期刊
IEEE JOURNAL OF SOLID-STATE CIRCUITS
卷 48, 期 7, 页码 1625-1637出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSSC.2013.2253226
关键词
Active learning (subject-specific adaptation); biomedical electronics; machine learning (artificial intelligence); medical signal processing; support vector machine (SVM)
资金
- SRC
- NSF
- Qualcomm Innovation Fellowship
Low-power sensing technologies have emerged for acquiring physiologically indicative patient signals. However, to enable devices with high clinical value, a critical requirement is the ability to analyze the signals to extract specific medical information. Yet given the complexities of the underlying processes, signal analysis poses numerous challenges. Data-driven methods based on machine learning offer distinct solutions, but unfortunately the computations are not well supported by traditional DSP. This paper presents a custom processor that integrates a CPU with configurable accelerators for discriminative machine-learning functions. A support-vector-machine accelerator realizes various classification algorithms as well as various kernel functions and kernel formulations, enabling range of points within an accuracy-versus-energy and -memory trade space. An accelerator for embedded active learning enables prospective adaptation of the signal models by utilizing sensed data for patient-specific customization, while minimizing the effort from human experts. The prototype is implemented in 130-nm CMOS and operates from 1.2 V-0.55 V (0.7 V for SRAMs). Medical applications for EEG-based seizure detection and ECG-based cardiac-arrhythmia detection are demonstrated using clinical data, while consuming 273 mu J and 124 mu J per detection, respectively; this represents 62.4x and 144.7x energy reduction compared to an implementation based on the CPU. A patient-adaptive cardiac-arrhythmia detector is also demonstrated, reducing the analysis-effort required for model customization by 20x.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据