A method based on a computational intelligence information model is proposed to study the visualization of large data packages. Since the CAIM algorithm only considers the distribution of the largest number of classes in an interval, it offers an optimization method and simultaneously determines the appropriate stopping conditions to avoid overcrowding. The effectiveness of the improved algorithm has been experimentally proven. Methods of character reduction and weight determination are used to reduce the index and weight, establishing a large packaging information system. Experimental results show that the improved algorithm in this article produces more classification rules than the CAIM algorithm, because the discrete intervals created by the CAIM algorithm are relatively simple, but the classification rules are few, but less than the number of CAIM algorithms. Classification rules are generated by entropy-based sampling algorithms. This can make the classification rules simple and universal, and it is clear that the optimal sampling algorithm is more accurate than the CAIM algorithm.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9056241 | PMC |
| http://dx.doi.org/10.1155/2022/4558839 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
CAIM: coverage-based analysis for identification of microbiome.
Brief Bioinform
July 2024
Department of Biomedical Informatics, University of Arkansas for Medical Sciences, 4301 W Markham St, Little Rock, AR 72205, United States.
Accurate taxonomic profiling of microbial taxa in a metagenomic sample is vital to gain insights into microbial ecology. Recent advancements in sequencing technologies have contributed tremendously toward understanding these microbes at species resolution through a whole shotgun metagenomic approach. In this study, we developed a new bioinformatics tool, coverage-based analysis for identification of microbiome (CAIM), for accurate taxonomic classification and quantification within both long- and short-read metagenomic samples using an alignment-based method.
View Article and Find Full Text PDFCataract-1K Dataset for Deep-Learning-Assisted Analysis of Cataract Surgery Videos.
Sci Data
April 2024
Center for Artificial Intelligence in Medicine (CAIM), Department of Medicine, University of Bern, Bern, Switzerland.
In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room management, and overall surgical outcomes. However, the progression of deep-learning-powered surgical technologies is profoundly reliant on large-scale datasets and annotations. In particular, surgical scene understanding and phase recognition stand as pivotal pillars within the realm of computer-assisted surgery and post-operative assessment of cataract surgery videos.
View Article and Find Full Text PDFCurrent and Evolving Multimodality Cardiac Imaging in Managing Transthyretin Amyloid Cardiomyopathy.
JACC Cardiovasc Imaging
February 2024
Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland. Electronic address:
Article Synopsis
- ATTR amyloidosis is a disease caused by protein misfolding, leading to fibril buildup in tissues, primarily affecting the heart and causing serious health issues.
- Advanced cardiac imaging techniques, like echocardiography and MRI, are crucial for accurately diagnosing ATTR cardiomyopathy, especially since new treatments are most effective in the early stages of the disease.
- The review discusses the latest cardiac imaging methods for diagnosing and managing ATTR-CM, and also explores how artificial intelligence could enhance clinical decisions and patient care in the future.
Computational Evidence for Laboratory Diagnostic Pathways: Extracting Predictive Analytes for Myocardial Ischemia from Routine Hospital Data.
Diagnostics (Basel)
December 2022
Department of Clinical Chemistry, Inselspital, Bern University Hospital, 3010 Bern, Switzerland.
Laboratory parameters are critical parts of many diagnostic pathways, mortality scores, patient follow-ups, and overall patient care, and should therefore have underlying standardized, evidence-based recommendations. Currently, laboratory parameters and their significance are treated differently depending on expert opinions, clinical environment, and varying hospital guidelines. In our study, we aimed to demonstrate the capability of a set of algorithms to identify predictive analytes for a specific diagnosis.
View Article and Find Full Text PDFUsing domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction.
Nat Commun
October 2022
Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
Despite the potential of deep learning (DL)-based methods in substituting CT-based PET attenuation and scatter correction for CT-free PET imaging, a critical bottleneck is their limited capability in handling large heterogeneity of tracers and scanners of PET imaging. This study employs a simple way to integrate domain knowledge in DL for CT-free PET imaging. In contrast to conventional direct DL methods, we simplify the complex problem by a domain decomposition so that the learning of anatomy-dependent attenuation correction can be achieved robustly in a low-frequency domain while the original anatomy-independent high-frequency texture can be preserved during the processing.
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!