Accuracy verification of low-cost CO2 concentration measuring devices for general use as a countermeasure against COVID-19

Within the context of the COVID-19 pandemic, CO2 sensors that measure ventilation conditions and thereby reduce the risk of airborne infection, are gaining increasing attention. We investigated and verified the accuracy of 12 relatively low-cost sensor models that retail for less than $45 and are advertised as infection control measures on a major e-commerce site. Our results indicate that 25% of the tested sensors can be used to identify trends in CO2 concentration, if correctly calibrated. However, 67% of sensors did not respond to the presence of CO2, which suggests that a type of pseudo-technique is used to display the CO2 concentration. We recommend that these sensors are not suitable for infection prevention purposes. Furthermore, 58% of the investigated sensors showed significant responses to the presence of alcohol. Owing to the widespread use of alcohol in preventing the spread of infectious diseases, sensors that react to alcohol can display inaccurate values, resulting in inappropriate ventilation behavior. Therefore, we strongly recommended that these sensors not be used. Based on our results, we offer practical recommendations to the average consumer, who does not have special measuring equipment, on how to identify inaccurate CO2 sensors.

Configurable Sensor Model Architecture for the Development of Automated Driving Systems

Sensor models provide the required environmental perception information for the development and testing of automated driving systems in virtual vehicle environments. In this article, a configurable sensor model architecture is introduced. Based on methods of model-based systems engineering (MBSE) and functional decomposition, this approach supports a flexible and continuous way to use sensor models in automotive development. Modeled sensor effects, representing single-sensor properties, are combined to an overall sensor behavior. This improves reusability and enables adaptation to specific requirements of the development. Finally, a first practical application of the configurable sensor model architecture is demonstrated, using two exemplary sensor effects: the geometric field of view (FoV) and the object-dependent FoV.

Data Fusion of XRF and Vis-NIR Using Outer Product Analysis, Granger–Ramanathan, and Least Squares for Prediction of Key Soil Attributes

Visible-near-infrared (vis-NIR) and X-ray fluorescence (XRF) are key technologies becoming pervasive in proximal soil sensing (PSS), whose fusion holds promising potential to improve the estimation accuracy of soil attributes. In this paper, we examine different data fusion methods for the prediction of key soil fertility attributes including pH, organic carbon (OC), magnesium (Mg), and calcium (Ca). To this end, the vis-NIR and XRF spectra of 267 soil samples were collected from nine fields in Belgium, from which the soil samples of six fields were used for calibration of the single-sensor and data fusion models while the validation was performed on the remaining three fields. The first fusion method was the outer product analysis (OPA), for which the outer product (OP) of the two spectra is computed, flattened, and then subjected to partial least squares (PLS) regression model. Two versions of OPA were evaluated: (i) OPA-FS in which the full spectra were used as input; and (ii) OPA-SS in which selected spectral ranges were used as input. In addition, we examined the potential of least squares (LS) and Granger–Ramanathan (GR) analyses for the fusion of the predictions provided by the single-sensor PLS models. Results demonstrate that the prediction performance of the single-sensor PLS models is improved by GR in addition to the LS fusion method for all soil attributes since it accounts for residuals. Resorting to LS, the largest improvements compared to the single-sensor models were obtained, respectively, for Mg (residual prediction deviation (RPD) = 4.08, coefficient of determination (R2) = 0.94, ratio of performance of inter-quantile (RPIQ) = 1.64, root mean square error (RMSE) = 4.57 mg/100 g), OC (RPD = 1.79, R2 = 0.69, RPIQ = 2.82, RMSE = 0.16%), pH (RPD = 1.61, R2 = 0.61, RPIQ = 3.06, RMSE = 0.29), and Ca (RPD = 3.33, R2 = 0.91, RPIQ = 1, RMSE = 207.48 mg/100 g). OPA-FS and OPA-SS outperformed the individual, GR, and LS models for pH only, while OPA-FS was effective in improving the individual sensor models for Mg as well. The results of this study suggest LS as a robust fusion method in improving the prediction accuracy for all the studied soil attributes.

Towards Easy-to-Use Bacteria Sensing: Modeling and Simulation of a New Environmental Impedimetric Biosensor in Fluids

Conventional pathogenic bacteria-detection methods are lab-bound, time-consuming and need trained personnel. Microelectrodes can be used to recognize harmful microorganisms by dielectric impedance spectroscopy. However, crucial for this spectroscopy method are the spatial dimensions and layout of the electrodes, as the corresponding distribution of the electric field defines the sensor system parameters such as sensitivity, SNR, and dynamic range. Therefore, a variety of sensor models are created and evaluated. FEM simulations in 2D and 3D are conducted for this impedimetric sensor. The authors tested differently shaped structures, verified the linear influence of the excitation amplitude and developed a mathematical concept for a quality factor that practically allows us to distinguish arbitrary sensor designs and layouts. The effect of guard electrodes blocking outer influences on the electric field are investigated, and essential configurations are explored. The results lead to optimized electronic sensors in terms of geometrical dimensions. Possible material choices for real sensors as well as design and layout recommendations are presented.

Integrating Sensor Models in Deep Learning Boosts Performance: Application to Monocular Depth Estimation in Warehouse Automation

Deep learning is the mainstream paradigm in computer vision and machine learning, but performance is usually not as good as expected when used for applications in robot vision. The problem is that robot sensing is inherently active, and often, relevant data is scarce for many application domains. This calls for novel deep learning approaches that can offer a good performance at a lower data consumption cost. We address here monocular depth estimation in warehouse automation with new methods and three different deep architectures. Our results suggest that the incorporation of sensor models and prior knowledge relative to robotic active vision, can consistently improve the results and learning performance from fewer than usual training samples, as compared to standard data-driven deep learning.