With the development of Internet of Medical Things, massive healthcare sensor data (HSD) are transmitted in the Internet, which faces various security problems. Healthcare data are sensitive and important for patients. Automatic classification of HSD has significant value for protecting the privacy of patients. Recently, the edge computing-based federated learning has brought new opportunities and challenges. It is difficult to develop a lightweight HSD classification system for edge computing. In particular, the classification system should consider the dynamic characteristics of HSD, e.g., the change of data distributions and the appearance of initially unknown classes. To solve these problems, the paper proposes a scalable and transferable classification system, called SCALT. It is a one-classifier-per-class system based on federated learning. It comprises a one-dimensional convolution-based network for feature extraction, and an individual mini-classifier for each class. It is easy to be scaled when new class appears since only a mini-classifier will be trained. The feature extractor is updated only when it is transferred to a new task. SCALT has a parameter protection mechanism, which can avoid catastrophic forgetting in sequential HSD classification tasks. We conduct comprehensive experiments to evaluate SCALT on three different physiological signal datasets: Electrocardiogram, Electroencephalogram and Photoplethysmograph. The accuracies on the three datasets are 98.65%, 91.10% and 89.93% respectively, which are higher than the compared state-of-the-art works. At last, an application of applying SCALT to protect the privacy of patients is presented.

With the rapid development of the Internet of Things (IoT), it becomes convenient to use mobile devices to remotely monitor the physiological signals (e.g., Arrhythmia diseases) of patients with chronic diseases [e.g., cardiovascular diseases (CVDs)]. High classification accuracy of interpatient electrocardiograms is extremely important for diagnosing Arrhythmia. The Supraventricular ectopic beat (S) is especially difficult to be classified. It is often misclassified as Normal (N) or Ventricular ectopic beat (V). Class imbalance is another common and important problem in electronic health (eHealth), as abnormal samples (i.e., samples of specific diseases) are usually far less than normal samples. To solve these problems, we propose a sustainable deep learning-based heart beat classification system, called BeatClass. It contains three main components: two stacked bidirectional long short-term memory networks (Bi-LSTMs), called Rist and Morst, and a generative adversarial network (GAN), called MorphGAN. Rist first classifies the heartbeats into five common Arrhythmia classes. The heartbeats classified as S and V by Rist are further classified by Morst to improve the classification accuracy. MorphGAN is used to augment the morphological and contextual knowledge of heartbeats in infrequent classes. In the experiment, BeatClass is compared with several state-of-the-art works for interpatient arrhythmia classification. The $F1$ -scores of classifying N, S, and V heartbeats are 0.6%, 16.0%, and 1.8% higher than the best baseline method. The experimental result demonstrates that taking multiple classification models to improve classification results step-by-step may significantly improve the classification performance. We also evaluate the classification sustainability of BeatClass. Based on different physical signal data sets, a trained BeatClass can be updated to classify heartbeats with different sampling rates. Finally, an engineering application indicates that BeatClass can promote the sustainable development of IoT-based eHealth.

With the development of the Augmented and Virtual Reality (AR/VR) technologies, massive biometric data are collected by different organizations. These data have great significance but also worsen the privacy risks. Electro-CardioGram (ECG)-based Identity Recognition (EIR) is a popular Biometric technology. An ECG record is an internal Biology feature of a person and has time continuity. Thus, compared with traditional Biometric methods like face recognition, EIR may be less vulnerable to attack. We propose an Autoencoder-based EIR system, called P ersonalized A uto E ncoder (PerAE). PerAE maintains a small autoencoder model (called Attention-MemAE) for each registered user of a system. The Attention-MemAE enhances the autoencoder by using a memory module and two attention mechanisms. A user’s Attention-MemAE classifies the hearbeats of other users as anomalies. An Attention-MemAE can be updated when the distribution of the user’s ECG data is changed. By using personalized autoencoder, PerAE can improve the time efficiency and reduce the memory overhead. It improves the adaptability, scalability, and maintainability of EIR systems. Experiment results show that to train an Attention-MemAE with 90 $\%$ identification accuracy for a user, we can just take five minutes to collect the user’s ECG data (around 500 heartbeat samples).

Deep learning-based time series classification in 6G-supported Intelligent Transportation Systems (ITS) helps transport decision-making. Deep learning classifier training necessitates a large amount of labeled data for feature extraction. Labeling time series data in 6G-supported ITS is tough. Meta-learning can be used to train deep classifiers with limited data. However, in meta-learning, the tasks are frequently modeled by a low-complexity base learner. It is unable to use more complicate and powerful structures. The meta-learning-pretrained classifier can only perform new classification problems with the same number of classes. Most pre-training strategies do not prioritize enhancing the pre-training phase’s convergence rate and lowering the computational cost. Most research work aims to improve classification performance by increasing the complexity of the classification model. However, this raises computing costs. In this paper, we propose a one-dimensional Multi-Scale Dilated Convolution Neural Network time series classifier (MSDCNN). MSDCNN combines multi-scale CNN and dilated CNN. It can extract multi-scale characteristics from time series and reduce the complexity of the classifier. Furthermore, we propose a pre-training strategy, called Meta-transfer metric Learning using Scale function (MLS). MLS allows the classifier to gain experience from different tasks with various numbers of classes. Experiments show that MLS reduces pre-training computation costs during the pre-training phase. The pre-trained classifier, without using any fine tuning techniques, achieves the highest accuracy by comparing with the state-of-the-art methods. Finally, we present a case study of applying MSDCNN and MLS to detect road accidents in 6G-supported transportation systems.