Saved Queries

Background/Objectives: Glioblastoma (GBM) is an aggressive brain tumor known for its profound heterogeneity and treatment resistance. Dysregulated complement signaling and epigenetic alterations have been implicated in GBM progression. This study identifies kynureninase (KYNU), a key enzyme in the kynurenine pathway, as a novel regulator of complement components and investigates its interaction with histone deacetylase 6 (HDAC6) in the context of therapeutic targeting. Methods: KYNU expression, and its association with complement signaling in GBM, were analyzed using publicly available datasets (TCGA, GTEx, HPA). Pathway enrichment was performed via LinkedOmics. In vitro studies in GBM cell lines (U87, U251, T98G) assessed the effects of KYNU silencing and treatment with an HDAC6 inhibitor (tubastatin) and a BET inhibitor (apabetalone) on gene expression and cell viability. Results: Bioinformatic analyses revealed significant overexpression of KYNU in GBM tissues compared to normal brain tissue. KYNU expression was positively associated with genes involved in complement and coagulation cascades. In vitro experiments demonstrated that KYNU silencing reduced the expression of C3, C3AR1, and C5AR1 and suppressed GBM cell viability. Treatment with tubastatin, while reducing viability, paradoxically upregulated complement genes, suggesting potential limitations in therapeutic efficacy. However, this effect was mitigated by KYNU knockdown. Combined treatment with apabetalone and tubastatin effectively suppressed KYNU expression and enhanced cytotoxicity, particularly in cells with high complement expression. Conclusions: Our findings establish the KYNU–HDAC6–complement axis as a critical regulatory pathway in GBM. Targeting KYNU-mediated complement activation through combined epigenetic approaches—such as HDAC6 and BET inhibition—represents a promising strategy to overcome complement-driven resistance in GBM therapy. Full article

►▼ Show Figures

Figure 1

23 pages, 1019 KiB

Open AccessArticle

Deciphering the Environmental Consequences of Competition-Induced Cost Rationalization Strategies of the High-Tech Industry: A Synergistic Combination of Advanced Machine Learning and Method of Moments Quantile Regression Procedures

by Salih Çağrı İlkay, Harun Kınacı and Esra Betül Kınacı

Sustainability 2025, 17(15), 6867; https://doi.org/10.3390/su17156867 - 28 Jul 2025

Abstract

This study intends to portray how varying degrees of environmental policy stringency and the growing pressure of global competition reflect on high-tech (HT) sectors’ cost rationalization strategies and lead to environmental consequences in 15 G20 countries (1992–2019). Moreover, we center the pattern of cost rationalization management regarding the opportunity cost of ecosystem service consumption and propose to test the fundamental hypothesis stating the possible transmission of competition-induced technological innovations to green economic transformation. Our new methodology estimates quantile-specific effects with MM-QR, while identifying the main interaction effects between regulatory pressure and trade competition uses an extended STIRPAT model. The results reveal a paradoxical finding: despite higher environmental policy stringency and opportunity costs of ecosystem services, HT sectors persistently adopt environmentally detrimental cost-reduction approaches. These findings carry important policy implications: (1) environmental regulations for HT sectors require complementary innovation subsidies, (2) trade agreements should incorporate clean technology transfer clauses, and (3) governments must monitor sectoral emission leakage risks. Our dual machine learning–econometric approach provides policymakers with targeted insights for different emission scenarios, highlighting the need for differentiated strategies across clean and polluting HT subsectors. Full article

►▼ Show Figures

Figure 1

37 pages, 3086 KiB

Open AccessArticle

Conformal On-Body Antenna System Integrated with Deep Learning for Non-Invasive Breast Cancer Detection

by Marwa H. Sharaf, Manuel Arrebola, Khalid F. A. Hussein, Asmaa E. Farahat and Álvaro F. Vaquero

