ORCID Profile
0000-0001-7542-8990
Current Organisation
University of Malaya
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: MDPI AG
Date: 06-09-2019
DOI: 10.3390/A12090186
Abstract: The aim of manifold learning is to extract low-dimensional manifolds from high-dimensional data. Manifold alignment is a variant of manifold learning that uses two or more datasets that are assumed to represent different high-dimensional representations of the same underlying manifold. Manifold alignment can be successful in detecting latent manifolds in cases where one version of the data alone is not sufficient to extract and establish a stable low-dimensional representation. The present study proposes a parallel deep autoencoder neural network architecture for manifold alignment and conducts a series of experiments using a protein-folding benchmark dataset and a suite of new datasets generated by simulating double-pendulum dynamics with underlying manifolds of dimensions 2, 3 and 4. The dimensionality and topological complexity of these latent manifolds are above those occurring in most previous studies. Our experimental results demonstrate that the parallel deep autoencoder performs in most cases better than the tested traditional methods of semi-supervised manifold alignment. We also show that the parallel deep autoencoder can process datasets of different input domains by aligning the manifolds extracted from kinematics parameters with those obtained from corresponding image data.
Publisher: Elsevier BV
Date: 04-2015
Publisher: Cold Spring Harbor Laboratory
Date: 31-07-2021
DOI: 10.1101/2021.07.28.21261299
Abstract: Approximately 40% of late-life dementia may be prevented by addressing modifiable risk factors, including physical activity and diet. Yet, it is currently unknown how multiple lifestyle factors interact to influence cognition. The ACTIVate Study aims to 1) Explore associations between 24-hour time-use and diet compositions with changes in cognition and brain function and 2) Identify durations of time-use behaviours and the dietary compositions to optimise cognition and brain function. This three-year prospective longitudinal cohort study will recruit 448 adults aged 60-70 years across Adelaide and Newcastle, Australia. Time-use data will be collected through wrist-worn activity monitors and the Multimedia Activity Recall for Children and Adults (MARCA). Dietary intake will be assessed using the Australian Eating Survey food frequency questionnaire. The primary outcome will be cognitive function, assessed using the Addenbrooke’s Cognitive Examination-III (ACE-III). Secondary outcomes include structural and functional brain measures using Magnetic Resonance Imaging (MRI), cerebral arterial pulse measured with Diffuse Optical Tomography (Pulse-DOT), neuroplasticity using simultaneous Transcranial Magnetic Stimulation (TMS) and Electroencephalography (EEG), and electrophysiological markers of cognitive control using event-related potential (ERP) and time-frequency analyses. Compositional data analysis, testing for interactions between time-point and compositions, will assess longitudinal associations between dependent (cognition, brain function) and independent (time-use and diet compositions) variables. The ACTIVate Study will be the first to examine associations between time-use and diet compositions, cognition and brain function. Our findings will inform new avenues for multidomain interventions that may more effectively account for the co-dependence between activity and diet behaviours for dementia prevention. Ethics approval has been obtained from University of South Australia’s Human Research Ethics committee (202639). Findings will be disseminated through peer reviewed manuscripts, conference presentations, targeted media releases and community engagement events. Australia New Zealand Clinical Trials Registry (ACTRN12619001659190). The ACTIVate Study will collect comprehensive measures of lifestyle behaviours and dementia risk over time in 448 older adults aged 60-70 years. Using newly developed Compositional Data Analysis (CoDA) techniques we will examine the associations between time-use and diet compositions, cognition and brain function. Data will inform the development of a digital tool to help older adults obtain personalised information about how to reduce their risk of cognitive decline based on changes to time use and diet. Recruitment will be focussed on older adults to maximise the potential of making an impact on dementia prevention in the next 10 years. Findings may not be generalisable to younger adults.
Publisher: Public Library of Science (PLoS)
Date: 29-08-2018
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 07-2019
Publisher: IOP Publishing
Date: 04-09-2014
DOI: 10.1088/1741-2560/11/5/056018
Abstract: This paper presents a wheelchair navigation system based on a hidden Markov model (HMM), which we developed to assist those with restricted mobility. The semi-autonomous system is equipped with obstacle/collision avoidance sensors and it takes the electrooculography (EOG) signal traces from the user as commands to maneuver the wheelchair. The EOG traces originate from eyeball and eyelid movements and they are embedded in EEG signals collected from the scalp of the user at three different locations. Features extracted from the EOG traces are used to determine whether the eyes are open or closed, and whether the eyes are gazing to the right, center, or left. These features are utilized as inputs to a few support vector machine (SVM) classifiers, whose outputs are regarded as observations to an HMM. The HMM determines the state of the system and generates commands for navigating the wheelchair accordingly. The use of simple features and the implementation of a sliding window that captures important signatures in the EOG traces result in a fast execution time and high classification rates. The wheelchair is equipped with a proximity sensor and it can move forward and backward in three directions. The asynchronous system achieved an average classification rate of 98% when tested with online data while its average execution time was less than 1 s. It was also tested in a navigation experiment where all of the participants managed to complete the tasks successfully without collisions.
Location: Bangladesh
No related grants have been discovered for Md. Fayeem Bin Aziz.