Search

The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.

In order to simplify the complexity and reduce the cost of the microphone array, this paper proposes a dual-microphone based sound localization and speech enhancement algorithm. Based on the time delay estimation of the signal received by the dual microphones, this paper combines energy difference estimation and controllable beam response power to realize the 3D coordinate calculation of the acoustic source and dual-microphone sound localization. Based on the azimuth angle of the acoustic source and the analysis of the independent quantity of the speech signal, the separation of the speaker signal of the acoustic source is realized. On this basis, post-wiener filtering is used to amplify and suppress the voice signal of the speaker, which can help to achieve speech enhancement. Experimental results show that the dual-microphone sound localization algorithm proposed in this paper can accurately identify the sound location, and the speech enhancement algorithm is more robust and adaptable than the original algorithm.

High-precision, low-temperature-sensitive microelectromechanical system (MEMS) capacitive accelerometers are widely used in aerospace, automotive, and navigation systems. An analytical study of the temperature drift of bias (TDB) and temperature drift of scale factor (TDSF) for an asymmetric comb capacitive accelerometer is presented in this paper. A five-layer model is established for the equivalent expansion ratio in the TDB and TDSF formulas, and the results calculated by the weighted average of thickness and elasticity modulus method are closest to the results of the numerical simulation. The analytical formulas of TDB and TDSF for an asymmetric structure are obtained. For an asymmetric structure, TDB is only related to thermal deformation and fabrication error. Additionally, half of the fixed electrode distance is not included in the expressions of Δ d and Δ D for asymmetric structures, thus resulting in the TDSF of the asymmetric structure being smaller compared to a symmetric structure with the same structural parameters. The TDSF of the symmetric structure is [−200.2 ppm/°C, −261.6 ppm/°C], while the results of the asymmetric structure are [−11.004 ppm/°C, −72.404 ppm/°C] under the same set of parameters. The parameters of the optimal asymmetric structure are obtained for fabrication guidance using numerical methods. In the experiment, the TDSF and TDB of the packaged structure and the non-packaged structure are compared, and a significant effect of the package on the signal output is found. The TDB is reduced from 3000 to 60 μg/°C, while the TDSF is reduced from 3000 to 140 ppm/°C.

Over the past decade, wireless mesh networks (WMNs) have seen significant advancements due to their simple deployment, cost-effectiveness, ease of implementation, and reliable service coverage. However, despite these advantages, the placement of nodes in WMNs presents a critical challenge that significantly impacts their performance. This issue is recognized as an NP-hard problem, underscoring the necessity of development optimization algorithms, such as heuristic and metaheuristic approaches. This motivated us to develop the Maximum Entropy Genetic Algorithm (MEGA) to address the issue of mesh router node placement in WMNs. To assess the proposed method, we conducted experiments across various scenarios with different settings, focusing on key metrics such as network connectivity and user coverage. The simulation results showed the comparative performance of MEGA in relation to other prominent algorithms, such as the Coyote Optimization Algorithm (COA), Firefly Algorithm (FA), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO), revealing MEGA’s effectiveness and usability in determining optimal locations for mesh routers.

In this paper, we consider the gain-phase error calibration problem for uniform linear arrays (ULAs). Based on the adaptive antenna nulling technique, a new gain-phase error pre-calibration method is proposed, requiring only one calibration source with known direction of arrival (DOA). In the proposed method, a ULA with M array elements is divided into M−1 sub-arrays, and the gain-phase error of each sub-array can be uniquely extracted one by one. Furthermore, in order to obtain the accurate gain-phase error in each sub-array, we formulate an errors-in-variables (EIV) model and present a weighted total least-squares (WTLS) algorithm by exploiting the structure of the received data on sub-arrays. In addition, the solution to the proposed WTLS algorithm is exactly analyzed in the statistical sense, and the spatial location of the calibration source is also discussed. Simulation results demonstrate the efficiency and feasibility of our proposed method in both large-scale and small-scale ULAs and the superiority to some state-of-the-art gain-phase error calibration approaches.

Pollutant gases, such as CO, NO2, O3, and SO2 affect human health, and low-cost sensors are an important complement to regulatory-grade instruments in pollutant monitoring. Previous studies focused on one or several species, while comprehensive assessments of multiple sensors remain limited. We conducted a 12-month field evaluation of four Alphasense sensors in Beijing and used single linear regression (SLR), multiple linear regression (MLR), random forest regressor (RFR), and neural network (long short-term memory (LSTM)) methods to calibrate and validate the measurements with nearby reference measurements from national monitoring stations. For performances, CO > O3 > NO2 > SO2 for the coefficient of determination (R2) and root mean square error (RMSE). The MLR did not increase the R2 after considering the temperature and relative humidity influences compared with the SLR (with R2 remaining at approximately 0.6 for O3 and 0.4 for NO2). However, the RFR and LSTM models significantly increased the O3, NO2, and SO2 performances, with the R2 increasing from 0.3–0.5 to >0.7 for O3 and NO2, and the RMSE decreasing from 20.4 to 13.2 ppb for NO2. For the SLR, there were relatively larger biases, while the LSTMs maintained a close mean relative bias of approximately zero (e.g., 3 and NO2), indicating that these sensors combined with the LSTMs are suitable for hot spot detection. We highlight that the performance of LSTM is better than that of random forest and linear methods. This study assessed four electrochemical air quality sensors and different calibration models, and the methodology and results can benefit assessments of other low-cost sensors.

Numerous particulate matter (PM) sensors with great development potential have emerged. However, whether the current sensors can be used for reliable long-term field monitoring is unclear. This study describes the research and application prospects of low-cost miniaturized sensors in PM2.5 monitoring. We evaluated five Plantower PMSA003 sensors deployed in Beijing, China, over 7 months (October 2019 to June 2020). The sensors tracked PM2.5 concentrations, which were compared to the measurements at the national control monitoring station of the Ministry of Ecology and Environment (MEE) at the same location. The correlations of the data from the PMSA003 sensors and MEE reference monitors (R2 = 0.83~0.90) and among the five sensors (R2 = 0.91~0.98) indicated a high accuracy and intersensor correlation. However, the sensors tended to underestimate high PM2.5 concentrations. The relative bias reached −24.82% when the PM2.5 concentration was >250 µg/m3. Conversely, overestimation and high errors were observed during periods of high relative humidity (RH > 60%). The relative bias reached 14.71% at RH > 75%. The PMSA003 sensors performed poorly during sand and dust storms, especially for the ambient PM10 concentration measurements. Overall, this study identified good correlations between PMSA003 sensors and reference monitors. Extreme field environments impact the data quality of low-cost sensors, and future corrections remain necessary.