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
remove_circle_outline
remove_circle_outline
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

Search Results (1,030)

Search Parameters:
Keywords = hybrid functional features

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
22 pages, 1249 KB  
Systematic Review
Radiomics vs. Deep Learning in Autism Classification Using Brain MRI: A Systematic Review
by Katerina Nalentzi, Georgios S. Ioannidis, Haralabos Bougias, Sotirios Bisdas, Myrsini Balafouta, Cleo Sgouropoulou, Michail E. Klontzas, Kostas Marias and Periklis Papavasileiou
Appl. Sci. 2025, 15(19), 10551; https://doi.org/10.3390/app151910551 - 29 Sep 2025
Abstract
Autism diagnosis through magnetic resonance imaging (MRI) has advanced significantly with the application of artificial intelligence (AI). This systematic review examines three computational paradigms: radiomics-based machine learning (ML), deep learning (DL), and hybrid models combining both. Across 49 studies (2011–2025), radiomics methods relying [...] Read more.
Autism diagnosis through magnetic resonance imaging (MRI) has advanced significantly with the application of artificial intelligence (AI). This systematic review examines three computational paradigms: radiomics-based machine learning (ML), deep learning (DL), and hybrid models combining both. Across 49 studies (2011–2025), radiomics methods relying on classical classifiers (i.e., SVM, Random Forest) achieved moderate accuracies (61–89%) and offered strong interpretability. DL models, particularly convolutional and recurrent neural networks applied to resting-state functional MRI, reached higher accuracies (up to 98.2%) but were hampered by limited transparency and generalizability. Hybrid models combining handcrafted radiomic features with learned DL representations via dual or fused architectures demonstrated promising balances of performance and interpretability but remain underexplored. A persistent limitation across all approaches is the lack of external validation and harmonization in multi-site studies, which affects robustness. Future pipelines should include standardized preprocessing, multimodal integration, and explainable AI frameworks to enhance clinical viability. This review underscores the complementary strengths of each methodological approach, with hybrid approaches appearing to be a promising middle ground of improved classification performance and enhanced interpretability. Full article
Show Figures

Figure 1

20 pages, 5249 KB  
Article
Research on Anomaly Detection in Wastewater Treatment Systems Based on a VAE-LSTM Fusion Model
by Xin Liu, Zhengxuan Gong and Xing Zhang
Water 2025, 17(19), 2842; https://doi.org/10.3390/w17192842 - 28 Sep 2025
Abstract
This study addresses the problem of anomaly detection in water treatment systems by proposing a hybrid VAE–LSTM model with a combined loss function that integrates reconstruction and prediction errors. Following the signal flow of wastewater treatment systems, data acquisition, transmission, and cyberattack scenarios [...] Read more.
This study addresses the problem of anomaly detection in water treatment systems by proposing a hybrid VAE–LSTM model with a combined loss function that integrates reconstruction and prediction errors. Following the signal flow of wastewater treatment systems, data acquisition, transmission, and cyberattack scenarios were simulated, and a dual-dimensional learning framework of “feature space—temporal space” was designed: the VAE learns latent data distributions and computes reconstruction errors, while the LSTM models temporal dependencies and computes prediction errors. Anomaly decisions are made through feature extraction and weighted scoring. Experimental comparisons show that the proposed fusion model achieves an accuracy of approximately 0.99 and an F1-Score of about 0.75, significantly outperforming single models such as Isolation Forest and One-Class SVM. It can accurately identify attack anomalies in devices such as the LIT101 sensor and MV101 actuator, e.g., water tank overflow and state transitions, with reconstruction errors primarily beneath 0.08 ensuring detection reliability. In terms of time efficiency, Isolation Forest is suitable for real-time preliminary screening, while VAE-LSTM adapts to high-precision detection scenarios with an “offline training (423 s) + online detection (1.39 s)” mode. This model provides a practical solution for intelligent monitoring of industrial water treatment systems. Future research will focus on model lightweighting, enhanced data generalization, and integration with edge computing to improve system applicability and robustness. The proposed approach breaks through the limitations of traditional single models, demonstrating superior performance in detection accuracy and scenario adaptability. It offers technical support for improving the operational efficiency and security of water treatment systems and serves as a paradigm reference for anomaly detection in similar industrial systems. Full article
(This article belongs to the Section Wastewater Treatment and Reuse)
Show Figures

