Browsing by Author "Mahmood, Riaz"

Now showing 1 - 2 of 2

Complete analytical model of GaN MESFETs for high power and Microwave frequency applications
(BRAC University, 2011-12) Shanta, Aysha Siddique; Huq, Tasneem Rumman; Hossain, Daraksha Binte; Mahmood, Riaz; Islam, Md. Shafiqul
In the past few years, growing interest has been paid to the wide band gap materials such as GaN because of its low thermal generation rate and high breakdown field for its potential use in high power, high temperature and microwave frequency applications. The use of GaN based devices for efficient, linear high power RF amplifiers has already been grown for military applications. GaN Metal Semiconductor Field Effect Transistors (MESFETs) have received much attention as its structure is simpler to analyze than that of High Electron Mobility Transistors (HEMTs) and its epi-layers and the physical effects are easier to realize and interpret. Flourishing interest in exploiting the properties and performance of GaN based devices requires the development of simple physics-based analytical models to simplify the device parameter acquisition and to be able to use it for computer-aided design of GaN integrated circuits (ICs). Few analytical models on GaN MESFETs are reported, though significant experimental work is available. Therefore more analytical models should be developed to understand the device operation accurately. In this thesis, analytical one- and two-dimensional channel potential models are developed for long-channel GaN MESFETs based on the solution of Poisson’s equation. The developed analytical channel potential model can be used for short-channel MESFETs with some modifications and assumptions. Analytical models for I-V and C-V characteristics of GaN MESFET are also presented considering the effect of parasitic resistances and gate length modulation. The models evaluate the transconductance and optimum noise figure. The models developed in this thesis will be very helpful to understand the device behaviour in nanometer regime for future applications.
Detecting propagandistic poster title: a machine learning approach
(BRAC University, 2024-03) Mahmood, Riaz; Shah, Intiajul Alam; Hassan, Tasnimul; Abdullah, Hasan; Mubassir, Taskin Mohammad; Alam, Md. Golam Rabiul
Detecting propagandistic content is crucial in today’s digital age where misinformation spreads rapidly. In this study, we propose a machine learning approach aimed at identifying propaganda in poster titles. Our methodology encompasses various text classification techniques, including Random Forest, Logistic Regression, K-Nearest Neighbor (KNN), Naive Bayes classifier, Support Vector Machine (SVM), RoBERTa, Stacking Classifier, Stacking Classifier With Feature Engineering, and RoBERTa XGBoost Hybrid Model. We employ robust feature extraction methods such as TF-IDF and Word2Vec, along with advanced ensemble learning strategies, to enhance the accuracy and effectiveness of the classification process. Specifically, we introduce two hybrid models: the Stacking Classifier With Feature Engineering, which incorporates word2vec and TF-IDF to improve accuracy, and the RoBERTa XGBoost Hybrid Model, which utilizes a combination of TF-IDF vectorization and RoBERTa embeddings followed by XGBoost classification. Through extensive experimentation and evaluation, we analyze the performance of each model in terms of accuracy, precision, recall, and F1-score. Our findings demonstrate promising results, with certain models exhibiting significant improvements over baseline approaches. Moreover, we conduct a thorough analysis of the models’ strengths and weaknesses, providing insights into their efficacy in detecting propagandistic content. Overall, our research contributes to the development of effective tools for combating propagandistic title and promoting media literacy in the digital landscape.