论文标题
基于离散余弦转化的因果卷积神经网络，用于化学传感器的漂移补偿
Discrete Cosine Transform Based Causal Convolutional Neural Network for Drift Compensation in Chemical Sensors
论文作者
论文摘要
传感器漂移是化学传感器中的主要问题，需要解决可靠，准确检测化学分析物的问题。在本文中，我们开发了一个具有离散余弦变换（DCT）层的因果卷积神经网络（CNN），以估计漂移信号。在DCT模块中，我们在转换域中应用软阈值非线性来降低数据并获得漂移信号的稀疏表示。软阈值的价值是在培训期间学习的。我们的结果表明，基于DCT层的CNN能够产生缓慢变化的基线漂移信号。我们在合成数据上训练CNN并在实际化学传感器数据上进行测试。我们的结果表明，即使观察到的传感器信号非常嘈杂，我们也可以具有准确且平稳的漂移估计。
Sensor drift is a major problem in chemical sensors that requires addressing for reliable and accurate detection of chemical analytes. In this paper, we develop a causal convolutional neural network (CNN) with a Discrete Cosine Transform (DCT) layer to estimate the drift signal. In the DCT module, we apply soft-thresholding nonlinearity in the transform domain to denoise the data and obtain a sparse representation of the drift signal. The soft-threshold values are learned during training. Our results show that DCT layer-based CNNs are able to produce a slowly varying baseline drift signal. We train the CNN on synthetic data and test it on real chemical sensor data. Our results show that we can have an accurate and smooth drift estimate even when the observed sensor signal is very noisy.
