Browsing by Author "Alshurideh, Muhammad Turki"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    BIDIRECTIONAL LSTM FOR ELECTRONIC PRODUCT RECOMMENDATION (Article)
    (Natural Sciences Publishing, 2024) Vasudevan, Asokan; Albinaa T.A; Mohammad, Suleiman Ibrahim; Sharmila E; Raja N; Soon, Eddie Eu Hui; Alshurideh, Muhammad Turki; Al-Adwan, Ahmad Samed
    In today’s retail landscape, the surge of online e-commerce platforms, especially in the electronics sector, has become ubiquitous, presenting a significant challenge of guiding customers towards relevant items. The proposed system addresses this challenge by leveraging Bidirectional LSTM neural network models, which offer more accuracy than traditional collaborative and content-based filtering methods, to deliver precise recommendations tailored to individual user preferences. Integration of speech technology enhances user interaction by vocalizing recommended products, thereby enhancing the overall user experience. The system’s use of advanced algorithms such as Bidirectional LSTM for recommendation not only enables businesses to make informed decisions but also enhances their product offerings, ultimately helping them to stay competitive in the e-commerce landscape. Overall, Recommendation Systems for User Satisfaction revolutionize e-commerce by simplifying decision-making, enhancing satisfaction, and driving sales through personalized product suggestions and seamless user interaction. Having recommendation systems that are focused on user satisfaction in a way that they not only completely change the e-commerce setting but also show changes in the online business’ approach to their customers is an interesting way to look at it. One of the most critical aspects of this system is that it not only caters to the user’s needs but also uses advanced algorithms to get them better services, thus, the system makes it possible for us to improve our decision-making skills and better the customer experience in the quickly changing online retail.
  • No Thumbnail Available
    Item
    PREDICTIVE MAINTENANCE FOR VEHICLE PERFORMANCE USING BIDIRECTIONAL LSTM (Article)
    (Natural Sciences Publishing, 2024) Vasudevan, Asokan; Gandhimathi K; Mohammad, Suleiman Ibrahim; Harsavarthini M; Raja N; Soon, Eddie Eu Hui; Abu-Shareha, Ahmad A; Alshurideh, Muhammad Turki
    The advancement of sensor and network technologies has led to an abundance of condition- monitoring and performance data, particularly in the automotive sector. This data and big data analytics offer opportunities to enhance predictive maintenance strategies. Various data preprocessing techniques, such as handling missing values and data normalization, are involved before the data is fed into the algorithm. The Feature selection process and Data splitting process also play a major role in determining which attributes in the data are more important and splitting the data for the testing and training process. The evolution of Deep Learning (DL) techniques becomes achievable to address potential equipment failures like a brake pad, fuel consumption, tire rotation, crankshaft detection, etc., and estimate the remaining useful life of the vehicle by using the algorithm bidirectional Long Short-Term Memory (LSTM) deep networks as a primary algorithm for predictive maintenance in vehicles.