Yazar "Yusof, M.H.M." seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Generating Network Intrusion Image through IGTD Algorithm for CNN Classification(Institute of Electrical and Electronics Engineers Inc., 2023) Nazarri, M.N.A.A.; Yusof, M.H.M.; Almohammedi, A.A.Stealthy attacks make Intrusion Detection System (IDS) research perennial and notably important. From the literature, a few problems were identified in IDS studies particularly with regards to image generation. Image generation is the preprocessing phase during the development of CNN classifier. Simple feature extraction process that are applied in a few studies may lose features' details. They disregard spatial information such as pair pixels information. Secondly several public datasets suffer from realistic network traits. This study will apply the improvised version of IGTD algorithm to resolve image generation process. IGTD algorithm has been adopted in Cancer Cell Lines (CCLs) study. Realistic dataset of CIRA-CIC-DoHBrw-2020 and CICIDS2017 will be run over the algorithm. These dataset have been reviewed to be the closest realistic production network dataset. Result shows the generated image has notable difference between attack and benign traffic. The highest trained classification model has achieved almost 80% of accuracy rate. © 2023 IEEE.Öğe An Intelligent Movies Recommendation System Based Facial Attributes Using Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2023) Balfaqih, M.; Altwaim, A.; Almohammedi, A.A.; Yusof, M.H.M.Movie theaters and platforms offer a wide selection of movies that require filtering to match the preferences of individual users. Recommender systems are an effective tool for this task. This study introduces a hybrid recommender system that combines collaborative filtering and content-based approaches to provide personalized movie recommendations. The proposed system considers age, gender, emotion, and genre attributes to ensure the suitability of the recommended movies. The proposed system targets the visitors of cinema theaters to try a new experience of choosing the next movie to watch by recognizing the visitor's face to determine his/her age, gender and emotion using camera. Therefore, our system is expected to achieve better results than traditional approaches. The system's performance is evaluated using standard metrics such as precision, recall, and F1-measure. The findings indicated that the proposed system outperforms the benchmark system in the most tested scenarios. However, the precision of the benchmark work is slightly higher in (8-14 and 15-24) age groups. © 2023 IEEE.Öğe Resistors Over Digital Analog Converter on PRBS Threat Generator with PLL Synchronizer: Comparison Between R2R & Weighted(Institute of Electrical and Electronics Engineers Inc., 2023) Almohammedi, A.A.; Yusof, M.H.M.; Bin, Tuan, Muda, S.R.; Shepelev, V.; Balfaqih, M.; Shamsuddin, S.Intrusion Detection System (IDS) must be developed based on latest live traffic dataset. This will facilitate the study on new attributes of current threat. Once again, researchers are locked on the same vicious circle of inability to access live traffic dataset. This is coupled with public domain logged dataset may not be useful for a new threat research. Due to these standing hurdles, Pseudo Random Binary Sequence (PRBS) is used to generate synthetic dataset in IDS studies. One of its components is the Digital to Analog (D/A) converter. There are two types of D/A implementations; 1) through Weighted and 2) R2R resistors. This paper compares the advantages and the disadvantages of designing D/A converter by using the abovementioned resistors. It is advisable to opt for R2R version over Weighted Resistor since it is easier and practical to choose the multiple types of resistors during circuit design process. Furthermore, the shifted parallel output from the circuit can be synchronized by the proposed PLL circuit. © 2023 IEEE.