Sensors 2025, 25(15), 4670; https://doi.org/10.3390/s25154670 - 28 Jul 2025

Abstract

Breast cancer detection through non-invasive and accurate techniques remains a critical challenge in medical diagnostics. This study introduces a deep learning-based framework that leverages a microwave radar system equipped with an arc-shaped array of six antennas to estimate key tumor parameters, including position, size, and depth. This research begins with the evolutionary design of an ultra-wideband octagram ring patch antenna optimized for enhanced tumor detection sensitivity in directional near-field coupling scenarios. The antenna is fabricated and experimentally evaluated, with its performance validated through S-parameter measurements, far-field radiation characterization, and efficiency analysis to ensure effective signal propagation and interaction with breast tissue. Specific Absorption Rate (SAR) distributions within breast tissues are comprehensively assessed, and power adjustment strategies are implemented to comply with electromagnetic exposure safety limits. The dataset for the deep learning model comprises simulated self and mutual S-parameters capturing tumor-induced variations over a broad frequency spectrum. A core innovation of this work is the development of the Attention-Based Feature Separation (ABFS) model, which dynamically identifies optimal frequency sub-bands and disentangles discriminative features tailored to each tumor parameter. A multi-branch neural network processes these features to achieve precise tumor localization and size estimation. Compared to conventional attention mechanisms, the proposed ABFS architecture demonstrates superior prediction accuracy and interpretability. The proposed approach achieves high estimation accuracy and computational efficiency in simulation studies, underscoring the promise of integrating deep learning with conformal microwave imaging for safe, effective, and non-invasive breast cancer detection. Full article

(This article belongs to the Special Issue Advanced Sensing and Signal Processing Technologies for Medical Applications)

17 pages, 1027 KiB

Open AccessArticle

Supramolecular Graphene Quantum Dots/Porphyrin Complex as Fluorescence Probe for Metal Ion Sensing

by Mariachiara Sarà, Andrea Romeo, Gabriele Lando, Maria Angela Castriciano, Roberto Zagami, Giovanni Neri and Luigi Monsù Scolaro

Int. J. Mol. Sci. 2025, 26(15), 7295; https://doi.org/10.3390/ijms26157295 - 28 Jul 2025

Abstract

Graphene quantum dots (GQDs) obtained by microwave-induced pyrolysis of glutamic acid and triethylenetetramine (trien) are fairly stable, emissive, water-soluble, and positively charged nano-systems able to interact with negatively charged meso-tetrakis(4-sulfonatophenyl) porphyrin (TPPS₄). The stoichiometric control during the preparation affords a supramolecular adduct, GQDs@TPPS₄, that exhibits a double fluorescence emission from both the GQDs and the TPPS₄ fluorophores. These supramolecular aggregates have an overall negative charge that is responsible for the condensation of cations in the nearby aqueous layer, and a three-fold acceleration of the metalation rates of Cu²⁺ ions has been observed with respect to the parent porphyrin. Addition of various metal ions leads to some changes in the UV/Vis spectra and has a different impact on the fluorescence emission of GQDs and TPPS₄. The quenching efficiency of the TPPS₄ emission follows the order Cu²⁺ > Hg²⁺ > Cd²⁺ > Pb²⁺ ~ Zn²⁺ ~ Co²⁺ ~ Ni²⁺ > Mn²⁺ ~ Cr³⁺ >> Mg²⁺ ~ Ca²⁺ ~ Ba²⁺, and it has been related to literature data and to the sitting-atop mechanism that large transition metal ions (e.g., Hg²⁺ and Cd²⁺) exhibit in their interaction with the macrocyclic nitrogen atoms of the porphyrin, inducing distortion and accelerating the insertion of smaller metal ions, such as Zn²⁺. For the most relevant metal ions, emission quenching of the porphyrin evidences a linear behavior in the micromolar range, with the emission of the GQDs being moderately affected through a filter effect. Deliberate pollution of the samples with Zn²⁺ reveals the ability of the GQDs@TPPS₄ adduct to detect sensitively Cu²⁺, Hg^2+, and Cd²⁺ ions. Full article

(This article belongs to the Special Issue Feature Papers in ‘Physical Chemistry and Chemical Physics’: Fourth Edition)

