Nor Safira Elaina Mohd Noor

Mrs. Nor Safira Elaina Mohd Noor

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 September 2021 in IEEE Access
Verified
Journal Article
Open access
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim
MLMuhammad Hanif Che Lah
Muhammad Hanif Che Lah
Jafri Malin AbdullahJafri Malin Abdullah
Jafri Malin Abdullah
Reliable prediction of traumatic brain injury (TBI) outcomes based on machine learning (ML) that is derived from quantitative electroencephalography (EEG) features has renewed interest in recent years. Nevertheless, the approach has suffered from imbalanced datasets. Hence, to get a reliable predictive model for predicting outcomes, specifically in a high proportion of moderate TBI with good outcomes, could be challenging. This work proposes an improved outcome predictive model that combines the absolute power spectral density (PSD) as input features for training random under-sampling boosting decision trees (RUSBoosted Trees) as a classifier. Resting-state, eyes-closed EEG data were obtained from 27 moderate TBI patients with follow-up visits. Patient outcome at 4-10 weeks to 12-month was dichotomized based on the Glasgow Outcome Scale as poor (GOS score ≤ 4) and good outcomes (GOS score = 5). The predictive values of absolute PSD from five frequency bands: δ (0.5-4Hz), θ (4-7Hz), α (7-13Hz), β (13-30Hz) and γ (30-100Hz) were evaluated to identify the most informative predictors for reliable prediction outcomes. RUSBoosted Trees performed best at discriminating patients into two outcomes categories (G-Mean = 92.95%, TP rate = 100%, TN rate = 86.4%) of absolute PSD in δ and γ bands, which was excellent compared to the other state-of-the-art methods. The highest area under the curve (AUC) of absolute PSD in δ (AUC δ = 0.97) and γ (AUC γ = 0.95) revealed their predictive values as robust prognostic markers for prediction outcomes. The RUSBoosted Trees presents a promising result in prognosis prediction of highly imbalanced data, making it an accessible prediction tool for clinical decision-making, unlike the black-box approaches.

20 February 2023 in Computers
Verified
Journal Article
Open access
PDF file
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim
CLChi Qin Lai
Chi Qin Lai
Jafri Malin AbdullahJafri Malin Abdullah
Jafri Malin Abdullah
Although traumatic brain injury (TBI) is a global public health issue, not all injuries necessitate additional hospitalisation. Thinking, memory, attention, personality, and movement can all be negatively impacted by TBI. However, only a small proportion of nonsevere TBIs necessitate prolonged observation. Clinicians would benefit from an electroencephalography (EEG)-based computational intelligence model for outcome prediction by having access to an evidence-based analysis that would allow them to securely discharge patients who are at minimal risk of TBI-related mortality. Despite the increasing popularity of EEG-based deep learning research to create predictive models with breakthrough performance, particularly in epilepsy prediction, its use in clinical decision making for the diagnosis and prognosis of TBI has not been as widely exploited. Therefore, utilising 60s segments of unprocessed resting-state EEG data as input, we suggest a long short-term memory (LSTM) network that can distinguish between improved and unimproved outcomes in moderate TBI patients. Complex feature extraction and selection are avoided in this architecture. The experimental results show that, with a classification accuracy of 87.50 ± 0.05%, the proposed prognostic model outperforms three related works. The results suggest that the proposed methodology is an efficient and reliable strategy to assist clinicians in creating an automated tool for predicting treatment outcomes from EEG signals.

