The architecture of the BI-LSTM model. by Arshad Hashmi (13835488)

“…The model’s binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. …”

Comparison of accuracy and DR on UNSW-NB15. by Arshad Hashmi (13835488)

“…The model’s binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. …”

Comparison of DR and FPR of UNSW-NB15. by Arshad Hashmi (13835488)

“…The model’s binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. …”

Table_1_Near infrared spectroscopy for cooking time classification of cassava genotypes.docx by Massaine Bandeira e Sousa (7866242)

“…Two NIRs devices, the portable QualitySpec® Trek (QST) and the benchtop NIRFlex N-500 were used to collect spectral data. Classification of genotypes was carried out using the K-nearest neighbor algorithm (KNN) and partial least squares (PLS) models. …”

Data Sheet 1_Detection of litchi fruit maturity states based on unmanned aerial vehicle remote sensing and improved YOLOv8 model.docx by Changjiang Liang (21099887)

Models and Dataset by M RN (9866504)

“…Its simplicity and lack of algorithm-specific parameters make it computationally efficient and easy to apply in high-dimensional problems such as gene selection for cancer classification.…”

Supplementary Material 8 by Nishitha R Kumar (19750617)

“…</li><li><b>Radial basis function kernel-support vector machine (RBF-SVM): </b>A more flexible version of SVM that uses a non-linear kernel to capture complex relationships in genomic data, improving classification accuracy.</li><li><b>Extra trees classifier: </b>This tree-based ensemble method enhances classification by randomly selecting features and thresholds, improving robustness in <i>E. coli</i> strain differentiation.…”

iNCog-EEG (ideal vs. Noisy Cognitive EEG for Workload Assessment) Dataset by Fariya Bintay Shafi (21692408)

“…Inside each folder, four <b>.EDF</b> files represent the workload conditions:</p><pre><pre>subxx_nw.EDF → No Workload (resting state) <br>subxx_lw.EDF → Low Workload (easy multitasking) <br>subxx_mw.EDF → Moderate Workload (medium multitasking) <br>subxx_hw.EDF → High Workload (hard multitasking) <br></pre></pre><ul><li><b>Subjects 01–30:</b> Clean EEG recordings</li><li><b>Subjects 31–40:</b> Noisy EEG recordings with real-world artifacts</li></ul><p dir="ltr">This structure ensures straightforward differentiation between clean vs. noisy data and across workload levels.</p><h3>Applications</h3><p dir="ltr">This dataset can be applied to a wide range of research areas, including:</p><ul><li>EEG signal denoising and artifact rejection</li><li>Binary and hierarchical <b>cognitive workload classification</b></li><li>Development of <b>robust Brain–Computer Interfaces (BCIs)</b></li><li>Benchmarking algorithms under <b>ideal and noisy conditions</b></li><li>Multitasking and mental workload assessment in <b>real-world scenarios</b></li></ul><p dir="ltr">By combining controlled multitasking protocols with deliberately introduced environmental noise, <b>iNCog-EEG provides a comprehensive benchmark</b> for advancing EEG-based workload recognition systems in both clean and challenging conditions.…”

Image_1_Validation of miRNA signatures for ovarian cancer earlier detection in the pre-diagnosis setting using machine learning approaches.pdf by Konrad Stawiski (4753380)

“…We employed the extreme gradient boosting (XGBoost) algorithm to train a binary classification model using 70% of the available data, while the model was tested on the remaining 30% of the dataset.…”