Figure 1

24 pages, 1263 KB  
Review
Shared and Context-Specific Mechanisms of EMT and Cellular Plasticity in Cancer and Fibrotic Diseases
by Victor Alexandre F. Bastos, Aline Gomes de Souza, Virginia C. Silvestrini Guedes and Thúlio M. Cunha
Int. J. Mol. Sci. 2025, 26(19), 9476; https://doi.org/10.3390/ijms26199476 - 27 Sep 2025
Abstract
Cellular plasticity enables cells to dynamically adapt their phenotype in response to environmental cues, a process central to development, tissue repair, and disease. Among the most studied plasticity programs is epithelial–mesenchymal transition (EMT), a transcriptionally controlled process by which epithelial cells acquire mesenchymal [...] Read more.
Cellular plasticity enables cells to dynamically adapt their phenotype in response to environmental cues, a process central to development, tissue repair, and disease. Among the most studied plasticity programs is epithelial–mesenchymal transition (EMT), a transcriptionally controlled process by which epithelial cells acquire mesenchymal traits. Originally described in embryogenesis, EMT is now recognized as a key driver in both tumor progression and fibrotic remodeling. In cancer, EMT and hybrid epithelial/mesenchymal (E/M) states promote invasion, metastasis, stemness, therapy resistance, and immune evasion. In fibrotic diseases, partial EMT (pEMT) contributes to fibroblast activation and excessive extracellular matrix deposition, sustaining organ dysfunction mainly in the kidney, liver, lung, and heart. This review integrates recent findings on the molecular regulation of EMT, including signaling pathways (TGF-β, WNT, NOTCH, HIPPO), transcription factors (SNAIL, ZEB, TWIST), and regulatory layers involving microRNAs and epigenetic modifications. Moreover, we discuss the emergence of pEMT states as drivers of phenotypic plasticity, functional heterogeneity, and poor prognosis. By comparing EMT in cancer and fibrosis, we reveal shared mechanisms and disease-specific features, emphasizing the translational relevance of targeting EMT plasticity. Finally, we explore how cutting-edge technologies, such as single-cell transcriptomics and lineage tracing, are reshaping our understanding of EMT across pathological contexts. Full article
(This article belongs to the Special Issue Cellular Plasticity and EMT in Cancer and Fibrotic Diseases)
Show Figures

Figure 1

31 pages, 1002 KB  
Article
Strengthening Small Object Detection in Adapted RT-DETR Through Robust Enhancements
by Manav Madan and Christoph Reich
Electronics 2025, 14(19), 3830; https://doi.org/10.3390/electronics14193830 - 27 Sep 2025
Abstract
RT-DETR (Real-Time DEtection TRansformer) has recently emerged as a promising model for object detection in images, yet its performance on small objects remains limited, particularly in terms of robustness. While various approaches have been explored, developing effective solutions for reliable small object detection [...] Read more.
RT-DETR (Real-Time DEtection TRansformer) has recently emerged as a promising model for object detection in images, yet its performance on small objects remains limited, particularly in terms of robustness. While various approaches have been explored, developing effective solutions for reliable small object detection remains a significant challenge. This paper introduces an adapted variant of RT-DETR, specifically designed to enhance robustness in small object detection. The model was first designed on one dataset and subsequently transferred to others to validate generalization. Key contributions include replacing components of the feed-forward neural network (FFNN) within a hybrid encoder with Hebbian, randomized, and Oja-inspired layers; introducing a modified loss function; and applying multi-scale feature fusion with fuzzy attention to refine encoder representations. The proposed model is evaluated on the Al-Cast Detection X-ray dataset, which contains small components from high-pressure die-casting machines, and the PCB quality inspection dataset, which features tiny hole anomalies. The results show that the optimized model achieves an mAP of 0.513 for small objects—an improvement from the 0.389 of the baseline RT-DETR model on the Al-Cast dataset—confirming its effectiveness. In addition, this paper contributes a mini-literature review of recent RT-DETR enhancements, situating our work within current research trends and providing context for future development. Full article
(This article belongs to the Special Issue Applications of Computer Vision, 3rd Edition)
Show Figures

