Displaying all 3 publications

Abstract:
Sort:
  1. Fulltext 3D texture-based face recognition system using fine-tuned deep residual networks
    Zheng S, Rahmat RWO, Khalid F, Nasharuddin NA
    PeerJ Comput Sci, 2019;5:e236.
    PMID: 33816889 DOI: 10.7717/peerj-cs.236
    As the technology for 3D photography has developed rapidly in recent years, an enormous amount of 3D images has been produced, one of the directions of research for which is face recognition. Improving the accuracy of a number of data is crucial in 3D face recognition problems. Traditional machine learning methods can be used to recognize 3D faces, but the face recognition rate has declined rapidly with the increasing number of 3D images. As a result, classifying large amounts of 3D image data is time-consuming, expensive, and inefficient. The deep learning methods have become the focus of attention in the 3D face recognition research. In our experiment, the end-to-end face recognition system based on 3D face texture is proposed, combining the geometric invariants, histogram of oriented gradients and the fine-tuned residual neural networks. The research shows that when the performance is evaluated by the FRGC-v2 dataset, as the fine-tuned ResNet deep neural network layers are increased, the best Top-1 accuracy is up to 98.26% and the Top-2 accuracy is 99.40%. The framework proposed costs less iterations than traditional methods. The analysis suggests that a large number of 3D face data by the proposed recognition framework could significantly improve recognition decisions in realistic 3D face scenarios.
  2. Fulltext Prioritising topics for developing e-learning resources in healthcare curricula: A comparison between students and educators using a modified Delphi survey
    Lim HM, Ng CJ, Teo CH, Lee PY, Kassim PSJ, Nasharuddin NA, et al.
    PLoS One, 2021;16(6):e0253471.
    PMID: 34166432 DOI: 10.1371/journal.pone.0253471
    BACKGROUND: Engaging students in the e-learning development process enhances the effective implementation of e-learning, however, students' priority on the topics for e-learning may differ from that of the educators. This study aims to compare the differences between the students and their educators in prioritising the topics in three healthcare curricula for reusable e-learning object (RLO) development.

    METHOD: A modified Delphi study was conducted among students and educators from University Malaya (UM), Universiti Putra Malaysia (UPM) and Taylor's University (TU) on three undergraduate programmes. In Round 1, participants were asked to select the topics from the respective syllabi to be developed into RLOs. Priority ranking was determined by using frequencies and proportions. The first quartile of the prioritised topics was included in Round 2 survey, which the participants were asked to rate the level of priority of each topic using a 5-point Likert scale. The mean score of the topics was compared between students and educators.

    RESULT: A total of 43 educators and 377 students participated in this study. For UM and TU Pharmacy, there was a mismatch in the prioritised topics between the students and educators. For UPM, both the educators and students have prioritised the same topics in both rounds. To harmonise the prioritisation of topics between students and educators for UM and TU Pharmacy, the topics with a higher mean score by both the students and educators were prioritised.

    CONCLUSION: The mismatch in prioritised topics between students and educators uncovered factors that might influence the prioritisation process. This study highlighted the importance of conducting needs assessment at the beginning of eLearning resources development.

  3. Fulltext Knowledge transfer of eLearning objects: Lessons learned from an intercontinental capacity building project
    Lim HM, Ng CJ, Wharrad H, Lee YK, Teo CH, Lee PY, et al.
    PLoS One, 2022;17(9):e0274771.
    PMID: 36126036 DOI: 10.1371/journal.pone.0274771
    BACKGROUND: Effective knowledge transfer of eLearning objects can hasten the adoption and dissemination of technology in teaching and learning. However, challenges exist which hinder inter-organisational knowledge transfer, particularly across continents. The ACoRD project aimed to transfer knowledge on digital learning development from UK/EU (provider) to Malaysian (receiver) higher education institutions (HEIs). This study explores the challenges encountered during the knowledge transfer process and lessons learned.

    METHODS: This is a qualitative study involving both the knowledge providers and receivers in focus group discussions (n = 25). Four focus group discussions were conducted in the early (n = 2) and mid-phase (n = 2) of the project by trained qualitative researchers using a topic guide designed to explore experiences and activities representing knowledge transfer in multi-institutional and multi-cultural settings. The interviews were audio-recorded, transcribed verbatim, and checked. The transcripts were analysed using thematic analysis.

    RESULTS: Five main themes emerged from this qualitative study: mismatched expectations between providers and receivers; acquiring new knowledge beyond the professional "comfort zone"; challenges in cascading newly acquired knowledge to colleagues and management; individual and organisational cultural differences; and disruption of knowledge transfer during the COVID-19 pandemic.

    CONCLUSION: This study highlights the need to create a conducive platform to facilitate continuous, timely and bi-directional needs assessment and feedback; this should be done in the early phase of the knowledge transfer process. The challenges and strategies identified in this study could guide more effective knowledge transfer between organisations and countries.

Related Terms
    Try searching for something
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links