Home / Current Issue / Paper 1707638
Enhanced Structural Health Monitoring Through LSTM-Enhanced Gradient Boosting Regressor
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
This research paper highlights a novel hybrid model, LSTM-Enhanced Gradient Boosting Regressor (LE-GBR), which aims to improve prediction of failure in critical infrastructure like bridges and buildings. Structures naturally degrade over time due to many factors like material fatigue and environmental pressures, making accurate predictions essential for safety and maintenance planning. Traditional models often miss complex interactions between these factors, but our method integrates Gradient Boosting Regressor (GBR) with Long Short-Term Memory (LSTM) networks, allowing us to capture both fixed and evolving patterns in structural health data. Through experiments on a collected dataset, LE-GBR model outperformed other approaches, providing more accurate forecasts of structural health conditions. This model offers a promising tool for enhancing structural safety by enabling more precise failure predictions, thereby supporting improved maintenance strategies and risk mitigation for critical infrastructure.
Keywords
Failure Prediction, Gradient Boosting Regressor, Hybrid Model, Infrastructure Safety, LSTM, Predictive Modeling, Structural Health Monitoring, Structural Integrity
How to cite this paper
@article{1707638,
author = {Aryan Kesarkar, Chrisil Dabre, Raghav Agarwal, Yash Chavan, Prof. Ruhina Karani},
title = {Enhanced Structural Health Monitoring Through LSTM-Enhanced Gradient Boosting Regressor},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {9},
pages = {1221-1231},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1707638.pdf},
abstract = {This research paper highlights a novel hybrid model, LSTM-Enhanced Gradient Boosting Regressor (LE-GBR), which aims to improve prediction of failure in critical infrastructure like bridges and buildings. Structures naturally degrade over time due to many factors like material fatigue and environmental pressures, making accurate predictions essential for safety and maintenance planning. Traditional models often miss complex interactions between these factors, but our method integrates Gradient Boosting Regressor (GBR) with Long Short-Term Memory (LSTM) networks, allowing us to capture both fixed and evolving patterns in structural health data. Through experiments on a collected dataset, LE-GBR model outperformed other approaches, providing more accurate forecasts of structural health conditions. This model offers a promising tool for enhancing structural safety by enabling more precise failure predictions, thereby supporting improved maintenance strategies and risk mitigation for critical infrastructure.},
keywords = {Failure Prediction, Gradient Boosting Regressor, Hybrid Model, Infrastructure Safety, LSTM, Predictive Modeling, Structural Health Monitoring, Structural Integrity},
month = {March},
}