Data Analysis for The Student Health Digital Profile

Mansurova, Madina; Zubairova, Malika; Kadyrbek, Nurgali; Tyulepberdinova, Gulnur; Sarsembayeva, Talshyn

doi:10.1109/icecco53203.2021.9663804

Cited by 4 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent sensor network innovations such as the Internet of Things (IoT) are revolutionizing cost-effective home and work healthcare services [21,22]. AmI medical services use assistive technologies and innovations of two important types: complex sensor networks and networks of body regions in intelligent environments [23,24].…”

Section: Introductionmentioning

confidence: 99%

Information and Analytical System for Assessing the Health Status of Students

Tyulepberdinova

Sarsembayeva

Adilzhanova

et al. 2023

JMMCS

View full text Add to dashboard Cite

The purpose of our work was to study the effectiveness of using an intelligent informationanalytical system to assess the health status of students on the basis of one of the universities in Kazakhstan, the Kazakh National University named after Al-Farabi. For this purpose, a simulation was performed using individual health data 4456 university students. The study involved 47.4% of female students and 52.6% of males; the predominant age ranged from 18 to 21 years (66.9%), and the distribution of students by years of study was almost uniform. For classification were used such as Vector Machine, K -Nearest Neighbour, Random Forest and Naive Bayes supports. The performance metrics chosen to evaluate the use of various prediction algorithms were Specifity, Sensitivity, Accuracy, and Accessibility. It has been established that when using the classifier Support Vector Machine 's Specifity, Sensitivity, Accuracy, and Accessibility scores are at their highest, reaching 97%. The overall performance of the developed intelligent information and analytical system was evaluated using the Reliability parameter. In comparison with other wellknown systems for monitoring the health of patients (AmbIGEM and AAL ), the system developed by us showed higher reliability (90-95%). In the future, the developed model can be used to expand health monitoring by including external parameters that can also affect the health of students. In addition, it is planned to introduce Deep Learning to monitor the health of students in other educational institutions in Kazakhstan and the world.

show abstract

Section: Introductionmentioning

confidence: 99%