Combining medical data and machine learning has fully utilized the value of medical data. However, medical data contain a large amount of sensitive information, and the inappropriate handling of data can lead to the leakage of personal privacy. Thus, both publishing data and training data in machine learning may reveal the privacy of patients. To address the above issue, we propose two effective approaches. One combines a differential privacy and decision tree (DPDT) approach to provide strong privacy guarantees for publishing data, which establishes a weight calculation system based on the classification and regression tree (CART) method and takes weights as a new element of differential privacy to participate in privacy protection and reduce the negative impact of differential privacy on data availability. Another uses the differentially private mini-batch gradient descent algorithm (DPMB) to provide strong protection for training data; it tracks the privacy loss and allows the model to satisfy differential privacy in the process of gradient descent to prevent attackers from invading personal privacy with the training data. It is worth mentioning that, in this paper, we adopt the data processed by DPDT as the training data of DPMB to further strengthen the privacy of data. INDEX TERMS Deep learning, data privacy, differential privacy, data publishing.

Aiming at the intrusion detection problem of the wireless sensor network (WSN), considering the combined characteristics of the wireless sensor network, we consider setting up a corresponding intrusion detection system on the edge side through edge computing. An intrusion detection system (IDS), as a proactive network security protection technology, provides an effective defense system for the WSN. In this paper, we propose a WSN intelligent intrusion detection model, through the introduction of the k-Nearest Neighbor algorithm (kNN) in machine learning and the introduction of the arithmetic optimization algorithm (AOA) in evolutionary calculation, to form an edge intelligence framework that specifically performs the intrusion detection when the WSN encounters a DoS attack. In order to enhance the accuracy of the model, we use a parallel strategy to enhance the communication between the populations and use the Lévy flight strategy to adjust the optimization. The proposed PL-AOA algorithm performs well in the benchmark function test and effectively guarantees the improvement of the kNN classifier. We use Matlab2018b to conduct simulation experiments based on the WSN-DS data set and our model achieves 99% ACC, with a nearly 10% improvement compared with the original kNN when performing DoS intrusion detection. The experimental results show that the proposed intrusion detection model has good effects and practical application significance.

Wireless sensor networks (WSN) have gradually integrated into the concept of the Internet of Things (IoT) and become one of the key technologies. This paper studies the optimization algorithm in the field of artificial intelligence (AI) and effectively solves the problem of node location in WSN. Specifically, we propose a hybrid algorithm WOA-QT based on the whale optimization (WOA) and the quasi-affine transformation evolutionary (QUATRE) algorithm. It skillfully combines the strengths of the two algorithms, not only retaining the WOA’s distinctive framework advantages but also having QUATRE’s excellent coevolution ability. In order to further save optimization time, an auxiliary strategy for dynamically shrinking the search space (DSS) is introduced in the algorithm. To ensure the fairness of the evaluation, this paper selects 30 different types of benchmark functions and conducts experiments from multiple angles. The experiment results demonstrate that the optimization quality and efficiency of WOA-QT are very prominent. We use the proposed algorithm to optimize the weighted centroid location (WCL) algorithm based on received signal strength indication (RSSI) and obtain satisfactory positioning accuracy. This reflects the high value of the algorithm in practical applications.

With the fast development of electronics and wireless communication technologies in recent years, intelligent wireless sensor nodes are becoming increasingly popular in the online machinery condition monitoring systems. They bring a number of benefits, such as reduced investment on the installation and maintenance of expensive communication cables, ease of deployment and upgrading. For the condition monitoring of dynamic signals, distributed computation on wireless sensor nodes is getting popular with wireless sensor nodes becoming more computation powerful and power efficient. As a widely recognised algorithm for bearing fault diagnosis, envelope analysis has been previously proved suitable for being embedded on the wireless sensor nodes to effectively extract fault features from common machinery components such as bearings and gears. As a continuation, this paper studies into several envelope detection methods, including Hilbert transform, spectral correlation, band-pass squared rectifier and short-time RMS. Regarding to the fact that only low frequency components in the bearing envelope is of interest, spectral correlation can be simplified for fast calculation and short-time RMS method can be considered as a simplified band-pass squared rectifier, in which partial aliasing is allowed. Thereafter, spectral correlation and short-time RMS are employed to speed up the calculation of envelope analysis on a wireless sensor node, which thereafter provides the potential to reduce power consumption of wireless sensor nodes. The computation speed comparison shows that the spectral correlation method and short-time RMS can speed up the computation speed by more than two times and five times in comparison with the Hilbert transform method. The simulation study shows that spectral correlation and shorttime RMS based methods achieves similar level of accuracy as Hilbert transform. Furthermore, the experimental study shows that spectral correlation and short-time RMS based methods can well reveal the simulated three types of bearing faults while with the computation speed significantly improved.

No abstract