With the development of blockchain, artificial intelligence and data mining technology, abnormal network traffic data has become easy to obtain. The traffic detection model detects the traffic patterns in the network to find abnormal traffic that does not conform to the normal traffic law, which has great security significance for Industrial Internet of Things (IIoT) networks and devices in real scenarios. However, previous abnormal detection models rely on expert experience and cannot cope with real-time changes in IIoT scenarios. The manual features cannot be sufficiently representative and adaptive. Moreover, there are few abnormal traffic data in real scenarios, which makes the model unable to fully learn the potential distribution in abnormal data. Therefore, in this work, we propose a deep abnormal network traffic detection model (DANTD) for security of IIoT using high-order features and novel data augmentation strategies. The DANTD model first adopts a deep convolutional autoencoder to extract effective high-order features to make it more representative. Then the DANTD model uses generative adversarial networks as data augmentation strategies to enrich the abnormal data, so that the model can fully consider the information of the data distribution. Comprehensive experiments on real IIoT datasets validate the effectiveness of the DANTD model.

Mechanism analysis of the RFID-Sensor communication interference can effectively improve the information collection quality of the perception layer. In our study, multipath Interference analysis of low-power RFID-Sensor under metal medium environment was considered. Firstly, the dual-antenna RFID-Sensor architecture was developed based on low power strategy, the multipath loss model and interference theory under metal medium environment was discussed. Secondly, by full consideration of electromagnetic interference energy loss factors, the time-frequency domain characteristics of electromagnetic signals, such as direct radiation, refraction, diffraction, scattering, absorption and polarization, were analyzed. Thirdly, the normalized electric field strength between the low-power RFID-Sensor with different distance was obtained through simulation/experiment scenario. The distance between the low-power RFID-Sensor and transmitting antennas is represented by r , when r is from 1 m to 5 m, the minimum working distance between the RFID-Sensor antenna and the metal medium surface changed from 6.9 mm to 7.0 mm at the frequency of 915 MHz. This paper was conducive for expanding the functions of the perception layer system of the IoT and enhancing the application potential of existing RFID and sensor networks.

Cataluminescence-based sensors do not require external light sources and complex circuitry, which enables them to avoid light scattering with high sensitivity, selectivity, and widely linear range. In this study, a wireless sensor system based on hierarchical CuO microspheres assembled from nano-sheets was constructed for Volatile Organic Compound (VOC) online detection. Through sensor characteristics and data process analysis, the results showed that the luminous sensor system has good luminous characteristics, including the intensity of visible light, high signal/noise (S/N) values, and very short response and recovery times. Different VOC concentration values can be detected on multiple wavelength channels and different Cataluminescence signal spectra separations can process multiple sets of Cataluminescence data combinations concurrently. This study also briefly studied the mechanism action of the Cataluminescence sensor, which can specifically be used for VOC detecting.

High concentrations of ammonia pose a potential threat to human and animal/plant health. Active detection methods such as semiconductor, electrochemical, and optical methods have been used for ammonia detection. These methods increase energy consumption and heat accumulation, which may affect the performance of detection systems. Therefore, the research on passive ammonia detection methods is of great significance. In our study, a passive wireless sensor for ammonia detection based on carbon nanotube-loaded Chipless Radio Frequency Identification (CRFID) was considered, which have the advantages of low cost, passive wireless ability, miniaturization, universality, and long life. However, path loss, tag position, and actual environmental interference can affect detection efficiency. In order to better improve the robustness of ammonia detection, the principle of carbon nanotube-loaded RFID-inspired for ammonia detection was introduced in our study. High-Frequency Simulator Structure (HFSS) simulation and fabrication for RFID-inspired sensor based on metal ink material printing is proposed, which operated at the central frequency of 2.4 GHz. The resistance value changes when the ammonia concentration is 0 mg/L-200 mg/L, which shows a negative growth coefficient after absorbing ammonia. Furthermore, detection and analysis in real and simulated environments were derived, such as power reflection coefficient, tag angle, path loss, identification distances, and phase. The measurement comparison outside the laboratory environment and cross-sensitivity of CO2 was also carried out. The result provides a reliable theoretical and practical basis for passive wireless ammonia detection and is of great significance for environmental quality assessment and food safety traceability information disclosure.