Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (396)

Search Parameters:
Keywords = stacked-informer networks

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 28899 KiB  
Article
MSDP-Net: A Multi-Scale Domain Perception Network for HRRP Target Recognition
by Hongxu Li, Xiaodi Li, Zihan Xu, Xinfei Jin and Fulin Su
Remote Sens. 2025, 17(15), 2601; https://doi.org/10.3390/rs17152601 - 26 Jul 2025
Viewed by 345
Abstract
High-resolution range profile (HRRP) recognition serves as a foundational task in radar automatic target recognition (RATR), enabling robust classification under all-day and all-weather conditions. However, existing approaches often struggle to simultaneously capture the multi-scale spatial dependencies and global spectral relationships inherent in HRRP [...] Read more.
High-resolution range profile (HRRP) recognition serves as a foundational task in radar automatic target recognition (RATR), enabling robust classification under all-day and all-weather conditions. However, existing approaches often struggle to simultaneously capture the multi-scale spatial dependencies and global spectral relationships inherent in HRRP signals, limiting their effectiveness in complex scenarios. To address these limitations, we propose a novel multi-scale domain perception network tailored for HRRP-based target recognition, called MSDP-Net. MSDP-Net introduces a hybrid spatial–spectral representation learning strategy through a multiple-domain perception HRRP (DP-HRRP) encoder, which integrates multi-head convolutions to extract spatial features across diverse receptive fields, and frequency-aware filtering to enhance critical spectral components. To further enhance feature fusion, we design a hierarchical scale fusion (HSF) branch that employs stacked semantically enhanced scale fusion (SESF) blocks to progressively aggregate information from fine to coarse scales in a bottom-up manner. This architecture enables MSDP-Net to effectively model complex scattering patterns and aspect-dependent variations. Extensive experiments on both simulated and measured datasets demonstrate the superiority of MSDP-Net, achieving 80.75% accuracy on the simulated dataset and 94.42% on the measured dataset, highlighting its robustness and practical applicability. Full article
Show Figures

Figure 1

21 pages, 4388 KiB  
Article
An Omni-Dimensional Dynamic Convolutional Network for Single-Image Super-Resolution Tasks
by Xi Chen, Ziang Wu, Weiping Zhang, Tingting Bi and Chunwei Tian
Mathematics 2025, 13(15), 2388; https://doi.org/10.3390/math13152388 - 25 Jul 2025
Viewed by 280
Abstract
The goal of single-image super-resolution (SISR) tasks is to generate high-definition images from low-quality inputs, with practical uses spanning healthcare diagnostics, aerial imaging, and surveillance systems. Although cnns have considerably improved image reconstruction quality, existing methods still face limitations, including inadequate restoration of [...] Read more.
The goal of single-image super-resolution (SISR) tasks is to generate high-definition images from low-quality inputs, with practical uses spanning healthcare diagnostics, aerial imaging, and surveillance systems. Although cnns have considerably improved image reconstruction quality, existing methods still face limitations, including inadequate restoration of high-frequency details, high computational complexity, and insufficient adaptability to complex scenes. To address these challenges, we propose an Omni-dimensional Dynamic Convolutional Network (ODConvNet) tailored for SISR tasks. Specifically, ODConvNet comprises four key components: a Feature Extraction Block (FEB) that captures low-level spatial features; an Omni-dimensional Dynamic Convolution Block (DCB), which utilizes a multidimensional attention mechanism to dynamically reweight convolution kernels across spatial, channel, and kernel dimensions, thereby enhancing feature expressiveness and context modeling; a Deep Feature Extraction Block (DFEB) that stacks multiple convolutional layers with residual connections to progressively extract and fuse high-level features; and a Reconstruction Block (RB) that employs subpixel convolution to upscale features and refine the final HR output. This mechanism significantly enhances feature extraction and effectively captures rich contextual information. Additionally, we employ an improved residual network structure combined with a refined Charbonnier loss function to alleviate gradient vanishing and exploding to enhance the robustness of model training. Extensive experiments conducted on widely used benchmark datasets, including DIV2K, Set5, Set14, B100, and Urban100, demonstrate that, compared with existing deep learning-based SR methods, our ODConvNet method improves Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and the visual quality of SR images is also improved. Ablation studies further validate the effectiveness and contribution of each component in our network. The proposed ODConvNet offers an effective, flexible, and efficient solution for the SISR task and provides promising directions for future research. Full article
Show Figures

Figure 1

26 pages, 2875 KiB  
Article
Sustainable THz SWIPT via RIS-Enabled Sensing and Adaptive Power Focusing: Toward Green 6G IoT
by Sunday Enahoro, Sunday Cookey Ekpo, Mfonobong Uko, Fanuel Elias, Rahul Unnikrishnan, Stephen Alabi and Nurudeen Kolawole Olasunkanmi
Sensors 2025, 25(15), 4549; https://doi.org/10.3390/s25154549 - 23 Jul 2025
Viewed by 344
Abstract
Terahertz (THz) communications and simultaneous wireless information and power transfer (SWIPT) hold the potential to energize battery-less Internet-of-Things (IoT) devices while enabling multi-gigabit data transmission. However, severe path loss, blockages, and rectifier nonlinearity significantly hinder both throughput and harvested energy. Additionally, high-power THz [...] Read more.
Terahertz (THz) communications and simultaneous wireless information and power transfer (SWIPT) hold the potential to energize battery-less Internet-of-Things (IoT) devices while enabling multi-gigabit data transmission. However, severe path loss, blockages, and rectifier nonlinearity significantly hinder both throughput and harvested energy. Additionally, high-power THz beams pose safety concerns by potentially exceeding specific absorption rate (SAR) limits. We propose a sensing-adaptive power-focusing (APF) framework in which a reconfigurable intelligent surface (RIS) embeds low-rate THz sensors. Real-time backscatter measurements construct a spatial map used for the joint optimisation of (i) RIS phase configurations, (ii) multi-tone SWIPT waveforms, and (iii) nonlinear power-splitting ratios. A weighted MMSE inner loop maximizes the data rate, while an outer alternating optimisation applies semidefinite relaxation to enforce passive-element constraints and SAR compliance. Full-stack simulations at 0.3 THz with 20 GHz bandwidth and up to 256 RIS elements show that APF (i) improves the rate–energy Pareto frontier by 30–75% over recent adaptive baselines; (ii) achieves a 150% gain in harvested energy and a 440 Mbps peak per-user rate; (iii) reduces energy-efficiency variance by half while maintaining a Jain fairness index of 0.999;; and (iv) caps SAR at 1.6 W/kg, which is 20% below the IEEE C95.1 safety threshold. The algorithm converges in seven iterations and executes within <3 ms on a Cortex-A78 processor, ensuring compliance with real-time 6G control budgets. The proposed architecture supports sustainable THz-powered networks for smart factories, digital-twin logistics, wire-free extended reality (XR), and low-maintenance structural health monitors, combining high-capacity communication, safe wireless power transfer, and carbon-aware operation for future 6G cyber–physical systems. Full article
Show Figures

Figure 1

17 pages, 2893 KiB  
Article
Insulator Defect Detection Based on Improved YOLO11n Algorithm Under Complex Environmental Conditions
by Shoutian Dong, Yiqi Qin, Benrui Li, Qi Zhang and Yu Zhao
Electronics 2025, 14(14), 2898; https://doi.org/10.3390/electronics14142898 - 20 Jul 2025
Viewed by 387
Abstract
Detecting defects in transmission line insulators is crucial to prevent power grid failures as power systems continue to expand. This study introduces YOL011n-SSA, an enhanced insulator defect detection technique method that addresses the challenges of effectively identifying flaws in complex environments. First, this [...] Read more.
Detecting defects in transmission line insulators is crucial to prevent power grid failures as power systems continue to expand. This study introduces YOL011n-SSA, an enhanced insulator defect detection technique method that addresses the challenges of effectively identifying flaws in complex environments. First, this study incorporates the StarNet network into the backbone of the model. By stacking multiple layers of star operations, the model reduces both parameter count and model size, improving its adaptability to real-time object detection tasks. Secondly, the SOPN feature pyramid network is introduced into the neck part of the model. By optimizing the multi-scale feature fusion of the richer information obtained after expanding the channel dimension, the detection efficiency for low-resolution images and small objects is improved. Then, the ADown module was adopted to improve the backbone and neck parts of the model. It effectively reduces parameter count and significantly lowers the computational cost by implementing downsampling operations between different layers of the feature map, thereby enhancing the practicality of the model. Meanwhile, by introducing the NWD to improve the evaluation index of the loss function, the detection model’s capability in assessing the similarities among various small-object defects is enhanced. Experimental results were obtained using an expanded dataset based on a public dataset, incorporating three types of insulator defects under complex environmental conditions. The results demonstrate that the YOLO11n-SSA algorithm achieved an mAP@0.5 of 0.919, an mAP@0.5:0.95 of 70.7%, a precision of 0.95, and a recall of 0.875, representing improvements of 3.9%, 5.5%, 2%, and 5.7%, respectively, when compared to the original YOLO1ln method. The detection time per image is 0.0134 s. Compared to other mainstream algorithms, the YOLO11n-SSA algorithm demonstrates superior detection accuracy and real-time performance. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