Figure 1

18 pages, 4048 KB  
Article
Isolation, Pathogenicity and Genomic Analysis of Mannheimia haemolytica Strain XJCJMh1 in Bovine-Mycoplasma Co-Infection
by Chengzhe Liang, Kashaf Kareem, Lichun Zhang, Yafei Liang, Huiying Wu, Beibei Li and Jinliang Sheng
Microorganisms 2025, 13(10), 2258; https://doi.org/10.3390/microorganisms13102258 - 26 Sep 2025
Abstract
Mixed infections of Mannheimia haemolytica and Mycoplasma bovis are relatively common in bovine respiratory diseases, presenting severe respiratory symptoms and high mortality that severely endanger the cattle industry. In this study, a serotype A1 strain of Mannheimia haemolytica, designated as XJCJMh1, was [...] Read more.
Mixed infections of Mannheimia haemolytica and Mycoplasma bovis are relatively common in bovine respiratory diseases, presenting severe respiratory symptoms and high mortality that severely endanger the cattle industry. In this study, a serotype A1 strain of Mannheimia haemolytica, designated as XJCJMh1, was isolated and identified from the lung tissue of a hybrid Simmental calf infected with Mycoplasma bovis. The pathogenicity of this strain was evaluated using Kunming mice as a model. The results indicated that infection with XJCJMh1 caused pathological manifestations such as pulmonary hemorrhage and edema in mice. Subsequently, the genome of this strain was sequenced and assembled using Illumina sequencing to obtain general genomic features. The genome was annotated and analyzed for gene functions using the Swiss-Prot, NR, GO, COG, KEGG, CAZy, TCDB, and Pfam databases. Additionally, the virulence factors and resistance genes of this strain were annotated using the PHI, VFDB, and CARD databases. The genome of Mannheimia haemolytica XJCJMh1 is 2,595,489 base pairs (bp) in length, with a GC content of 40.93%. Notably, this strain exhibits three distinct genomic islands and contains 98 effectors associated with the type III secretion system (T3SS). The XJCJMh1 strain harbors 74 virulence genes and 45 resistance genes. We annotated the proteins, genes, and associated GO and KEGG pathways of the XJCJMh1 strain; exploring the relationship between these annotations and the strain’s pathogenicity is of considerable value. This study is of great significance for clarifying the pathogenic mechanism and genetic characteristics of the Mannheimia haemolytica strain XJCJMh1 in cattle, and its results provide a scientific reference for analyzing the genomic basis of pathogenicity and drug resistance of Mannheimia haemolytica under co-infection conditions. Full article
(This article belongs to the Section Veterinary Microbiology)
Show Figures

Figure 1

37 pages, 16383 KB  
Article
Generating Realistic Urban Patterns: A Controllable cGAN Approach with Hybrid Loss Optimization
by Amgad Agoub and Martin Kada
ISPRS Int. J. Geo-Inf. 2025, 14(10), 375; https://doi.org/10.3390/ijgi14100375 - 25 Sep 2025
Abstract
This study explores the use of conditional Generative Adversarial Networks (cGANs) for simulating urban morphology, a domain where such models remain underutilized but have significant potential to generate realistic and controllable city patterns. To explore this potential, this research includes several contributions: a [...] Read more.
This study explores the use of conditional Generative Adversarial Networks (cGANs) for simulating urban morphology, a domain where such models remain underutilized but have significant potential to generate realistic and controllable city patterns. To explore this potential, this research includes several contributions: a bespoke model architecture that integrates attention mechanisms with visual reasoning through a generalized conditioning layer. A novel mechanism that enables the steering of urban pattern generation through the use of statistical input distributions, the development of a novel and comprehensive training dataset, meticulously derived from open-source geospatial data of Berlin. Our model is trained using a hybrid loss function, combining adversarial, focal and L1 losses to ensure perceptual realism, address challenging fine-grained features, and enforce pixel-level accuracy. Model performance was assessed through a combination of qualitative visual analysis and quantitative evaluation using metrics such as Kullback–Leibler Divergence (KL Divergence), Structural Similarity Index (SSIM), and Dice Coefficient. The proposed approach has demonstrated effectiveness in generating realistic and spatially coherent urban patterns, with promising potential for controllability. In addition to showcasing its strengths, we also highlight the limitations and outline future directions for advancing future work. Full article
(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)
Show Figures

