Session Tracks

This track focuses on novel methodologies for data cleaning that enhance the quality of datasets. Researchers are encouraged to present their findings on automated and semi-automated approaches to data cleansing.

This session will explore sophisticated preprocessing techniques that improve the performance of machine learning models. Topics may include normalization, transformation, and feature extraction.

This track aims to discuss the latest advancements in predictive modeling techniques within data science. Contributions should highlight the application of supervised and unsupervised learning methods.

This session will delve into innovative approaches for detecting anomalies in engineering datasets. Researchers are invited to share their methodologies and case studies on outlier detection.

This track will cover various strategies for missing data imputation and their implications for data integrity. Presentations should focus on both theoretical frameworks and practical applications.

This session will address the challenges and solutions related to data integration from multiple sources. Emphasis will be placed on techniques that support data-driven decision making in engineering contexts.

This track will explore the role of feature engineering in predictive maintenance applications. Participants are encouraged to present innovative features that enhance model accuracy and reliability.

This session will focus on statistical approaches to preprocessing data for analysis. Contributions should discuss the impact of these methods on data quality and model performance.

This track will investigate the application of deep learning methods in data preprocessing tasks. Researchers are invited to present their findings on how deep learning can automate and improve preprocessing workflows.

This session will examine frameworks and methodologies for assessing data quality in engineering datasets. Presentations should focus on metrics, evaluation techniques, and case studies.

This track will address the unique challenges of data cleaning in the context of Industrial IoT. Researchers are encouraged to share insights on preprocessing techniques tailored for IoT-generated data.