21 pages, 5313 KiB  
Article
MixtureRS: A Mixture of Expert Network Based Remote Sensing Land Classification
by Yimei Liu, Changyuan Wu, Minglei Guan and Jingzhe Wang
Remote Sens. 2025, 17(14), 2494; https://doi.org/10.3390/rs17142494 - 17 Jul 2025
Viewed by 349
Abstract
Accurate land-use classification is critical for urban planning and environmental monitoring, yet effectively integrating heterogeneous data sources such as hyperspectral imagery and laser radar (LiDAR) remains challenging. To address this, we propose MixtureRS, a compact multimodal network that effectively integrates hyperspectral imagery and [...] Read more.
Accurate land-use classification is critical for urban planning and environmental monitoring, yet effectively integrating heterogeneous data sources such as hyperspectral imagery and laser radar (LiDAR) remains challenging. To address this, we propose MixtureRS, a compact multimodal network that effectively integrates hyperspectral imagery and LiDAR data for land-use classification. Our approach employs a 3-D plus heterogeneous convolutional stack to extract rich spectral–spatial features, which are then tokenized and fused via a cross-modality transformer. To enhance model capacity without incurring significant computational overhead, we replace conventional dense feed-forward blocks with a sparse Mixture-of-Experts (MoE) layer that selectively activates the most relevant experts for each token. Evaluated on a 15-class urban benchmark, MixtureRS achieves an overall accuracy of 88.6%, an average accuracy of 90.2%, and a Kappa coefficient of 0.877, outperforming the best homogeneous transformer by over 12 percentage points. Notably, the largest improvements are observed in water, railway, and parking categories, highlighting the advantages of incorporating height information and conditional computation. These results demonstrate that conditional, expert-guided fusion is a promising and efficient strategy for advancing multimodal remote sensing models. Full article
Show Figures

Graphical abstract

22 pages, 2492 KiB  
Article
VJDNet: A Simple Variational Joint Discrimination Network for Cross-Image Hyperspectral Anomaly Detection
by Shiqi Wu, Xiangrong Zhang, Guanchun Wang, Puhua Chen, Jing Gu, Xina Cheng and Licheng Jiao
Remote Sens. 2025, 17(14), 2438; https://doi.org/10.3390/rs17142438 - 14 Jul 2025
Viewed by 227
Abstract
To enhance the generalization of networks and avoid redundant training efforts, cross-image hyperspectral anomaly detection (HAD) based on deep learning has been gradually studied in recent years. Cross-image HAD aims to perform anomaly detection on unknown hyperspectral images after a single training process [...] Read more.
To enhance the generalization of networks and avoid redundant training efforts, cross-image hyperspectral anomaly detection (HAD) based on deep learning has been gradually studied in recent years. Cross-image HAD aims to perform anomaly detection on unknown hyperspectral images after a single training process on the network, thereby improving detection efficiency in practical applications. However, the existing approaches may require additional supervised information or stacking of networks to improve model performance, which may impose high demands on data or hardware in practical applications. In this paper, a simple and lightweight unsupervised cross-image HAD method called Variational Joint Discrimination Network (VJDNet) is proposed. We leverage the reconstruction and distribution representation ability of the variational autoencoder (VAE), learning the global and local discriminability of anomalies jointly. To integrate these representations from the VAE, a probability distribution joint discrimination (PDJD) module is proposed. Through the PDJD module, the VJDNet can directly output the anomaly score mask of pixels. To further facilitate the unsupervised paradigm, a sample pair generation module is proposed, which is able to generate anomaly samples and background representation samples tailored for the cross-image HAD task. The experimental results show that the proposed method is able to maintain the detection accuracy with only a small number of parameters. Full article
Show Figures