Figure 1

25 pages, 10025 KB  
Article
Short-Term Photovoltaic Power Forecasting Based on ICEEMDAN-TCN-BiLSTM-MHA
by Yuan Li, Shiming Zhai, Guoyang Yi, Shaoyun Pang and Xu Luo
Symmetry 2025, 17(10), 1599; https://doi.org/10.3390/sym17101599 - 25 Sep 2025
Abstract
In this paper, an efficient hybrid photovoltaic (PV) power forecasting model is proposed to enhance the stability and accuracy of PV power prediction under typical weather conditions. First, the Improved Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) is employed to decompose [...] Read more.
In this paper, an efficient hybrid photovoltaic (PV) power forecasting model is proposed to enhance the stability and accuracy of PV power prediction under typical weather conditions. First, the Improved Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) is employed to decompose both meteorological features affecting PV power and the power output itself into intrinsic mode functions. This process enhances the stationarity and noise robustness of input data while reducing the computational complexity of subsequent model processing. To enhance the detail-capturing capability of the Bidirectional Long Short-Term Memory (BiLSTM) model and improve its dynamic response speed and prediction accuracy under abrupt irradiance fluctuations, we integrate a Temporal Convolutional Network (TCN) into the BiLSTM architecture. Finally, a Multi-head Self-Attention (MHA) mechanism is employed to dynamically weight multivariate meteorological features, enhancing the model’s adaptive focus on key meteorological factors while suppressing noise interference. The results show that the ICEEMDAN-TCN-BiLSTM-MHA combined model reduces the Mean Absolute Percentage Error (MAPE) by 78.46% and 78.59% compared to the BiLSTM model in sunny and cloudy scenarios, respectively, and by 58.44% in rainy scenarios. This validates the accuracy and stability of the ICEEMDAN-TCN-BiLSTM-MHA combined model, demonstrating its application potential and promotional value in the field of PV power forecasting. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

14 pages, 1507 KB  
Article
Diagnostic Efficacy of Olfactory Function Test Using Functional Near-Infrared Spectroscopy with Machine Learning in Healthy Adults: A Prospective Diagnostic-Accuracy (Feasibility/Validation) Study in Healthy Adults with Algorithm Development
by Minhyuk Lim, Seonghyun Kim, Dong Keon Yon and Jaewon Kim
Diagnostics 2025, 15(19), 2433; https://doi.org/10.3390/diagnostics15192433 - 24 Sep 2025
Viewed by 82
Abstract
Background/Objectives: The YSK olfactory function (YOF) test is a culturally adapted psychophysical tool that assesses threshold, discrimination, and identification. This study evaluated whether functional near-infrared spectroscopy (fNIRS) synchronized with routine YOF testing, combined with machine learning, can predict YOF subdomain performance in [...] Read more.
Background/Objectives: The YSK olfactory function (YOF) test is a culturally adapted psychophysical tool that assesses threshold, discrimination, and identification. This study evaluated whether functional near-infrared spectroscopy (fNIRS) synchronized with routine YOF testing, combined with machine learning, can predict YOF subdomain performance in healthy adults, providing an objective neural correlate to complement behavioral testing. Methods: In this prospective diagnostic-accuracy (feasibility/validation) study in healthy adults with algorithm development, 100 healthy adults completed the YOF test while undergoing prefrontal/orbitofrontal fNIRS during odor blocks. Feature sets from ΔHbO/ΔHbR included time-domain descriptors, complexity (Lempel–Ziv), and information-theoretic measures (mutual information); the identification task used a hybrid attention–CNN. Separate models were developed for threshold (binary classification), discrimination (binary classification), and identification (binary classification). Performance was summarized with accuracy, area under the curve (AUC), F1-score, and (where applicable) sensitivity/specificity, using participant-level cross-validation. Results: The threshold classifier achieved accuracy 0.86, AUC 0.86, and F1 0.86, indicating strong discrimination of correct vs. incorrect threshold responses. The discrimination model yielded accuracy 0.75, AUC 0.76, and F1 0.75. The identification model (attention–convolutional neural network [CNN]) achieved accuracy 0.88, sensitivity 0.86, specificity 0.91, and F1 0.88. Feature-attribution (e.g., SHapley Additive exPlanations [SHAP]) provided interpretable links between fNIRS features and task performance for threshold and discrimination. Conclusions: Olfactory-evoked fNIRS signals can accurately predict YOF subdomain performance in healthy adults, supporting the feasibility of non-invasive, portable, near–real-time olfactory monitoring. These findings are preliminary and not generalizable to clinical populations; external validation in diverse cohorts is warranted. The approach clarifies the scientific essence of the method by (i) aligning psychophysical outcomes with objective hemodynamic signatures and (ii) introducing a feature-rich modeling pipeline (ΔHbO/ΔHbR + Lempel–Ziv complexity/mutual information; attention–CNN) that advances prior work. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