8 pages, 296 KiB

Open AccessCommunication

Enhancing Medical Education Through Statistics: Bridging Quantitative Literacy and Sports Supplementation Research for Improved Clinical Practice

by Alexander A. Huang and Samuel Y. Huang

Nutrients 2025, 17(15), 2463; https://doi.org/10.3390/nu17152463 - 28 Jul 2025

Abstract

In modern medical education, a robust understanding of statistics is essential for fostering critical thinking, informed clinical decision-making, and effective communication. This paper explores the synergistic value of early and continued statistical education for medical students and residents, particularly in relation to the expanding field of sports supplementation and its impact on athletic performance. Early exposure to statistical principles enhances students’ ability to interpret clinical research, avoid cognitive biases, and engage in evidence-based practice. Continued statistical learning throughout residency further refines these competencies, enabling more sophisticated analysis and application of emerging data. The paper also addresses key challenges in integrating statistics into medical curricula—such as limited curricular space, student disengagement, and resource constraints—and proposes solutions including interactive learning, case-based teaching, and the use of public datasets. A unique emphasis is placed on connecting statistical literacy to the interpretation of research in sports science, particularly regarding the efficacy, safety, and ethical considerations of sports supplements. By linking statistical education to a dynamic and relatable domain like sports performance, educators can not only enrich learning outcomes but also foster lasting interest and competence in quantitative reasoning. This integrated approach holds promise for producing more analytically proficient and clinically capable physicians. Full article

(This article belongs to the Special Issue The Role of Sports Supplements in Sport Performance)

24 pages, 2035 KiB

Open AccessArticle

Seismic Response Analysis of a Six-Story Building in Sofia Using Accelerograms from the 2012 Mw5.6 Pernik Earthquake

by Lyubka Pashova, Emil Oynakov, Ivanka Paskaleva and Radan Ivanov

Appl. Sci. 2025, 15(15), 8385; https://doi.org/10.3390/app15158385 - 28 Jul 2025

Abstract

On 22 May 2012, a magnitude Mw 5.6 earthquake struck the Pernik region of western Bulgaria, causing structural damage in nearby cities, including Sofia. This study assesses the seismic response of a six-story reinforced concrete building in central Sofia, utilizing real accelerogram data recorded at the basement (SGL1) and sixth floor (SGL2) levels during the earthquake. Using the Kanai–Yoshizawa (KY) model, the study estimates inter-story motion and assesses amplification effects across the structure. Analysis of peak ground acceleration (PGA), velocity (PGV), displacement (PGD), and spectral ratios reveals significant dynamic amplification of peak ground acceleration and displacement on the sixth floor, indicating flexible and dynamic behavior, as well as potential resonance effects. The analysis combines three spectral techniques—Horizontal-to-Vertical Spectral Ratio (H/V), Floor Spectral Ratio (FSR), and the Random Decrement Method (RDM)—to determine the building’s dynamic characteristics, including natural frequency and damping ratio. The results indicate a dominant vibration frequency of approximately 2.2 Hz and damping ratios ranging from 3.6% to 6.5%, which is consistent with the typical damping ratios of mid-rise concrete buildings. The findings underscore the significance of soil–structure interaction (SSI), particularly in sedimentary basins like the Sofia Graben, where localized geological effects influence seismic amplification. By integrating accelerometric data with advanced spectral techniques, this research can enhance ongoing site-specific monitoring and seismic design practices, contributing to the refinement of earthquake engineering methodologies for mitigating seismic risk in earthquake-prone urban areas. Full article

(This article belongs to the Special Issue Seismic-Resistant Materials, Devices and Structures)

31 pages, 3715 KiB

Open AccessReview

Cutting Force—Vibration Interactions in Precise—and Micromilling Processes: A Critical Review on Prediction Methods

by Szymon Wojciechowski, Marcin Suszyński, Rafał Talar, Vit Černohlávek and Jan Štěrba