6 January 2022 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim
MLMuhammad Hanif Che Lah
Muhammad Hanif Che Lah
Jafri Malin AbdullahJafri Malin Abdullah
Jafri Malin Abdullah
The computational electroencephalogram (EEG) is recently garnering significant attention in examining whether the quantitative EEG (qEEG) features can be used as new predictors for the prediction of recovery in moderate traumatic brain injury (TBI). However, the brain’s recorded electrical activity has always been contaminated with artifacts, which in turn further impede the subsequent processing steps. As a result, it is crucial to devise a strategy for meticulously flagging and extracting clean EEG data to retrieve high-quality discriminative features for successful model development. This work proposed the use of multiple artifact rejection algorithms (MARA), which is an independent component analysis (ICA)-based algorithm, to eliminate artifacts automatically, and explored their effects on the predictive performance of the random undersampling boosting (RUSBoost) model. Continuous EEG were acquired using 64 electrodes from 27 moderate TBI patients at four weeks to one-year post-accident. The MARA incorporates an artifact removal stage based on ICA prior to RUSBoost, SVM, DT, and k-NN classification. The area under the curve (AUC) of RUSBoost was higher in absolute power spectral density (PSD) in AUCδ = 0.75, AUC α = 0.73 and AUCθ = 0.71 bands than SVM, DT, and k-NN. The MARA has provided a good generalization performance of the RUSBoost prediction model.

20 February 2026 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
CJChengcheng Jin
Chengcheng Jin
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
TNTheam Foo Ng
Theam Foo Ng
MAMohd Shahrimie Mohd Asaari
Mohd Shahrimie Mohd Asaari
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim

9 September 2025 in IEEE Access
Verified
Journal Article
Open access
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim
LQLai Chi Qin
Lai Chi Qin
JAJafri Malin Abdullah
Jafri Malin Abdullah
An electroencephalography (EEG)-based prognostic model for moderate traumatic brain injury (moTBI) overcomes the limitations of traditional clinical assessment. Although machine learning (ML) algorithms promise better results, existing frameworks often struggle to capture the complex temporal patterns in EEG data, resulting in poor prediction accuracy. This study addresses this gap by presenting a novel hybrid deep learning (DL) architecture of a prediction model that uses resting-state EEG data as input. This architecture synergistically combines bidirectional long short-term memory (BiLSTM) with adaptive boosting (AdaBoost), which enables accurate discrimination between poor and good prognosis of moTBI. The BiLSTM component extracts complex features from the EEG signals, while AdaBoost serves as a classifier discriminator, replacing the conventional softmax function to optimize performance. Experimental results show that the BiLSTM-AdaBoost model achieves impressive under the curve (AUC) performance of 99.51 ± 1.36% and 98.91 ± 2.47% for preprocessed and 98.91 ± 2.47% for unprocessed EEG sequences. Notably, the model outperforms conventional DL architectures and other hybrid models, showing improvements of up to 14.14% over DL-only models and 24.51% over traditional ML approaches. This innovative architecture of the BiLSTM-AdaBoost model represents a significant advance in EEG-based decision support systems for moTBI and rapid assessment of a potentially overlooked poor prognosis.

2 June 2026 in IEEE Access
Verified
Journal Article
Open access
CJChengcheng Jin
Chengcheng Jin
NNNor Safira Elaina Mohd Noor
Nor Safira Elaina Mohd Noor
Haidi IbrahimHaidi Ibrahim
Haidi Ibrahim
Accurate brain tumor segmentation in magnetic resonance imaging (MRI) is crucial for clinical diagnosis and treatment planning. Deep learning-based glioma segmentation can assist doctors in making more informed decisions. Some segmentation models are computationally intensive and memory-heavy, making them impractical for real-time deployment in resource-constrained environments. To further realize the clinical potential of these models, it is essential to ensure both high segmentation accuracy and lightweight design for efficient operations. However, these two goals are usually difficult to achieve simultaneously. Therefore, this paper proposes a Dynamic Mamba U-Net (DM-UNet) model, based on Mamba, fully leveraging the linear computational complexity of the Mamba architecture. Considering the morphological variability of brain tumors, both axial and coronal scan results are utilized, and a dynamic Mamba mechanism is designed. To capture shallow features, channel attention and dynamic Mamba are employed in a parallel manner. Partial convolution is integrated into multi-scale convolutional layers to obtain more detailed tumor features. With these approaches, the number of model parameters is reduced to less than 0.1M, the model size is merely 0.36M, and the computational cost is 14.96G FLOPs. We conduct 5-fold cross-validation on BraTS2023, obtaining an average Dice of 89.60% and an HD of 4.11 mm. The performance is superior to other advanced glioma segmentation models, providing further support for the deployment of lightweight models on edge devices.