Gene Selection in Disease: Review
release_qtzwkkhpwvhg7h3j2z6erx6y6q
by
M. Rashmi, Manish Varshney
2022 p19-26
Abstract
In utilizing AI algorithms to investigate expression patterns, genetic factors are a significant problem for objective aggregates. Numerous genetic characteristics exist, but just a few have substantial relationships with a specific aggregate. For example, a two-way malignant growth/non-disease investigation involves the identification of fifty of these genetic variables. Three distinct techniques are as follows. A system based on affiliation rules and half-fluffy dynamic trees has been developed for disease detection using data mining technologies. The primary approach proposes an effective half-and-half strategy for reducing the number of exceptions. Anomaly detection is an interesting topic of research in data mining. Due to the usage of bunching strategies, anomalies that do not fit into any of the groups are discovered. Nonetheless, a few ambiguous features may be included in the group. To completely purge the dataset of superfluous data, it is required to identify and purge data that has converged with the groups. This approach depends on two distinct types of data mining algorithms to discover anomalies in a dataset: multilayer neural networks (MLN) and thickness-based K-implies. Affiliation rules are established, and the effect % of everything derived from the standard upon which the fluffy guidelines are based is calculated in the manner illustrated below.
In application/xml+jats
format
Archived Files and Locations
application/pdf 319.7 kB
file_pggjkphrqzcangyqzu64xik7me
|
journaljpri.com (publisher) web.archive.org (webarchive) |
article-journal
Stage
published
Date 2022-02-15
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar