Yazar "Yusof, Mohammad Hafiz Mohd" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Sentiment analysis comparisons across selected ml models: application on Malaysia online banking twitter data
    (Elsevier, 2024) Fadhil, Intan Sorfina Mohd; Yusof, Mohammad Hafiz Mohd; Khalid, Ilyani Abd; Teoh, Sian Hoon; Almohammedi, Akram A.
    Sentiment analysis study predominantly revolves around classification tasks by Machine Learning. None of these studies had demonstrated the comparative analysis between different type of ML models accuracy level. On the other hand, the banking industry is rapidly embracing digitalization and security-related matters like trust and privacy remain critical factors in influencing customer's acceptance and usage towards those services. Hence, sentiment analysis serves as a powerful tool for banks to gauge customer satisfactory level towards these security services. However, this process is done previously without optimizing the selection of ML models accuracy level. Furthermore, the results are often invisible and kept in manual book. Hence the ultimate goal of this study is to comparatively measure the accuracy performance of different type of ML sentiment analysis accuracy against the Malaysia online banking security services Twitter data (a.k.a X). Subsequently, the report will be visualized through web application. It is done in six-fold methodology namely data collection, data pre-processing and data wrangling, data analysis, model training and finally model testing and evaluations. The result shows Decision tree has achieved the highest accuracy of 76%.
  • Küçük Resim Yok
    Öğe
    Visualizing Realistic Benchmarked IDS Dataset: CIRA-CIC-DoHBrw-2020
    (Ieee-Inst Electrical Electronics Engineers Inc, 2022) Yusof, Mohammad Hafiz Mohd; Almohammedi, Akram A.; Shepelev, Vladimir; Ahmed, Osman
    Intrusion Detection System (IDS) dataset is crucial to detect lateral movement of cyber-attacks. IDS dataset will help to train the IDS classifier model to achieve earliest detection. A good near-realism public dataset is essential to assist the development of advanced IDS classifier models. However, the available public IDS dataset has long been under scrutiny for its practicality to reflect real low-footprint cyber threats, render real-time network scenario, reflect recent malware attack over newly developed DoH protocol, disregard layer 3 information and finally publish contradictory results of classification and analysis between various studies which makes it non-reproducible and without shareable results. This problem can be resolved by sophisticatedly visualizing a new realistic, real-time, low footprint and up-to-date benchmarked dataset. Visualization helps to detect data deformation before designing the optimized and highly accurate classifier model. Therefore, this study aims to review a new realistic benchmarked IDS dataset and apply sophisticated technique to visualize them. The review starts by carefully examining production network features. These are then compared with various well-established public IDS datasets. Many of them are static, unrealistic meta-features and disregard source and destination Internet Protocol (IP) information except CIRA-CIC-DoHBrw-2020 dataset. The study then applies Eigen Centrality (EC) technique from the graph theory to visualize this layer 3 (L3) information. Finally, using various visualization techniques such as Principal Component Analysis (PCA) and Gaussian Mixture Model (GMM), the study further analyzes and subsequently visualizes the data. Results show that the CIRA-CIC-DoHBrw-2020 simulated recent malware attack and has a very imbalanced dataset which reflects the realistic low-footprint cyber-attacks. The centrality graph clearly visualizes IPs that are compromised by recent DoH attack in real-time, and the study concludes decisively that smaller packet length of size 1000 to 2000 bytes is to fit an attack trait.