=Paper=
{{Paper
|id=Vol-2278/paper02
|storemode=property
|title=MEMS Sensors Bias Thermal Profiles Classification Using Machine Learning
|pdfUrl=https://ceur-ws.org/Vol-2278/paper02.pdf
|volume=Vol-2278
|authors=Sergey Reginya,Vladislav Nikolaenko,Roman Voronov,Alexei Soloviev,Axel Sikora,Alex Moschevikin
}}
==MEMS Sensors Bias Thermal Profiles Classification Using Machine Learning==
https://ceur-ws.org/Vol-2278/paper02.pdf
MEMS Sensors Bias Thermal Profiles
Classification Using Machine Learning
Sergey Reginya1 , Vladislav Nikolaenko2 , Roman Voronov2 , Alexei
Soloviev2 , Axel Sikora3,4 , and Alex Moschevikin1,2
1
Nanoseti LTD, Petrozavodsk, Russian Federation
alexmou@lab127.karelia.ru
http://lab127.ru
2
Petrozavodsk State University, Petrozavodsk, Russian Federation
http://petrsu.ru
3
Hahn-Schickard Gesellschaft für Angewandte Forschung e.V.,
Villingen-Schwenningen, Germany
axel.sikora@hahn-schickard.de
4
Offenburg University of Applied Sciences, Offenburg, Germany
axel.sikora@hs-offenburg.de
Abstract. The paper describes the methodology and experimental re-
sults for revealing similarities in thermal dependencies of biases of ac-
celerometers and gyroscopes from 250 inertial MEMS chips (MPU-9250).
Temperature profiles were measured on an experimental setup with a
Peltier element for temperature control. Classification of temperature
curves was carried out with machine learning approach.
A perfect sensor should not have thermal dependency at all. Thus, only
sensors inside the clusters with smaller dependency (smaller total tem-
perature slopes) might be pre-selected for production of high accuracy
inertial navigation modules.
It was found that no unified thermal profile (“family” curve) exists for
all sensors in a production batch. However, obviously, sensors might be
grouped according to their parameters. Therefore, the temperature com-
pensation profiles might be regressed for each group. 12 slope coefficients
on 5 degrees temperature intervals from 0o C to +60o C were used as the
features for the k-means++ clustering algorithm.
The minimum number of clusters for all sensors to be well separated
from each other by bias thermal profiles in our case is 6. It was found by
applying the elbow method. For each cluster a regression curve can be
obtained.
Keywords: MEMS · accelerometer · gyroscope · inertial measurement
unit · temperature dependency · cluster · machine learning.
1 Introduction
A Micro-Electro-Mechanical-Systems (MEMS) device is a combination of inte-
grated mechanical and electrical systems on a single chip that should be batch
fabricated with high yield and no additional or subsequent assembly. The inte-
gration process may be implemented as hybrid integration using conventional
wire bonding and flip-chips, or monolithic integration [11]. Monolithic integra-
tion offers superior system integration performance to hybrid systems but at an
overall higher effort in upfront and non-recurring engineering (NRE) costs in
terms of involved technology and processing [1].
Despite the many similarities between IC (integrated circuit) and MEMS fab-
rication, MEMS fabrication methods are significantly more complex, especially
in case of production of multisensor modules [7,11]. Unlike an ordinary IC fac-
tory, which performs one or two standard processes, a MEMS factory normally
performs a wide variety of processes.
The physical characteristics of the base material, accuracy of topology build-
ing over the wafer and the complexity of MEMS fabrication are the major factors,
which have an impact on random and systematic errors of sensor readouts. The
error mechanisms affecting the accuracy of MEMS sensors originate from sensi-
tivities and stability of dimensions of sensor parts and sensitivities and stability
of electronics. Mechanical stress also could be a source of inaccuracies.
Under static conditions major part of errors can be considered, measured and
excluded. However, in dynamics it is hard to separate fluctuating zero offsets
from the true physical signal.
