Advanced searches left 3/3

Artificial Intelligence - Wiley Online Library

Summarized by Plex Scholar
Last Updated: 10 January 2023

* If you want to update the article please login/register

Modeling and optimization of malondialdehyde (MDA) absorbance behavior through response surface methodology (RSM) and artificial intelligence network (AIN): An endeavor to estimate lipid peroxidation by Determination of MDA

Malondialdehyde is one of the end products of polyunsaturated fatty acids peroxidation. MDA and total MDA, DNA & proteins adducts aren't well understood by U201t; however, revaluation and refinement of new analytical techniques with greater sensitivity and specificity in reaction to free MDA and total MDA, DNA & proteins adducts aren't well understood. The absorbance rate of MDA's PMA was then calculated based on the interactions between MDA&PMA at various times and temperatures. MDA's optimal absorbance rate for MDA u2010PMA is at the temperature of 74. 99 b0C with a PMA concentration of 499. 87 u03bcM & MDA concentration of 49. 98 u03bcM. Our new MLP u2010ANN kit was 2. 08%, an improvement over existing assay kits, overcoming limitations such as time, temperature, and reliability with a hopeful future in human samples.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/cem.3468


Pull‐out capacity prediction of sustainable cementitious composites with artificial intelligence and statistical methods

Concrete is used with reinforcement in buildings, so adhesion is on the rise, particularly in fire scenarios. Generally, granulated blast furnace slag, fly ash, and silica fume were used to contribute to the manufacturing of environmentally friendly concrete by the end of 2010. Composite composites were tested with a pull-out test, and the elevated temperature resistance of by-u2010added composites was determined in this study. For prediction models, an artificial neural network and adaptive neurofuzzy inference algorithm were used. According to coefficient of correlation, mean square error, and mean percentage error, pull out prediction models' results were compared to coefficient of correlation, mean square error, and mean percentage error. Quadratic and pure quadratic scores, according to the statistical models, surpassed the ANFIS model, which is a combination of ANN and fuzzy techniques. Because, ANN can develop a new and useful model to accurately forecast POC of by-u2010product-u2010added cementituous composites under fire control.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/suco.202200275


Avoiding bias in artificial intelligence

Artificial intelligence is ubiquitous and expanding, and machine learning has quickly adopted AI and machine learning for several applications in the healthcare industry. We must take responsibility for proactive stewardship to guard against bias, not only for latest AI algorithms but also for our research findings, which could one day have statistics for those algorithms.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/alr.23129


Artificial Intelligence and Advanced Materials

Artificial intelligence is on the rise, and materials science can both contribute to and profit from it. Understanding how machine learning can aid in the creation of new materials would benefit future materials scientists. This report examines computing from the basics to outcomes, procedures, and applications of artificial intelligence, from the beginnings to the consequences created by computation and computation. Machine learning and its techniques are reviewed in order to give basic information on its usage and potential. Other information carrying and processing agents are gaining considerable competition from the materials and systems used to implement artificial intelligence with electric charges. Instead of finding applications to found materials, the impact these methods are having on the inception of new advanced materials is so deep that a new paradigm is emerging where implicit knowledge is being mined to develop materials and systems for functions rather than discovering applications to find materials.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/adma.202208683


Managing artificial intelligence projects: Key insights from an AI consulting firm

Although companies are increasingly interested in artificial intelligence, some AI projects run into significant challenges or even fail entirely. Consult's AI project management is a multi-u2010method strategy that draws on elements from traditional project planning, agile methodologies, and AI workflow techniques. Although Consulting's design enables Consult to be more cost-effective in delivering AI services to their clients, our analysis shows that managing AI projects in this way puts forth three key logics, namely, widely shared norms, values, and prescribed behavior that influence actors' perceptions of how work should be carried out. The simultaneous presence of these three logics, along with an agile logic and an AI workflow framework, gives rise to conflicts and challenges in implementing AI projects at Consult, and successfully executing these AI projects requires resolving conflicts that arise between them.

Source link: https://onlinelibrary.wiley.com/doi/10.1111/isj.12420


Artificial intelligence in the work context

Artificial intelligence reconfigures work and organization, while automation and organization shape AI. We explore AI's socioeconomic and organizational characteristics, the historical evolution of AI in this series, the AI research landscape in the context of work, and the primary contextual factors on the macrou2010 and microu2010 times that help figure out the AI nexus.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/asi.24730


Development of an artificial intelligence approach that employs genomic and brain imaging features to improve the diagnosis of Alzheimer’s Disease (AD)

Background 1 (u20133) Background In the last 20 years, genome wide association studies and brain imaging studies have reported multiple genetic risk variants and structural brain differences between AD and cognitively normal subjects1;u20133. We used a novel artificial intelligence (u2010) based strategy to convert both genomic and brain imaging measurements into 2D artificial images in this study, and then used a deep convolutional neural network to classify these artificial images5,6.

Source link: https://onlinelibrary.wiley.com/doi/10.1002/alz.062638

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions