Journal: Scientific Reports

Article Title: A spatially aware global and local perspective approach for few-shot incremental learning

doi: 10.1038/s41598-025-08323-5

Figure Lengend Snippet: The spatial-aware global perspective enhances the feature representation of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\textbf{X}_{i}^{ext}$$\end{document} and riches the semantic information by weighting pixel features in a global scope. “Conv” is the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1\times 1$$\end{document} convolution network. \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\oplus$$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\otimes$$\end{document} denote the multiplication and addition operations, respectively.

Article Snippet: As discussed in Section , SALP assumes that adjacent pixels convey similar semantic information and applies the simple Gaussian filtering operator \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {G(\cdot )}$$\end{document} to smooth local features.

Techniques:

Journal: Scientific Reports

Article Title: Machine learning-based real-time anomaly detection using data pre-processing in the telemetry of server farms

doi: 10.1038/s41598-024-72982-z

Figure Lengend Snippet: AnDePeD Pro additional notations.

Article Snippet: We compare our new methods, AnDePeD and AnDePeD Pro, with state-of-the-art anomaly detection algorithms (Bayesian Changepoint , Windowed Gaussian , Relative Entropy , KNN CAD , Earthgecko Skyline , the Alter- \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\hbox {Re}^2$$\end{document} algorithm and AREP ) on traditional metrics (Precision, Recall, F-score and adjusted MCC).

Techniques:

Journal: Scientific Reports

Article Title: Machine learning-based real-time anomaly detection using data pre-processing in the telemetry of server farms

doi: 10.1038/s41598-024-72982-z

Figure Lengend Snippet: Parameter settings for AnDePeD and AnDePeD Pro.

Article Snippet: We compare our new methods, AnDePeD and AnDePeD Pro, with state-of-the-art anomaly detection algorithms (Bayesian Changepoint , Windowed Gaussian , Relative Entropy , KNN CAD , Earthgecko Skyline , the Alter- \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\hbox {Re}^2$$\end{document} algorithm and AREP ) on traditional metrics (Precision, Recall, F-score and adjusted MCC).

Techniques:

Journal: Scientific Reports

Article Title: Machine learning-based real-time anomaly detection using data pre-processing in the telemetry of server farms

doi: 10.1038/s41598-024-72982-z

Figure Lengend Snippet: Computational complexity of algorithms tested by the number of past data points - \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n_\text {p}$$\end{document} .

Article Snippet: We compare our new methods, AnDePeD and AnDePeD Pro, with state-of-the-art anomaly detection algorithms (Bayesian Changepoint , Windowed Gaussian , Relative Entropy , KNN CAD , Earthgecko Skyline , the Alter- \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\hbox {Re}^2$$\end{document} algorithm and AREP ) on traditional metrics (Precision, Recall, F-score and adjusted MCC).

Techniques: Targeted Proteomics