换一批摘要With the advent of the Internet of Things and Big Data analysis, it is possible to create an intelligent ecosystem for continuous patient monitoring with minimal human interaction. But the machine learning algorithms associated with such smart healthcare ecosystems are usually resource-intensive and require communication of private data to cloud servers. In this article, we proposed an approximation method for neural networks, which can be efficiently implemented on FPGAs, and therefore enable on-device FER. We implemented several CNN models on the FPGA for FER. Our approximated method can save at least 22% FPGA resource usage, which is advantageous for embedded systems.
更多相关知识
关键词
facial expression detectionemotion recognitionFPGA implementationconvolutional neural networksigned digit approximationfacial expression detectionemotion recognitionFPGA implementationconvolutional neural networksigned digit approximation
栏目名称
DOI
10.15302/J-QB-022-0312
发布时间
2024-07-26（万方平台首次上网日期，不代表论文的发表时间）
- 浏览1
- 被引0
- 下载0
相似文献
- 中文期刊
- 外文期刊
- 学位论文
- 会议论文
