Saved Queries

Industrial structure upgrading serves as an important driving force for the sustained and healthy development of the economy, and it has a positive effect on reducing carbon emission intensity. This study uses provincial panel data from China from 2004 to 2019, starting from the dual perspectives of green total factor productivity and labor misallocation, and employs a four-stage mediation regression model to estimate the mechanism of industrial structure upgrading on carbon emission intensity. The research findings show that: for every 1% increase in industrial structure upgrading, carbon emission intensity will decrease by 0.296%; the central region shows the most significant effect, followed by the western region, while the eastern region shows no significant effect. From the view of the influencing mechanism, industrial structure upgrading will promote green total factor productivity and labor misallocation. When each of the two mediating variables increase by 1%, carbon emission intensity will decrease by 0.12% and 0.054%, respectively. Under the influence of industrial structure upgrading, the inhibitory effects of green total factor productivity and labor misallocation on carbon emission intensity have weakened, and the two factors have made it difficult to form a mediating superposition effect within the sample period. The research conclusion provides the policy implications for China to continuously adhere to industrial structure upgrading, pay attention to improving green total factor productivity, and enhance the low-carbon technical level of workers to achieve the “dual carbon” goals. Full article

►▼ Show Figures

Figure 1

24 pages, 7981 KiB

Open AccessArticle

A Flexible and Compact UWB MIMO Antenna with Dual-Band-Notched Double U-Shaped Slot on Mylar^® Polyester Film

by Vanvisa Chutchavong, Wanchalerm Chanwattanapong, Norakamon Wongsin, Paitoon Rakluea, Maleeya Tangjitjetsada, Chawalit Rakluea, Chatree Mahatthanajatuphat and Prayoot Akkaraekthalin

Electronics 2025, 14(17), 3363; https://doi.org/10.3390/electronics14173363 (registering DOI) - 24 Aug 2025

Abstract

Ultra-wideband (UWB) technology is a crucial facilitator for high-data-rate wireless communication due to its extensive frequency spectrum and low power consumption. Simultaneously, multiple-input multiple-output (MIMO) systems have garnered considerable attention owing to their capability to enhance channel capacity and link dependability. This article discusses the development of small, high-performance MIMO UWB antennas with mutual suppression capabilities to fully use the benefits of both technologies. Additionally, the suggested antenna features a straightforward design and dual-band-notched characteristics. The antenna structure includes two radiating elements measuring 85 × 45 mm². These elements use a rectangular patch provided by a coplanar waveguide (CPW). Double U-shaped slots are incorporated into the rectangular patch to introduce dual-band-notched properties, which help mitigate interference from WiMAX and WLAN communication systems. The antenna is fabricated on a Mylar^® polyester film substrate of 0.3 mm in thickness, with a dielectric constant of 3.2. According to the measurement results, the suggested antenna functions efficiently across the frequency spectrum of 2.29 to 20 GHz, with excellent impedance matching throughout the bandwidth. Furthermore, it provides dual-band-notched coverage at 3.08–3.8 GHz for WiMAX and 4.98–5.89 GHz for WLAN. The antenna exhibits impressive performance, including favorable radiation attributes, consistent gain, and little mutual coupling (less than −20 dB). Additionally, the envelope correlation coefficient (ECC) is extremely low (ECC < 0.01) across the working bandwidth, which indicates excellent UWB MIMO performance. This paper offers an appropriate design methodology for future flexible and compact UWB MIMO systems that can serve as interference-resilient antennas for next-generation wireless applications. Full article

(This article belongs to the Collection MIMO Antennas)

►▼ Show Figures

Figure 1

44 pages, 2508 KiB

Open AccessArticle

Red-Crowned Crane Optimization: A Novel Biomimetic Metaheuristic Algorithm for Engineering Applications

by Jie Kang and Zhiyuan Ma

Biomimetics 2025, 10(9), 565; https://doi.org/10.3390/biomimetics10090565 (registering DOI) - 24 Aug 2025