Materials 2025, 18(15), 3539; https://doi.org/10.3390/ma18153539 - 28 Jul 2025

Abstract

In recent years, much research has been devoted to the evaluation of physical phenomena and the technological effects of precise and micromilling processes. However, the available current literature lacks synthetic work covering the current state of the art regarding cutting force–tool displacement interactions in precise and micromilling manufacturing systems. Therefore, this literature review aims to fill this research gap and focuses on the critical literature review regarding the current state of the art within the prediction methods of cutting forces and machining system’s displacements/vibrations during precise and micromilling techniques. In the first part, a currently available cutting force, as well as the static and dynamic machining system displacement models applied in precise and micromilling conditions are presented. In the next stage, a relationship between the geometrical elements of cut and generated cutting forces and tool displacements are discussed, based on the recent literature. A subsequent part concerns the formulation of the generalized analytical models for a prediction of cutting forces and vibrations during precise and micromilling conditions. In the last stage, the conclusions and outlook are formulated based on the conducted analysis of the literature. In this context, this paper constitutes a synthetic work presenting current trends in the prediction of precise milling and micromilling mechanics. Full article

(This article belongs to the Special Issue Precision and Ultra-Precision Subtractive and Additive Manufacturing Processes of Alloys and Steels, 3rd Edition)

►▼ Show Figures

Figure 1

14 pages, 966 KiB

Open AccessArticle

Investigation of the Thermal Conductance of MEMS Contact Switches

by Zhiqiang Chen and Zhongbin Xie

Micromachines 2025, 16(8), 872; https://doi.org/10.3390/mi16080872 - 28 Jul 2025

Abstract

Microelectromechanical system (MEMS) devices are specialized electronic devices that integrate the benefits of both mechanical and electrical structures. However, the contact behavior between the interfaces of these structures can significantly impact the performance of MEMS devices, particularly when the surface roughness approaches the characteristic size of the devices. In such cases, the contact between the interfaces is not a perfect face-to-face interaction but occurs through point-to-point contact. As a result, the contact area changes with varying contact pressures and surface roughness, influencing the thermal and electrical performance. By integrating the CMY model with finite element simulations, we systematically explored the thermal conductance regulation mechanism of MEMS contact switches. We analyzed the effects of the contact pressure, micro-hardness, surface roughness, and other parameters on thermal conductance, providing essential theoretical support for enhancing reliability and optimizing thermal management in MEMS contact switches. We examined the thermal contact, gap, and joint conductance of an MEMS switch under different contact pressures, micro-hardness values, and surface roughness levels using the CMY model. Our findings show that both the thermal contact and gap conductance increase with higher contact pressure. For a fixed contact pressure, the thermal contact conductance decreases with rising micro-hardness and root mean square (RMS) surface roughness but increases with a higher mean asperity slope. Notably, the thermal gap conductance is considerably lower than the thermal contact conductance. Full article

►▼ Show Figures

Figure 1

13 pages, 600 KiB

Open AccessArticle

Validating the Arabic Adolescent Nutrition Literacy Scale (ANLS): A Reliable Tool for Measuring Nutrition Literacy

by Sahar Obeid, Souheil Hallit, Feten Fekih-Romdhane, Yonna Sacre, Marie Hokayem, Ayoub Saeidi, Lamya Sabbah, Nikolaos Tzenios and Maha Hoteit

