Personalized Human Activity Recognition Using Convolutional Neural\n Networks

2018/01/24 by Seyed Ali Rokni, Rokni, Seyed Ali, Marjan Nourollahi +3
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.1801.08252

openalex publication_date 2018/01/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A major barrier to the personalized Human Activity Recognition using wearable\nsensors is that the performance of the recognition model drops significantly\nupon adoption of the system by new users or changes in physical/ behavioral\nstatus of users. Therefore, the model needs to be retrained by collecting new\nlabeled data in the new context. In this study, we develop a transfer learning\nframework using convolutional neural networks to build a personalized activity\nrecognition model with minimal user supervision.\n

Related

• Transfer Learning in Human Activity Recognition: A Survey
• Application of Transfer Learning Approaches in Multimodal Wearable Human Activity Recognition
• TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation
• Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art
• Human Activity Recognition from Wearable Sensor Data Using Self-Attention