Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for binary... by Amin Ullah (12015113)

The workflow diagram for the gene expression biomarker study which involve using principal component analysis (PCA) to reduce the number of features (principal components), thus re... by Aninda Astuti (21736334)

The Pseudo-Code of the IRBMO Algorithm. by Chenyi Zhu (9383370)

“…To adapt to the feature selection problem, we convert the continuous optimization algorithm to binary form via transfer function, which further enhances the applicability of the algorithm. …”

EvoImp’s GA structure example. by Antonio Fernando Lavareda Jacob Junior (17816730)

IRBMO vs. meta-heuristic algorithms boxplot. by Chenyi Zhu (9383370)

“…To adapt to the feature selection problem, we convert the continuous optimization algorithm to binary form via transfer function, which further enhances the applicability of the algorithm. …”

IRBMO vs. feature selection algorithm boxplot. by Chenyi Zhu (9383370)

“…To adapt to the feature selection problem, we convert the continuous optimization algorithm to binary form via transfer function, which further enhances the applicability of the algorithm. …”

Neyman-Pearson Multi-Class Classification via Cost-Sensitive Learning by Ye Tian (220278)

“…We extend the concept of NP oracle inequalities, crucial in binary classifications, to NP oracle properties in the multi-class context. …”

ROC curves of our out-of-class algorithm (blue) and a threshold decision boundary (red) representing the true positive rates (TPR) compared to the false positive rates (FPR) for te... by G. Christopher Marais (21492084)

Hierarchical Neyman-Pearson Classification for Prioritizing Severe Disease Categories in COVID-19 Patient Data by Lijia Wang (314011)

Passive sensing data. by Thierry Jean (20691795)

“…We trained 120 machine learning models to forecast 10 mental states (e.g., Calm, Depressed, Seeing things) from passive sensor data on 2 predictive tasks (ordinal regression, binary classification) with 2 learning algorithms (XGBoost, LSTM) over 3 forecast horizons (same day, next day, next week). …”

Secure MANET routing with blockchain-enhanced latent encoder coupled GANs and BEPO optimization by Sandeep Jagonda Patil (22048337)

“…The performance of the proposed LEGAN-BEPO-BCMANET technique attains 29.786%, 19.25%, 22.93%, 27.21%, 31.02%, 26.91%, and 25.61% greater throughput, compared to existing methods like Blockchain-based BATMAN protocol utilizing MANET with an ensemble algorithm (BATMAN-MANET), Block chain-based trusted distributed routing scheme with optimized dropout ensemble extreme learning neural network in MANET (DEELNN-MANET), A secured trusted routing utilizing structure of a new directed acyclic graph-blockchain in MANET internet of things environment (DAG-MANET), An Optimized Link State Routing Protocol with Blockchain Framework for Efficient Video-Packet Transmission and Security over MANET (OLSRP-MANET), Auto-metric Graph Neural Network based Blockchain Technology for Protected Dynamic Optimum Routing in MANET (AGNN-MANET) and Data security-based routing in MANETs under key management process (DSR-MANET) respectively.…”

Timeline of a single trial for dataset 1. by Rabia Avais Khan (16955056)

“…So in this study, a novel framework has been proposed to classify the binary-class electroencephalogram (EEG) data. The proposed framework is tested on BCI Competition IV dataset 1 and BCI Competition III dataset 4a. …”

Block diagram of proposed methodology. by Rabia Avais Khan (16955056)

“…So in this study, a novel framework has been proposed to classify the binary-class electroencephalogram (EEG) data. The proposed framework is tested on BCI Competition IV dataset 1 and BCI Competition III dataset 4a. …”

Timeline of a single trial for dataset 2. by Rabia Avais Khan (16955056)

“…So in this study, a novel framework has been proposed to classify the binary-class electroencephalogram (EEG) data. The proposed framework is tested on BCI Competition IV dataset 1 and BCI Competition III dataset 4a. …”

LITNET-2020 data splitting approach. by Asmaa Ahmed Awad (16726315)

DataSheet_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. …”

Flow diagram of the proposed model. by Uğur Ejder (22683228)

“…Clinical, demographic, and supplement variables were preprocessed into 21 predictors. Four algorithms (K-Nearest Neighbors, Classification and Regression Tree, Support Vector Machine, and Random Forest) were implemented alongside their LR–ABC hybrid counterparts. …”

Reproducing kernel-based semiparametric functional smoothed score estimation with binary responses by Meichen Liu (8168148)

Data_Sheet_1_Crystal Structure Prediction of Binary Alloys via Deep Potential.PDF by Haidi Wang (9694004)

Ordinal regression predictions. by Thierry Jean (20691795)