Nutrients 2025, 17(15), 2457; https://doi.org/10.3390/nu17152457 - 28 Jul 2025

Abstract

Introduction: Nutrition literacy has garnered growing research attention worldwide, yet only a few instruments have been developed to specifically measure this construct among adolescents. Accordingly, the present research sought to examine the validity and reliability of the Adolescent Nutrition Literacy Scale (ANLS) within a group of Lebanese adolescents. Methods: A cross-sectional study was carried out from December 2022 to March 2023, targeting a nationally representative sample. Results: Fit indices of the three-factor structure were good. Internal reliability was adequate for the following three subscales: Functional Nutrition Literacy (FNL) (ω = 0.88/α = 0.88), Interactive Nutrition Literacy (INL) (ω = 0.87/α = 0.86) and Critical Nutrition Literacy (CNL) (ω = 0.89/α = 0.89). Invariance was established across genders at configural, metric, and scalar levels. A significantly higher mean FNL and INL scores were found in males compared to females, with no significant difference between the two genders in terms of CNL. Higher FNL, but not CNL and INL scores were significantly associated with lower child food security. Conclusions: The Arabic ANLS has exhibited robust psychometric reliability, validity, and cost-effectiveness as a tool for assessing nutrition literacy. By utilizing the Arabic version of the ANLS, we can more efficiently and accurately assess the nutritional literacy of adolescents. Full article

(This article belongs to the Topic Transforming Childhood Nutrition: New Perspectives on Food Literacy and Healthy Diets: 2nd Edition)

12 pages, 1304 KiB

Open AccessCommunication

Pharmacological Interaction of Botulinum Neurotoxins with Excitatory and Inhibitory Neurotransmitter Systems Involved in the Modulation of Inflammatory Pain

by Sara Marinelli, Flaminia Pavone and Siro Luvisetto

Toxins 2025, 17(8), 374; https://doi.org/10.3390/toxins17080374 - 28 Jul 2025

Abstract

Botulinum neurotoxins (BoNTs) are known to inhibit synaptic transmission by targeting SNARE proteins, but their selectivity toward central excitatory and inhibitory pathways is not yet fully understood. In this study, the interaction of serotypes A (BoNT/A) and B (BoNT/B) with the glutamatergic and GABAergic systems has been investigated using a pharmacological approach in an animal model of inflammatory pain, i.e., the formalin test in mice. BoNTs were administered intracerebroventricularly, three days before testing, followed 15 min before testing by systemic administration of sub-analgesic doses of MK801, an NMDA receptor antagonist, or muscimol, a GABA_A receptor agonist. BoNT/A reduced the second phase of the formalin test without affecting both the first phase and the interphase, suggesting a selective action on excitatory glutamatergic circuits while sparing GABAergic inhibition. Co-administration of MK801 with BoNT/A did not enhance analgesia, and muscimol did not further reduce interphase, confirming preserved GABAergic transmission. In contrast, BoNT/B abolished the interphase, consistent with impaired GABA release. Co-administration of MK801 or muscimol with BoNT/B restored the interphase, indicating compensatory rebalancing of excitatory-inhibitory networks. These results demonstrate that BoNT/A and BoNT/B exert distinct effects on central neurotransmission and support the hypothesis that BoNT/A preferentially targets excitatory synapses, while BoNT/B targets inhibitory synapses. This work contributes to a deeper understanding of anti-inflammatory mechanisms of BoNTs and their selective interaction with central pain pathways. Full article

(This article belongs to the Special Issue Botulinum Toxins: New Uses in the Treatment of Diseases (2nd Edition))

28 pages, 10987 KiB

Open AccessArticle

Multifactor Configurational Pathways Driving the Eco-Efficiency of Cultivated Land Utilization in China: A Dynamic Panel QCA

