Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach

The advances in deep neural networks (DNN) have significantly enhanced real-time detection of anomalous data in IoT applications. However, the complexity-accuracy-delay dilemma persists: Complex DNN models offer higher accuracy, but typical IoT devices can barely afford the computation load, and the remedy of offloading the load to the cloud incurs long delay. In this article, we address this challenge by proposing an adaptive anomaly detection scheme with hierarchical edge computing (HEC). Specifically, we first construct multiple anomaly detection DNN models with increasing complexity and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network . We also incorporate a parallelism policy training method to accelerate the training process by taking advantage of distributed models. We build an HEC testbed using real IoT devices and implement and evaluate our contextual-bandit approach with both univariate and multivariate IoT datasets. In comparison with both baseline and state-of-the-art schemes, our adaptive approach strikes the best accuracy-delay tradeoff on the univariate dataset and achieves the best accuracy and F1-score on the multivariate dataset with only negligibly longer delay than the best (but inflexible) scheme.

Damage Detection of Laminated Rubber Bearings Based on the Antiresonance Frequencies of Periodic Structure and Its Sensitivity Analysis

An isolation bearing consumes most of the seismic energy of a structure and is vulnerable to destruction. The performance of isolation bearings is usually evaluated according to the global stiffness and energy dissipation capacity. However, the early minor damage in isolation bearings is difficult to identify. In this study, a damage detection scheme for the isolation bearing is proposed by focusing on the antiresonance of the quasiperiodic structure. Firstly, a laminated rubber bearing was simplified as a monocoupled periodic rubber-steel structure. The characteristic equation of the driving point antiresonance frequency of the periodic system was achieved via the dynamic stiffness method. Secondly, the sensitivity coefficient of the driving point antiresonance, which was obtained from the first-order derivative of the antiresonance frequency, with respect to the damage scaling parameter was derived using the antiresonance frequency characteristic equation. Thirdly, the optimised driving points of the antiresonance frequencies were selected by means of sensitivity analysis. Finally, from the measured changes in the antiresonance frequencies, the damage was identified by solving the sensitivity identification equation via a numerical optimisation method. The application of the proposed method to laminated rubber bearings under various damage cases demonstrates the feasibility of this method. This study has proven that changes in the shear modulus of each rubber layer can be identified accurately.

Peak Space Motion Artifact Cancellation Applied to Textile Electrode Waist Electrocardiograms Recording During Outdoors Walking and Jogging

Background: Obtaining reliable rate heart estimates from waist based electrocardiograms (ECGs) poses a very challenging problem due to the presence of extreme motion artifacts. The literature reveals few, if any, attempts to apply motion artifact cancellation methods to waist based ECGs. This paper describes a new methodology for ameliorating the effects of motion artifacts in ECGs by specifically targeting ECG peaks for elimination that are determined to be correlated with accelerometer peaks. This peak space cancellation was applied to real world waist based ECGs. Algorithm Summary: The methodology includes successive applications of a previously described pattern-based heart beat detection scheme (Temporal Pattern Search, or TEPS) that can also detect patterns in other types of peak sequences. In the first application, TEPS is applied to accelerometer signals recorded contemporaneously with ECG signals to identify high-quality accelerometer peak sequences (SA) indicative of quasi-periodic motion likely to impair identification of peaks in a corresponding ECG signal. The process then performs ECG peak detection and locates the closest in time ECG peak to each peak in an SA. The differences in time between ECG and SA peaks are clustered. If the number of elements in a cluster of peaks in an SA exceeds a threshold, the ECG peaks in that cluster are removed from further processing. After this peak removal process, further QRS detection proceeds according to TEPS. Experiment: The above procedure was applied to data from real world experiments involving four sessions of walking and jogging on a dirt road for approximately 20-25 minutes. A compression shirt with textile electrodes served as the ground truth recording. A textile electrode based chest strap was worn around the waist to generate a single channel signal upon which to test peak space cancellation/TEPS. Results: Both walking and jogging heart rates were generally well tracked. In the four recordings, the percentage of 5 second segments within 10 beats/minute of reference was 96%, 99%, 92% and 96%. The percentage of segments within 5 beats/minute of reference was 86%, 90%, 82% and 78%. There was very good agreement between the RR intervals associated with the reference and waist recordings. For acceptable quality segments, the root mean square sum of successive RR interval differences (RMSSD) was calculated for both the reference and waist recordings. Next, the difference between waist and reference RMSSDs was calculated (∆RMSSD). The mean ∆RMSSD (over acceptable segments) was 4.6 m, 5.2 ms, 5.2 ms and 6.6 ms for the four recordings. Conclusion: Given that only one waist ECG channel was available, and that the strap used for the waist recording was not tailored for that purpose, the proposed methodology shows promise for waist based sinus rhythm QRS detection.

A frequency-weighted energy operator and swarm decomposition for bearing fault diagnosis

The weak fault characteristics of rolling bearings are difficult to identify due to strong background noise. To address this issue, a bearing fault detection scheme combining swarm decomposition (SWD) and frequency-weighted energy operator (FWEO) is presented. First, SWD is applied to decompose the bearing fault signal into single mode components. Then, a new evaluation index termed LEP is constructed by combining the advantages of envelope entropy, Pearson correlation coefficient and L-kurtosis, and it is utilized to choose the sensitive component containing the richest bearing fault characteristics. Finally, FWEO is employed for extracting the bearing fault features from the sensitive component. Simulation and experimental analyses indicate that the LEP index has better performance than the L-kurtosis index in determining the sensitive component. The method has the effect of suppressing noise and enhancing impulse characteristics, which is superior to the SWD-based envelope demodulation method.

Weigh-in-Motion: Lightweight Real-Time Identification of Gbps Wireless Traffic

Distinguishing between wireless and wired traffic in a network middlebox is an essential ingredient for numerous applications including security monitoring and quality-of-service (QoS) provisioning. The majority of existing approaches have exploited the greater delay statistics, such as round-trip-time and inter-packet arrival time, observed in wireless traffic to infer whether the traffic is originated from Ethernet (i.e., wired) or Wi-Fi (i.e., wireless) based on the assumption that the capacity of the wireless link is much slower than that of the wired link. However, this underlying assumption is no longer valid due to increases in wireless data rates over Gbps enabled by recent Wi-Fi technologies such as 802.11ac/ax. In this paper, we revisit the problem of identifying Wi-Fi traffic in network middleboxes as the wireless link capacity approaches the capacity of the wired. We present Weigh-in-Motion, a lightweight online detection scheme, that analyzes the traffic patterns observed at the middleboxes and infers whether the traffic is originated from high-speed Wi-Fi devices. To this end, we introduce the concept of ACKBunch that captures the unique characteristics of high-speed Wi-Fi, which is further utilized to distinguish whether the observed traffic is originated from a wired or wireless device. The effectiveness of the proposed scheme is evaluated via extensive real experiments, demonstrating its capability of accurately identifying wireless traffic from/to Gigabit 802.11 devices.

Analysis of Scope of Data Mining in Fraud Detection and Studying Solutions to Prevent Them

This paper will explain the process of fraud detection suing datamining techniques. Fraud detection is important task and many domains have risk of attack of fraudsters in the data that they have stored. It is very important that each domain like banking etc should have reliable fraud detection scheme so that the personal details of the users of the banks is safe and secure. There are a lot of techniques which can be used to detect fraud attack in the system