一个轻量级的混合视觉变压器网络,用于基于雷达的人类活动识别
Sha Huan1,2, Zhaoyue Wang1, Xiaoqiang Wang3
1School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, 510006, China.
Scientific reports
|October 21, 2023
概括
本研究介绍了一种轻型混合视觉变压器 (LH-ViT),用于高效的基于雷达的人类活动识别 (HAR). 新型网络实现了高精度和低延迟,使其适合嵌入式应用程序.
科学领域:
- 计算机科学 计算机科学
- 信号处理 信号处理
- 人工智能的人工智能
背景情况:
- 基于雷达的人类活动识别 (HAR) 提供隐私保护和光强度强大的传感.
- 深度神经网络擅长对HAR进行雷达微多普勒信号的分类,但对于嵌入式系统来说计算密集.
研究的目的:
- 为基于雷达的HAR开发一个高效和轻量级的网络,以平衡精度和计算成本.
- 解决在资源有限的嵌入式应用程序中实施复杂的深度学习模型的挑战.
主要方法:
- 提出了一种轻量级的混合视觉变压器 (LH-ViT),将高效的卷积与视觉变压器 (ViT) 自主注意力集成在一起.
- 采用特征金字塔架构用于多尺度微多普勒地图特征提取.
- 使用叠加式雷达-ViT与折叠/展开操作和RES-SE块来减少计算负载和增强功能.
主要成果:
- 与传统方法相比,拟议的LH-ViT方法显示出更高的表达力和计算效率.
- 在两个人类活动数据集上的实验结果验证了网络的性能优势.
结论:
- 在嵌入式系统中,LH-ViT为基于雷达的HAR提供了有效的解决方案,在减少计算要求的情况下实现高精度.
- 这种方法可使先进的HAR技术在资源有限的设备中实际部署.
相关概念视频
01:25Transformers with Off-Nominal Turns Ratios
162
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
162
02:16Light Acquisition
8.5K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.5K