Attribute Heaving Extraction and Performance Analysis for the Prophesy of Roof Fall Rate using Principal Component Analysis
M. Shyamala Devi1, Rincy Merlin Mathew2, R. Suguna3
1M. Shyamala Devi, Associate Professor, Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, (Tamil Nadu), India.
2Rincy Merlin Mathew, Lecturer, Department of Computer Science, College of Science and Arts, Khamis Mushayt, King Khalid university, Abha, Asir, Saudi Arabia.
3R. Suguna, Professor, Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, (Tamil Nadu), India.
Manuscript received on 08 June 2019 | Revised Manuscript received on 13 June 2019 | Manuscript published on 30 June 2019 | PP: 2319-2323 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7518068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Roof fall of the building is the major threat to the society as it results in severe damages to the life of the people. Recently, engineers are focusing on the prediction of roof fall of the building in order to avoid the damage to the environment and people. Early prediction of Roof fall is the social responsibility of the engineers towards existence of health and wealth of the nation. By considering these aspects, this paper proposes the usage of machine learning algorithms for predicting the roof fall rate of the building. This paper uses Rooffall data set extracted from UCI machine learning repository and is subjected to the feature extraction methods like Principal Component Analysis (PCA), Kernel Principal Component Analysis, Sparse Principal Component Analysis, Mini Batch Sparse Principal Component Analysis and Incremental Principal Component Analysis. The optimized dimensionality reduced dataset from each of the above methods are then processed to find the mean squared error (MSE), Mean Absolute Error (MAE) and R2 Score. We have achieved the prediction of roof fall rate in two ways. Firstly, the dimensionality reduction is done using five feature extraction methods which results in the survival of sensible attribute to predict the roof fall rate. Secondly, the comparison of each method is done by the accuracy parameters. The performance analysis is done by implementing python scripts in Anaconda Spyder Navigator. Experimental Result shows that the Incremental PCA have achieved the effective prediction of roof fall rate with minimum MSE of 17.08, MAE of 3.19 and reasonable R2 Score of 0.20.
Keywords: Machine Learning, Feature Extraction, PCA, MSE, MAE, R2 Score.
Scope of the Article: Machine Learning