Esmaeili Fatemeh, Cassie Erica, Nguyen Hong Phan T, Plank Natalie O V, Unsworth Charles P, Wang Alan
Department of Engineering Science, University of Auckland, Auckland 1010, New Zealand.
The MacDiarmid Institute for Advanced Materials and Nanotechnology, Victoria University of Wellington, Wellington 6021, New Zealand.
Bioengineering (Basel). 2023 Mar 24;10(4):405. doi: 10.3390/bioengineering10040405.
Anomaly detection is a significant task in sensors' signal processing since interpreting an abnormal signal can lead to making a high-risk decision in terms of sensors' applications. Deep learning algorithms are effective tools for anomaly detection due to their capability to address imbalanced datasets. In this study, we took a semi-supervised learning approach, utilizing normal data for training the deep learning neural networks, in order to address the diverse and unknown features of anomalies. We developed autoencoder-based prediction models to automatically detect anomalous data recorded by three electrochemical aptasensors, with variations in the signals' lengths for particular concentrations, analytes, and bioreceptors. Prediction models employed autoencoder networks and the kernel density estimation (KDE) method for finding the threshold to detect anomalies. Moreover, the autoencoder networks were vanilla, unidirectional long short-term memory (ULSTM), and bidirectional LSTM (BLSTM) autoencoders for the training stage of the prediction models. However, the decision-making was based on the result of these three networks and the integration of vanilla and LSTM networks' results. The accuracy as a performance metric of anomaly prediction models showed that the performance of vanilla and integrated models were comparable, while the LSTM-based autoencoder models showed the least accuracy. Considering the integrated model of ULSTM and vanilla autoencoder, the accuracy for the dataset with the lengthier signals was approximately 80%, while it was 65% and 40% for the other datasets. The lowest accuracy belonged to the dataset with the least normal data in its dataset. These results demonstrate that the proposed vanilla and integrated models can automatically detect abnormal data when there is sufficient normal data for training the models.
异常检测是传感器信号处理中的一项重要任务，因为解读异常信号可能会在传感器应用方面导致做出高风险决策。深度学习算法因其能够处理不平衡数据集而成为异常检测的有效工具。在本研究中，我们采用了半监督学习方法，利用正常数据训练深度学习神经网络，以应对异常的多样和未知特征。我们开发了基于自动编码器的预测模型，以自动检测三种电化学适体传感器记录的异常数据，这些数据在特定浓度、分析物和生物受体下信号长度存在变化。预测模型采用自动编码器网络和核密度估计（KDE）方法来寻找检测异常的阈值。此外，在预测模型的训练阶段，自动编码器网络分别为普通自动编码器、单向长短期记忆（ULSTM）自动编码器和双向LSTM（BLSTM）自动编码器。然而，决策是基于这三个网络的结果以及普通自动编码器和LSTM网络结果的整合。作为异常预测模型性能指标的准确率表明，普通自动编码器模型和整合模型的性能相当，而基于LSTM的自动编码器模型准确率最低。考虑到ULSTM和普通自动编码器的整合模型，对于信号较长的数据集，准确率约为80%，而对于其他数据集，准确率分别为65%和40%。准确率最低的是数据集中正常数据最少的数据集。这些结果表明，当有足够的正常数据用于训练模型时，所提出的普通自动编码器模型和整合模型能够自动检测异常数据。
