0.902, and the root mean squared error (RMSE) was 1.556. This confirms the effectiveness of the proposed model. It provides a new option for more efficient and accurate phenotypic extraction of blueberry clusters. Full article

In wireless communication, multiple signals are utilized to receive and send information in the form of signals simultaneously. These signals consume little power and are usually inexpensive, with a high data rate during data transmission. An Multi Input Multi Output (MIMO) system uses numerous antennas to enhance the functionality of the system. Moreover, system intricacy and power utilization are difficult and highly complicated tasks to achieve in an Analog to Digital Converter (ADC) at the receiver side. An infinite number of MIMO channels are used in wireless networks to improve efficiency with Cross Entropy Optimization (CEO). ADC is a serious issue because the data of the accepted signal are completely lost. ADC is used in the MIMO channels to overcome the above issues, but it is very hard to implement and design. So, an efficient way to enhance the estimation of channels in the MIMO system is proposed in this paper with the utilization of the heuristic-based optimization technique. The main task of the implemented channel prediction framework is to predict the channel coefficient of the MIMO system at the transmitter side based on the receiver side error ratio, which is obtained from feedback information using a Hybrid Serial Cascaded Network (HSCN). Then, this multi-scaled cascaded autoencoder is combined with Long Short Term Memory (LSTM) with an attention mechanism. The parameters in the developed Hybrid Serial Cascaded Multi-scale Autoencoder and Attention LSTM are optimized using the developed Hybrid Revised Position-based Wild Horse and Energy Valley Optimizer (RP-WHEVO) algorithm for minimizing the “Root Mean Square Error (RMSE), Bit Error Rate (BER) and Mean Square Error (MSE)” of the estimated channel. Various experiments were carried out to analyze the accomplishment of the developed MIMO model. It was visible from the tests that the developed model enhanced the convergence rate and prediction performance along with a reduction in the computational costs. Full article

Instance segmentation has been widely applied in building extraction from remote sensing imagery in recent years, and accurate instance segmentation results are crucial for urban planning, construction and management. However, existing methods for building instance segmentation (BSI) still have room for improvement. To achieve better detection accuracy and superior performance, we introduce a Hybrid Task Cascade (HTC)-based building extraction method, which is more tailored to the characteristics of buildings. As opposed to a cascaded improvement that performs the bounding box and mask branch refinement separately, HTC intertwines them in a joint multilevel process. The experimental results also validate its effectiveness. Our approach achieves better detection accuracy compared to mainstream instance segmentation methods on three different building datasets, yielding outcomes that are more in line with the distinctive characteristics of buildings. Furthermore, we evaluate the effectiveness of each module of the HTC for building extraction and analyze the impact of the detection threshold on the model’s detection accuracy. Finally, we investigate the generalization ability of the proposed model. Full article

Rehabilitation of paralysis caused by a stroke or a spinal cord injury remains a complex and time-consuming task. This work proposes a hybrid exoskeleton approach combining a traditional exoskeleton and functional electrical stimulation (FES) as a promising method in rehabilitation. However, hybrid exoskeletons with a closed-loop FES control strategy are functionally challenging to achieve and have not been reported often. Therefore, this study aimed to investigate a powered lower-limb exoskeleton with a closed-loop FES control for Sit-to-Stand (STS) movements. A body motion capture system was applied to record precise hip and knee trajectories of references for establishing the human model. A closed-loop control strategy with allocation factors is proposed featuring a two-layer cascaded proportional–integral–derivative (PID) controller for both FES and exoskeleton control. Experiments were performed on two participants to examine the feasibility of the hybrid exoskeleton and the closed-loop FES control. Both open- and closed-loop FES control showed the desired performance with a relatively low root-mean-squared error (max 1.3${}^{\circ }$ in open-loop and max 4.1${}^{\circ }$ in closed-loop) in hip and knee trajectories. Notably, the closed-loop FES control strategy can achieve the same performance with nearly 60% of the electrical power input compared to the open-loop control, which reduced muscle fatigue and improved robustness during the training. This study provides novel insights into body motion capture application and proposes a closed-loop FES control for hybrid exoskeletons. Full article

There are known limitations in mobile omnidirectional camera systems with an equirectangular projection in the wild, such as momentum-caused object distortion within images, partial occlusion and the effects of environmental settings. The localization, instance segmentation and classification of traffic signs from image data is of significant importance to applications such as Traffic Sign Detection and Recognition (TSDR) and Advanced Driver Assistance Systems (ADAS). Works show the efficacy of using state-of-the-art deep pixel-wise methods for this task yet rely on the input of classical landscape image data, automatic camera focus and collection in ideal weather settings, which does not accurately represent the application of technologies in the wild. We present a new processing pipeline for extracting objects within omnidirectional images in the wild, with included demonstration in a Traffic Sign Detection and Recognition (TDSR) system. We compare Mask RCNN, Cascade RCNN, and Hybrid Task Cascade (HTC) methods, while testing RsNeXt 101, Swin-S and HRNetV2p backbones, with transfer learning for localization and instance segmentation. The results from our multinomial classification experiment show that using our proposed pipeline, given that a traffic sign is detected, there is above a 95% chance that it is classified correctly between 12 classes despite the limitations mentioned. Our results on the projected images should provide a path to use omnidirectional images with image processing to enable the full surrounding awareness from one image source. Full article

Rainy degeneration damages an image’s visual effect and influences the performance of subsequent vision tasks. Various deep learning methods for single image deraining have been proposed, obtaining appropriate recovery results. Unfortunately, most existing methods ignore the interaction between rain-layer and rain-free components when extracting relevant features, leading to undesirable results. To break the above limitations, we propose a progressive hybrid-modulated network (PHMNet) for single image deraining based on the two-branch and coarse-to-fine framework. Specifically, a hybrid-modulated module (HMM) with a two-branch framework is proposed to blend and modulate the feature of rain-free layers and rain streaks. After cascading several HMMs in the coarsest reconstructed stage of the PHMNet, a multi-level refined module (MLRM) is adopted to refine the final deraining results in the refined reconstructed stage. By being trained using loss functions such as contrastive learning, the PHMNet can obtain satisfactory deraining results. Extended experiments on several datasets and downstream tasks demonstrate that our method performs favorably against state-of-the-art methods in quantitative evaluation and visual effects. Full article