Figure 1

22 pages, 7562 KiB  
Article
FIGD-Net: A Symmetric Dual-Branch Dehazing Network Guided by Frequency Domain Information
by Luxia Yang, Yingzhao Xue, Yijin Ning, Hongrui Zhang and Yongjie Ma
Symmetry 2025, 17(7), 1122; https://doi.org/10.3390/sym17071122 - 13 Jul 2025
Viewed by 361
Abstract
Image dehazing technology is a crucial component in the fields of intelligent transportation and autonomous driving. However, most existing dehazing algorithms only process images in the spatial domain, failing to fully exploit the rich information in the frequency domain, which leads to residual [...] Read more.
Image dehazing technology is a crucial component in the fields of intelligent transportation and autonomous driving. However, most existing dehazing algorithms only process images in the spatial domain, failing to fully exploit the rich information in the frequency domain, which leads to residual haze in the images. To address this issue, we propose a novel Frequency-domain Information Guided Symmetric Dual-branch Dehazing Network (FIGD-Net), which utilizes the spatial branch to extract local haze features and the frequency branch to capture the global haze distribution, thereby guiding the feature learning process in the spatial branch. The FIGD-Net mainly consists of three key modules: the Frequency Detail Extraction Module (FDEM), the Dual-Domain Multi-scale Feature Extraction Module (DMFEM), and the Dual-Domain Guidance Module (DGM). First, the FDEM employs the Discrete Cosine Transform (DCT) to convert the spatial domain into the frequency domain. It then selectively extracts high-frequency and low-frequency features based on predefined proportions. The high-frequency features, which contain haze-related information, are correlated with the overall characteristics of the low-frequency features to enhance the representation of haze attributes. Next, the DMFEM utilizes stacked residual blocks and gradient feature flows to capture local detail features. Specifically, frequency-guided weights are applied to adjust the focus of feature channels, thereby improving the module’s ability to capture multi-scale features and distinguish haze features. Finally, the DGM adjusts channel weights guided by frequency information. This smooths out redundant signals and enables cross-branch information exchange, which helps to restore the original image colors. Extensive experiments demonstrate that the proposed FIGD-Net achieves superior dehazing performance on multiple synthetic and real-world datasets. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

18 pages, 4696 KiB  
Article
A Deep-Learning Framework with Multi-Feature Fusion and Attention Mechanism for Classification of Chinese Traditional Instruments
by Jinrong Yang, Fang Gao, Teng Yun, Tong Zhu, Huaixi Zhu, Ran Zhou and Yikun Wang
Electronics 2025, 14(14), 2805; https://doi.org/10.3390/electronics14142805 - 12 Jul 2025
Viewed by 343
Abstract
Chinese traditional instruments are diverse and encompass a rich variety of timbres and rhythms, presenting considerable research potential. This work proposed a deep-learning framework for the automated classification of Chinese traditional instruments, addressing the challenges of acoustic diversity and cultural preservation. By integrating [...] Read more.
Chinese traditional instruments are diverse and encompass a rich variety of timbres and rhythms, presenting considerable research potential. This work proposed a deep-learning framework for the automated classification of Chinese traditional instruments, addressing the challenges of acoustic diversity and cultural preservation. By integrating two datasets, CTIS and ChMusic, we constructed a combined dataset comprising four instrument families: wind, percussion, plucked string, and bowed string. Three time-frequency features, namely MFCC, CQT, and Chroma, were extracted to capture diverse sound information. A convolutional neural network architecture was designed, incorporating 3-channel spectrogram feature stacking and a hybrid channel–spatial attention mechanism to enhance the extraction of critical frequency bands and feature weights. Experimental results demonstrated that the feature-fusion method improved classification performance compared to a single feature as input. Meanwhile, the attention mechanism further boosted test accuracy to 98.79%, outperforming baseline models by 2.8% and achieving superior F1 scores and recall compared to classical architectures. Ablation study confirmed the contribution of attention mechanisms. This work validates the efficacy of deep learning in preserving intangible cultural heritage through precise analysis, offering a feasible methodology for the classification of Chinese traditional instruments. Full article
Show Figures

