Predicting Important Features That Influence COVID-19 Infection Through Light Gradient Boosting Machine: Case of Toronto
Issue:
Volume 6, Issue 3, September 2021
Pages:
43-49
Received:
21 June 2021
Accepted:
2 July 2021
Published:
13 July 2021
Abstract: COVID-19, a disease starting from December 2019, spreads from person to person through contact, and has symptoms of cough, fever, muscle pain, etc. The diagnosis is usually done by polymerase chain reaction (PCR) test which collects samples from the nasopharyngeal area. Today, machine learning or deep learning is used to analyze data such as confirmed cases or mortality, differentiate x-ray images of COVID-19 patients and others. Not many of the researches completed before predicted important features that influence COVID-19. Therefore, we mainly address the influence of related features. Our data includes demographic, geographic, and severity information in Toronto. The experiment was developed in this order: data import, label encoding, correlation matrix, train-test split, min-max normalization, machine learning models, gridsearchcv, and feature importance. We applied a boosting algorithm and light gradient boosting machine to increase accuracy and speed, gridsearchcv, feature importance function to find the importance of the variable and best hyper parameters for models. Among two experiments, the first experiment using a feature-selected model concluded important features such as outbreak associated, FSA, and classification with 88 percent accuracy. The second experiment that did not select features but used entire features resulted in that neighborhood name, FSA, and age group as important features. The accuracy was mostly around 89 percent. The data did not include personal information but mostly geographical information, which might have influenced the result, determining geographical features as key features of infection, and the accuracy. Yet, the model for the experiment has advanced computation speed, less memory usage, and showed impressive performance.
Abstract: COVID-19, a disease starting from December 2019, spreads from person to person through contact, and has symptoms of cough, fever, muscle pain, etc. The diagnosis is usually done by polymerase chain reaction (PCR) test which collects samples from the nasopharyngeal area. Today, machine learning or deep learning is used to analyze data such as confir...
Show More
A Study on (Q,L)-fuzzy Normal ℓ-subsemiring of a ℓ-semiring Under Homomorphism and Anti-homomorphism
Rock Arokiaraj,
Vellaiyan Saravanan,
Jonadoss Jon Arockiaraj
Issue:
Volume 6, Issue 3, September 2021
Pages:
50-54
Received:
3 August 2021
Accepted:
23 August 2021
Published:
4 September 2021
Abstract: Our motivation in this paper is to start and study the algebraic nature of (Q,L)-fuzzy normal ℓ-subsemirings of a ℓ-semiring. Our purpose of this paper is to initiate and study the notions of (Q,L) - fuzzy normal ℓ-subsemirings of ℓ-semiring.We introduce the concept of (Q,L)-fuzzy normal ℓ-subsemirings of a ℓ-semiring. We study few of their elementary properties by (Q,L)-fuzzy normal ℓ-subsemirings of a ℓ-semiring and establish some results on these. These ideas are utilized in the improvement of some significant outcomes. We additionally made an endeavor to study the few properties of (Q,L)-fuzzy normal ℓ-subsemirings of ℓ-semiring under homomorphism and anti-homomorphism. Also some theorem is the composition operation of functions (Q,L)-fuzzy normal ℓ-subsemirings of ℓ-semiring under isomorphism and anti- isomorphism. Also prove some more properties of homomorphism and anti-homomorphism image and pre- image of (Q,L)-fuzzy normal ℓ-subsemirings of ℓ-semiring. Finally, we present the theorems of (Q,L)-fuzzy normal ℓ-subsemirings of ℓ-semiring under image and pre- image of isomorphism and anti- isomorphism.
Abstract: Our motivation in this paper is to start and study the algebraic nature of (Q,L)-fuzzy normal ℓ-subsemirings of a ℓ-semiring. Our purpose of this paper is to initiate and study the notions of (Q,L) - fuzzy normal ℓ-subsemirings of ℓ-semiring.We introduce the concept of (Q,L)-fuzzy normal ℓ-subsemirings of a ℓ-semiring. We study few of their element...
Show More