As is typical of inertial sensors, thermal effects are a primary driver of in-
accuracies [13,14]. For example, the stiffness coefficient of beams, the damping
ratio and other MEMS material parameters change with temperature and affect
the gyroscope. These phenomena are subject to analysis, modelling [8,21] and
compensating [4,12,22].
Consequently, MEMS chips manufacturers denote large error intervals for
produced sensors. For example, gyroscope zero-rate output (ZRO) variation over
temperature range of −40o C · · · + 85o C is declared as ±30o /s [15].
Inertial sensors may be embedded in dead reckoning systems, which calculate
the current position by using a previously determined position (also called fix),
and advancing that position based upon known or estimated linear or rotational
speeds or accelerations over elapsed time and trajectory.
One possible way to improve the accuracy of the estimation positioning or ori-
entation is to carry out periodical self-calibration of inertial modules. However,
during long periods of continuous motion under conditions of varying tempera-
ture it is impossible to run autocalibration algorithms.
For this, developers use temperature compensation data obtained in prelimi-
nary tests in thermal chambers. The compensation functions might be presented
in either “family” curves (tables) or unique profiles for the chips. Both depen-
dencies are pre-measured for the manufactured inertial measurement unit on a
factory side, not by a customer, which leads to both a limited visibility of the
internal processes in the modules and a significant dependency from the module
vendor. This is restricting the achievable performance as the chip vendor will
typically choose a compromise between accuracy and computational complex-
ity. If the algorithms were open, system developers could more flexibly trade-off
these two objectives and reach better accuracy with the same physical modules
through more complex compensation algorithms.
So the goal is either to find the “family” curve for all sensors in a batch, or to
divide them into groups and to obtain separate regression curves for each group.
In order to achieve this goal, we started this cluster analysis of thermal curves
of MEMS sensors, which is - to our best knowledge - the first public discussion
of these aspects.
The remainder of the paper is organized as follows. In chapter 2 we give a
short overview of the related works for the state of the art. In chapter 3, we
describe our ongoing project, sensor chips used as devices under test (DUT) and
our experimental setup and proposed processing algorithms. In Section 4 we
present clustering groups of obtained bias thermal profiles and discuss possible
correlation between them. Section 5 concludes the paper.
2 Related Works
Machine learning is widely applied to separate signal spectra in groups [18].
However, the papers devoted to the statistical analysis of sensors compensation
curves are rare, since researchers usually do not have statistically significant
amount of sensors. One of the examples of applying polynomial regression for
finding a “family” curve for MEMS barometric sensors is presented in [9].
One of the problems concerning clustering time series data or any other func-
tional data is that each data point contains a noise component. Thus, additional
data preprocessing is required. T. Tarpey investigated the curve clustering per-
formance depending on the quality of how the curves are fit to the data [20].
Another approach was demostrated by A. Antoniadis et al. [3]. They represent
time series data on electricity consumption as a set of wavelets and then tried
to group the processed data by means of K-centroid algorithm.
In practice, the clustering problem can be solved by various algorithms: K-
medoids, hierarchical clustering, density-based clustering, etc. [10].
It this paper the k-means++ algorithm was applied [2,5]. The algorithm is
based on minimizing the within-cluster sum of squares. Euclidean distance is
used as a metric in data space. We also implemented additional procedure of
initialization of the cluster centers as presented in [6]. It is known that the k-
means++ algorithm converges to a local minimum. Therefore, if it is appropriate,
the exact optimum might be found by the brute force.
3 Devices Under Test and Measurements
3.1 Devices Under Test
Our ongoing project is devoted to the development of the high precision au-
tonomous self-calibrating MEMS multisensor inertial module unit MIMU2.5,
presented in Fig. 1 [17,19].
Fig. 1: Multisensor inertial measurement module MIMU2.5
Each MIMU2.5 consists of five 9DOF MPU-9250 chips (3D accelerometer,
3D wope, 3D magnetometer and temperature sensor) [15]. MPU-9250 chips are
mounted on the inner surface of the top aluminium cover at different angles to
each other.
