Statistical data pre-processing and time series incorporation for high-efficacy calibration of low-cost NO2 sensor using machine learning.

Air pollution stands as a significant modern-day challenge impacting life quality, the environment, and the economy. It comprises various pollutants like gases, particulate matter, biological molecules, and more, stemming from sources such as vehicle emissions, industrial operations, agriculture, and natural events. Nitrogen dioxide (NO2), among these harmful gases, is notably prevalent in densely populated urban regions. Given its adverse effects on health and the environment, accurate monitoring of NO2 levels becomes imperative for devising effective risk mitigation strategies. However, the precise measurement of NO2 poses challenges as it traditionally relies on costly and bulky equipment. This has prompted the development of more affordable alternatives, although their reliability is often questionable. The aim of this article is to introduce a groundbreaking method for precisely calibrating cost-effective NO2 sensors. This technique involves statistical preprocessing of low-cost sensor readings, aligning their distribution with reference data. Central to this calibration is an artificial neural network (ANN) surrogate designed to predict sensor correction coefficients. It utilizes environmental variables (temperature, humidity, atmospheric pressure), cross-references auxiliary NO2 sensors, and incorporates short time series of previous readings from the primary sensor. These methods are complemented by global data scaling. Demonstrated using a custom-designed cost-effective monitoring platform and high-precision public reference station data collected over 5 months, every component of our calibration framework proves crucial, contributing to its exceptional accuracy (with a correlation coefficient near 0.95 concerning the reference data and an RMSE below 2.4 µg/m3). This level of performance positions the calibrated sensor as a viable, cost-effective alternative to traditional monitoring approaches.

Real-Time PPG Signal Conditioning with Long Short-Term Memory (LSTM) Network for Wearable Devices.

This paper presents an algorithm for real-time detection of the heart rate measured on a person's wrist using a wearable device with a photoplethysmographic (PPG) sensor and accelerometer. The proposed algorithm consists of an appropriately trained LSTM network and the Time-Domain Heart Rate (TDHR) algorithm for peak detection in the PPG waveform. The Long Short-Term Memory (LSTM) network uses the signals from the accelerometer to improve the shape of the PPG input signal in a time domain that is distorted by body movements. Multiple variants of the LSTM network have been evaluated, including taking their complexity and computational cost into consideration. Adding the LSTM network caused additional computational effort, but the performance results of the whole algorithm are much better, outperforming the other algorithms from the literature.

Photoplethysmographic Time-Domain Heart Rate Measurement Algorithm for Resource-Constrained Wearable Devices and its Implementation.

This paper presents an algorithm for the measurement of the human heart rate, using photoplethysmography (PPG), i.e., the detection of the light at the skin surface. The signal from the PPG sensor is processed in time-domain; the peaks in the preprocessed and conditioned PPG waveform are detected by using a peak detection algorithm to find the heart rate in real time. Apart from the PPG sensor, the accelerometer is also used to detect body movement and to indicate the moments in time, for which the PPG waveform can be unreliable. This paper describes in detail the signal conditioning path and the modified algorithm, and it also gives an example of implementation in a resource-constrained wrist-wearable device. The algorithm was evaluated by using the publicly available PPG-DaLia dataset containing samples collected during real-life activities with a PPG sensor and accelerometer and with an ECG signal as ground truth. The quality of the results is comparable to the other algorithms from the literature, while the required hardware resources are lower, which can be significant for wearable applications.

Support for Employees with ASD in the Workplace Using a Bluetooth Skin Resistance Sensor⁻A Preliminary Study.

The application of a Bluetooth skin resistance sensor in assisting people with Autism Spectrum Disorders (ASD), in their day-to-day work, is presented in this paper. The design and construction of the device are discussed. The authors have considered the best placement of the sensor, on the body, to gain the most accurate readings of user stress levels, under various conditions. Trial tests were performed on a group of sixteen people to verify the correct functioning of the device. Resistance levels were compared to those from the reference system. The placement of the sensor has also been determined, based on wearer convenience. With the Bluetooth Low Energy block, users can be notified immediately about their abnormal stress levels via a smartphone application. This can help people with ASD, and those who work with them, to facilitate stress control and make necessary adjustments to their work environment.