Abstract

This paper proposes a novel bio-inspired metaheuristic algorithm called the Red-crowned Crane Optimization (RCO) algorithm. This algorithm is developed by mathematically modeling four habits of red-crowned cranes: dispersing for foraging, gathering for roosting, dancing, and escaping from danger. The foraging strategy is used to search unknown areas to ensure the exploration ability, and the roosting behavior prompts cranes to approach better positions, thereby enhancing the exploitation performance. The crane dancing strategy further balances the local and global search capabilities of the algorithm. Additionally, the introduction of the escaping mechanism effectively reduces the possibility of the algorithm falling into local optima. The RCO algorithm is compared with eight popular optimization algorithms on a large number of benchmark functions. The results show that the RCO algorithm can find better solutions for 74% of the CEC-2005 test functions and 50% of the CEC-2022 test functions. This algorithm has a fast convergence speed and high search accuracy on most functions, and it can handle high-dimensional problems. The Wilcoxon signed-rank test results demonstrate the significant superiority of the RCO algorithm over other algorithms. In addition, applications to eight practical engineering problems further demonstrate its ability to find near-optimal solutions. Full article

(This article belongs to the Special Issue Nature-Inspired Metaheuristic Optimization Algorithms 2025)

16 pages, 6809 KiB

Open AccessArticle

Flaxseed Fiber-Structured Nanoemulgels for Salad Dressing Applications: Processing and Stability

by María-Carmen Alfaro-Rodríguez, Fátima Vela, María-Carmen García-González and José Muñoz

Gels 2025, 11(9), 678; https://doi.org/10.3390/gels11090678 (registering DOI) - 24 Aug 2025

Abstract

This study aimed to investigate the production of nanoemulgels structured with flaxseed fiber, designed to simulate salad dressings. For this purpose, the influence of microfluidizer passes (from one to four) on physicochemical and rheological properties was determined, followed by an assessment of thermal behavior. Rotor–stator homogenization followed by microfluidization were employed to produce nanoemulgels, which were characterized using laser diffraction, multiple light scattering, and rheological measurements. The resulting systems exhibited monomodal particle size distributions with mean diameters below 220 nm. Increasing the number of microfluidizer passes from one to four led to slight reductions in particle size, although they were not statistically significant. The formulation with two passes demonstrated superior physical stability during aging studies. Rheological evaluation indicated enhanced gel-like behavior with up to three passes, whereas excessive energy input (four passes) slightly compromised structural integrity. The linear viscoelastic region decreased notably after the first pass but remained relatively stable thereafter. The two-pass nanoemulgel, identified as the optimal formulation, was further tested for thermal stability. Temperature increases (5–20 °C) led to minor decreases in viscosity and firmness, yet the structure remained thermally stable. These findings support microfluidization as an effective strategy for developing stable flaxseed fiber-based nanoemulgels, with potential applications in functional food systems. Full article

(This article belongs to the Special Issue Food Gel-Based Systems: Gel-Forming and Food Applications)

►▼ Show Figures

Figure 1

27 pages, 3909 KiB

Open AccessReview

Identifying Root Causes and Sustainable Solutions for Reducing Construction Waste Using Social Network Analysis

by Mona Salah, Emad Elbeltagi, Meshal Almoshaogeh, Fawaz Alharbi and Mohamed T. Elnabwy

Sustainability 2025, 17(17), 7638; https://doi.org/10.3390/su17177638 (registering DOI) - 24 Aug 2025

Abstract

The construction industry is a major contributor to environmental degradation, primarily due to the substantial volumes of construction waste (CW) generated on-site. As sustainability becomes a global imperative aligned with the UN 2030 Agenda, identifying and mitigating the root causes of CW is essential. This study adopts a cross-disciplinary approach to explore the drivers of CW and support more effective, sustainable waste reduction strategies. A systematic literature review was conducted to extract 25 key CW source factors from academic publications. These were analyzed using Social Network Analysis (SNA) to reveal their structural relationships and relative influence. The results indicate that the lack of structured on-site waste management planning, accumulation of residual materials, and insufficient worker training are among the most influential CW drivers. Comparative analysis with industry data highlights theoretical–practical gaps and the need for improved alignment between research insights and site implementation. This paper recommends the adoption of tiered waste management protocols as part of contractual documentation, integrating Building Information Modeling (BIM)-based residual material traceability systems, and increasing attention to workforce training programs focused on material handling efficiency. Future research should extend SNA frameworks to sector-specific waste patterns (e.g., pavement or demolition projects) and explore the intersection between digital technologies and circular economy practices. The study contributes to enhancing waste governance, promoting resource efficiency, and advancing circularity in the built environment by offering data-driven prioritization of CW sources and actionable mitigation strategies. Full article

(This article belongs to the Section Waste and Recycling)

►▼ Show Figures

Figure 1

22 pages, 2791 KiB

Open AccessArticle

Optimizing Crisp Meat Quality with Modified Starches: From Rheological Properties to Post-Freezing Performance

by Can Ouyang, Zhen Zeng, Zhizhi Qin, Jiaqi Ding and Yuntao Liu

Foods 2025, 14(17), 2947; https://doi.org/10.3390/foods14172947 (registering DOI) - 24 Aug 2025

Abstract

Crisp meat, a traditional Chinese food, is widely consumed due to its convenience and long frozen shelf life. However, conventional preparation methods lead to excessive oil absorption during frying and ice crystal formation during freezing, causing coating softening and reduced crispiness after reheating. This study aimed to enhance the quality of crisp meat before and after freezing by incorporating modified starches into the batter. Four types—oxidized starch, hydroxypropyl distarch phosphate, starch acetate, and acetylated distarch phosphate—were tested at replacement levels of 10–40% for natural potato starch (NS). Results showed that all modified starches improved batter rheology by 20%, increased viscosity and stability during frying, and delayed retrogradation during freezing compared to NS. Among them, 20% acetylated starch has a better effect on improving the quality of frozen small crisp meat for enhancing water-holding capacity, increasing immobilized water content, reducing oil uptake by 12–18%, and improving product texture. Specifically, they helped maintain a crispier coating after reheating, addressing a key drawback of traditional crisp meat. In conclusion, modified starches significantly improved frying performance and minimized quality loss during freezing compared to NS. This study provides practical insights for the food industry in optimizing batter formulations for better-quality crisp meat products. Full article

(This article belongs to the Special Issue Factors Impacting Meat Product Quality: From Farm to Table)

►▼ Show Figures

Figure 1

30 pages, 5976 KiB

Open AccessReview

Electrochemical Sensors for Chloramphenicol: Advances in Food Safety and Environmental Monitoring

by Matiar M. R. Howlader, Wei-Ting Ting and Md Younus Ali

Pharmaceuticals 2025, 18(9), 1257; https://doi.org/10.3390/ph18091257 (registering DOI) - 24 Aug 2025

Abstract

Excessive use of antibiotics can lead to antibiotic resistance, posing a significant threat to human health and the environment. Chloramphenicol (CAP), once widely used, has been banned in many regions for over 20 years due to its toxicity. Detecting CAP residues in food products is crucial for regulating safe use and preventing unnecessary antibiotic exposure. Electrochemical sensors are low-cost, sensitive, and easily detect CAP. This paper reviews recent research on electrochemical sensors for CAP detection, with a focus on the materials and fabrication techniques employed. The sensors are evaluated based on key performance parameters, including limit of detection, sensitivity, linear range, selectivity, and the ability to perform simultaneous detection. Specifically, we highlight the use of metal and carbon-based electrode modifications, including gold nanoparticles (AuNPs), nickel–cobalt (Ni-Co) hollow nano boxes, platinum–palladium (Pt-Pd), graphene (Gr), and covalent organic frameworks (COFs), as well as molecularly imprinted polymers (MIPs) such as polyaniline (PANI) and poly(o-phenylenediamine) (P(o-PD)). The mechanisms by which these modifications enhance CAP detection are discussed, including improved conductivity, increased surface-to-volume ratio, and enhanced binding site availability. The reviewed sensors demonstrated promising results, with some exhibiting high selectivity and sensitivity, and the effective detection of CAP in complex sample matrices. This review aims to support the development of next-generation sensors for antibiotic monitoring and contribute to global efforts to combat antibiotic resistance. Full article

(This article belongs to the Special Issue Application of Biosensors in Pharmaceutical Research)

27 pages, 3693 KiB

Open AccessArticle

Energy Management Strategy for Hybrid Electric Vehicles Based on Experience-Pool-Optimized Deep Reinforcement Learning

by Jihui Zhuang, Pei Li, Ling Liu, Hongjie Ma and Xiaoming Cheng

Appl. Sci. 2025, 15(17), 9302; https://doi.org/10.3390/app15179302 (registering DOI) - 24 Aug 2025