Figure 1

18 pages, 2148 KiB  
Article
A Cross-Spatial Differential Localization Network for Remote Sensing Change Captioning
by Ruijie Wu, Hao Ye, Xiangying Liu, Zhenzhen Li, Chenhao Sun and Jiajia Wu
Remote Sens. 2025, 17(13), 2285; https://doi.org/10.3390/rs17132285 - 3 Jul 2025
Viewed by 348
Abstract
Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of changes in bi-temporal remote sensing images, providing more semantically interpretable results than conventional pixel-level change detection methods. However, existing approaches often rely on stacked Transformer modules, leading to suboptimal feature [...] Read more.
Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of changes in bi-temporal remote sensing images, providing more semantically interpretable results than conventional pixel-level change detection methods. However, existing approaches often rely on stacked Transformer modules, leading to suboptimal feature discrimination. Moreover, direct difference computation after feature extraction tends to retain task-irrelevant noise, limiting the model’s ability to capture meaningful changes. This study proposes a novel cross-spatial Transformer and symmetric difference localization network (CTSD-Net) for RSICC to address these limitations. The proposed Cross-Spatial Transformer adaptively enhances spatial-aware feature representations by guiding the model to focus on key regions across temporal images. Additionally, a hierarchical difference feature integration strategy is introduced to suppress noise by fusing multi-level differential features, while residual-connected high-level features serve as query vectors to facilitate bidirectional change representation learning. Finally, a causal Transformer decoder creates accurate descriptions by linking visual information with text. CTSD-Net achieved BLEU-4 scores of 66.32 and 73.84 on the LEVIR-CC and WHU-CDC datasets, respectively, outperforming existing methods in accurately locating change areas and describing them semantically. This study provides a promising solution for enhancing interpretability in remote sensing change analysis. Full article
Show Figures

Figure 1

19 pages, 4801 KiB  
Article
Attention-Enhanced CNN-LSTM Model for Exercise Oxygen Consumption Prediction with Multi-Source Temporal Features
by Zhen Wang, Yingzhe Song, Lei Pang, Shanjun Li and Gang Sun
Sensors 2025, 25(13), 4062; https://doi.org/10.3390/s25134062 - 29 Jun 2025
Viewed by 419
Abstract
Dynamic oxygen uptake (VO2) reflects moment-to-moment changes in oxygen consumption during exercise and underpins training design, performance enhancement, and clinical decision-making. We tackled two key obstacles—the limited fusion of heterogeneous sensor data and inadequate modeling of long-range temporal patterns—by integrating wearable [...] Read more.
Dynamic oxygen uptake (VO2) reflects moment-to-moment changes in oxygen consumption during exercise and underpins training design, performance enhancement, and clinical decision-making. We tackled two key obstacles—the limited fusion of heterogeneous sensor data and inadequate modeling of long-range temporal patterns—by integrating wearable accelerometer and heart-rate streams with a convolutional neural network–LSTM (CNN-LSTM) architecture and optional attention modules. Physiological signals and VO2 were recorded from 21 adults through resting assessment and cardiopulmonary exercise testing. The results showed that pairing accelerometer with heart-rate inputs improves prediction compared with considering the heart rate alone. The baseline CNN-LSTM reached R2 = 0.946, outperforming a plain LSTM (R2 = 0.926) thanks to stronger local spatio-temporal feature extraction. Introducing a spatial attention mechanism raised accuracy further (R2 = 0.962), whereas temporal attention reduced it (R2 = 0.930), indicating that attention success depends on how well the attended features align with exercise dynamics. Stacking both attentions (spatio-temporal) yielded R2 = 0.960, slightly below the value for spatial attention alone, implying that added complexity does not guarantee better performance. Across all models, prediction errors grew during high-intensity bouts, highlighting a bottleneck in capturing non-linear physiological responses under heavy load. These findings inform architecture selection for wearable metabolic monitoring and clarify when attention mechanisms add value. Full article
(This article belongs to the Special Issue Sensors for Physiological Monitoring and Digital Health)
Show Figures

