For each classification algorithm, the classification accuracies for binary subject groups NC versus EMCI, NC versus LEMC, EMCI versus LEMC, EMCI versus AD, LMCI versus AD, AD versus NC. by Qian Zhang (49333)

“…<p>For each classification algorithm, the classification accuracies for binary subject groups NC versus EMCI, NC versus LEMC, EMCI versus LEMC, EMCI versus AD, LMCI versus AD, AD versus NC.…”

The maximum accuracy (lowest error rate) with the least number of ANOVA-ranked genes achieved by different feature filtering methods and classification algorithms refined by SIRRFE under various classification tasks, including: the multiclass classification for distinguishing each individual PAH patient group (Control <i>vs</i>.... by Song Cui (553627)

“…<p>The maximum accuracy (lowest error rate) with the least number of ANOVA-ranked genes achieved by different feature filtering methods and classification algorithms refined by SIRRFE under various classification tasks, including: the multiclass classification for distinguishing each individual PAH patient group (Control <i>vs</i>. …”

Cognitive test and self-perceived health and social functioning presented for the low-moderate and high PA levels group. by Xin Zhang (35492)

Difference of overall MET values and variables derived from physical performance tests between low-moderate and high PA levels group. by Xin Zhang (35492)

A* Path-Finding Algorithm to Determine Cell Connections by Max Weng (22327159)

“…</p><p dir="ltr">Astrocytes were dissociated from E18 mouse cortical tissue, and image data were processed using a Cellpose 2.0 model to mask nuclei. Pixel paths were classified using a z-score brightness threshold of 1.21, optimized for noise reduction and accuracy. …”

The SHAP (Shapley Additive exPlanations) values of observed variables. by Xin Zhang (35492)

Partial dependence plots (A – G) and the resulting clustered feature importance (H) for each feature and trained model. by Daniel Walke (21680915)

“…In H), we hierarchically clustered (Euclidean distance with average linking) the feature importance resulting from the normalized variance in the partial dependence plots for each trained model. Tree-based algorithms (i.e., Decision Tree, Random Forest, XGBoost, and RUSBoost) are grouped together indicating similar underlying mechanisms for the classification. …”

Receiver operating curves for NLP classification. by Charlene Jennifer Ong (8997278)

“…These curves represent different combinations of text featurization (BOW, tf-idf, GloVe) and binary classification algorithms (Logistic Regression, k-NN, CART, OCT, OCT-H, RF, RNN). …”

Flowchart scheme of the ML-based model. by Noshaba Qasmi (20405009)

“…<b>I)</b> Testing data consisting of 20% of the entire dataset. <b>J)</b> Optimization of hyperparameter tuning. <b>K)</b> Algorithm selection from all models. …”

Data_Sheet_1_Multiclass Classification Based on Combined Motor Imageries.pdf by Cecilia Lindig-León (7889777)

“…In this way, for each binary problem, the CSP algorithm produces features to determine if the specific body part is engaged in the task or not. …”

Algoritmo de clasificación de expresiones de odio por tipos en español (Algorithm for classifying hate expressions by type in Spanish) by Daniel Pérez Palau (11097348)

“…</li></ul><p dir="ltr"><b>File Structure</b></p><p dir="ltr">The code generates and saves:</p><ul><li>Weights of the trained model (.h5)</li><li>Configured tokenizer</li><li>Training history in CSV</li><li>Requirements file</li></ul><p dir="ltr"><b>Important Notes</b></p><ul><li>The model excludes category 2 during training</li><li>Implements transfer learning from a pre-trained model for binary hate detection</li><li>Includes early stopping callbacks to prevent overfitting</li><li>Uses class weighting to handle category imbalances</li></ul><p dir="ltr">The process of creating this algorithm is explained in the technical report located at: Blanco-Valencia, X., De Gregorio-Vicente, O., Ruiz Iniesta, A., & Said-Hung, E. (2025). …”

Super.Complex identifies likely protein complexes within a PPI network using a distributed supervised AutoML method. by Meghana Venkata Palukuri (11890672)

Participants’ demographic characteristics. by Reihaneh Hassanzadeh (11986041)

“…We used confounder-controlled rs-FNC and applied machine learning algorithms (including support vector machine, logistic regression, random forest, and k-nearest neighbor) and deep learning models (i.e., fully-connected neural networks) to classify subjects in binary and three-class categories according to their diagnosis labels (e.g., AD, SZ, and CN). …”

Imaging parameters. by Reihaneh Hassanzadeh (11986041)

“…We used confounder-controlled rs-FNC and applied machine learning algorithms (including support vector machine, logistic regression, random forest, and k-nearest neighbor) and deep learning models (i.e., fully-connected neural networks) to classify subjects in binary and three-class categories according to their diagnosis labels (e.g., AD, SZ, and CN). …”

Supplementary Material for: Detecting atrial fibrillation by artificial intelligence enabled neuroimaging examination. by figshare admin karger (2628495)

“…We hypothesise that machine learning algorithm increases the accurate classification of MRIs of stroke patients into those due to AF vs large artery atherosclerosis. …”

PathOlOgics_RBCs Python Scripts.zip by Ahmed Elsafty (16943883)

“…</p><p dir="ltr">In terms of classification, a second algorithm was developed and employed to preliminary sort or group the individual cells (after excluding the overlapping cells manually) into different categories using five geometric measurements applied to the extracted contour from each binary image mask (see PathOlOgics_script_2; preliminary shape measurements). …”

DataSheet1_Comparison of Descriptor- and Fingerprint Sets in Machine Learning Models for ADME-Tox Targets.docx by Álmos Orosz (12828104)

“…The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. …”

Image1_Comparison of Descriptor- and Fingerprint Sets in Machine Learning Models for ADME-Tox Targets.TIF by Álmos Orosz (12828104)

“…The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. …”

DataSheet_2_MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation.pdf by Francesca Piludu (10706391)

“…The model with the final feature set was achieved using the support vector machine binary classification algorithm.</p>Results<p>Models for discriminating between Warthin’s and malignant tumors, benign and Warthin’s tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. …”

DataSheet_1_MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation.xlsx by Francesca Piludu (10706391)

“…The model with the final feature set was achieved using the support vector machine binary classification algorithm.</p>Results<p>Models for discriminating between Warthin’s and malignant tumors, benign and Warthin’s tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. …”