by Zihao Xu, Jialong Duan, Lei Zhan, Chuanmin Yan and Zhigang Huang

Land 2025, 14(8), 1549; https://doi.org/10.3390/land14081549 - 28 Jul 2025

Abstract

Cultivated land is fundamental to agricultural production, and the eco-efficiency of cultivated land utilization is widely acknowledged as a crucial indicator for assessing rational land use. Accordingly, this study applies a Super-SBM model with undesirable outputs to evaluate the eco-efficiency of cultivated land utilization (ECLU) across 31 provinces in China utilizing provincial panel data from 2005 to 2023 and further employs dynamic fuzzy-set qualitative comparative analysis to investigate, across spatial and temporal dimensions, how government policy, agricultural technology, socioeconomic conditions, and natural conditions interact to achieve a high ECLU and to elucidate the diverse configurational pathways through which these factors converge to deliver a high ECLU. Our findings demonstrate that the ECLU originates from the joint influence of several factors, and no single factor alone can provide a high level of eco-efficiency. In particular, a high GDP per capita and strong government agricultural expenditure intensity are pivotal for achieving a high ECLU, whereas a low GDP per capita and weak government agricultural expenditure intensity are the core conditions associated with poor eco-efficiency outcomes. We identify three distinct driving pathways that foster a high ECLU: the Economy–Technology–Government Synergistic Pathway, Nature–Economy Dual-Driver Pathway, and Government-Supported Land–Economy Pathway. Between-configuration consistency (BECONS) exhibits no significant temporal effect; however, a constellation of external factors triggered a pronounced, collective reduction in configurational consistency from 2008 to 2014. Regional analysis reveals pronounced heterogeneity: Spatially, the Economy–Technology–Government Synergistic Pathway is concentrated in China’s central and eastern provinces, the Nature–Economy Dual-Driver Pathway clusters mainly in the central belt, and the Government-Supported Land–Economy Pathway predominates in the west. Full article

(This article belongs to the Section Land Use, Impact Assessment and Sustainability)

15 pages, 290 KiB

Open AccessArticle

The Role of Need for Cognition and Its Interaction with Fluid Intelligence in the Prediction of School Grades in Primary School Children

by Anke Hufer-Thamm, Sebastian Bergold and Ricarda Steinmayr

J. Intell. 2025, 13(8), 94; https://doi.org/10.3390/jintelligence13080094 - 28 Jul 2025

Abstract

Fluid intelligence and need for cognition are relevant predictors of school grades and might also interact in the prediction of grades. We examined the independent predictive values of fluid intelligence and need for cognition as well as their interaction for math and German grades and changes therein in a sample of 565 German primary school children (298 girls, 261 boys, 6 with no gender specified; M_age = 8.40, SD = 0.59). Parental education was considered a control variable. Cross-sectional analyses showed that both intelligence and need for cognition were uniquely related to grades. However, in the latent change score analyses, fluid intelligence, but not need for cognition, was related to change in math grades, but not in German grades, and only when parental education was not considered as a control variable. We found no interaction effects between fluid intelligence and need for cognition. The findings imply that the need for cognition might not play a comparably relevant role for school grades in primary school as it has been shown in previous studies focusing on secondary or tertiary education. Full article

(This article belongs to the Section Studies on Cognitive Processes)

16 pages, 1169 KiB

Open AccessArticle

Environmental Microbiome Characteristics and Disinfection Strategy Optimization in Intensive Dairy Farms: Bactericidal Efficacy of Glutaraldehyde-Based Combination Disinfectants and Regulation of Gut Microbiota

by Tianchen Wang, Tao He, Mengqi Chai, Liyan Zhang, Xiangshu Han and Song Jiang

Vet. Sci. 2025, 12(8), 707; https://doi.org/10.3390/vetsci12080707 - 28 Jul 2025

Abstract

As the primary biological risk threatening safe dairy production, bovine mastitis control highly relies on environmental disinfection measures. However, the mechanisms by which chemical disinfectants influence host–environment microbial interactions remain unclear. This study systematically investigated the disinfection efficacy and regulatory effects on microbial community composition and diversity of glutaraldehyde-benzalkonium chloride (BAC) and glutaraldehyde-didecyl dimethyl ammonium bromide (DAB) at recommended concentrations (2–5%), using 80 environmental samples from intensive dairy farms in Xinjiang, China. Combining 16S rDNA sequencing with culturomics, the results showed that BAC achieved a disinfection rate of 99.33%, higher than DAB’s 97.87%, and reduced the environment–gut microbiota similarity index by 23.7% via a cationic bacteriostatic film effect. Microbiome analysis revealed that BAC selectively suppressed Fusobacteriota abundance (15.67% reduction) and promoted Bifidobacterium proliferation (7.42% increase), enhancing intestinal mucosal barrier function through butyrate metabolism. In contrast, DAB induced Actinobacteria enrichment in the environment (44.71%), inhibiting pathogen colonization via bioantagonism. BAC’s long-acting bacteriostatic properties significantly reduced disinfection costs and mastitis incidence. This study first elucidated the mechanism by which quaternary ammonium compound (QAC) disinfectants regulate host health through “environment-gut” microbial interactions, providing a critical theoretical basis for developing precision disinfection protocols integrating “cost reduction-efficiency enhancement-risk mitigation.” Full article

