Browsing by Author "Nawal, Nafisa"

Now showing 1 - 3 of 3

A Web Application on Blood Bank Management System
(Independent University, Bangladesh, 2022-09-14) Nawal, Nafisa
The definition of an internship is the acquisition of practical knowledge for diverse businesses. It helps to establish a link between information from theory and information from practice. It is crucial because a student has never before had the opportunity to act on information from other groups. Once granted, I Through my internship at at B Co. Ltd, I had the chance to work and learn alongside a group of engineers. This project's goal was to build a web application using the Laravel framework which allowed the framework to function in real-time. Every project I worked on during my study period is covered in this report. I had to finish my study sessions before beginning any projects, and after learning my lesson this time, the majority of my work on a web application.
Automatic brain tumor segmentation using U-ResUNet chain model approach
(BRAC University, 2021-09) Alam, Mohd Tanjeem; Nawal, Nafisa; Nishi, Nusrat Jahan; Sahan, MD Samiul; Islam, Mohammad Tanjil; Akhond, Mosta jur Rahman
Identifying brain tumors precisely within the early stage is still a challenging problem for the medical sector consistent with recent research. In a previous research approved by Cancer. Net Editorial Board, it was observed that this year, approximately twenty four thousand ve hundred thirty adults will be detected with initial stage cancer tumors of the brain and spinal cord in the United States. So, a developed technology is required to identify this tumor in an early stage to increase the survival rate from this disease. To overcome this problem, many Deep Learning models like CNN (Convolutional Neural Network), LSTM(Long-Short Term Memory) were proposed to detect tumor areas in the primary stage through segmentation and classi cation in previous research. In our proposed paper, we will attempt to use combination of Res-Unet and Unet model to perform segmentation on brain MRI images. So, basically, our target will be to take brain MRI images as input data and after that, we will try to t the combination of Unet and Res-Unet model on the dataset to perform segmentation to compare the result with other proposed models to get better result.
Recommendation system for mood stabilization using content recommendation
(BRAC University, 2023-09) Al-Wakil, Kazi Md.; Rahman, Rifai; Nawal, Nafisa; Meem, Sababa Rahman; Rashid, Sajid; Rabiul Alam, Dr. Md. Golam; Rahman, Mr. Rafeed
In the era of accelerating technological development, society is confronted with the paradoxical situation of making technological advancements while experiencing a decline in mental health. The importance of mental health seems to be declining significantly. The impact of our daily content intake on emotional well-being is clearly visible. For instance, while a melancholic song can make a person feel sad, an inspirational movie can charge a person’s spirit to come up stronger. Hence we intend to employ this concept to propose a system designed to recommend “Feel Good” YouTube videos with the aim of stabilizing an individual’s mood when it wavers or becomes low. To do this efficiently, we worked on the SEED Dataset, which is composed of EEG signals and Eye Movement data. We implemented a multifaceted approach, including the extraction of Differential Entropy Features, Wavelet Transform, Shannon Entropy features and Eye movement features. These were further harnessed by Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) networks to ensure accurate emotion classification. A thorough evaluation of these two deep learning models in the context of emotion classification is presented by focusing on their relevant merits and demerits. Based on the comparisons it is found that CNN is the most suited for our study with an accuracy of 93.01%. Once a mood classification is achieved, our proposed system will curate and suggest trending “Feel Good” content. To tackle this, we implemented a recommendation system based on the fusion of two prevalent techniques. Initially, text classification was employed to extract the emotion associated with the video and later, Pearson Correlation was utilized to obtain accurate correlation between the contents of the videos based on their corresponding ratings from viewers. Furthermore, concepts of Analytic Hierarchy Process (AHP) have been implemented to come up with an efficient algorithm which works in stabilizing an individual’s mood gradually. In essence, our innovative system encompasses two primary objectives: the detection of an individual’s emotional state through EEG signal analysis and the subsequent stabilization of their mood through targeted content recommendations. By combining these components, we envision a tool that not only comprehends the user’s emotional well-being but actively contributes to its enhancement.