Android Based Car Parking System

Langote,; Prathmesh, Lonkar; Bagwan, A. B.; Vayandeshkar, Rushikesh

doi:10.32628/cseit2173121

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two types of marginal filtering: univariate marginal filtering and multivariate marginal filtering. For instances univariate filtering processes are the paired t-test (TS), the IG, and the PCC [14], [15].…”

Section: Introductionmentioning

confidence: 99%

An Application of the Filter Feature Selection Method in a Machine Learning Model for the Prognostic of Parkinson's Disease

David¹

2022

View full text Add to dashboard Cite

Parkinson's disease is the most prevalent kind of neurodegenerative sickness that cannot be cured. Neurodegeneration is a word that includes memory loss and other cognitive functions. The conventional methods of medical testing take a lot of time and are not very good at spotting early warning signs. As Parkinson's disease progresses, different treatment approaches are required for patients at different stages of the illness. In this regard, the early identification of Parkinson's disease and the subsequent categorization of its stages may be of great assistance in the process of treating the symptoms of the illness. The objective of the study, on the other hand, is to model a classification approach that could possibly predict the untimely phases of Parkinson's disease by utilizing accurate early-stage gene expression data from the blood that was generated from a clinical Parkinson's dataset. This data is obtained from participants who had the disease. A set of criteria is selected with the use of Information Gain (IG) in order to give sufficient information for differentiating among Normal Control (NC) participants and untimely phases Parkinson's disease (AD) participants. The data is segmented into different sizes, and then 3 unique Machine Learning (ML) methods are used in order to construct the classification approaches: Naive Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN). The capability of the algorithms to accurately forecast the condition of cognitive impairment is analyzed, compared, and evaluated by utilizing the Weka software tool, as well as a range of metrics to assess the approaches' performance. According to the most recent data, a classification model based on SVM can properly discriminate cognitively impaired Parkinson's patients from normal healthy persons with a success rate of 96.6 percent. As revealed and verified, a gene expression pattern in the blood correctly separates Parkinson's patients from cognitively healthy controls, suggesting that alterations unique to AD may be identified distant from the disease's core location.

show abstract

Section: Introductionmentioning

confidence: 99%

An Application of the Filter Feature Selection Method in a Machine Learning Model for the Prognostic of Parkinson's Disease

David¹

2022

View full text Add to dashboard Cite

show abstract

Android Based Car Parking System

Cited by 1 publication

References 0 publications

An Application of the Filter Feature Selection Method in a Machine Learning Model for the Prognostic of Parkinson's Disease

An Application of the Filter Feature Selection Method in a Machine Learning Model for the Prognostic of Parkinson's Disease

Contact Info

Product

Resources

About