Mahathir Almashor

Mahathir Almashor

Auto-generated profile, based on publicly available information

Mahathir Almashor

CSIRO Energy, Australia

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 April 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
AKAditya Pribadi Kalapaaking
Aditya Pribadi Kalapaaking
IKIbrahim Khalil
Ibrahim Khalil
MRMohammad Saidur Rahman
Mohammad Saidur Rahman
MAMohammed Atiquzzaman
Mohammed Atiquzzaman
XYXun Yi
Xun Yi
MAMahathir Almashor
Mahathir Almashor
This article proposes a blockchain-based federated learning (FL) framework with Intel Software Guard Extension (SGX)-based trusted execution environment (TEE) to securely aggregate local models in Industrial Internet-of-Things (IIoTs). In FL, local models can be tampered with by attackers. Hence, a global model generated from the tampered local models can be erroneous. Therefore, the proposed framework leverages a blockchain network for secure model aggregation. Each blockchain node hosts an SGX-enabled processor that securely performs the FL-based aggregation tasks to generate a global model. Blockchain nodes can verify the authenticity of the aggregated model, run a blockchain consensus mechanism to ensure the integrity of the model, and add it to the distributed ledger for tamper-proof storage. Each cluster can obtain the aggregated model from the blockchain and verify its integrity before using it. We conducted several experiments with different CNN models and datasets to evaluate the performance of the proposed framework.

1 January 2016 in Simulation Modelling Practice and Theory
Verified
Journal Article
Closed access
ABAnton Beloglazov
Anton Beloglazov
MAMahathir Almashor
Mahathir Almashor
EAErmyas Abebe
Ermyas Abebe
JRJan Richter
Jan Richter
KSKent Charles Barton Steer
Kent Charles Barton Steer

27 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
CTChandra Thapa
Chandra Thapa
JTJun Wen Tang
Jun Wen Tang
SASharif Abuadbba
Sharif Abuadbba
YGYansong Gao
Yansong Gao
Seyit A. CamtepeSeyit A. Camtepe
Seyit A. Camtepe
YZYifeng Zheng
Yifeng Zheng
The use of artificial intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which has opened it up to a myriad of privacy, trust, and legal issues. Moreover, organizations have been loath to share emails, given the risk of leaking commercially sensitive information. Consequently, it has been difficult to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly federated learning (FL), is a desideratum. As it is already prevalent in the healthcare sector, questions remain regarding the effectiveness and efficacy of FL-based phishing detection within the context of multi-organization collaborations. To the best of our knowledge, the work herein was the first to investigate the use of FL in phishing email detection. This study focused on building upon a deep neural network model, particularly recurrent convolutional neural network (RNN) and bidirectional encoder representations from transformers (BERT), for phishing email detection. We analyzed the FL-entangled learning performance in various settings, including (i) a balanced and asymmetrical data distribution among organizations and (ii) scalability. Our results corroborated the comparable performance statistics of FL in phishing email detection to centralized learning for balanced datasets and low organizational counts. Moreover, we observed a variation in performance when increasing the organizational counts. For a fixed total email dataset, the global RNN-based model had a 1.8% accuracy decrease when the organizational counts were increased from 2 to 10. In contrast, BERT accuracy increased by 0.6% when increasing organizational counts from 2 to 5. However, if we increased the overall email dataset by introducing new organizations in the FL framework, the organizational level performance improved by achieving a faster convergence speed. In addition, FL suffered in its overall global model performance due to highly unstable outputs if the email dataset distribution was highly asymmetric.

13 August 2019 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
CWchunwu wang
chunwu wang
BGBijay Guragain
Bijay Guragain
AVAjay K. Verma
Ajay K. Verma
LALewis Archer
Lewis Archer
SMShubha Majumder
Shubha Majumder
KTKouhyar Tavakolian
Kouhyar Tavakolian
Drowsiness detection has a significant importance in aviation industry. Electroencephalogram (EEG) has been extensively studied to characterize drowsiness, nevertheless, its behavior with respect to accurately annotated drowsy periods remains to be investigated. At present, Karolinska Sleepiness Scale (KSS) and Psychomotor Vigilance Task (PVT) are widely used references for subjective drowsiness analysis. However, their practical application in real time monitoring of alertness is limited. To address this limitation, we combined Seeing Machines Driver Monitoring System (DMS) and electrooculogram (EOG) for localization of microsleep (MS) events and studied EEG spectral behavior during MS events. EEG, EOG, and facial behavior data were recorded simultaneously from sixteen commercially-rated pilots during simulated flight. Relative spectral power in delta (0.5-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) in frontal, central, temporal, parietal, and occipital brain regions were analyzed. Compared to baseline, delta power reduced during MS (p<0.05 in all regions), alpha power increased during MS (p0.05). The research findings highlight the capability of EEG delta and alpha spectrum towards characterizing MS events, therefore, with consideration to user acceptability, application towards drowsiness detection is plausible via EEG electrodes embedded in the typical aviation headset.

1 December 2017 in Fire Safety Journal
Verified
Journal Article
Closed access
KSKent Steer
Kent Steer
EAErmyas Abebe
Ermyas Abebe
MAMahathir Almashor
Mahathir Almashor
ABAnton Beloglazov
Anton Beloglazov
XZXu Zhong
Xu Zhong

1 August 2015 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
MAMahathir Almashor
Mahathir Almashor
IKIbrahim Khalil
Ibrahim Khalil
ZTZahir Tari
Zahir Tari
Albert ZomayaAlbert Zomaya
Albert Zomaya
SSSartaj Sahni
Sartaj Sahni
Ensuring high data availability is a vital prerogative for Content Delivery Networks (CDN), and as we look to deploy CDN mechanisms onto mobile platforms, this imperative becomes ever more challenging. In traditional CDNs, replication ensures high availability of data, with server-loads and content-popularity often used as parameters to tightly control the process. However, the highly transient properties of such wireless and mobile devices constitute a major hurdle for any replication algorithm, rendering most simplified methods inadequate. Our contribution begins with a unique message-pulsing mechanism operating within a wireless cluster, that detects devices and ascertains their reliability. Results show the viability of our pulsing algorithm in determining a base replication level. Next, a Markovian queueing model is introduced, allowing us to induce replication based on the required speed of service. This affords finer control over the replication process, creating a more effective replication strategy suited for mobile-based CDNs. Extensive analysis of the model were performed, with parameters derived from real-world conditions. Results indicate that the model is able to compute logical values for the expected waiting times in service and thus, control the speed of replication within the CDN.