28 pages, 14783 KB  
Article
HSSTN: A Hybrid Spectral–Structural Transformer Network for High-Fidelity Pansharpening
by Weijie Kang, Yuan Feng, Yao Ding, Hongbo Xiang, Xiaobo Liu and Yaoming Cai
Remote Sens. 2025, 17(19), 3271; https://doi.org/10.3390/rs17193271 - 23 Sep 2025
Viewed by 133
Abstract
Pansharpening fuses multispectral (MS) and panchromatic (PAN) remote sensing images to generate outputs with high spatial resolution and spectral fidelity. Nevertheless, conventional methods relying primarily on convolutional neural networks or unimodal fusion strategies frequently fail to bridge the sensor modality gap between MS [...] Read more.
Pansharpening fuses multispectral (MS) and panchromatic (PAN) remote sensing images to generate outputs with high spatial resolution and spectral fidelity. Nevertheless, conventional methods relying primarily on convolutional neural networks or unimodal fusion strategies frequently fail to bridge the sensor modality gap between MS and PAN data. Consequently, spectral distortion and spatial degradation often occur, limiting high-precision downstream applications. To address these issues, this work proposes a Hybrid Spectral–Structural Transformer Network (HSSTN) that enhances multi-level collaboration through comprehensive modelling of spectral–structural feature complementarity. Specifically, the HSSTN implements a three-tier fusion framework. First, an asymmetric dual-stream feature extractor employs a residual block with channel attention (RBCA) in the MS branch to strengthen spectral representation, while a Transformer architecture in the PAN branch extracts high-frequency spatial details, thereby reducing modality discrepancy at the input stage. Subsequently, a target-driven hierarchical fusion network utilises progressive crossmodal attention across scales, ranging from local textures to multi-scale structures, to enable efficient spectral–structural aggregation. Finally, a novel collaborative optimisation loss function preserves spectral integrity while enhancing structural details. Comprehensive experiments conducted on QuickBird, GaoFen-2, and WorldView-3 datasets demonstrate that HSSTN outperforms existing methods in both quantitative metrics and visual quality. Consequently, the resulting images exhibit sharper details and fewer spectral artefacts, showcasing significant advantages in high-fidelity remote sensing image fusion. Full article
(This article belongs to the Special Issue Artificial Intelligence in Hyperspectral Remote Sensing Data Analysis)
Show Figures

