Instrumentation & Measurement Magazine 24-2 - 84

Machine Learning in Measurement
Part 1: Error Contribution and
Terminology Confusion
Shervin Shirmohammadi and Hussein Al Osman

ike any science and engineering field, Instrumentation
and Measurement (I&M) is currently experiencing the
impact of the recent rise of Applied AI and in particular Machine Learning (ML) [1]. But I&M and ML use
terminology that sometimes sound or look similar, though
they might only have a marginal relationship or even be false
friends. Therefore, understanding the terminology used by
both communities and how they do and do not relate to one another is of crucial importance to understand the influences of
ML in an I&M system. In addition, while I&M experts are well
aware of the importance of measurement uncertainty, the concept has been understudied in the ML context. In this article,
we will give an overview of ML's contribution to measurement
error, and how to avoid confusion with the said terminology,
to better understand the application of ML in measurement.
Then, in Part 2 [2], we use that understanding and terminology to show how to quantify the uncertainty introduced by ML
in a measurement system. This is of particular importance for
measurement in the age of
big data because we need
to evaluate the trustworthiness of the available data
and their impact on the
derived conclusions and
decision-making [3].

relationship " [4, 311-02-02]. Fig. 1 depicts the concept of indirect measurement, which is used when directly measuring
y is difficult, expensive, or does not fulfill the timeliness requirements of the application. In those cases, we can directly
measure other quantities such as x1, x2, and x3, which are easier,
less costly, or faster to measure, and which have a functional
relationship f with y. We can then find the value of y from the
values of those other quantities using f. This means that the
total measurement experiment in indirect measurement still
contains a direct measurement component, as shown with the
gray box in Fig. 1. If we represent the variables x1 to xn by vector x, then we simply have y=f(x).
As a concrete example, let's say we want to measure the
calories of some random food we are served in a restaurant.
We can directly measure the calories in a Bomb Calorimeter
instrument; however, this is expensive, not something one
can carry with oneself, and destroys the food by burning it
in the measurement process. Alternatively, we can use a food

Machine
Learning in I&M
In I&M, ML is used for indirect measurement, which
is defined as a " method of
measurement in which the
value of a quantity is obtained from measurements
made by direct methods
of measurement of other
quantities linked to the
measurand [the quantity to
be measured] by a known
84

Fig. 1. Indirect Measurement. In this case y is being measured indirectly from x1, x2, and x3.

IEEE Instrumentation & Measurement Magazine
1094-6969/21/$25.00©2021IEEE

April 2021

Instrumentation & Measurement Magazine 24-2

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 24-2