Fig 3 - uploaded by Mario Molinara
Content may be subject to copyright.
Source publication
![Fig. 3. The behaviour of the previous EMA [11].](profile/Mario-Molinara/publication/355306827/figure/fig3/AS:1080242219298910@1634561223811/The-behaviour-of-the-previous-EMA-11_Q320.jpg)
Water monitoring systems continuously working
ensure real–time pollutant detection capabilities according to
their sensitivity and specificity. It is necessary to balance such
features because, although being able to sense several substances
is a desired feature, the reduction of false positives is a primary
goal a classification system should have...
Contexts in source publication
Context 1
... It is unable to follow the sensor drift during the phase in which only SWW is present; • It is unable to preserve a stable value during the phase in which a substance is present; • Finally, it works in counter-phase during wash-out (when the substance go away). Figures 3 and 4 represent the behaviours of the old baseline and the new baseline. A set of instants are highlighted: t 0 when the acquisition starts, t 1 when the substance is injected, t 2 when the substance is removed (through dilution), t 3 when the substance "disappears" because the dilution becomes very high. ...
Context 2
... set of instants are highlighted: t 0 when the acquisition starts, t 1 when the substance is injected, t 2 when the substance is removed (through dilution), t 3 when the substance "disappears" because the dilution becomes very high. In figure 3, the baseline for a single signal is generated without any adaptation to the signal behaviour. It is possible to see that, in the interval [t 0 , t 1 ], the baseline is far from the true signal. ...
Citations
... [mm 2 ] and 1.5 [mW ] power absorption, shown in Fig. 1. The SCW is produced by Sensichips Srl [25] and is based on the micro-chip SENSIPLUS [26] they developed in collaboration with the University of Pisa, Italy. ...
... In terms of data processing, acquired measurements are generally processed to become features to feed Machine Learning (ML)/ Deep Learning (DL) algorithms adopted for classification (Lowe et al., 2022;Koditala and Pandey, 2018;Bansal and Geetha, 2020;Dilmi and Ladjal, 2021;Bria et al., 2021;Bria et al., 2020). Major challenges regard finding pathways to have fast data exchange, classify with acceptable computational complexity in nearly real-time and be able to discriminate among different pollutants that can be found in the flowing wastewater. ...
The problem of detecting illegal pollutants in wastewater is of fundamental importance for public health and security. The availability of distributed, low–cost and low–power monitoring systems, particularly enforced by IoT communication mechanisms and low-complexity machine learning algorithms, would make it feasible and easy to manage in a widespread manner. Accordingly, an End-to-End IoT-ready node for the sensing, local processing, and transmission of the data collected on the pollutants in the wastewater is presented here. The proposed system, organized in sensing and data processing modules, can recognize and distinguish contaminants from unknown substances typically present in wastewater. This is particularly important in the classification stage since distinguishing between background (not of interest) and foreground (of interest) substances drastically improves the classification performance, especially in terms of false positive rates. The measurement system, i.e., the sensing part, is represented by the so-called Smart Cable Water based on the SENSIPLUS chip, which integrates an array of sensors detecting various water-soluble substances through impedance spectroscopy. The data processing is based on a commercial Micro Control Unit (MCU), including an anomaly detection module, a classification module, and a false positive reduction module, all based on machine learning algorithms that have a computational complexity suitable for low-cost hardware implementation.
An extensive experimental campaign on different contaminants has been carried out to train machine-learning algorithms suitable for low-cost and low-power MCU. The corresponding dataset has been made publicly available for download. The obtained results demonstrate an excellent classification ability, achieving an accuracy of more than 95% on average, and are a reliable ”proof of concept” of a pervasive IoT system for distributed monitoring.
