Machine learning-assisted extrusion-based 3D bioprinting for tissue regeneration applications

Annals of 3D Printed Medicine, Год журнала: 2023, Номер 12, С. 100132 - 100132

Опубликована: Сен. 14, 2023

Extrusion-based 3D bioprinting (EBBP) prints tissues, including nerve guide conduits, bone tissue engineering, skin repair, cartilage and muscle repair. The EBBP demands optimized parameters for obtaining good printability cell viability. However, finding optimal process is always essential the researcher. biological, mechanical, rheological all together need to be evaluated enhance of tissue. A degree simplicity may required interpret each parameter's effect. overcoming complexity with a multiparameter quite tricky through conventional methods. It can overcome implementation machine learning. This article concisely delineates application learning algorithms modeling as function influential was elaborately discussed. Additionally, indispensable challenges futuristic aspects were briefed concerning regeneration applications.

Язык: Английский

---

A review of medical text analysis: Theory and practice

Information Fusion, Год журнала: 2025, Номер unknown, С. 103024 - 103024

Опубликована: Фев. 1, 2025

Язык: Английский

---

Artificial intelligence in general internal medicine: A glimpse into the future

Canadian Journal of General Internal Medicine, Год журнала: 2025, Номер 20(1), С. 2 - 5

Опубликована: Янв. 1, 2025

---

Artificial Intelligence-Based Machine Learning toward the Solution of Climate-Friendly Hydrogen Fuel Cell Electric Vehicles

Vehicles, Год журнала: 2022, Номер 4(3), С. 663 - 680

Опубликована: Июль 4, 2022

The rapid conversion of conventional powertrain technologies to climate-neutral new energy vehicles requires the ramping electrification. popularity fuel cell electric with improved economy has raised great attention for many years. Their use green hydrogen is proposed be a promising clean way fill gap and maintain zero-emission ecosystem. complex architecture influenced by multiphysics interactions, driving patterns, environmental conditions that put multitude power requirements boundary around vehicle subsystems, including system, motor, battery, itself. Understanding its optimal systematic assessment these interactions. Artificial intelligence-based machine learning methods have been emerging showing potential accelerated data analysis aid in thorough understanding systems. present study investigates peaks during an NEDC vehicles. An innovative approach combining traditional analyses, design experiments, effective blend supply accurately predicts consumption trained validated models show very accurate results less than 1% error.

Язык: Английский

---

Multi-modality relation attention network for breast tumor classification

Computers in Biology and Medicine, Год журнала: 2022, Номер 150, С. 106210 - 106210

Опубликована: Окт. 12, 2022

Язык: Английский

---

COVID-AleXception: A Deep Learning Model Based on a Deep Feature Concatenation Approach for the Detection of COVID-19 from Chest X-ray Images

Healthcare, Год журнала: 2022, Номер 10(10), С. 2072 - 2072

Опубликована: Окт. 18, 2022

The novel coronavirus 2019 (COVID-19) spread rapidly around the world and its outbreak has become a pandemic. Due to an increase in afflicted cases, quantity of COVID-19 tests kits available hospitals decreased. Therefore, autonomous detection system is essential tool for reducing infection risks spreading virus. In literature, various models based on machine learning (ML) deep (DL) are introduced detect many pneumonias using chest X-ray images. cornerstone this paper use pretrained CNN architectures construct automated diagnosis. work, we used feature concatenation (DFC) mechanism combine features extracted from input images two modern pre-trained models, AlexNet Xception. Hence, propose COVID-AleXception: neural network that Xception overall improvement prediction capability To evaluate proposed model build dataset large-scale images, there was careful selection multiple several sources. COVID-AleXception can achieve classification accuracy 98.68%, which shows superiority over achieved 94.86% 95.63%, respectively. performance results demonstrate pertinence help radiologists diagnose more quickly.

Язык: Английский

---

Unleashing the power of advanced technologies for revolutionary medical imaging: pioneering the healthcare frontier with artificial intelligence

Discover Artificial Intelligence, Год журнала: 2024, Номер 4(1)

Опубликована: Авг. 23, 2024

Abstract This study explores the practical applications of artificial intelligence (AI) in medical imaging, focusing on machine learning classifiers and deep models. The aim is to improve detection processes diagnose diseases effectively. emphasizes importance teamwork harnessing AI’s full potential for image analysis. Collaboration between doctors AI experts crucial developing tools that bridge gap concepts applications. demonstrates effectiveness classifiers, such as forest algorithms models, These techniques enhance accuracy expedite analysis, aiding development accurate medications. evidenced technologically assisted analysis significantly improves efficiency across various imaging modalities, including X-ray, ultrasound, CT scans, MRI, etc. outcomes were supported by reduced diagnosis time. exploration also helps us understand ethical considerations related privacy security data, bias, fairness algorithms, well role consultation ensuring responsible use healthcare.

Язык: Английский

---

Potential of vibrational spectroscopy coupled with machine learning as a non-invasive diagnostic method for COVID-19

Computer Methods and Programs in Biomedicine, Год журнала: 2022, Номер 229, С. 107295 - 107295

Опубликована: Дек. 1, 2022

Язык: Английский

---

Material and Performance Optimisation for Syngas Preparation Using Artificial Intelligence (AI)-Based Machine Learning (ML)

Hydrogen, Год журнала: 2023, Номер 4(3), С. 474 - 492

Опубликована: Июль 25, 2023

Working towards a more sustainable future with zero emissions, the International Future Laboratory for Hydrogen Economy at Technical University of Munich (TUM) exhibits concerted efforts across various hydrogen technologies. The current research focuses on pre-reforming processes high-quality reversible solid oxide cell feedstock preparation. An AI-based machine learning model has been developed, trained, and deployed to predict optimise controlled utilisation methane gas. Using blend design experiments validated 3D computational fluid dynamics model, process data have generated syngas mixtures. results this study indicate that it is possible achieve targeted rate 20% while decreasing amount catalyst material by 11%. Furthermore, was found precise parameters could be determined efficiently minimal resource consumption in order higher fuel rates 25% 30%. effectively employed analyse outlet conditions process, contributing better understanding preparation furthering safe (r-SOC) process.

Язык: Английский

---

Deep Learning-Based COVID-19 Detection from Chest X-ray Images: A Comparative Study

Journal of Computer Science and Technology Studies, Год журнала: 2023, Номер 5(4), С. 132 - 141

Опубликована: Ноя. 28, 2023

The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has rapidly spread across globe, leading to a significant number of illnesses and fatalities. Effective containment virus relies on timely accurate identification infected individuals. While methods like RT-PCR assays are considered gold standard for diagnosis due their accuracy, they can be limited in use cost availability issues, particularly resource-constrained regions. To address this challenge, our study presents set deep learning techniques predicting detection using chest X-ray images. Chest imaging emerged as valuable cost-effective diagnostic tool managing because it is non-invasive widely accessible. However, interpreting X-rays complex, radiographic features pneumonia subtle may overlap with those other respiratory illnesses. In research, we evaluated performance various models, including VGG16, VGG19, DenseNet121, Resnet50, determine ability differentiate between cases coronavirus non-COVID-19 pneumonia. Our dataset comprised 4,649 images, 1,123 them depicting 3,526 representing cases. We used metrics confusion matrices assess models' performance. study's results showed that DenseNet121 outperformed achieving an impressive accuracy rate 99.44%.

Язык: Английский

---