Augmented sequence features and subcellular localization for functional characterization of unknown protein sequences

Agrawal, Saurabh; Sisodia, Dilip Singh; Nagwani, Naresh Kumar

doi:10.1007/s11517-021-02436-5

Cited by 5 publications

(1 citation statement)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the area of concentration was medicine, most of these studies are related to cardiovascular diseases (TIWARI et al, 2022;LEE et al, 2022;NUSINOVISI et al, 2020), health implications as a result of COVID-19 (SANTANA et al, 2021;AKTAR et al, 2021;BAIERLE et al, 2020), clinical studies of patients (MAO et al, 2022;SHAH et al, 2022;MAO et al, 2022;WIE et al, 2022;ALFI et al, 2022;PATEL et al, 2022;JEN et al, 2021;SHIM et al, 2020;HUSSAIN et al, 2021;DEIF et al, 2021;VERMA et al, 2020;SHIM et al, 2021;CHO et al, 2019;KENDALE et al, 2018;ZHANG et al, 2019) and protein substances (AGRAWAL et al, 2021;SCHAEFER et al, 2021;WU et al, 2021;NORA et al, 2016). No work has been identified using a database similar to the case of this study related to demand management for telemedicine services.…”

Section: Content Analysismentioning

confidence: 99%

Sales Predicting Telemedicine Services During Covid-19 Using Machine Learning Techniques

CUNHA,

ZUCHETTI,

OLIVEIRA

et al. 2023

Anais Do Encontro Nacional De Engenharia De Produção

View full text Add to dashboard Cite

Telehealth care has been a viable alternative in terms of safety against disease contamination, travel time, and cost reduction for medical consultations during the COVID-19 pandemic. In 2022, Brazil approved the law that authorizes the use of telemedicine services in the country, and since then the services by virtual attendance have grown exponentially. Thus, the demand management process in organizations needed to adapt quickly to this new scenario. Therefore, this research aims to apply machine learning techniques to assist in forecasting sales of remote medical consultation services (telemedicine) during the Covid-19 pandemic in a digital services consulting company. To achieve the objective, first a systematic review of the literature was performed, then collection and analysis of the data needed for the prediction process, and finally choice of the best method from metrics based on minimum error. As a result, it obtained that the technique with the lowest prediction error was Random Forest, which presented only 22% error when applied to the test data set.

show abstract