Figure 1

18 pages, 1059 KiB  
Article
Exponential Backoff and Its Security Implications for Safety-Critical OT Protocols over TCP/IP Networks
by Matthew Boeding, Paul Scalise, Michael Hempel, Hamid Sharif and Juan Lopez
Future Internet 2025, 17(7), 286; https://doi.org/10.3390/fi17070286 - 26 Jun 2025
Viewed by 319
Abstract
The convergence of Operational Technology (OT) and Information Technology (IT) networks has become increasingly prevalent with the growth of Industrial Internet of Things (IIoT) applications. This shift, while enabling enhanced automation, remote monitoring, and data sharing, also introduces new challenges related to communication [...] Read more.
The convergence of Operational Technology (OT) and Information Technology (IT) networks has become increasingly prevalent with the growth of Industrial Internet of Things (IIoT) applications. This shift, while enabling enhanced automation, remote monitoring, and data sharing, also introduces new challenges related to communication latency and cybersecurity. Oftentimes, legacy OT protocols were adapted to the TCP/IP stack without an extensive review of the ramifications to their robustness, performance, or safety objectives. To further accommodate the IT/OT convergence, protocol gateways were introduced to facilitate the migration from serial protocols to TCP/IP protocol stacks within modern IT/OT infrastructure. However, they often introduce additional vulnerabilities by exposing traditionally isolated protocols to external threats. This study investigates the security and reliability implications of migrating serial protocols to TCP/IP stacks and the impact of protocol gateways, utilizing two widely used OT protocols: Modbus TCP and DNP3. Our protocol analysis finds a significant safety-critical vulnerability resulting from this migration, and our subsequent tests clearly demonstrate its presence and impact. A multi-tiered testbed, consisting of both physical and emulated components, is used to evaluate protocol performance and the effects of device-specific implementation flaws. Through this analysis of specifications and behaviors during communication interruptions, we identify critical differences in fault handling and the impact on time-sensitive data delivery. The findings highlight how reliance on lower-level IT protocols can undermine OT system resilience, and they inform the development of mitigation strategies to enhance the robustness of industrial communication networks. Full article
Show Figures

Figure 1

23 pages, 5579 KiB  
Article
End-to-End Interrupted Sampling Repeater Jamming Countermeasure Network Under Low Signal-to-Noise Ratio
by Gane Dai, Xiaoxuan Yang, Sha Huan, Ziyang Chen, Cong Peng and Yuanqin Xu
Sensors 2025, 25(13), 3925; https://doi.org/10.3390/s25133925 - 24 Jun 2025
Viewed by 353
Abstract
Interrupted sampling repeater jamming (ISRJ) is characterized by its coherent processing gains and flexible modulation techniques. ISRJ generates spurious targets along the range, which presents significant challenges to the radar systems. However, existing ISRJ countermeasure methods struggle to eliminate ISRJ signals without compromising [...] Read more.
Interrupted sampling repeater jamming (ISRJ) is characterized by its coherent processing gains and flexible modulation techniques. ISRJ generates spurious targets along the range, which presents significant challenges to the radar systems. However, existing ISRJ countermeasure methods struggle to eliminate ISRJ signals without compromising the integrity of the real target signal, especially under low-signal-to-noise-ratio (SNR) conditions, resulting in a deteriorated sidelobe and diminished detection performance. We propose a complex-valued encoder–decoder network (CVEDNet) to address these challenges based on signal decomposition. This network offers an end-to-end ISRJ suppression approach, working on complex-valued time-domain signals without the need for additional preprocessing. The encoding and decoding structure suppresses noise components and obtains more compact echo feature representations through layer-by-layer compression and reconstruction. A stacked dual-branch structure and multi-scale dilated convolutions are adopted to further separate the echo signal and ISRJ based on high-dimensional features. A multi-domain combined loss function integrates the waveform and range-pulse-compression information to ensure the amplitude and phase integrity of the reconstructed echo waveform during the training process. The effectiveness of the proposed method was validated in terms of its jamming suppression capability, echo fidelity, and detection performance indicators under low-SNR conditions compared to conventional methods. Full article
(This article belongs to the Special Issue Detection, Recognition and Identification in the Radar Applications)
Show Figures

