Browsing by Author "Tabassum, N."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A STUDY TO FIND THE MOST SIMILAR REAL EARTHQUAKE RESPONSE SPECTRUM TO THE RESPONSE SPECTRUM DEVELOPED FROM BNBC 2006 NORMALIZED RESPONSE SPECTRUM
    (Dept. of CE, CUET, 19-Dec-2018) Shafi, S M; Tabassum, N.; Mazumder, A.
    Earthquake is a natural phenomenon which has an adverse effect on human lives and natural resources. It is now a growing concern of our structural engineer to design an earthquake resisting structure. In this study, the comparison has been made between earthquake response spectra with our national building code provided response spectra. BNBC 2006 has provided us with a normalized response spectrum for 5% damping ratio. This is used in this study to develop a response spectrum for rock and stiff soil (soil type S1) and earthquake zone 2. With the help of Pacific Earthquake Engineering Research Centre (PEER) we have selected 5 earthquake response spectra named Friuli earthquake Italy, Gazli earthquake Uzbekistan, Imperial Valley 2 earthquake USA, Imperial Valley 6 earthquake USA, and Tabas earthquake Iran for the comparison. The analysis has been done by using SAP2000 on a steel structure. With some modification, the model structure has been developed from Federal Emergency Management Agency (FEMA) 355C report Appendix B which is a 9 storied building, square in plan and with 5 bays in each direction with one underground basement. The structural response like base reaction, joint reaction, and joint displacement has been considered for the comparison. Finally, it is found out that the response spectrum for earthquake Gazli of Uzbekistan which is a magnitude of 7.0 provides response close to BNBC response spectrum for soil type S1.
  • Thumbnail Image
    Item
    PhishGuard: A Convolutional Neural Network-Based Model for Detecting Phishing URLs with Explainability Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2024-04-27) Islam, M.R.; Islam, M.M.; Afrin, M.S.; Antara, A.; Tabassum, N.; Amin, A.
    Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models' decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a 1 D Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85 %. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL