基于在线增量学习的可穿戴设备的敏捷人类活动识别
Lulu Fan1, Hanyan Peng1, Lei Xiao2
1Department of Hematology, Shanghai Changzheng Hospital, Shanghai, China.
Frontiers in public health
|February 23, 2026
概括
这项研究引入了一个新的适应性学习框架,用于在边缘设备上识别人类活动. 它通过协同优化特征提取,模型复杂性和适应速度来实现高精度和低延迟.
科学领域:
- 边缘计算 边缘计算
- 机器学习 机器学习
- 传感器数据分析数据分析
背景情况:
- 在资源有限的边缘设备上,人类活动识别 (HAR) 在精度,延迟和适应性方面面临挑战.
- 现有的HAR方法通常优化单个方面 (例如,在线学习,模型散散化),但缺乏对准确性,延迟和功率的协同优化.
- 非静止的传感器数据流使HAR性能指标的动态平衡变得复杂.
研究的目的:
- 开发一个端到端的闭环自适应式学习框架,用于边缘设备上的 HAR.
- 为了协同优化HAR系统的特征提取,模型复杂性和适应速度.
- 解决现有 HAR 方法在平衡精度,延迟和功耗方面的局限性.
主要方法:
- 为 HAR.设计了一个端到端的闭环自适应学习框架.
- 利用快速主要组件分析来实现自适应特征的维度减少.
- 实施了基于信息理论的动态稀疏子网络激活,用于模型选择.
- 集成了一个低复杂度的在线增量学习模块,用于概念漂移跟踪.
主要成果:
- 该框架在五个数据集中实现了高准确度,从85.6%到97.4%不等.
- 推断延迟大约为1.0ms,满足实时要求.
- 证明了特征提取,模型复杂性和适应速度的联合动态优化.
结论:
- 拟议的框架有效地解决了边缘设备上的 HAR 的挑战.
- 系统级协同设计使准确性,延迟和功耗的动态平衡成为可能.
- 该框架满足适应性人类活动识别的实时性能需求.
相关概念视频
Introduction to Learning
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Cognitive Learning
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...


