JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
@unpublished{khaleghi:ibic2023-wep044,
author = {A. Khaleghi and M. Akbari and H.H. Haedar and K. Mahmoudi},
title = {{Key Factors and Drivers for Utilizing Machine Learning in Experimental Data Analysis: A Case Study of Synchrotron Experimental Data}},
% booktitle = {Proc. IBIC'23},
booktitle = {Proc. Int. Beam Instrum. Conf. (IBIC'23)},
language = {english},
intype = {presented at the},
series = {International Beam Instrumentation Conference},
number = {12},
venue = {Saskatoon, Canada},
publisher = {JACoW Publishing, Geneva, Switzerland},
month = {12},
year = {2023},
note = {presented at IBIC'23 in Saskatoon, Canada, unpublished},
abstract = {{Concurrently with the application of AI and Machin learning (ML), their remarkable influences are being observed. This study reviews the use of ML in analyzing experimental data, focusing on synchrotron data. It explores key factors and drivers shaping the application of ML in this context. The research model employs a forward-looking approach, aiming to advance ML in experimental data analysis. The study addresses challenges unique to synchrotron data, such as high dimensionality, complexity, large volume, noise, and uncertainty. Advanced techniques like dimensionality reduction, pattern recognition, anomaly detection, and predictive modeling are introduced as novel approaches. Results highlight the potential of ML in improving performance and obtaining more accurate outcomes in synchrotron data analysis. In conclusion, this research offers valuable insights and proposes strategies to enhance the analysis of synchrotron experimental data using ML. Identified drivers and research trends benefit synchrotron analysis and other scientific disciplines. The discussion explores broader implications and future directions for utilizing ML in experimental data analysis.}},
}