Add Theoretical Foundation #78

2025-05-22T20:10:42Z

meowndor commented

2025-05-22 20:10:42 +00:00

(Migrated from github.com)

This pull request introduces significant updates to the literature review and theoretical foundation sections of a LaTeX document. The changes include detailed discussions on structural health monitoring (SHM) techniques, enhancements to the theoretical foundation with new subsections, and the addition of specific algorithms and methods used in the study. Below are the most important changes grouped by theme:

Literature Review Enhancements:

Replaced a placeholder input with a comprehensive discussion on traditional SHM methods and their limitations, including the introduction of CNN-based and machine-learning-based approaches for damage detection. This includes detailed case studies from \textcite{abdeljaber2017}, \textcite{eraliev2022}, and others.

Theoretical Foundation Additions:

Added a subsection on Hann window, explaining its mathematical formulation, advantages in reducing spectral leakage, and its suitability for STFT applications.
Expanded the Short-Time Fourier Transform (STFT) subsection to include its mathematical basis, use in time-frequency analysis, and its application in the study for extracting vibration signal features.
Introduced a new subsection on the role of Windowing functions in signal processing, emphasizing their importance in minimizing spectral leakage and improving time-frequency representation accuracy.

Machine Learning Algorithms:

Reorganized and expanded the machine learning section into a detailed discussion of seven classification algorithms, including SVM, KNN, Decision Tree, Random Forest, XGBoost, Bagged Trees, and LDA. Each algorithm is described with its strengths, limitations, and relevance to the study's dataset and objectives.

This pull request introduces significant updates to the literature review and theoretical foundation sections of a LaTeX document. The changes include detailed discussions on structural health monitoring (SHM) techniques, enhancements to the theoretical foundation with new subsections, and the addition of specific algorithms and methods used in the study. Below are the most important changes grouped by theme: ### Literature Review Enhancements: * Replaced a placeholder input with a comprehensive discussion on traditional SHM methods and their limitations, including the introduction of CNN-based and machine-learning-based approaches for damage detection. This includes detailed case studies from \textcite{abdeljaber2017}, \textcite{eraliev2022}, and others. ### Theoretical Foundation Additions: * Added a subsection on `Hann window`, explaining its mathematical formulation, advantages in reducing spectral leakage, and its suitability for STFT applications. * Expanded the `Short-Time Fourier Transform (STFT)` subsection to include its mathematical basis, use in time-frequency analysis, and its application in the study for extracting vibration signal features. * Introduced a new subsection on the role of `Windowing` functions in signal processing, emphasizing their importance in minimizing spectral leakage and improving time-frequency representation accuracy. ### Machine Learning Algorithms: * Reorganized and expanded the machine learning section into a detailed discussion of seven classification algorithms, including SVM, KNN, Decision Tree, Random Forest, XGBoost, Bagged Trees, and LDA. Each algorithm is described with its strengths, limitations, and relevance to the study's dataset and objectives.

nuluh (Migrated from github.com) reviewed 2025-05-22 20:10:42 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: nuluh/thesis#78