Figure 1

23 pages, 8102 KiB  
Article
Ensemble Learning for Spatial Modeling of Icing Fields from Multi-Source Remote Sensing Data
by Shaohui Zhou, Zhiqiu Gao, Bo Gong, Hourong Zhang, Haipeng Zhang, Jinqiang He and Xingya Xi
Remote Sens. 2025, 17(13), 2155; https://doi.org/10.3390/rs17132155 - 23 Jun 2025
Viewed by 323
Abstract
Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential for both mapping ice distribution and predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids [...] Read more.
Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential for both mapping ice distribution and predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids is challenging due to the uneven distribution of monitoring stations, data confidentiality restrictions, and the limitations of existing interpolation methods. In this study, we propose a new approach for constructing real-time icing grid fields using 1339 online terminal monitoring datasets provided by the China Southern Power Grid Research Institute Co., Ltd. (CSPGRI) during the winter of 2023. Our method integrates static geographic information, dynamic meteorological factors, and ice_kriging values derived from parameter-optimized Empirical Bayesian Kriging Interpolation (EBKI) to create a spatiotemporally matched, multi-source fused icing thickness grid dataset. We applied five machine learning algorithms—Random Forest, XGBoost, LightGBM, Stacking, and Convolutional Neural Network Transformers (CNNT)—and evaluated their performance using six metrics: R, RMSE, CSI, MAR, FAR, and fbias, on both validation and testing sets. The stacking model performed best, achieving an R-value of 0.634 (0.893), RMSE of 3.424 mm (2.834 mm), CSI of 0.514 (0.774), MAR of 0.309 (0.091), FAR of 0.332 (0.161), and fbias of 1.034 (1.084), respectively, when comparing predicted icing values with actual measurements on pylons. Additionally, we employed the SHAP model to provide a physical interpretation of the stacking model, confirming the independence of selected features. Meteorological factors such as relative humidity (RH), 10 m wind speed (WS10), 2 m temperature (T2), and precipitation (PRE) demonstrated a range of positive and negative contributions consistent with the observed growth of icing. Thus, our multi-source remote-sensing data-fusion approach, combined with the stacking model, offers a highly accurate and interpretable solution for generating real-time icing grid fields. Full article
(This article belongs to the Special Issue Remote Sensing for High Impact Weather and Extremes (2nd Edition))
Show Figures