Figure 1

30 pages, 4822 KB  
Article
Combining Deep Learning Architectures with Fuzzy Logic for Robust Pneumonia Detection in Chest X-Rays
by Azeddine Mjahad and Alfredo Rosado-Muñoz
Appl. Sci. 2025, 15(19), 10321; https://doi.org/10.3390/app151910321 - 23 Sep 2025
Viewed by 186
Abstract
Early and accurate detection of pneumonia from chest X-ray images is essential for improving treatment and clinical outcomes. Medical imaging datasets often exhibit class imbalance and uncertainty in feature extraction, which complicates conventional classification methods and motivates the use of advanced approaches combining [...] Read more.
Early and accurate detection of pneumonia from chest X-ray images is essential for improving treatment and clinical outcomes. Medical imaging datasets often exhibit class imbalance and uncertainty in feature extraction, which complicates conventional classification methods and motivates the use of advanced approaches combining deep learning and fuzzy logic. This study proposes a hybrid approach that combines deep learning architectures (VGG16, EfficientNetV2, MobileNetV2, ResNet50) for feature extraction with fuzzy logic-based classifiers, including Fuzzy C-Means, Fuzzy Decision Tree, Fuzzy KNN, Fuzzy SVM, and ANFIS (Adaptive Neuro-Fuzzy Inference System). Feature selection techniques were also applied to enhance the discriminative power of the extracted features. The best-performing model, ANFIS with MobileNetV2 features and Gaussian membership functions, achieved an overall accuracy of 98.52%, with Normal class precision of 97.07%, recall of 97.48%, and F1-score of 97.27%, and Pneumonia class precision of 99.06%, recall of 98.91%, and F1-score of 98.99%. Among the fuzzy classifiers, Fuzzy SVM and Fuzzy KNN also showed strong performance with accuracy above 96%, while Fuzzy Decision Tree and Fuzzy C-Means achieved moderate results. These findings demonstrate that integrating deep feature extraction with neuro-fuzzy reasoning significantly improves diagnostic accuracy and robustness, providing a reliable tool for clinical decision support. Future research will focus on optimizing model efficiency, interpretability, and real-time applicability. Full article
(This article belongs to the Special Issue Machine Learning-Based Feature Extraction and Selection: 2nd Edition)
Show Figures

Figure 1

12 pages, 1247 KB  
Review
Imaging Flow Cytometry as a Molecular Biology Tool: From Cell Morphology to Molecular Mechanisms
by Yoshikazu Matsuoka
Int. J. Mol. Sci. 2025, 26(19), 9261; https://doi.org/10.3390/ijms26199261 - 23 Sep 2025
Viewed by 149
Abstract
Insights into the state of individual cells within a living organism are essential for identifying diseases and abnormalities. The internal state of a cell is reflected in its morphological features and changes in the localization of intracellular molecules. Using this information, it is [...] Read more.
Insights into the state of individual cells within a living organism are essential for identifying diseases and abnormalities. The internal state of a cell is reflected in its morphological features and changes in the localization of intracellular molecules. Using this information, it is possible to infer the state of the cells with high precision. In recent years, technological advancements and improvements in instrument specifications have made large-scale analyses, such as single-cell analysis, more widely accessible. Among these technologies, imaging flow cytometry (IFC) is a high-throughput imaging platform that can simultaneously acquire information from flow cytometry (FCM) and cellular images. While conventional FCM can only obtain fluorescence intensity information corresponding to each detector, IFC can acquire multidimensional information, including cellular morphology and the spatial arrangement of proteins, nucleic acids, and organelles for each imaging channel. This enables the discrimination of cell types and states based on the localization of proteins and organelles, which is difficult to assess accurately using conventional FCM. Because IFC can acquire a large number of single-cell morphological images in a short time, it is well suited for automated classification using machine learning. Furthermore, commercial instruments that combine integrated imaging and cell sorting capabilities have recently become available, enabling the sorting of cells based on their image information. In this review, we specifically highlight practical applications of IFC in four representative areas: cell cycle analysis, protein localization analysis, immunological synapse formation, and the detection of leukemic cells. In addition, particular emphasis is placed on applications that directly contribute to elucidating molecular mechanisms, thereby distinguishing this review from previous general overviews of IFC. IFC enables the estimation of cell cycle phases from large numbers of acquired cellular images using machine learning, thereby allowing more precise cell cycle analysis. Moreover, IFC has been applied to investigate intracellular survival and differentiation signals triggered by external stimuli, to monitor DNA damage responses such as γH2AX foci formation, and more recently, to detect immune synapse formation among interacting cells within large populations and to analyze these interactions at the molecular level. In hematological malignancies, IFC combined with fluorescence in situ hybridization (FISH) enables high-throughput detection of chromosomal abnormalities, such as BCR-ABL1 translocations. These advances demonstrate that IFC provides not only morphological and functional insights but also clinically relevant genomic information at the single-cell level. By summarizing these unique applications, this review aims to complement existing publications and provide researchers with practical insights into how IFC can be implemented in both basic and translational research. Full article
Show Figures

