Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants
Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants
复制标题
DOI：
10.3390/electronics11050682
复制
发表时间：
2022-02
期刊：
影响因子：
2.9
通讯作者：
A. Paul;Md. Abu Saleh Tajin;Anup Das;W. Mongan;K. Dandekar
中科院分区：
文献类型：
--
作者：
A. Paul;Md. Abu Saleh Tajin;Anup Das;W. Mongan;K. Dandekar
精确监测早产儿的呼吸频率对于根据需要启动医疗干预措施至关重要。有线技术对患者来说可能具有侵入性和干扰性。我们为早产儿提出了一种支持深度学习的可穿戴式监测系统，该系统使用从婴儿身上的非侵入性可穿戴式 Bellypatch 无线收集的信号来预测呼吸停止。我们提出了一个五阶段的设计流程，涉及数据收集和标记、特征缩放、具有超参数调整的深度学习模型选择、模型训练和验证以及模型测试和部署。使用的模型是一维卷积神经网络（1DCNN）架构，具有 1 个卷积层、1 个池化层和 3 个全连接层，实现了 97.15% 的分类精度。为了解决可穿戴处理的能量限制，探索了几种量化技术，并分析了它们在呼吸分类任务中的性能和能耗。结果表明，能量足迹和模型存储开销减少，分类精度显着下降，这意味着量化和其他模型压缩技术并不是可穿戴设备上呼吸分类问题的最佳解决方案。为了提高准确性，同时降低能耗，我们提出了一种新颖的基于尖峰神经网络（SNN）的呼吸分类解决方案，该解决方案可以在事件驱动的神经形态硬件平台上实现。为此，我们提出了一种方法，将我们基线训练的 1DCNN 的模拟操作转换为其尖峰等效操作。我们使用转换后的 SNN 参数进行设计空间探索，以生成具有不同精度和能量足迹的推理解决方案。我们选择的解决方案的准确率达到 93.33%，且能量比基线 1DCNN 模型低 18 倍。此外，所提出的 SNN 解决方案以低 4 倍的能量实现了与量化模型相似的精度。
Precise monitoring of respiratory rate in premature newborn infants is essential to initiating medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a deep-learning-enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on the infant’s body. We propose a five-stage design pipeline involving data collection and labeling, feature scaling, deep learning model selection with hyperparameter tuning, model training and validation, and model testing and deployment. The model used is a 1-D convolutional neural network (1DCNN) architecture with one convolution layer, one pooling layer, and three fully-connected layers, achieving 97.15% classification accuracy. To address the energy limitations of wearable processing, several quantization techniques are explored, and their performance and energy consumption are analyzed for the respiratory classification task. Results demonstrate a reduction of energy footprints and model storage overhead with a considerable degradation of the classification accuracy, meaning that quantization and other model compression techniques are not the best solution for respiratory classification problem on wearable devices. To improve accuracy while reducing the energy consumption, we propose a novel spiking neural network (SNN)-based respiratory classification solution, which can be implemented on event-driven neuromorphic hardware platforms. To this end, we propose an approach to convert the analog operations of our baseline trained 1DCNN to their spiking equivalent. We perform a design-space exploration using the parameters of the converted SNN to generate inference solutions having different accuracy and energy footprints. We select a solution that achieves an accuracy of 93.33% with 18× lower energy compared to the baseline 1DCNN model. Additionally, the proposed SNN solution achieves similar accuracy as the quantized model with a 4× lower energy.