With the rapid development of 5G communication technology, the data in the Internet of Medical Things (IoMT) application systems exhibits complex characteristics such as large volume, high dimensionality, nonlinearity, and diversity, which significantly affect the efficiency and detection performance of anomaly detection tasks. How to efficiently extract nonlinear features from high-dimensional data in the context of the IoMT while minimizing information distortion in data objects are challenging problems in recent academic research. A novel adaptive nonlinear feature extraction method via fruit fly olfactory neural network (Fly dimension expansion projection and remain main components by PCA, FDEPCA) is proposed, where 1) the data are mean-centered; 2) a binary sparse random projection matrix is used for dimension expansion projection; and 3) PCA is used to extract principal component information. The proposed method overcomes the problems of present nonlinear feature extraction in the face of high-dimensional outliers where the intrinsic geometric structure of the data is severely distorted and computationally expensive. The dataset after nonlinear feature extraction by the FDEPCA algorithm is applied to specific anomaly detection models, using ROC curves and AUC as evaluation metrics for classification performance. Extensive comparison experiments are conducted on eight publicly available datasets, and experimental results show that compared with the popular nonlinear feature extraction algorithms, the FDEPCA algorithm has better classification performance and projection time advantage. When applied to proximity-based, probability-based, and ensemble-based different anomaly detection models respectively, the FDEPCA algorithm exhibits strong applicability in different types of anomaly detection classifiers.

Abstract With the rapid development of communication technology, various complex heterogeneous sensor network applications produce a large number of high‐dimensional dynamic data streams, which results in more difficult to anomaly detection than ever before. So, anomaly detection for high‐dimensional dynamic data streams is of a more and more challenging problem. This paper proposes a novel method for detecting anomalies in high‐dimensional dynamic data streams by utilizing several components. Firstly, it uses a stacked habituation autoencoder with habituation physiological mechanism to detect similarity anomalies more easily and capture feature relationships. Secondly, a union kernel density estimator with micro‐cluster is designed to improve online anomaly detection accuracy by estimating the data density. Lastly, candidate anomaly sets and a delayed processing approach are utilized to cope with conceptual drift and evolution in the data stream, allowing the system to adapt to changes in the data over time. Extensive experiments on four high‐dimensional dynamic data streams of the Internet of Things show that the proposed method is very effective.