A
Amatul Bushra Akhi
Researcher at Daffodil International University
Publications - 5
Citations - 10
Amatul Bushra Akhi is an academic researcher from Daffodil International University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 2, co-authored 2 publications receiving 4 citations.
Papers
More filters
Book ChapterDOI
Modeling the Role of C2C Information Quality on Purchase Decision in Facebook
Rafita Haque,Imran Mahmud,Md. Hasan Sharif,S. Rayhan Kabir,Arpita Chowdhury,Farzana Akter,Amatul Bushra Akhi +6 more
TL;DR: This study exhibits a model to influences of C2C communication on Bangladeshi consumers’ purchase decision in the online communities of F-Commerce and shows that Argument Quality, Source Credibility and Tie Strength positively influence Purchase Decision through Product Usefulness Evaluation (PUE).
Journal ArticleDOI
IoTSAMS: A Novel Framework for Internet of Things (IoT) Based Smart Attendance Management System
TL;DR: This paper presents a simple technique of taking student attendance in the form of an Internet of Things (IoT) based system that records the attendance using fingerprint-based system and stores them securely in a database.
Journal ArticleDOI
Prediction of Breast Cancer using Traditional and Ensemble Technique: A Machine Learning Approach
TL;DR: In this article , the authors used decision tree (DT), Random Forest (RF), Logistic Regression (LR), K-Nearest Classifier (KNN), and Boosting Decision Tree (BDT) to identify potential breast cancer cases.
Journal ArticleDOI
Blockchain-Based Islamic Marriage Certification with the Supremacy of Web 3.0
TL;DR: In this article , the authors proposed an approach to revolutionize the entire marriage recording system of Bangladesh, which describes step-by-step procedures and the better way to implement a digital Muslim marriage data preservation system.
Journal ArticleDOI
BrainNet-7: A CNN Model for Diagnosing Brain Tumors from MRI Images based on an Ablation Study
TL;DR: In this article , a robust deep learning model that categorizes brain tumors using MRI images into four classes based on a convolutional neural network (CNN) was proposed, and the proposed BrainNet-7 achieved the best results with 99.01% test accuracy and 99.21% validation accuracy.