Anomaly detection in multivariate time series is crucial to monitor system status, such as fault detection in industrial systems. However, detecting anomalies in multivariate time series is challenging due to few labels, complex spatiotemporal correlations, and ultrafast detecting demands. Existing anomaly detection methods rarely address these challenges simultaneously. Herein, we design an adversarial transformers-based unsupervised anomaly detection model (ATUAD). In ATUAD, a Transformer-based encoder–decoder is constructed to learn sequence features, and adversarial training is adopted to amplify mild anomalies and enhance the robustness. Besides, we propose a peak-over-threshold-based dynamic threshold mechanism to improve the anomaly detection performance of ATUAD by automatically determining the threshold. In addition, we provide an anomaly explanation method to help ATUAD pinpoint root causes for anomalies. Comparison experiments, ablation studies, and overhead analysis on public datasets show that ATUAD can outperform the state-of-the-art baseline methods.

Gases emissions estimation and analysis by using carbon dioxide balance method in natural-ventilated dairy cow barns

Biometric recognition is extensive for user security authentication in the Industrial Internet of Things (IIoT). However, the potential leakage of biometric data has severe repercussions, such as identity theft or tracking. Existing authentication schemes primarily focus on protecting biometric templates but often overlook the “one-authentication multiple-access” mode. As a result, these schemes still confront challenges related to privacy leakage and low efficiency for users who frequently access the server. In this regard, this paper proposes an efficient authentication scheme syncretizing physical unclonable function (PUF) and revocable biometrics in IIoT. Specifically, we design a revocable biometric template generation method syncretizing the user’s biometric data and the device’s PUF to enhance the security and revocability of the dual identity information. Given the generated revocable biometric template and the secret sharing, our scheme implements secure authentication and key negotiation between users and servers. Additionally, we establish an access boundary and an authentication validity period to permit multiple accesses following one authentication, thus significantly decreasing the computational cost of the user-side device. We leverage BAN logic and the ROR model to prove our scheme’s security. Informal security analysis and performance comparison demonstrate that our scheme satisfies more security features with higher authentication efficiency.

Reliable estimation of the ventilation rate (VR) in intensive livestock buildings is necessary for studying building environmental control strategies and predicting indoor air quality and air emissions. As direct air exchange measurements are time-consuming and expensive, it is environmentally inefficient to measure livestock building VR continuously in practice. Hence, indirect VR estimation methods have been widely used in modelling environmental control and air emissions, and also to measure airflow in the field. The accuracy of indirect measurement methods needs to be evaluated by comparing with direct measurements. In this study, the direct and indirect methods of determining hourly and daily mean VRs were applied to a mechanically-ventilated dairy free stall barn monitored by the 24-month National Air Emissions Monitoring Study. The direct method was used to continuously monitor fan rotational speeds, and differential static pressures, coupled with periodic in-situ fan performance assessments, to calculate the VR. The indirect method consisted of estimating the VR using CO2 concentration measurements and the CO2 mass balance method. The average daily and hourly means (mean +/- SD) of directly measured barn ventilation rates for two years were (246 +/- 73) m(3)/s and (245 +/- 77) m(3)/s, respectively. The average daily and hourly means (mean +/- SD) of barn ventilation rates estimated by the CO2 mass balance method were (287 +/- 93.4) m(3)/s and (287 +/- 118) m(3)/s, respectively. Correlation analyses showed a strong correlation between the indirect CO2 mass balance method and direct measurement methods (r=0.93 for daily means and r=0.85 for hourly means).