Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
(a) Placement of the 32 low-cost temperature sensors schematically represented atop a thermal image of the hotplate when set at 50 • C. The two rows bounded in the black box are analog sensors, where as the green box contains digital sensors. (b) Schematic of our circuit. Only four sensors of each type are shown to simplify the figure.
Source publication
In the upcoming years, artificial intelligence (AI) is going to transform the practice of medicine in most of its specialties. Deep learning can help achieve better and earlier problem detection, while reducing errors on diagnosis. By feeding a deep neural network (DNN) with the data from a low-cost and low-accuracy sensor array, we demonstrate tha...
Contexts in source publication
Context 1
... sensors are mounted on an IKA C-MAG HS 7 control hotplate 33 with thermal paste to ensure conductivity and fixed with thermally-conductive tape, using the configurations shown in Figures 1 & 2. The sensors are placed in a 4x8 array, covering the center of the plate as indicated in Figure 1(a). Two (2) rows consist of the digital sensors and two (2) rows for the analog sensors. ...
Context 2
... two types of sensors helps diversify our dataset, while providing enough data for a meaningful distribution (see Supplementary Information section to compare both sensor types). All 32 sensors are connected through wires to the Arduino microcontroller as shown in Figure 1. There, Figure 1(a) shows a representation of the experimental setup condition. ...
Context 3
... 32 sensors are connected through wires to the Arduino microcontroller as shown in Figure 1. There, Figure 1(a) shows a representation of the experimental setup condition. The approximate placement of the 32 low-cost temperature sensors is schematically represented atop a thermal image of the hotplate when set at 50 • C. From the thermal image acquired using a FLIR-One infrared camera, it is clear that the temperature is not uniform everywhere on the hotplate. ...
Context 4
... we want our model learn to predict the established temperature of the plate, even if it is changing wildly depending on the position of the sensors on the hotplate. Figure 1(b) shows the circuit on the Arduino Mega2650. For each degree measurement, we waited for two minutes to make sure that the hotplate's temperature is stable before collecting the sensors' readings each 1.5 seconds for four minutes using the Arduino. ...
Context 5
... 4 shows a 3D representation of our 4x8 sensor array as the temperature increases on the hotplate (heatmap) from two (2) different viewpoints. Just like the thermal image of Figure 1, it is clear that some sensors are subjected to different temperatures locally. At 30 • , the whole array is red (lower temperatures), and it then becomes increasingly yellow (higher temperatures) at different rates. ...
Similar publications
In the upcoming years, artificial intelligence is going to transform the practice of medicine in most of its specialties. Deep learning can help achieve better and earlier problem detection, while reducing errors on diagnosis. By feeding a deep neural network (DNN) with the data from a low-cost and low-accuracy sensor array, we demonstrate that it...
