On Data-Driven Self-Calibration for IoT-Based Gas Concentration Monitoring Systems

Abstract

In this paper, data-driven self-calibration algorithms for the Internet-of-Things-based gas concentration monitoring systems embedded with low-cost gas sensors are designed. The measurement errors are assumed to be caused by imperfect compensation for the variation of sensor component behavior. Specifically, the calibration procedure for the non-dispersive infrared CO2 sensors is developed, for which the temperature dependency is the most dominant drift source. For a single sensor, the hidden Markov model is used to characterize the statistical relationship between different quantities introduced by the physical model that builds on the Beer-Lambert law. For the calibration in the Internet-of-Things-based system, sensors first transmit their belief functions of the true gas concentration level to the cloud. Then the cloud fusion center computes a fused belief function according to certain rules. This belief function is then used as reference for calibrating the sensors. To deal with the case where belief functions highly conflict with each other, a Wasserstein distance based weighted average belief function fusion approach is first proposed as networked calibration algorithm. To achieve more long-term stable calibration results, the networked calibration problem is further formulated as a partially observed Markov decision process problem, and the calibration strategies are derived in a sequential manner. Correspondingly, the deep Q-network approach is applied as a computationally efficient method to solve the proposed Markov decision process problem. The performance of practical designs of the proposed self-calibration algorithms is finally illustrated in numerical experiments utilizing real data.

Time-Adaptive Expectation Maximization Learning Framework for HMM Based Data-Driven Gas Sensor Calibration

“…The general operation principle of an NDIR sensor is illustrated Fig. 1, more details can be found in previous works [15] and [28]. In this work, we focus on the CO 2 NDIR sensors for which the temperature dependency is the most dominant effect on the sensor components behavior [7].…”

“…We use the same HMM framework as proposed in [15] and [28] to jointly model the statistical relationship between observed sensor measurements sequence, observed environmental temperature sequences, and the sequence of true calibration parameter. This stochastic model is designed to capture the aforementioned dependency between the behavior of the sensor components and the temperature.…”

“…Remark 1: To make sure that the hidden states proposed above fit into the basic HMM framework as defined in Section II-B, we need to quantize the true calibration parameter and the temperature change to different finite sets. More details regarding the quantization scheme can be found in papers [15] and [28]. The quantization of the continuous hidden state space will lead to a decrease in the model accuracy.…”

Review–Modern Data Analysis in Gas Sensors

“…A hybrid pattern recognition model based on PCA and K-means clustering was proposed in another study 151 for explosive detection. An example of deep reinforcement learning was reported in a prior study 152 where a deep Q-network was used to self-calibrate the sensors of a remote system. Genetic algorithm is also getting popular toward feature selection for fast and reliable decision-making.…”

“…For self-calibration of Internet of things (IoT) based sensor systems, the hidden Markov model was used for characterization of a single sensor. 159 You et al 152 proposed a complete scheme of calibrating IoT gas sensors which eradicates the Markov decision process problem by utilizing a deep Q-network. To suppress faulty sensor data from inserting to the classifier, Magna et al 160 proposed a self-repairing scheme, where the faulty sensor will be replaced by a replica to increase the consistency of model performance.…”