Figure 1

23 pages, 6234 KiB  
Article
Characterizing Breast Tumor Heterogeneity Through IVIM-DWI Parameters and Signal Decay Analysis
by Si-Wa Chan, Chun-An Lin, Yen-Chieh Ouyang, Guan-Yuan Chen, Chein-I Chang, Chin-Yao Lin, Chih-Chiang Hung, Chih-Yean Lum, Kuo-Chung Wang and Ming-Cheng Liu
Diagnostics 2025, 15(12), 1499; https://doi.org/10.3390/diagnostics15121499 - 12 Jun 2025
Viewed by 1687
Abstract
Background/Objectives: This research presents a novel analytical method for breast tumor characterization and tissue classification by leveraging intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) combined with hyperspectral imaging techniques and deep learning. Traditionally, dynamic contrast-enhanced MRI (DCE-MRI) is employed for breast tumor diagnosis, but [...] Read more.
Background/Objectives: This research presents a novel analytical method for breast tumor characterization and tissue classification by leveraging intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) combined with hyperspectral imaging techniques and deep learning. Traditionally, dynamic contrast-enhanced MRI (DCE-MRI) is employed for breast tumor diagnosis, but it involves gadolinium-based contrast agents, which carry potential health risks. IVIM imaging extends conventional diffusion-weighted imaging (DWI) by explicitly separating the signal decay into components representing true molecular diffusion (D) and microcirculation of capillary blood (pseudo-diffusion or D*). This separation allows for a more comprehensive, non-invasive assessment of tissue characteristics without the need for contrast agents, thereby offering a safer alternative for breast cancer diagnosis. The primary purpose of this study was to evaluate different methods for breast tumor characterization using IVIM-DWI data treated as hyperspectral image stacks. Dice similarity coefficients and Jaccard indices were specifically used to evaluate the spatial segmentation accuracy of tumor boundaries, confirmed by experienced physicians on dynamic contrast-enhanced MRI (DCE-MRI), emphasizing detailed tumor characterization rather than binary diagnosis of cancer. Methods: The data source for this study consisted of breast MRI scans obtained from 22 patients diagnosed with mass-type breast cancer, resulting in 22 distinct mass tumor cases analyzed. MR images were acquired using a 3T MRI system (Discovery MR750 3.0 Tesla, GE Healthcare, Chicago, IL, USA) with axial IVIM sequences and a bipolar pulsed gradient spin echo sequence. Multiple b-values ranging from 0 to 2500 s/mm2 were utilized, specifically thirteen original b-values (0, 15, 30, 45, 60, 100, 200, 400, 600, 1000, 1500, 2000, and 2500 s/mm2), with the last four b-value images replicated once for a total of 17 bands used in the analysis. The methodology involved several steps: acquisition of multi-b-value IVIM-DWI images, image pre-processing, including correction for motion and intensity inhomogeneity, treating the multi-b-value data as hyperspectral image stacks, applying hyperspectral techniques like band expansion, and evaluating three tumor detection methods: kernel-based constrained energy minimization (KCEM), iterative KCEM (I-KCEM), and deep neural networks (DNNs). The comparisons were assessed by evaluating the similarity of the detection results from each method to ground truth tumor areas, which were manually drawn on DCE-MRI images and confirmed by experienced physicians. Similarity was quantitatively measured using the Dice similarity coefficient and the Jaccard index. Additionally, the performance of the detectors was evaluated using 3D-ROC analysis and its derived criteria (AUCOD, AUCTD, AUCBS, AUCTDBS, AUCODP, AUCSNPR). Results: The findings objectively demonstrated that the DNN method achieved superior performance in breast tumor detection compared to KCEM and I-KCEM. Specifically, the DNN yielded a Dice similarity coefficient of 86.56% and a Jaccard index of 76.30%, whereas KCEM achieved 78.49% (Dice) and 64.60% (Jaccard), and I-KCEM achieved 78.55% (Dice) and 61.37% (Jaccard). Evaluation using 3D-ROC analysis also indicated that the DNN was the best detector based on metrics like target detection rate and overall effectiveness. The DNN model further exhibited the capability to identify tumor heterogeneity, differentiating high- and low-cellularity regions. Quantitative parameters, including apparent diffusion coefficient (ADC), pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (PF), were calculated and analyzed, providing insights into the diffusion characteristics of different breast tissues. Analysis of signal intensity decay curves generated from these parameters further illustrated distinct diffusion patterns and confirmed that high cellularity tumor regions showed greater water molecule confinement compared to low cellularity regions. Conclusions: This study highlights the potential of combining IVIM-DWI, hyperspectral imaging techniques, and deep learning as a robust, safe, and effective non-invasive diagnostic tool for breast cancer, offering a valuable alternative to contrast-enhanced methods by providing detailed information about tissue microstructure and heterogeneity without the need for contrast agents. Full article
(This article belongs to the Special Issue Recent Advances in Breast Cancer Imaging)
Show Figures

Figure 1

28 pages, 3463 KiB  
Article
A Stacked Machine Learning-Based Intrusion Detection System for Internal and External Networks in Smart Connected Vehicles
by Xinlei Zhou, Yujing Wu, Junhao Lin, Yinan Xu and Samuel Woo
Symmetry 2025, 17(6), 874; https://doi.org/10.3390/sym17060874 - 4 Jun 2025
Viewed by 637
Abstract
In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking the time needed for training and detection. Moreover, they may not fully leverage the [...] Read more.
In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking the time needed for training and detection. Moreover, they may not fully leverage the combined utilization of CAN bus IDs and the data field with external network data. Consequently, these systems frequently struggle to meet the real-time demands and broader attack scenarios inherent in in-vehicle systems. To overcome these challenges, we propose a stacked-model IDS architecture deployed across the CAN bus and central gateway, capable of detecting both internal and external vehicular network attacks. The system extracts key features from in-vehicle and external network data, builds base learners (CART, LightGBM, XGBoost), and integrates them through stacking with a meta-learner. Feature selection and training efficiency are enhanced using information gain and maximal information coefficient algorithms. Experiments show that the proposed IDS achieves an average detection accuracy of 99.99% for internal CAN bus attacks and 99.81% for external network attacks, with fast detection times of 0.018 ms and 0.088 ms, respectively. These results highlight the system’s real-time capability, high accuracy, and adaptability to complex attack scenarios. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

Back to TopTop