The pilot production batch of MIMU2.5 modules consisted of 50 pieces. Thus,
approximately 250 MPU-9250 chips can be used as devices under test (DUTs).
According to the datasheet of MPU-9250 [15], it contains two dice: a MPU-
6500 accelerometer and gyroscope produced by InvenSense and an AK8963 mag-
netometer of Asahi Kasei Microdevices Corporation.
3.2 Temperature Dependence Registration
To register temperature profiles for all axes of accelerometers and gyroscopes
an experimental setup was constructed. It consists of a thermoelectric cooler
(TEC, Peltier element) controlled by a microcontroller and a cooling system
comprising a heat sink and a fan (Fig. 2a). The aluminium flange of MIMU
module was attached to the cooling side of the TEC.
First, the inertial module was cooled to the minimum temperature of approx-
imately 0o C, which depends on the ambient temperature. The achieved temper-
ature was monitored by the sensors embedded in MPU9250 chips. Acceleration
and rotation rate values along with the temperature data were registered by the
external computer connected to the MIMU module via RS-232 interface.
Then, the polarity of the supplied voltage was changed to inverted and heat-
ing started. After reaching 60o C the experiment ended.
3.3 Clustering Methods for the Bias Thermal Dependencies
We propose the following method for clustering bias thermal profiles. First, ther-
mal dependencies are registered as a set of measurement points. Then, the whole
temperature range is divided into n intervals. In each interval the regressed slope
coefficients for all sensors are determined. Thus each sensor curve is characterized
by a set of n slope coefficients. Then, slope coefficients are standardized and used
as features in machine learning. Finally, bias thermal profiles are distributed in
a number of clusters according to their sets of n slope coefficients.
Fig. 2: a) Scheme of the experimental setup. b) An example of registered accel-
eration in still condition in temperature cycle from 0o C to 60o C.
From the one hand, the number of intervals should not be large in order to
improve classification. From the other, it should not be small, since the obtained
piece-wise function should well describe the curved profile.
In our investigation we chose n = 12, leaving 5 measurement points per
interval for linear regression. The number of clusters was varied from 5 to 12.
Both accelerometer and gyroscope bias thermal profiles are handled similarly.
Further in formal representation of the algorithm we consider measurements from
a triaxial accelerometer.
Let I be the index set used for numbering accelerometers.
Consider a vector ai (t) = (aiX (t), aiY (t), aiZ (t)) consisting of temperature
profiles registered for X-, Y-, and Z-axes of i-th accelerometer, i ∈ I. We assume
that
aiX (t) = aX + ∆iX (t) + δiX
aiY (t) = aY + ∆iY (t) + δiY (1)
aiZ (t) = aZ + ∆iZ (t) + δiZ ,
where a = (aX , aY , aZ ) is the vector of true accelerations,
∆i (t) = (∆iX (t), ∆iY (t), ∆iZ (t)) is the bias (zero offset) vector of the accelero-
meter i at a temperature t,
δ i = (δiX , δiY , δiZ ) is the vector of normally distributed random variables with
zero means, characterizing the noise of measurements.
The functions ai (t) are assumed differentiable in the mean-square sense.
Let the temperature range T = [t1 , t2 ] is divided into N = mn points with
equal intervals: τ0 = t1 , τ1 = τ0 + h, . . . , τN = t2 . The interval h is selected as
−t1
follows: h = t2N , where m is the size of the temperature interval, n is the
number of features for the subsequent clustering of sensors.
Thus we divide thermal profiles aiX (t), aiY (t), aiZ (t) into a certain number
of intervals n, see Fig. 3 (n = 12).
F3
F2 F4
F1
F11
F12
Fig. 3: Extracting features from a temperature curve of accelerometer bias.
F1 ...F12 – slopes of linear approximations on intervals.
Similar thermal profiles of different sensors can be grouped. Every group has
a typical set of derivatives (F1 ...F12 , Fig. 3).
