Spatial Upscaling-Based Algorithm for Detection and Estimation of Hazardous Gases

Abstract

Recently, society/industry is getting smarter and sustainable through artificial intelligencebased solutions. However, this rapid advancement is also polluting our air ambience. Hence real-time detection and estimation of hazardous gases/odors in the air ambiance has become a critical need. In this paper, a convolutional neural network (CNN) based multi-element gas sensor arrays signature response analysis approach has been presented to achieve higher accuracy in detection and estimation of hazardous gases. Accordingly, the real-time gas sensor array responses are spatially upscaled and processed on the edge, using lightweight CNNs. For the verification of our hypothesis, we have used a four-element metaloxide semi-conductor (MOS)-based thick-film gas sensor array, fabricated by our group, by using SnO2, ZnO, MoO, CdS materials for detection and estimation of four target hazardous gases, viz., acetone, carbon-tetrachloride, ethyl-methyl-ketone, and xylene. The four-element (2×2) raw sensor responses are first upscaled to 6×6 responses and a lightweight CNN is trained on 42 samples of 6×6 input vectors. The trained system is then tested using 16 unknown (not used during training) test samples of the considered gases/odors. All the 16 test samples are detected correctly. The Mean Squared Error (MSEs) of detection has been 1.42×10 -14 while the estimation accuracy of 2.43×10 -3 were achieved for the considered gases. Our designed system is generic in design and can be extended to other gases/odors of interest.

An IoT-Enabled E-Nose for Remote Detection and Monitoring of Airborne Pollution Hazards Using LoRa Network Protocol

“…This work used the standardized linear discriminant analysis (SLDA) space transformation method. The SLDA transforms raw data into respective space transformation domains [ 7 , 24 , 25 , 26 , 27 , 28 ]. The first three principal components contained 98.88% of the information, using which we obtained a 3D scatter plot which showed well-separated clusters with good intercluster separation [ 8 ], as shown in Figure 6 .…”

Potential of Satellite-Airborne Sensing Technologies for Agriculture 4.0 and Climate-Resilient: A Review

“…By providing detailed information on greenhouse gas emissions, land use changes, and vegetation dynamics, these technologies contribute to assessing and monitoring carbon sequestration efforts in agricultural landscapes [130]. The data can support implementing and evaluating climate-smart agricultural practices, such as agroforestry, precision nutrient management, and conservation agriculture, which aim to reduce greenhouse gas emissions [131,132,133,134,135] and enhance carbon sinks in agricultural ecosystems.…”

Real-Time Monitoring of Toxic Gases using Artificial Neural Networks with SnO2-based Thick Film Gas Sensors

“…There is increasing public unease regarding the environmental repercussions of industrial activities. Comprehensive environmental quality monitoring encompasses various aspects, such as global, local, indoor, and outdoor air quality assessments, tailored to the specific pollutants, their sources, and their environmental effects [ [1], [2]]. Global surveillance typically focuses on tracing greenhouse gases like CO2, CH4, N2O, NO, and CO, while the scope of local, indoor, and outdoor assessments extends to the detection of toxic, explosive gases, and odors, predominantly volatile organic compounds (VOCs).…”