Norfadila Mahrom
Thumbnail Image
Preferred name
Norfadila Mahrom
Official Name
Norfadila, Mahrom
Alternative Name
Mahrom, Norfadila
Mahrom, N.
Mahrom, Norfadilla
Main Affiliation
Scopus Author ID
57200080959
Researcher ID
DDY-3868-2022

Research Output

Filters

4 1
2
4
Reset filters

Settings
Now showing 1 - 4 of 4
  • Publication
    Review of big data application in smart manufacturing
    ( 2023-07-19)
    Ahmad Faizal Annuar
    ;
    Ab-Samat H.
    ;
    Norfadila Mahrom
    This paper reviews the application of big data in smart manufacturing. Currently, the application of big data into the manufacturing operation is still a premature undertaking, with cost, compatibility, and lack of expertise hindering decision-making for many organizations. The selected papers discuss a variety of situations in which big data analytics and its applications have been used to enhance decision-making in the manufacturing operations, productions, scheduling, quality assurance, maintenance, and sustainability with significant data analytics considerations, obstacles to extensive data analytics adoption, machine learning, and use of sensors for data extraction. This article presents the discussions in the manufacturing industry surrounding the use of big data analytics.
  • Publication
    Design and Implementation of FPGA-based Single Computing Engine of VLC Image Transfer
    ( 2023-10-06)
    Ismail S.N.
    ;
    Mohd Rashidi Che Beson
    ;
    Salih M.H.
    ;
    Norfadila Mahrom
    This paper has proposed a single computing engine based on VLC technology for use in real-time to secured image of transmitter and receiver systems implemented on an FPGA in real time. It is proposed that a single computing engine system consist of the following components be implemented: UART control, FIFO buffer, VGA controller, and 128-bits AES algorithm decryption and encryption. An Altera DE1-SoC board is used to implement the design, coded in VHDL, and implemented in Quartz prime 15.1 FPGA using a software platform system architecture. The single computing engine communication via VLC system hardware provides the highest security benefit with excellent image quality and unnoticeable local area communication security features. It has been demonstrated through implementation results that the single computing engine can operate at a maximum clock frequency of Fmax 170.97 MHz and achieve a throughput of 1.367 Mbps with the design single computing engine.
  • Publication
    Analysis of Dielectric Properties on Agricultural Waste for Microwave Communication Application
    ( 2017-12-11)
    Nurul Ain Zulkifli
    ;
    Wee Fwen Hoon
    ;
    Norfadila Mahrom
    ;
    Been Seok Yew
    ;
    Yeng Seng Lee
    ;
    Siti Zuraidah Ibrahim
    ;
    Anusha Leemsuthep Am Phan
    This paper presents the analysis of dielectric properties of agricultural waste for microwave communication application such as microwave absorber and antenna. The residues products - rice straw, rice husk, banana leaves and sugar cane bagasse were studied in the range between 1-20GHz. Firstly, the 2 types of resins namely Epoxy der 331 and Polyamine clear hardener were mixed with the agricultural waste materials to produce the small size of agricultural waste sample. Then, the sample were measured using PNA network analyzer. The permittivity and tangent loss of different agricultural waste samples have been measured using dielectric probe technique. Besides, other objectives of this paper is to replace the conventional printed circuit board (PCB) using FR4, Taconic, and Roger material with the agricultural waste material. Besides that, the different percentage of filer for each agricultural waste materials were also investigated to specify the best material to be used as the substrate board and as the resonant material. the result shows the average of dielectric constants and the average of the tangent loss of agricultural waste materials.
  • Publication
    Tuberculosis Classification Using Deep Learning and FPGA Inferencing
    ( 2023-02-01)
    Fazrul Faiz Zakaria
    ;
    Asral Bahari Jambek
    ;
    Norfadila Mahrom
    ;
    Rafikha Aliana A Raof
    ;
    Mohd Nazri Mohd Warip
    ;
    Al Eh Kan P.L.
    ;
    Mustapa M.
    Among the top 10 leading causes of mortality, tuberculosis (TB) is a chronic lung illness caused by a bacterial infection. Due to its efficiency and performance, using deep learning technology with FPGA as an accelerator has become a standard application in this work. However, considering the vast amount of data collected for medical diagnosis, the average inference speed is inadequate. In this scenario, the FPGA speeds the deep learning inference process enabling the real-time deployment of TB classification with low latency. This paper summarizes the findings of model deployment across various computing devices in inferencing deep learning technology with FPGA. The study includes model performance evaluation, throughput, and latency comparison with different batch sizes to the extent of expected delay for real-world deployment. The result concludes that FPGA is the most suitable to act as a deep learning inference accelerator with a high throughput-to-latency ratio and fast parallel inference. The FPGA inferencing demonstrated an increment of 21.8% in throughput while maintaining a 31% lower latency than GPU inferencing and 6x more energy efficiency. The proposed inferencing also delivered over 90% accuracy and selectivity to detect and localize the TB.
      2