Ghazal Bargshady

Dr. Ghazal Bargshady

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 July 2020 in Expert Systems with Applications
Verified
Journal Article
Closed access
Ghazal BargshadyGhazal Bargshady
Ghazal Bargshady
XZXujuan Zhou
Xujuan Zhou
Ravinesh DeoRavinesh Deo
Ravinesh Deo
JSJeffrey Soar
Jeffrey Soar
FWFrank Whittaker
Frank Whittaker
HWHua Wang
Hua Wang

1 August 2025 in ACM Transactions on Computing for Healthcare
Verified
Journal Article
Open access
Ghazal BargshadyGhazal Bargshady
Ghazal Bargshady
SASumair Aziz
Sumair Aziz
SGStefanos Gkikas
Stefanos Gkikas
Manolis TsiknakisManolis Tsiknakis
Manolis Tsiknakis
RGRoland Goecke
Roland Goecke
RRRaul Fernandez Rojas
Raul Fernandez Rojas
This study investigates the effectiveness of various machine learning and deep learning models for automated pain detection using functional near-infrared spectroscopy (fNIRS) data from the AI4Pain Grand Challenge dataset. Four different near-infrared spectroscopy metrics – oxygenated haemoglobin (HbO2), deoxygenated haemoglobin (HHb), total haemoglobin (HT), and haemoglobin difference (HbDiff) – were investigated to determine their contributions to pain assessment and identify which metric offers the most reliable performance. Across all models, both traditional and deep learning, HbDiff consistently outperformed the other metrics in terms of classification accuracy. The multi-kernel fully convolutional network hybrid with long short-term memory (MK-FCN-LSTM) model, particularly when utilising the HbDiff metric, achieved superior performance with a binary classification accuracy of 64.73%. These findings suggest that haemoglobin difference may provide more sensitive and reliable features for pain assessment, highlighting its potential as a key biomarker in fNIRS-based pain detection systems.

8 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
Ghazal BargshadyGhazal Bargshady
Ghazal Bargshady
HUHakki Gokalp Ustun
Hakki Gokalp Ustun
YBYasaman Baradaran
Yasaman Baradaran
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Ravinesh DeoRavinesh Deo
Ravinesh Deo
RRRaul Fernandez Rojas
Raul Fernandez Rojas
Driver distraction remains a critical factor in road accidents, necessitating intelligent systems for real-time detection. This study introduces a novel fNIRS-based method to to classify varying levels of driver distraction across diverse simulated scenarios, including cognitive, visual–manual, and auditory sources of inattention. Unlike previous work, we evaluated multiple neurophysiological metrics—including oxygenated, deoxygenated, and combined haemoglobin—to identify the most reliable biomarker for distraction detection. Neurophysiological data were collected, and three multi-class classifiers (SVM, KNN, decision tree) were applied across different fNIRS metrics. Our results show that oxygenated haemoglobin outperforms other signals in distinguishing distracted from non-distracted states, while the combined signal performs best in differentiating distraction from baseline. The proposed SVM model achieved ≈ 77.9% accuracy in detecting distracted and relaxed driving states based on brain oxygen levels. Our findings also show that increased distraction correlates with elevated activity in the dorsolateral prefrontal cortex and premotor cortex, whereas driving without distraction exhibits lower neurovascular engagement. This study contributes to affective computing and intelligent transportation systems and could support the development of future driver distraction monitoring systems for safer and more adaptive vehicle control.



9 August 2025 in Sensors
Verified
Journal Article
Open access
PDF file
MKMehshan Ahmed Khan
Mehshan Ahmed Khan
Houshyar AsadiHoushyar Asadi
Houshyar Asadi
Mohammad Reza Chalak QazaniMohammad Reza Chalak Qazani
Mohammad Reza Chalak Qazani
Ghazal BargshadyGhazal Bargshady
Ghazal Bargshady
SOSam Oladazimi
Sam Oladazimi
SNSaeid Nahavandi
Saeid Nahavandi
The shift from manual to conditionally automated driving, supported by Advanced Driving Assistance Systems (ADASs), introduces challenges, particularly increased crash risks due to human factors like cognitive overload. Driving simulators provide a safe and controlled setting to study these human factors under complex conditions. This study leverages Functional Near-Infrared Spectroscopy (fNIRS) to dynamically assess cognitive load in a realistic driving simulator during a challenging night-time-rain scenario. Thirty-eight participants performed an auditory n-back task (0-, 1-, and 2-back) while driving, simulating multitasking demands. A sliding window approach was applied to the time-series fNIRS data to capture short-term fluctuations in brain activation. The data were analyzed using EEGNet, a deep learning model, with both overlapping and non-overlapping temporal segmentation strategies. Results revealed that classification performance is significantly influenced by the learning rate and windowing method. Notably, a learning rate of 0.001 yielded the highest performance, with 100% accuracy using overlapping windows and 97% accuracy with non-overlapping windows. These findings highlight the potential of combining fNIRS and deep learning for real-time cognitive load monitoring in simulated driving scenarios and demonstrate the importance of temporal modeling in physiological signal analysis.