27 pages, 1128 KiB

Open AccessArticle

Adaptive Multi-Hop P2P Video Communication: A Super Node-Based Architecture for Conversation-Aware Streaming

by Jiajing Chen and Satoshi Fujita

Information 2025, 16(8), 643; https://doi.org/10.3390/info16080643 - 28 Jul 2025

Abstract

This paper proposes a multi-hop peer-to-peer (P2P) video streaming architecture designed to support dynamic, conversation-aware communication. The primary contribution is a decentralized system built on WebRTC that eliminates reliance on a central media server by employing super node aggregation. In this architecture, video streams from multiple peer nodes are dynamically routed through a group of super nodes, enabling real-time reconfiguration of the network topology in response to conversational changes. To support this dynamic behavior, the system leverages WebRTC data channels for control signaling and overlay restructuring, allowing efficient dissemination of topology updates and coordination messages among peers. A key focus of this study is the rapid and efficient reallocation of network resources immediately following conversational events, ensuring that the streaming overlay remains aligned with ongoing interaction patterns. While the automatic detection of such events is beyond the scope of this work, we assume that external triggers are available to initiate topology updates. To validate the effectiveness of the proposed system, we construct a simulation environment using Docker containers and evaluate its streaming performance under dynamic network conditions. The results demonstrate the system’s applicability to adaptive, naturalistic communication scenarios. Finally, we discuss future directions, including the seamless integration of external trigger sources and enhanced support for flexible, context-sensitive interaction frameworks. Full article

(This article belongs to the Special Issue Second Edition of Advances in Wireless Communications Systems)

►▼ Show Figures

Figure 1

29 pages, 36252 KiB

Open AccessArticle

CCDR: Combining Channel-Wise Convolutional Local Perception, Detachable Self-Attention, and a Residual Feedforward Network for PolSAR Image Classification

by Jianlong Wang, Bingjie Zhang, Zhaozhao Xu, Haifeng Sima and Junding Sun

Remote Sens. 2025, 17(15), 2620; https://doi.org/10.3390/rs17152620 - 28 Jul 2025

Abstract

In the task of PolSAR image classification, effectively utilizing convolutional neural networks and vision transformer models with limited labeled data poses a critical challenge. This article proposes a novel method for PolSAR image classification that combines channel-wise convolutional local perception, detachable self-attention, and a residual feedforward network. Specifically, the proposed method comprises several key modules. In the channel-wise convolutional local perception module, channel-wise convolution operations enable accurate extraction of local features from different channels of PolSAR images. The local residual connections further enhance these extracted features, providing more discriminative information for subsequent processing. Additionally, the detachable self-attention mechanism plays a pivotal role: it facilitates effective interaction between local and global information, enabling the model to comprehensively perceive features across different scales, thereby improving classification accuracy and robustness. Subsequently, replacing the conventional feedforward network with a residual feedforward network that incorporates residual structures aids the model in better representing local features, further enhances the capability of cross-layer gradient propagation, and effectively alleviates the problem of vanishing gradients during the training of deep networks. In the final classification stage, two fully connected layers with dropout prevent overfitting, while softmax generates predictions. The proposed method was validated on the AIRSAR Flevoland, RADARSAT-2 San Francisco, and RADARSAT-2 Xi’an datasets. The experimental results demonstrate that the proposed method can attain a high level of classification performance even with a limited amount of labeled data, and the model is relatively stable. Furthermore, the proposed method has lower computational costs than comparative methods. Full article

(This article belongs to the Section Remote Sensing Image Processing)

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 1146.

Go to page 1 2 3 4 5

Search Results (57,265)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI