Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1136/bmj.j1684 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Enhancing glaucoma diagnosis: Generative adversarial networks in synthesized imagery and classification with pretrained MobileNetV2.
MethodsX
June 2025
Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Tamil Nadu 600062, India.
The disease affects the optic nerve and represents the principle reasons of irreversible vision loss, mostly asymptomatic and uncontrolled. Consequently, early and accurate diagnosis is critical to prevent or reduce its effect, however, conventional diagnostic techniques often fail to provide concrete results. In this regard, we present a new approach built on Generative Adversarial Networks (GAN) and MobileNetV2 pretrained architecture for diagnosing glaucoma.
View Article and Find Full Text PDFGenerative adversarial networks with fully connected layers to denoise PPG signals.
Physiol Meas
January 2025
Faculty of Sciences, University of Coimbra, Palacio de las Escuelas 3004-531, Coimbra, 3004-504, PORTUGAL.
Objective: The detection of arterial pulsating signals at the skin periphery with Photoplethysmography (PPG) are easily distorted by motion artifacts. This work explores the alternatives to the aid of PPG reconstruction with movement sensors (accelerometer and/or gyroscope) which to date have demonstrated the best pulsating signal reconstruction.
Approach: A generative adversarial network with fully connected layers (FC-GAN) is proposed for the reconstruction of distorted PPG signals.
Preparation of Novel Slow-Release Acid Materials for Oilfield Development via Encapsulation.
Materials (Basel)
December 2024
Department of Chemical Engineering, Tsinghua University, Beijing 100084, China.
Acid-fracturing technology has been applied to form pathways between deep oil/gas resources and oil production pipelines. The acid fracturing fluid is required to have special slow-release performance, with no acidity at low temperatures, while steadily generating acid at high temperatures underground. At present, commercial acid systems in oilfields present problems such as the uncontrollable release effect, high costs, and significant pollution.
View Article and Find Full Text PDFFabrication of lignin nanoparticles with adjustable size, antioxidant, antibacterial, and hydrophobic properties by a two-step fractionation.
Int J Biol Macromol
January 2025
Beijing Key Laboratory of Lignocellulosic Chemistry, and Engineering Research Center of Forestry Biomass Materials and Energy, Ministry of Education, Beijing Forestry University, Beijing 100083, China. Electronic address:
Article Synopsis
- Lignin nanoparticles (LNPs) are being recognized for their eco-friendly properties and potential in sustainable materials.
- A new two-step fractionation technique has created four lignin fractions (F1, F2, F3, and F4) with optimal characteristics for LNPs production, achieving a high recovery rate of 88.7% from alkali lignin.
- The study highlights how the size and structural properties of LNPs can be controlled for better antibacterial and antioxidant performance, particularly favoring a higher syringyl/guaiacyl ratio for smaller nanoparticles.
Pakistani lignite (PLC) was thermally dissolved at 300 °C using isopropanol (IPA) to obtain a soluble portion (SP) and insoluble portion (ISP). Proximate analysis, ultimate analysis, Fourier transform infrared spectrometry (FTIR), thermogravimetric analysis (TG-DTG) and pyrolysis-gas chromatography/mass spectrometry (Py-GC/MS) results were compared to explore the influence of the thermal dissolution process on the pyrolysis for PLC and ISP. Results showed that the thermal dissolution process mainly dissolved some light components of low-rank coal, and more phenols, aldehydes, esters and ethers were found in the SP, indicating that low-carbon alcohols can break the ether bridge bond in coal and generate oxygen-containing organic compounds (OCOCs).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!