We define ∆i (t), i ∈ I as the bias thermal dependance for i-th accelerometer
and carry out clustering accelerometers on the basis of the similarity of the
derivatives of functions ∆iX (t), ∆iY (t), ∆iZ (t).
We describe the clustering method for the X-axis. For the Y - and Z-axes the
method works similarly.
Since the expectation value E[δiX ] = 0, then
∆iX (t) = E[aiX (t)] − aX . (2)
Further,
∆0iX (t) = (E[aiX (t)])0 . (3)
We will use ãiXj as the sample mean values of aiX (t) on every intervals
[τj−1 , τj ) to estimate the expectation of the values of this function, j = 1, . . . , N .
We will use the following method to estimate the derivatives of the expecta-
tion value of the function aiX (t).
For each k = 1, . . . , n we construct linear regressions
f (τ ) = BiXk · τ + CXk (4)
by sets of m points
h
τj + , ãiXj | j = (k − 1)m + 1, . . . , km . (5)
2
The angular coefficients BiXk will serve as estimates for (E[aiX (t)])0 on the
intervals [τ(k−1)m , τkm ) for k = 1, . . . , n.
Before clustering, the resulting values of BiXk attributes for accelerometers
need to be standardized.
Let B Xk be the sample mean and σiXk be the sample standard deviation for
the numbers BiXk , i ∈ I.
We introduce the standardized features:
BiXk − B iXk
DiXk = , i ∈ I, k = 1, . . . , n. (6)
σiXk
Standardization involves the preprocessing of data, after that every feature
has an average value of 0 and a variance of 1.
For clustering we use the k-means++ algorithm [6]. Though it converges
to a local minimum, visual control of plots with grouped profiles approved the
possibility of this approach. Also we checked the results by applying hierarchical
clustering method. It yielded similar results for clustering bias thermal profiles.
For the axes Y and Z, clustering is carried out in a similar way.
3.4 Similarity of Thermal Profiles in Different Clusters
We estimate the similarity between clusters belonging to different sensors (either
between different axes of the single sensor or between the accelerometer and the
gyroscope in the certain chip) by means of the Jaccard index J(A, B), which
measaures the similarity and diversity between two finite sample sets A and B.
The Jaccard index is defined as the size of the intersection divided by the
size of the union of the sets A and B:
|A ∩ B|
J(A, B) = . (7)
|A ∪ B|
The closer the value of the index to 1, the more similar the sets of data. If
the Jaccard index is 1, then the sets are identical. If the Jaccard index is zero,
then the sets do not contain common elements. This index was calculated for all
pairs of sets of obtained clusters.
4 Results and Discussion
The bias thermal profiles for 250 MPU-9250 chips were obtained according the
procedure described in Sec. 3.2. The overall per-axis data for accelerometers and
gyroscopes are presented in Fig. 4. At first, it seems that no unified “family”
curve can be applied for all sensors in the batch to compensate the temperature
dependencies of biases. From the other side, it is possible to split thermal profiles
for each axis into groups with similar shape of the curves inside each group.
Thus, the procedure of clustering was applied. As the temperature range for the
obtained bias dependencies was 0 . . . 60◦ C, the size of the temperature interval
X axis Y axis Z axis
0.6 1.0
0.6
0.4 0.4
0.5
0.2
Acc, [m/s 2]
0.2
0.0 0.0
0.0 −0.2
−0.4 −0.5
−0.2
−0.6
−0.4 −1.0
−0.8
−20 0 20 40 60 −20 0 20 40 60 −20 0 20 40 60
T, [oC] T, [oC] T, [oC]
4
3 8
2 2 6
1 4
Gyro, [dps]
0
0
2
−2 −1
0
−2
−4 −2
−3
−4
−6 −4
−20 0 20 40 60 −20 0 20 40 60 −20 0 20 40 60
T, [oC] T, [oC] T, [oC]
Fig. 4: The obtained bias thermal profiles for X, Y, Z axis of 250 accelerometers
(top) and gyroscopes (bottom).
was chosen of 5o C, that corresponded to 12 features – 12 slope coefficients for
each bias curve.
