Journal: BMC Genomics

Article Title: ML-DSP: Machine Learning with Digital Signal Processing for ultrafast, accurate, and scalable genome classification at all taxonomic levels

doi: 10.1186/s12864-019-5571-y

Figure Lengend Snippet: Average classification accuracies for 13 numerical representations. Averages over the six classifiers are in bold

Article Snippet: In this paper we used the Linear discriminant, Linear SVM, Quadratic SVM, Fine KNN, Subspace discriminant and Subspace KNN classifiers from the Classification Learner application of MATLAB (Statistics and Machine Learning Toolbox).

Techniques:

Journal: Journal of Clinical Medicine

Article Title: Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

doi: 10.3390/jcm10225330

Figure Lengend Snippet: All tested classifiers ranked in terms of accuracy (%).

Article Snippet: In detail: Optimizable KNN (k-nearest neighbor classifier), via the “fitcknn” function ( https://it.mathworks.com/help/stats/fitcknn.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features; Optimizable SVM (support vector machine classifier), via the “fitcsvm” function ( https://it.mathworks.com/help/stats/fitcsvm.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features.

Techniques: Plasmid Preparation

Journal: Journal of Clinical Medicine

Article Title: Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

doi: 10.3390/jcm10225330

Figure Lengend Snippet: Performance of the trained optimizable k-nearest neighbor (KNN) classifier. ( a ) Confusion matrix showing the true and predicted classes of the ToF patients’ videos. The blue diagonal is related to the number of videos that were truly recognized (Predicted Class = True Class), whereas the pink antidiagonal is related to the number of videos that were falsely recognized (Predicted Class ≠ True Class). ( b ) Same as ( a ) with the True Positive Rate (TPR) in blue and the False Negative Rate (FNR) in pink.

Article Snippet: In detail: Optimizable KNN (k-nearest neighbor classifier), via the “fitcknn” function ( https://it.mathworks.com/help/stats/fitcknn.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features; Optimizable SVM (support vector machine classifier), via the “fitcsvm” function ( https://it.mathworks.com/help/stats/fitcsvm.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features.

Techniques:

Journal: Journal of Clinical Medicine

Article Title: Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

doi: 10.3390/jcm10225330

Figure Lengend Snippet: Performance of the trained optimizable support vector machine (SVM) classifier. ( a ) Confusion matrix showing the true and predicted classes of the ToF patients’ videos. The blue diagonal is related to the number of videos that were truly recognized (Predicted Class = True Class), whereas the pink antidiagonal is related to the number of videos that were falsely recognized (Predicted Class ≠ True Class). ( b ) Same as ( a ) the True Positive Rate (TPR) in blue and the False Negative Rate (FNR) in pink.

Article Snippet: In detail: Optimizable KNN (k-nearest neighbor classifier), via the “fitcknn” function ( https://it.mathworks.com/help/stats/fitcknn.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features; Optimizable SVM (support vector machine classifier), via the “fitcsvm” function ( https://it.mathworks.com/help/stats/fitcsvm.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features.

Techniques: Plasmid Preparation

Journal: Journal of Clinical Medicine

Article Title: Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

doi: 10.3390/jcm10225330

Figure Lengend Snippet: Optimization of the k-nearest neighbor (KNN) classifier. ( a ) The classifier was optimized over 100 iterations via the minimization of the classification error and its optimized hyperparameters are reported as “Optimization Results”. In detail, for each iteration of the optimization, the classifier was also 10-fold cross-validated. ( b ) Receiver Operating Characteristic (ROC) curve with the area under the curve (AUC) painted in blue; a value of AUC close to 1 means a very low classification error for the optimized classifier.

Article Snippet: In detail: Optimizable KNN (k-nearest neighbor classifier), via the “fitcknn” function ( https://it.mathworks.com/help/stats/fitcknn.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features; Optimizable SVM (support vector machine classifier), via the “fitcsvm” function ( https://it.mathworks.com/help/stats/fitcsvm.html , accessed on 1 August 2021) with a total of 100 optimization iterations and no standardization of the input features.

Techniques:

Journal:

Article Title: Validation of the Riboleukogram to Detect Ventilator-Associated Pneumonia After Severe Injury

doi: 10.1097/SLA.0b013e3181b8fbd5

Figure Lengend Snippet: Models Used to Test the Predictive (Diagnostic) Potential of 85 Leukocyte Genes *

Article Snippet: K-Nearest Neighbor (SAS).

Techniques: Diagnostic Assay, Plasmid Preparation

Journal: Current Biology

Article Title: Transdiagnostic Brain Mapping in Developmental Disorders

doi: 10.1016/j.cub.2020.01.078

Figure Lengend Snippet:

Article Snippet: K nearest-neighbor algorithm , MATLAB 2015a , Knnimpute function.

Techniques: Software