Figure 1

18 pages, 1694 KB  
Article
FAIR-Net: A Fuzzy Autoencoder and Interpretable Rule-Based Network for Ancient Chinese Character Recognition
by Yanling Ge, Yunmeng Zhang and Seok-Beom Roh
Sensors 2025, 25(18), 5928; https://doi.org/10.3390/s25185928 - 22 Sep 2025
Viewed by 150
Abstract
Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, [...] Read more.
Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, as they are typically trained on modern printed or handwritten text and lack interpretability. To tackle these challenges, we propose FAIR-Net, a hybrid architecture that combines the unsupervised feature learning capacity of a deep autoencoder with the semantic transparency of a fuzzy rule-based classifier. In FAIR-Net, the deep autoencoder first compresses high-resolution character images into low-dimensional, noise-robust embeddings. These embeddings are then passed into a Fuzzy Neural Network (FNN), whose hidden layer leverages Fuzzy C-Means (FCM) clustering to model soft membership degrees and generate human-readable fuzzy rules. The output layer uses Iteratively Reweighted Least Squares Estimation (IRLSE) combined with a Softmax function to produce probabilistic predictions, with all weights constrained as linear mappings to maintain model transparency. We evaluate FAIR-Net on CASIA-HWDB1.0, HWDB1.1, and ICDAR 2013 CompetitionDB, where it achieves a recognition accuracy of 97.91%, significantly outperforming baseline CNNs (p < 0.01, Cohen’s d > 0.8) while maintaining the tightest confidence interval (96.88–98.94%) and lowest standard deviation (±1.03%). Additionally, FAIR-Net reduces inference time to 25 s, improving processing efficiency by 41.9% over AlexNet and up to 98.9% over CNN-Fujitsu, while preserving >97.5% accuracy across evaluations. To further assess generalization to historical scripts, FAIR-Net was tested on the Ancient Chinese Character Dataset (9233 classes; 979,907 images), achieving 83.25% accuracy—slightly higher than ResNet101 but 2.49% lower than SwinT-v2-small—while reducing training time by over 5.5× compared to transformer-based baselines. Fuzzy rule visualization confirms enhanced robustness to glyph ambiguities and erosion. Overall, FAIR-Net provides a practical, interpretable, and highly efficient solution for the digitization and preservation of ancient Chinese character corpora. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

22 pages, 2938 KB  
Article
Real-Time Braille Image Detection Algorithm Based on Improved YOLOv11 in Natural Scenes
by Yu Sun, Wenhao Chen, Yihang Qin, Xuan Li and Chunlian Li
Appl. Sci. 2025, 15(18), 10288; https://doi.org/10.3390/app151810288 - 22 Sep 2025
Viewed by 199
Abstract
The development of Braille recognition technology is intrinsically linked to the educational rights of individuals with visual impairments. The key challenges in natural scene Braille detection include three core trade-offs: difficulty extracting small-target features under complex background interference, a balance between model accuracy [...] Read more.
The development of Braille recognition technology is intrinsically linked to the educational rights of individuals with visual impairments. The key challenges in natural scene Braille detection include three core trade-offs: difficulty extracting small-target features under complex background interference, a balance between model accuracy and real-time performance, and generalization across diverse scenes. To address these issues, this paper proposes an improved YOLOv11 algorithm that integrates a lightweight gating mechanism and subspace attention. By reconstructing the C3k2 module into a hybrid structure containing Gated Bottleneck Convolutions (GBC), the algorithm effectively captures weak Braille dot matrix features. A super-lightweight subspace attention module (ULSAM) enhances the attention to Braille regions, while the SDIoU loss function optimizes bounding box regression accuracy. Experimental results on a natural scene Braille dataset show that the algorithm achieves a Precision of 0.9420 and a Recall of 0.9514 with only 2.374 M parameters. Compared to the base YOLOv11, this algorithm improves the combined detection performance (Precision: 0.9420, Recall: 0.9514) by 3.2% and reduces computational complexity by 6.3% (with only 2.374 M parameters). Ablation experiments validate the synergistic effect of each module: the GBC structure reduces the model parameter count by 8.1% to maintain lightweight properties, and the ULSAM effectively lowers the missed detection rate of ultra-small Braille targets. This study provides core algorithmic support for portable Braille assistive devices, advancing the technical realization of equal information access for individuals with visual impairments. Full article
Show Figures

