paper-with-me

홈 › Papers

iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets

2024-06-03 · Mengxi Liu, Sizhen Bian, Bo Zhou, Paul Lukowicz

This work proposes an incremental learning (IL) framework for wearable sensor human activity recognition (HAR) that tackles two challenges simultaneously: catastrophic forgetting and non-uniform inputs. The scalable framework, iKAN, pioneers IL with Kolmogorov-Arnold Networks (KAN) to replace multi-layer perceptrons as the classifier that leverages the local plasticity and global stability of splines. To adapt KAN for HAR, iKAN uses task-specific feature branches and a feature redistribution layer. Unlike existing IL methods that primarily adjust the output dimension or the number of classifier nodes to adapt to new tasks, iKAN focuses on expanding the feature extraction branches to accommodate new inputs from different sensor modalities while maintaining consistent dimensions and the number of classifier outputs. Continual learning across six public HAR datasets demonstrated the iKAN framework's incremental learning performance, with a last performance of 84.9\% (weighted F1 score) and an average incremental performance of 81.34\%, which significantly outperforms the two existing incremental learning methods, such as EWC (51.42\%) and experience replay (59.92\%).

📄 PDF Abstract BibTeX arXiv:2406.01646

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionContinual LearningHuman Activity RecognitionIncremental LearningKolmogorov-Arnold Networks

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
EWC The methon to overcome catastrophic forgetting in neural network while continual learning

Similar Papers 제목 키워드 기반

Incremental Activity Modeling and Recognition in Streaming Videos

2014-06-01 · CVPR 2014 6 · Mahmudul Hasan, Amit K. Roy-Chowdhury

Most of the state-of-the-art approaches to human activity recognition in video need an intensive training stage and assume that all of the training examples are labeled and available beforehand. But these assumptions are…

Active LearningActivity RecognitionHuman Activity Recognition

Personalizing human activity recognition models using incremental learning

2019-05-29 · Pekka Siirtola, Heli Koskimäki, Juha Röning

In this study, the aim is to personalize inertial sensor data-based human activity recognition models using incremental learning. At first, the recognition is based on user-independent model. However, when personal strea…

Activity RecognitionGeneral ClassificationHuman Activity RecognitionIncremental Learning

Incremental Learning Techniques for Online Human Activity Recognition

2021-09-20 · Meysam Vakili, Masoumeh Rezaei

Unobtrusive and smart recognition of human activities using smartphones inertial sensors is an interesting topic in the field of artificial intelligence acquired tremendous popularity among researchers, especially in rec…

Activity RecognitionHuman Activity RecognitionIncremental Learning

On Handling Catastrophic Forgetting for Incremental Learning of Human Physical Activity on the Edge

2023-02-18 · Jingwei Zuo, George Arvanitakis, Hakim Hacid

Human activity recognition (HAR) has been a classic research problem. In particular, with recent machine learning (ML) techniques, the recognition task has been largely investigated by companies and integrated into their…

Activity RecognitionHuman Activity RecognitionIncremental Learning

MAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization

2024-02-11 · Jingwei Zuo, George Arvanitakis, Mthandazo Ndhlovu, Hakim Hacid

Human activity recognition (HAR) is a well-established field, significantly advanced by modern machine learning (ML) techniques. While companies have successfully integrated HAR into consumer products, they typically rel…

Activity RecognitionHuman Activity RecognitionIncremental Learning