Browsing by Author "Hossain, Shoaib"

Now showing 1 - 4 of 4

Classification of Ethical and Unethical Social Media Activities Using Data Analytics
(Daffodil International University, 23-02-18) Yesmin, Farzana; Hossain, Shoaib
In a society and era when they are prevalent, such as Instagram, Twitter, and Facebook, it could be challenging to identify the shortcomings of each program or website. In 2022, almost every person uses social media to get connected and relate to each other through these platforms. As it is a modern age and a technological revolution has happened already, people need to get connected to social media by their own privileges. Merely, everyone must continue their study and official work. Therefore, it has been found that many people become addicted to using social media in all cases and in all circumstances. It is necessary to find out the exact reasons why people become addicted to social media and maintain social media activities during working or studying time. Researchers all over the world found out that a huge quantity of people become addicted to social media, however they are not their workplace or not. By using machine learning technologies and data analytics, it can be found out the reason to use social media in that environment where it is not allowed. As everyone is concerned about their own workplaces, they must have known it is unethical. In this research, these questions are answered with proper explanation with the help of data analytics and machine learning. Soon, it will be great to understand and find out the reasons for natural language processing or human activities.
Classification of Ethical and Unethical Social Media Activities Using Data Analytics
(Daffodil International University, 23-02-18) Yesmin, Farzana; Hossain, Shoaib
In a society and era when they are prevalent, such as Instagram, Twitter, and Facebook, it could be challenging to identify the shortcomings of each program or website. In 2022, almost every person uses social media to get connected and relate to each other through these platforms. As it is a modern age and a technological revolution has happened already, people need to get connected to social media by their own privileges. Merely, everyone must continue their study and official work. Therefore, it has been found that many people become addicted to using social media in all cases and in all circumstances. It is necessary to find out the exact reasons why people become addicted to social media and maintain social media activities during working or studying time. Researchers all over the world found out that a huge quantity of people become addicted to social media, however they are not their workplace or not. By using machine learning technologies and data analytics, it can be found out the reason to use social media in that environment where it is not allowed. As everyone is concerned about their own workplaces, they must have known it is unethical. In this research, these questions are answered with proper explanation with the help of data analytics and machine learning. Soon, it will be great to understand and find out the reasons for natural language processing or human activities.
Deep Learning Based Instance Segmentation of Leaf diseases
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-08-19) Hossain, Shoaib
Crop disease is a significant issue for Bangladesh's economy, but it can be prevented with early detection. This thesis proposes a deep learning-based instance segmentation technique for detecting 10 of the most common crop diseases in Bangladesh. This technique can enable automated crop disease detection on a large scale. The paper introduces a new annotated dataset of around 4600 images for 10 different disease classes. Image annotation is usually the most time- consuming phase for any segmentation task. To reduce this time, the paper proposes a new semi- automated annotation pipeline. It showcases how this pipeline can reduce image annotation time by approximately 85%. After annotating all the images, three different models were trained – two variants of YOLOv8 (YOLOv8, YOLOv8l) and YOLOv9c. These models were trained on three different versions of the dataset: the first version with only manually annotated images, the second version with a combination of manually and semi-automated annotated images, and the third version with an augmented combined dataset. The augmented version did not perform well, but when increasing the dataset using semi-automated annotation, the mAP score increased. YOLOv8l achieved the best mAP score of 0.7417.
Network based location tracking using MAC address of smart devices
(BRAC University, 2017-12) Chowdhury, Md. Abu Hena; Chowdhury, Rakib Hasan; Hossain, Shoaib; Sakib, Sadman Md; Uddin, Dr. Jia
Most of the devices we use today from a day to day basis are considered smart. What do they mean by smart? What they mean is that they possess the ability to share and hold information amongst each other. Since the capacity of machines has evolved so has its needs and applications. Personnel location is one such capacity that has a huge array of applications. Our thesis, provides a segmented approach to locating targets namely staff in a working environment under a previously configured network i.e a system of routers repeater and extenders connected toeach otherfor our proposed system to work . We propose to use the 48 bit physical address known as MAC address of a regular smart phone which will help us connect to a WIFI network to track people's location. We are trying to implement an android based application which will employ Wi-Fi routers, repeaters and extenders to obtain the location of a target in a defined network. This location will be viewable through a map on the android app. After initial testing on a small network consisting of a router and a wifi signal extender which basically acts as another router we achieved total coverage every time i.e every time our discovery feature prompted a list of all connected devices without missing any device. We plan to use our university quarters as the test site and this will allow our app to access multiple MAC addresses as the campus is home to thousands of students and their devices.