Survey on Highly Imbalanced Multi-class Data

Machine learning technology has a massive impact on society because it offers solutions to solve many complicated problems like classification, clustering analysis, and predictions, especially during the COVID-19 pandemic. Data distribution in machine learning has been an essential aspect in providing unbiased solutions. From the earliest literatures published on highly imbalanced data until recently, machine learning research has focused mostly on binary classification data problems. Research on highly imbalanced multi-class data is still greatly unexplored when the need for better analysis and predictions in handling Big Data is required. This study focuses on reviews related to the models or techniques in handling highly imbalanced multi-class data, along with their strengths and weaknesses and related domains. Furthermore, the paper uses the statistical method to explore a case study with a severely imbalanced dataset. This article aims to (1) understand the trend of highly imbalanced multi-class data through analysis of related literatures;(2) analyze the previous and current methods of handling highly imbalanced multi-class data;(3) construct a framework of highly imbalanced multi-class data. The chosen highly imbalanced multi-class dataset analysis will also be performed and adapted to the current methods or techniques in machine learning, followed by discussions on open challenges and the future direction of highly imbalanced multi-class data. Finally, for highly imbalanced multi-class data, this paper presents a novel framework. We hope this research can provide insights on the potential development of better methods or techniques to handle and manipulate highly imbalanced multi-class data. © 2022. International Journal of Advanced Computer Science and Applications.All Rights Reserved

Facemask quality measurement using AMG8833 multiarray thermal sensor

Face masks have become a necessary thing that people need to wear daily. Even though some people might already be vaccinated, there is still a chance that the Covid-19 virus could still infect them. Hence, this paper presents a device developed to help determine the quality of face masks crucial in preventing the spread of the virus. These devices can calculate the temperature outside the face mask at a maximum distance of three meters. The way this device works is by measuring the temperature released out of the face mask. Here, the developments of the device with the ability to help determine the quality of face masks are explained and discussed. In the end, the device is perfectly functioning and definitely would assist in verifying the quality of the face masks being worn by someone. Two types of faces are used as test materials: the KN95 type face mask and the 3ply facemask used in Malaysia. Each facemask collected data from 30 minutes to 300 minutes for ten subjects over ten days. Studies that have been conducted show that the thermal value of the KN95 facemask increased to 30.27°C after 5 hours of use. At the same time, the 3ply type facemask offers a thermal value of up to 34.58°C after 5 hours of use. This shows a thermal value difference of up to 4.31°C for both facemasks after 5 hours of use. © 2021 Institute of Physics Publishing. All rights reserved.