Browsing by Author "Sharmin, Shayla"

Now showing 1 - 4 of 4

Developing a Bidiretional Mutual Gaze Mechanism for Human Robot Interaction
(Faculty of Electrical and Computer Engineering, CUET, 7-Feb-2019) Sharmin, Shayla; Hoque, Mohammed Moshiul
Establishing mutual gaze is one of the most
IOT Based Temperature Control System of Home by Using an Android Device
(2021 1st International Conference on Emerging Smart Technologies and Applications (eSmarTA), IEEE, 2021-08-23) Foysal, Musfiqur Rahman; Hossain, Refath Ara; Islam, Mohammad Monirul; Sharmin, Shayla; Moon, Nazmun Nessa
This IOT-based architecture research project is created for people who are familiar with emerging smart technologies. This project is primarily based on controlling the voltage of AC-supported equipment and developing an automatic temperature ventilation system that can make a space fully temperate. Additionally, this will protect our appliances from overheating. Using the widely used Node MCU microcontroller and IP networking for remote access and control, this project aims to automate machines and appliances. You can also use an Android-based smartphone app to access these computers while you are not at work. Many electrical and appliances, such as lamps, fans, and refrigerators, can be controlled by an Android smartphone, which can also help against overheating. This technology is more valuable in today's world in business environments where temperature control is a big concern. The proposed voltage control scheme has been combined with products such as an AC lamp, an AC fan, and a DC cooling fan to demonstrate its feasibility and effectiveness.
Machine Learning Approach to Find Students' Best Place to Study
(2021 2nd International Conference on Innovative and Creative Information Technology (ICITech), IEEE, 2021-11-15) Nooder, Jarin; Mahbuba, Ashrarfi; Sharmin, Shayla; Moon, Nazmun Nessa; Poushy, Lamisha Haque; Bhuiyan, Salauddin Ahmed; Nawshin, Samia
Students are a country's backbone. The appropriate surroundings for studying must be provided for them. Of all these criteria, a place where you may locate the appropriate setting for your requirements is the most important. The purpose of the study is to identify the best environment to study among students living with parents and hostels. This research also explores issues such as the life and academic chances of students. Adapted questionnaires were utilized to evaluate the responses of 400 students from different colleges, institutes, and students freshly graduated. According to the findings of the survey, students choose to live and study at home because it is healthy and convenient. A variety of algorithm techniques are used, but the Logistics Regression algorithm was the key preference for this study because it had the highest accuracy score. This leads to the conclusion that students opt to stay at home
Prediction Hepatitis C Virus and Classifier Blood Donor and Disease using an Ensemble Approach in the Machine Learning Algorithm
(Scopus, 2024-12-19) Hirok, Md Kamruzzaman; Parvin, Masuma; Sharmin, Shayla
Hepatitis C, caused by the hepatitis C virus, is a liver condition that can lead to severe complications if left untreated. The disease progresses through different stages, and while it is more easily treatable in the early stages, reaching the final stage without proper treatment makes recovery much harder, often resulting in high costs and significant pain. The current research emphasizes the importance of early detection as a simple and effective way to manage the condition. This study focuses on accurately predicting hepatitis C status, categorizing individuals as either blood donors or affected by the disease, using an ensemble machine learning approach. The research utilizes thirteen attributes and classifies the target into five categories: Blood Donor (including Blood Donor and Suspect Blood Donor) and Disease (encompassing Hepatitis, Fibrosis, and Cirrhosis). Several machine learning algorithms are employed, includeincludeing Decision Tree, K-nearest neighbor, Random Forest, and a Stacking Classifier. Among these, the Stacking Classifier outperformed the others, achieving an accuracy of 99.4%, precision of 99.7%, recall of 97.7%, and an F1-score of 98.7%.