Knowledge-Driven Approach for Quality Assessment of HAR Data Sets: An Automated Tool

The quality of Human Activity Recognition (HAR) data sets is associated with several aspects of governance, diverse data collection protocols, through to information understanding challenges of labelling accuracy, imbalanced data, and the presence of missing or irrelevant information. The mentioned challenges can be addressed with the construction of standard quality metrics and quality assessment frameworks and tools. This research outlines a knowledge-driven based approach for the qualitative assessment of HAR data sets, including the development of an automated tool. Through the utilization of domain expertise, semantic modelling, and machine learning techniques, we determine quality metrics and criteria that effectively encapsulate the fundamental attributes of the HAR data set. The automated tool utilizes established techniques for assessing quality, including the Threshold-based method and the Aggregative-based approach. The proposed research provides a new method and tool that improves the evaluation of the quality of the HAR data set, thereby facilitating more informed decisions and enhancements in the HAR domain.