Figure 1

22 pages, 5746 KB  
Article
AGSK-Net: Adaptive Geometry-Aware Stereo-KANformer Network for Global and Local Unsupervised Stereo Matching
by Qianglong Feng, Xiaofeng Wang, Zhenglin Lu, Haiyu Wang, Tingfeng Qi and Tianyi Zhang
Sensors 2025, 25(18), 5905; https://doi.org/10.3390/s25185905 - 21 Sep 2025
Viewed by 269
Abstract
The performance of unsupervised stereo matching in complex regions such as weak textures and occlusions is constrained by the inherently local receptive fields of convolutional neural networks (CNNs), the absence of geometric priors, and the limited expressiveness of MLP in conventional ViTs. To [...] Read more.
The performance of unsupervised stereo matching in complex regions such as weak textures and occlusions is constrained by the inherently local receptive fields of convolutional neural networks (CNNs), the absence of geometric priors, and the limited expressiveness of MLP in conventional ViTs. To address these problems, we propose an Adaptive Geometry-aware Stereo-KANformer Network (AGSK-Net) for unsupervised stereo matching. Firstly, to resolve the conflict between the isotropic nature of traditional ViT and the epipolar geometry priors in stereo matching, we propose Adaptive Geometry-aware Multi-head Self-Attention (AG-MSA), which embeds epipolar priors via an adaptive hybrid structure of geometric modulation and penalty, enabling geometry-aware global context modeling. Secondly, we design Spatial Group-Rational KAN (SGR-KAN), which integrates the nonlinear capability of rational functions with the spatial awareness of deep convolutions, replacing the MLP with flexible, learnable rational functions to enhance the nonlinear expression ability of complex regions. Finally, we propose a Dynamic Candidate Gated Fusion (DCGF) module that employs dynamic dual-candidate states and spatially aware pre-enhancement to adaptively fuse global and local features across scales. Experiments demonstrate that AGSK-Net achieves state-of-the-art accuracy and generalizability on Scene Flow, KITTI 2012/2015, and Middlebury 2021. Full article
(This article belongs to the Special Issue Deep Learning Technology and Image Sensing: 2nd Edition)
Show Figures

Figure 1

23 pages, 10263 KB  
Article
DS-YOLO: A Lightweight Strawberry Fruit Detection Algorithm
by Hao Teng, Fuchun Sun, Haorong Wu, Dong Lv, Qiurong Lv, Fan Feng, Sichen Yang and Xiaoxiao Li
Agronomy 2025, 15(9), 2226; https://doi.org/10.3390/agronomy15092226 - 20 Sep 2025
Viewed by 318
Abstract
Strawberry detection in complex orchard environments remains a challenging task due to frequent leaf occlusion, fruit overlap, and illumination variability. To address these challenges, this study presents an improved lightweight detection framework, DS-YOLO, based on YOLOv8n. First, the backbone network of YOLOv8n is [...] Read more.
Strawberry detection in complex orchard environments remains a challenging task due to frequent leaf occlusion, fruit overlap, and illumination variability. To address these challenges, this study presents an improved lightweight detection framework, DS-YOLO, based on YOLOv8n. First, the backbone network of YOLOv8n is replaced with the lightweight StarNet to reduce the number of parameters while preserving the model’s feature representation capability. Second, the Conv and C2f modules in the Neck section are replaced with SlimNeck’s GSConv (hybrid convolution module) and VoVGSCSP (cross-stage partial network) modules, which effectively enhance detection performance and reduce computational burden. Finally, the original CIoU loss function is substituted with WIoUv3 to improve bounding box regression accuracy and overall detection performance. To validate the effectiveness of the proposed improvements, comparative experiments were conducted with six mainstream object detection models, four backbone networks, and five different loss functions. Experimental results demonstrate that the DS-YOLO achieves a 1.7 percentage point increase in mAP50, a 1.5 percentage point improvement in recall, and precision improvement of 1.3 percentage points. In terms of computational efficiency, the number of parameters is reduced from 3.2M to 1.8M, and computational cost decreases from 8.1G to 4.9G, corresponding to reductions of 43% and 40%, respectively. The improved DS-YOLO model enables real-time and accurate detection of strawberry fruits in complex environments with a more compact network architecture, providing valuable technical support for automated strawberry detection and lightweight deployment. Full article
Show Figures

Figure 1

Back to TopTop