Open AccessToward a Cloud based Disease Diagnosis System Using Sequential Quadratic Programming Approach
Author(s) -
Ali Hussein Shamman Al-Safi,
Zaid Ibrahim Rasool Hani,
Ahmed A. Hadi,
Musaddak Maher Abdul Zahra,
Wael Jabbar Abed Al-Nidawi
Publication year - 2021
Publication title -
webology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.259
H-Index - 18
ISSN - 1735-188X
DOI - 10.14704/web/v18i2/web18368
Subject(s) - computer science , cloud computing , machine learning , artificial intelligence , generalization , process (computing) , big data , data science , internet of things , the internet , computer security , data mining , world wide web , mathematical analysis , mathematics , operating system
The Internet of Things (IoT) relates to the process of utilizing computer networks to plan and model Internet-connected things. The Internet of Things (IoT)-based m-healthcare technologies have provided multi-dimensional functionality and real-time resources over the last few years. These apps provide millions of individuals with a forum to get wellness alerts for a healthy lifestyle constantly. Several aspects of these systems have been revitalized with the introduction of IoT devices in the healthcare sector. This work proposed a data-driven disease signal analytics by inventing a novel combination learning approach. The proposed Combination learning integrates different machine learning models to price disease signal for different options by leveraging the availability of a large amount of data through solving a sequential quadratic programming problem. The proposed approach demonstrates its superiority in prediction accuracy and strong model independence by overcoming traditional model-driven approaches' generalization issue. The findings illustrate the efficacy of the task for an effective disease signal diagnosis. It could be a modern and useful health approach to adopt the proposed procedure with potential changes and incorporate it into a low-cost unit.