Abstract

The energy management strategy of Hybrid Electric Vehicles (HEVs) plays a key role in improving fuel economy and reducing battery energy consumption. This paper proposes a Deep Reinforcement Learning-based energy management strategy optimized by the experience pool (P-HER-DDPG), aimed at improving the fuel efficiency of HEVs while accelerating the training speed. The method integrates the mechanisms of Prioritized Experience Replay (PER) and Hindsight Experience Replay (HER) to address the reward sparsity and slow convergence issues faced by the traditional Deep Deterministic Policy Gradient (DDPG) algorithm when handling continuous action spaces. Under various standard driving cycles, the P-HER-DDPG strategy outperforms the traditional DDPG strategy, achieving an average fuel economy improvement of 5.85%, with a maximum increase of 8.69%. Compared to the DQN strategy, it achieves an average improvement of 12.84%. In terms of training convergence, the P-HER-DDPG strategy converges in 140 episodes, 17.65% faster than DDPG and 24.32% faster than DQN. Additionally, the strategy demonstrates more stable State of Charge (SOC) control, effectively mitigating the risks of battery overcharging and deep discharging. Simulation results show that P-HER-DDPG can enhance fuel economy and training efficiency, offering an extended solution in the field of energy management strategies. Full article

(This article belongs to the Special Issue Power Systems and Energy Systems: Technologies and Applications, 2nd Edition)

11 pages, 1946 KiB

Open AccessFeature PaperArticle

Influence of Surface Treatments on the Pull-Off Performance of Adhesively Bonded Polylactic Acid (PLA) Specimens Manufactured by Fused Deposition Modeling (FDM)

by Gianluca Parodo, Giuseppe Moffa, Alessandro Silvestri, Luca Sorrentino, Gabriel Testa and Sandro Turchetta

Materials 2025, 18(17), 3965; https://doi.org/10.3390/ma18173965 (registering DOI) - 24 Aug 2025

Abstract

This study investigates the influence of different surface treatments (namely, mechanical abrasion and solvent cleaning with isopropyl alcohol and acetone) on the adhesive bonding performance of polylactic acid (PLA) substrates produced by Fused Deposition Modeling (FDM). Pull-off tests revealed that the isopropanol-cleaned specimens achieved the highest bond strength, with an average pull-off value exceeding 8.5 MPa, compared to approximately 5.6 MPa for untreated PLA. Conversely, acetone cleaning resulted in the lowest performance (about 3.5 MPa), while mechanical abrasion yielded intermediate values of about 6 MPa. FTIR analysis confirmed that no chemical reactions occurred, although acetone and abrasion induced significant physical surface changes, unlike isopropanol, which acted as an effective cleaning agent. These findings demonstrate that surface cleanliness plays a dominant role over morphological alterations in enhancing the adhesion of PLA-based 3D-printed joints. Full article

(This article belongs to the Special Issue Advanced Machining and Technologies in Materials Science)

►▼ Show Figures

Figure 1

21 pages, 1142 KiB

Open AccessArticle

Advancing Air Quality Monitoring: Deep Learning-Based CNN-RNN Hybrid Model for PM_2.5 Forecasting

by Anıl Utku, Umit Can, Mustafa Alpsülün, Hasan Celal Balıkçı, Azadeh Amoozegar, Abdulmuttalip Pilatin and Abdulkadir Barut

Atmosphere 2025, 16(9), 1003; https://doi.org/10.3390/atmos16091003 (registering DOI) - 24 Aug 2025

Abstract

Particulate matter, particularly PM_2.5, poses a significant threat to public health due to its ability to disperse widely and its detrimental impact on the respiratory and circulatory systems upon inhalation. Consequently, it is imperative to maintain regular monitoring and assessment of particulate matter levels to anticipate air pollution events and promptly mitigate their adverse effects. However, predicting air quality is inherently complex, given the multitude of variables that influence it. Deep learning models, renowned for their ability to capture nonlinear relationships, offer a promising approach to address this challenge, with hybrid architectures demonstrating enhanced performance. This study aims to develop and evaluate a hybrid model integrating Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for forecasting PM_2.5 levels in India, Milan, and Frankfurt. A comparative analysis with established deep learning and machine learning techniques substantiates the superior predictive capabilities of the proposed CNN-RNN model. The findings underscore its potential as an effective tool for air quality prediction, with implications for informed decision-making and proactive intervention strategies to safeguard public health. Full article

(This article belongs to the Section Air Quality)

27 pages, 1707 KiB

Open AccessArticle

EAR-CCPM-Net: A Cross-Modal Collaborative Perception Network for Early Accident Risk Prediction

by Wei Sun, Lili Nurliyana Abdullah, Fatimah Binti Khalid and Puteri Suhaiza Binti Sulaiman

Appl. Sci. 2025, 15(17), 9299; https://doi.org/10.3390/app15179299 (registering DOI) - 24 Aug 2025

Abstract

Early traffic accident risk prediction in complex road environments poses significant challenges due to the heterogeneous nature and incomplete semantic alignment of multimodal data. To address this, we propose a novel Early Accident Risk Cross-modal Collaborative Perception Mechanism Network (EAR-CCPM-Net) that integrates hierarchical fusion modules and cross-modal attention mechanisms to enable semantic interaction between visual, motion, and textual modalities. The model is trained and evaluated on the newly constructed CAP-DATA dataset, incorporating advanced preprocessing techniques such as bilateral filtering and a rigorous MINI-Train-Test sampling protocol. Experimental results show that EAR-CCPM-Net achieves an AUC of 0.853, AP of 0.758, and improves the Time-to-Accident (TTA_0.5) from 3.927 s to 4.225 s, significantly outperforming baseline methods. These findings demonstrate that EAR-CCPM-Net effectively enhances early-stage semantic perception and prediction accuracy, providing an interpretable solution for real-world traffic risk anticipation. Full article

23 pages, 7301 KiB

Open AccessArticle

A Study on the Associative Regulation Mechanism Based on the Water Environmental Carrying Capacity and Its Impact Indicators in the Songhua River Basin in Harbin City, China

by Zhongbao Yao, Xuebing Wang, Nan Sun, Tianyi Wang and Hao Yan

Sustainability 2025, 17(17), 7636; https://doi.org/10.3390/su17177636 (registering DOI) - 24 Aug 2025

Abstract

With intensifying watershed pollution pressures and growing ecological vulnerability, scientifically revealing and enhancing the water environmental carrying capacity is crucial for ensuring the long-term health of the basin and the sustainable socioeconomic development of the region. However, the dynamic regulatory mechanisms linking narrow-sense and broad-sense water environmental carrying capacity remain poorly understood, limiting the development of integrated management strategies. This study systematically investigated the changing trends of both the narrow-sense and broad-sense water environmental carrying capacity in the Harbin section of the Songhua River basin through model calculations, along with the regulatory mechanisms of its key influence indicators. The results of the study on the carrying capacity of the water environment in the narrow sense show that permanganate, total phosphorus, and ammonia nitrogen exhibited partial carrying capacity across water periods, while dissolved oxygen decreased during flat and dry periods, with only limited capacity remaining at the Ash River estuary and in the Hulan River. The biochemical oxygen demand in the Ash River was consistently overloaded, and total nitrogen showed insufficient capacity except during the abundant water period. Broad-sense analysis indicated that improving urbanization quality, water supply infrastructure, and drinking water safety could effectively reduce future overload risks, with projections suggesting a transition from critical to loadable levels by 2030, though latent threats persist. Correlation analysis between narrow- and broad-sense indicators informed targeted control strategies, including stricter regulation of nitrogen- and phosphorus-rich industrial discharges, restoration of aquatic vegetation, and periodic dredging of riverbed sediments. This work is the first to dynamically integrate pollutant and socio-economic indicators through a hybrid modelling framework, providing a scientific basis and actionable strategies for improving water quality and achieving sustainable management in the Songhua River Basin. Full article

(This article belongs to the Special Issue Sustainable Agricultural Engineering: Agroecology Sustainable Development and Agriculture Environmental Impact Assessment and Measurement)

17 pages, 3310 KiB

Open AccessArticle

Documentation of the Holy Monastery of Daphni Within a Time Span of 20 Years—A Comparative Approach

by Athanasios Iliodromitis, George Pantazis, Andreas Georgopoulos and Vasileios Patouras

Buildings 2025, 15(17), 3010; https://doi.org/10.3390/buildings15173010 (registering DOI) - 24 Aug 2025

Abstract

In 1999, the Attica region experienced a severe earthquake that damaged the Holy Monastery of Daphni, a UNESCO Heritage monument. The Ministry of Culture commissioned a detailed geometric documentation project using the state-of-the-art methods available at the time. More than two decades later, in 2023, a new documentation project was conducted using modern technologies and equipment. This paper makes a comparison of the two projects in terms of the equipment and the methodologies used, the personnel needed, and the hours spent documenting the same complicated monument in two different time periods, spanning 20 years. Moreover, it attempts to make a comparison between the different deliverables, focusing on regions that back then appeared damaged or cracked. Key differences include a significant reduction in field and processing time, a dramatic decrease in personnel needs, and a shift from 2D outputs to integrated 3D models. This study highlights how technological advancements have enhanced precision and efficiency in documenting complex heritage sites. Full article

(This article belongs to the Special Issue Resilience of Buildings and Infrastructure Addressing Climate Crisis)

22 pages, 639 KiB

Open AccessReview

Postbiotics of Marine Origin and Their Therapeutic Application

by Isabel M. Cerezo, Olivia Pérez-Gómez, Sonia Rohra-Benítez, Marta Domínguez-Maqueda, Jorge García-Márquez and Salvador Arijo

Mar. Drugs 2025, 23(9), 335; https://doi.org/10.3390/md23090335 (registering DOI) - 24 Aug 2025

Abstract

The increase in antibiotic-resistant pathogens has prompted the search for alternative therapies. One such alternative is the use of probiotic microorganisms. However, growing interest is now turning toward postbiotics—non-viable microbial cells and/or their components or metabolites—that can confer health benefits without the risks associated with administering live microbes. Marine ecosystems, characterized by extreme and diverse environmental conditions, are a promising yet underexplored source of microorganisms capable of producing unique postbiotic compounds. These include bioactive peptides, polysaccharides, lipoteichoic acids, and short-chain fatty acids produced by marine bacteria. Such compounds often exhibit enhanced stability and potent biological activity, offering therapeutic potential across a wide range of applications. This review explores the current knowledge on postbiotics of marine origin, highlighting their antimicrobial, anti-inflammatory, immunomodulatory, and anticancer properties. We also examine recent in vitro and in vivo studies that demonstrate their efficacy in human and animal health. Some marine bacteria that have been studied for use as postbiotics belong to the genera Bacillus, Halobacillus, Halomonas, Mameliella, Shewanella, Streptomyces, Pseudoalteromonas, Ruegeria, Vibrio, and Weissella. In conclusion, although the use of the marine environment as a source of postbiotics is currently limited compared to other environments, studies conducted to date demonstrate its potential. Full article

(This article belongs to the Section Marine-Derived Ingredients for Drugs, Cosmeceuticals and Nutraceuticals)

17 pages, 586 KiB

Open AccessArticle

An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism

by Qing Yang, Ying Wei, Fei Liu and Zhuang Wu

Appl. Sci. 2025, 15(17), 9298; https://doi.org/10.3390/app15179298 (registering DOI) - 24 Aug 2025

Abstract

Diabetic retinopathy (DR), a critical ocular disease that can lead to blindness, demands early and accurate diagnosis to prevent vision loss. Current automated DR diagnosis methods face two core challenges: first, subtle early lesions such as microaneurysms are often missed due to insufficient feature extraction; second, there is a persistent trade-off between model accuracy and efficiency—lightweight architectures often sacrifice precision for real-time performance, while high-accuracy models are computationally expensive and difficult to deploy on resource-constrained edge devices. To address these issues, this study presents a novel deep learning framework integrating depthwise separable convolution and a multi-view attention mechanism (MVAM) for efficient DR diagnosis using retinal images. The framework employs multi-scale feature fusion via parallel 3 × 3 and 5 × 5 convolutions to capture lesions of varying sizes and incorporates Gabor filters to enhance vascular texture and directional lesion modeling, improving sensitivity to early structural abnormalities while reducing computational costs. Experimental results on both the diabetic retinopathy (DR) dataset and ocular disease (OD) dataset demonstrate the superiority of the proposed method: it achieves a high accuracy of 0.9697 on the DR dataset and 0.9669 on the OD dataset, outperforming traditional methods such as CNN_eye, VGG, and UNet by more than 1 percentage point. Moreover, its training time is only half that of U-Net (on DR dataset) and VGG (on OD dataset), highlighting its potential for clinical DR screening. Full article

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 2000.

Go to page 1 2 3 4 5

Search Results (248,004)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI