Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

XHAC: Explainable Human Activity Classification From Sensor Data

XHAC: Explainable Human Activity Classification From Sensor Data
View Sample PDF
Author(s): Duygu Bagci Das (Dokuz Eylul University, Turkey) and Derya Birant (Dokuz Eylul University, Turkey)
Copyright: 2022
Pages: 19
Source title: Emerging Trends in IoT and Integration with Data Science, Cloud Computing, and Big Data Analytics
Source Author(s)/Editor(s): Pelin Yildirim Taser (Izmir Bakircay University, Turkey)
DOI: 10.4018/978-1-7998-4186-9.ch008


View XHAC: Explainable Human Activity Classification From Sensor Data on the publisher's website for pricing and purchasing information.


Explainable artificial intelligence (XAI) is a concept that has emerged and become popular in recent years. Even interpretation in machine learning models has been drawing attention. Human activity classification (HAC) systems still lack interpretable approaches. In this study, an approach, called eXplainable HAC (XHAC), was proposed in which the data exploration, model structure explanation, and prediction explanation of the ML classifiers for HAR were examined to improve the explainability of the HAR models' components such as sensor types and their locations. For this purpose, various internet of things (IoT) sensors were considered individually, including accelerometer, gyroscope, and magnetometer. The location of these sensors (i.e., ankle, arm, and chest) was also taken into account. The important features were explored. In addition, the effect of the window size on the classification performance was investigated. According to the obtained results, the proposed approach makes the HAC processes more explainable compared to the black-box ML techniques.

Related Content

Nuno Geada. © 2023. 14 pages.
Nuno Geada. © 2023. 12 pages.
Albérico Travassos Rosário. © 2023. 33 pages.
George Leal Jamil. © 2023. 23 pages.
George Leal Jamil. © 2023. 24 pages.
Presleyson Plínio de Lima. © 2023. 32 pages.
Anderson Fernando de Medeiros Carvalho, Danilo de Melo Costa. © 2023. 18 pages.
Body Bottom