Browsing by Author "Hasan, MD. Nahid"

Now showing 1 - 3 of 3

Economic crisis prediction due to pandemic outbreak using machine learning
(BRAC University, 2021-06) Ahmed, Tanvir; Hasan, MD. Nahid; Ashik, Md.; Hasan, Md. Jahid; Parvez, Mohammad Zavid
Since pandemic disease outbreaks are causing a major ﬁnancial crisis by aﬀecting the worldwide economy of a nation, machine learning techniques are urgently required to forecast and analyze the economy for early economic planning and growth and to resettle it.A large number of studies have shown that the spread of the disease has experienced a signiﬁcant change in the economy. As a consequence, we will use machine learning to construct early warning models for economic crisis prediction. This paper used a publicly available data-set containing information about National Revenue, Employment Rate, and Workers Earnings of USA over 239 days (1 January 2020 to 12 May 2020). Then, we applied Multilayer Perceptron (MLP) Neural Network and Random Forest classiﬁer to identify recession in revenue, employment rate, and workers earnings, therefore, got accuracy 95%, 81%, 89% and 85%, 81%, 89% respectively. To analyze how much the economy aﬀected by this pandemic, we drive revenue, employment rate, and workers earnings data-set into Long shortterm memory (LSTM) and Random Forest Regressor hence got accuracy 92%, 90%, 90%, and 95%, 93%, 93% respectively. Before a country faces an economic recession, it is important to identify which sector to emphasize to minimize this unexpected scenario. Using machine learning, we analyzed the data and predicted the economy so we could help save a signiﬁcant amount of capital for a country.
Economic crisis prediction due to pandemic outbreak using machine learning
(BRAC University, 2021-01) Ahmed, Tanvir; Hasan, MD. Nahid; Ashik, Md.; Hasan, Md. Jahid; Parvez, Mohammad Zavid
Since pandemic disease outbreaks are causing a major ﬁnancial crisis by aﬀecting the worldwide economy of a nation, machine learning techniques are urgently required to forecast and analyze the economy for early economic planning and growth and to resettle it.A large number of studies have shown that the spread of the disease has experienced a signiﬁcant change in the economy. As a consequence, we will use machine learning to construct early warning models for economic crisis prediction. This paper used a publicly available data-set containing information about National Revenue, Employment Rate, and Workers Earnings of USA over 239 days (1 January 2020 to 12 May 2020). Then, we applied Multilayer Perceptron (MLP) Neural Network and Random Forest classiﬁer to identify recession in revenue, employment rate, and workers earnings, therefore, got accuracy 95%, 81%, 89% and 85%, 81%, 89% respectively. To analyze how much the economy aﬀected by this pandemic, we drive revenue, employment rate, and workers earnings data-set into Long shortterm memory (LSTM) and Random Forest Regressor hence got accuracy 92%, 90%, 90%, and 95%, 93%, 93% respectively. Before a country faces an economic recession, it is important to identify which sector to emphasize to minimize this unexpected scenario. Using machine learning, we analyzed the data and predicted the economy so we could help save a signiﬁcant amount of capital for a country.
Unlearning to protect: a distilled reinforcement learning framework with privacy-preserving feature unlearning and XAI for IoT security
(BRAC University, 2025-11) Hasan, MD. Nahid; Alam, Md. Golam Rabiul
Botnets pose a significant cybersecurity threat, enabling attacks such as DDoS, data theft, and service disruptions on IoT devices. These devices often lack built-in botnet traffic filtering, leaving them highly exposed. Existing AI-based solutions improve detection capabilities but have limitations: (i) they are too heavy for IoT deployment, and (ii) they lack unlearning capabilities to forget sensitive or outdated features without retraining. To address these challenges, we propose DiRLU, a lightweight, reinforcement learning driven framework, while ensuring privacy by selectively unlearning sensitive or outdated features without requiring retraining. The framework leverages knowledge distillation to transfer knowledge from a teacher model into a lightweight student model, with both models trained using A2C. A post-hoc unlearning mechanism modifies weights to remove targeted features, while restored features show negligible performance loss, confirming reversibility. Unlike many benchmark models that used only 5% of the BoT-IoT dataset, this research leverages 25%, allowing us to develop a strong teacher model. Both the teacher and student models were trained using the A2C reinforcement learning algorithm, achieving impressive results, with the student model achieving 99.60% accuracy and a 99.80% F1 score. To enhance transparency, we integrated Explainable AI (XAI), particularly LIME, which helps interpret the model’s decisions and identify the key features influencing its predictions. Additionally, DiRLU requires only 2,370 FLOPS, approximately 3.87× more efficient than the state-of-the-art model, highlighting its efficiency for edge deployment. DiRLU combines efficiency with privacy, aligning with GDPR standards (right to be forgotten) to provide practical IoT security solution. By combining knowledge distillation, feature unlearning and XAI, this research not only strengthens botnet detection but also sets new standards for security, interpretability, and data privacy in cybersecurity.