Feature Relevance Analysis to Explain Concept Drift - A Case Study in Human Activity Recognition
Pages 386 - 391
Abstract
This article studies how to detect and explain concept drift. Human activity recognition is used as a case study together with a online batch learning situation where the quality of the labels used in the model updating process starts to decrease. Drift detection is based on identifying a set of features having the largest relevance difference between the drifting model and a model that is known to be accurate and monitoring how the relevance of these features changes over time. As a main result of this article, it is shown that feature relevance analysis cannot only be used to detect the concept drift but also to explain the reason for the drift when a limited number of typical reasons for the concept drift are predefined. To explain the reason for the concept drift, it is studied how these predefined reasons effect to feature relevance. In fact, it is shown that each of these has an unique effect to features relevance and these can be used to explain the reason for concept drift.
References
[1]
M. Albert, S. Toledo, M. Shapiro, and K. Kording. 2012. Using mobile phones for activity recognition in Parkinson’s patients. Frontiers in neurology 3(2012).
[2]
H. Amrani, D. Micucci, and P. Napoletano. 2021. Personalized Models in Human Activity Recognition using Deep Learning. In 2020 25th ICPR. IEEE, 9682–9688.
[3]
M. Henke, E. Souto, and E. M. dos Santos. 2015. Analysis of the evolution of features in classification problems with concept drift: Application to spam detection. In 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM). IEEE, 874–877.
[4]
P. Kulkarni and R. Ade. 2014. Incremental learning from unbalanced data with concept class, concept drift and missing features: a review. IJDMTA 4, 6 (2014), 15.
[5]
V. Losing, B. Hammer, and H. Wersing. 2016. Choosing the Best Algorithm for an Incremental On-line Learning Task. In European Symposium on Artificial Neural Networks.
[6]
J. Lu, A. Liu, F. Dong, F. Gu, J. Gama, and G. Zhang. 2019. Learning under Concept Drift: A Review. IEEE Transactions on Knowledge and Data Engineering 31, 12(2019), 2346–2363. https://doi.org/10.1109/TKDE.2018.2876857
[7]
A. Mannini and S. Intille. 2018. Classifier Personalization for Activity Recognition using Wrist Accelerometers. IEEE journal of biomedical and health informatics (2018).
[8]
A. Mazankiewicz, K. Böhm, and M. Bergés. 2020. Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 4 (2020), 1–20.
[9]
L. Mo, Z. Feng, and J. Qian. 2016. Human daily activity recognition with wearable sensors based on incremental learning. In Sensing Technology, International Conference on. 1–5. https://doi.org/10.1109/ICSensT.2016.7796224
[10]
S. Ntalampiras and M. Roveri. 2016. An incremental learning mechanism for human activity recognition. In IEEE Symposium Series on Computational Intelligence. 1–6. https://doi.org/10.1109/SSCI.2016.7850188
[11]
R. Polikar, L. Upda, S. S Upda, and V. Honavar. 2001. Learn++: An incremental learning algorithm for supervised neural networks. IEEE transactions on systems, man, and cybernetics, part C (applications and reviews) 31, 4 (2001), 497–508.
[12]
M. Saarela and S. Jauhiainen. 2021. Comparison of feature importance measures as explanations for classification models. SN Applied Sciences 3, 2 (2021), 1–12.
[13]
M. Shoaib, S. Bosch, O. D. Incel, H. Scholten, and P. Havinga. 2014. Fusion of Smartphone Motion Sensors for Physical Activity Recognition. Sensors 14, 6 (2014), 10146–10176. https://doi.org/10.3390/s140610146
[14]
P. Siirtola, H. Koskimäki, and J. Röning. 2018. Personalizing human activity recognition models using incremental learning. In ESANN. 627–632.
[15]
P. Siirtola and J. Röning. 2019. Incremental learning to personalize human activity recognition models: the importance of human AI collaboration. Sensors 19, 23 (2019), 5151.
[16]
P. Siirtola and J. Röning. 2021. Context-aware incremental learning-based method for personalized human activity recognition. Journal of Ambient Intelligence and Humanized Computing (2021), 1–15.
[17]
Meysam Vakili and Masoumeh Rezaei. 2021. Incremental Learning Techniques for Online Human Activity Recognition. arXiv preprint arXiv:2109.09435(2021).
[18]
Z. Wang, M. Jiang, Y. Hu, and H. Li. 2012. An incremental learning method based on probabilistic neural networks and adjustable fuzzy clustering for human activity recognition by using wearable sensors. IEEE Trans Inf Technol Biomed 16, 4 (2012), 691–699.
[19]
L. Yang, W. Guo, Q. Hao, A. Ciptadi, A. Ahmadzadeh, X. Xing, and G.Wang. 2021. CADE: Detecting and Explaining Concept Drift Samples for Security Applications. In 30th USENIX Security Symposium (USENIX Security 21). USENIX Association, 2327–2344. https://www.usenix.org/conference/usenixsecurity21/presentation/yang-limin
Index Terms
- Feature Relevance Analysis to Explain Concept Drift - A Case Study in Human Activity Recognition
Recommendations
Detecting group concept drift from multiple data streams
Highlights- Proposing a new type of concept drift group concept drift that commonly exists in multiple data streams.
AbstractConcept drift may lead to a sharp downturn in the performance of streaming in data-based algorithms, caused by unforeseeable changes in the underlying distribution of data. In this paper, we are mainly concerned with concept drift ...
Algorithm of Recurring Concept Drift Base on Main Feature Extraction
ICCAI '19: Proceedings of the 2019 5th International Conference on Computing and Artificial IntelligenceRecurring concept drift is one of the sub-types of concept drift. In recurring concept drift detection, it is very important to represent concepts and select the most appropriate classifier to classify. We propose an algorithm, conceptual clustering and ...
The Impact of Diversity on Online Ensemble Learning in the Presence of Concept Drift
Online learning algorithms often have to operate in the presence of concept drift (i.e., the concepts to be learned can change with time). This paper presents a new categorization for concept drift, separating drifts according to different criteria into ...
Comments
Information & Contributors
Information
Published In
September 2022
538 pages
ISBN:9781450394239
DOI:10.1145/3544793
Copyright © 2022 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 24 April 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
UbiComp/ISWC '22
Sponsor:
UbiComp/ISWC '22: The 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing
September 11 - 15, 2022
Cambridge, United Kingdom
Acceptance Rates
Overall Acceptance Rate 764 of 2,912 submissions, 26%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 147Total Downloads
- Downloads (Last 12 months)104
- Downloads (Last 6 weeks)12
Reflects downloads up to 10 Nov 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatGet Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in