Then the procedure of clustering was repeated with different number of clus-
ters. The typical result of clustering into 5 groups for accelerometers and gyro-
scopes are shown in Fig. 5.
It can be mentioned that five clusters are not enough for effective clustering
in our case, since a cluster might contain curves of different shapes. For example,
top and bottom curves on AX4 inset (Fig. 5) are slightly different from other 4
profiles.
The example of clustering of accelerometers x-axis bias thermal profile in 9
groups are shown in Fig. 6.
AX1 AX2 AX3 AX4 AX5 AX6 AX7 AX8 AX9
Fig. 6: Clustering results for accelerometer X axis (9 clusters).
The distribution in 9 clusters seems to be more adequate than in 5 clusters
as presented in Fig. 5. Though clusters AX1, AX4 and AX8 are very similar.
AX1 AX2 AX3 AX4 AX5
GX1 GX2 GX3 GX4 GX5
Fig. 5: Clustering thermal bias profiles into 5 groups for accelerometer X (top)
axis and for for gyroscope X axis (bottom).
Also, clustering the data on Z-axis of gyroscope (bottom right inset in Fig. 4)
produce good separation only in the case of at least 9 groups.
The number of clusters depends on the diversity of the profiles, which in
turn depends on the production lot, complexity of the circuit, used materials
and production technology, etc.
The elbow method [16] might be applied to determine the appropriate num-
ber of clusters. For the investigated set of MPU-9250 chips the results are pre-
sented in Fig. 7. Cost function is the inter cluster sum of squared distances from
all cluster elements to the cluster centroid.
1000
Cost function J(K)
800
600
K =9
400
200
5 10 15 20 25 30 35
Number of clusters K
Fig. 7: Inter cluster errors as the function of number of clusters
According to the plot presented in Fig. 7 we recommend to use 6-10 clusters
for each axis.
To check the correlation between clusters belonging to different measurement
axes (X-, Y- and Z-axes of both accelerometers and gyroscopes), the Jaccard
coefficient was calculated for all possible pairs of clusters (Sec. 3.4).
A typical result is shown in Table 1 demonstrating the data for accelerometer
X-Y pair. In headers, the number in brackets represents elements in certain
cluster. The number in brackets near a Jaccard index represents the number of
common elements (intersection) between two clusters.
Table 1: Jaccard Index between groups clustered by X and Y axes. The number
in brackets indicate the numbere of common elements for the two given clusters.
Cluster num. Y axis
(num. of items)
AY1 AY2 AY3 AY4 AY5 AY6 AY7 AY8 AY9
(35) (32) (42) (13) (23) (6) (14) (30) (15)
AX1 0.09 0.13 0.13 0.04 0.07 0.00 0.02 0.06 0.06
(37) (6) (8) (9) (2) (4) (0) (1) (4) (3)
AX2 0.10 0.02 0.13 0.00 0.05 0.00 0.06 0.02 0.06
(20) (5) (1) (7) (0) (2) (0) (2) (1) (2)
AX3 0.03 0.00 0.00 0.00 0.00 0.00 0.06 0.06 0.00
(4) (1) (0) (0) (0) (0) (0) (1) (2) (0)
AX4 0.14 0.08 0.08 0.04 0.05 0.02 0.06 0.14 0.00
(37) (9) (5) (6) (2) (3) (1) (3) (8) (0)
X axis
AX5 0.04 0.07 0.02 0.00 0.09 0.00 0.00 0.07 0.04
(13) (2) (3) (1) (0) (3) (0) (0) (3) (1)
AX6 0.04 0.04 0.02 0.04 0.11 0.00 0.00 0.07 0.11
(16) (2) (2) (1) (1) (4) (0) (0) (3) (3)
AX7 0.10 0.14 0.04 0.10 0.08 0.00 0.07 0.02 0.07
(32) (6) (8) (3) (4) (4) (0) (3) (1) (3)
AX8 0.02 0.06 0.12 0.03 0.04 0.07 0.03 0.12 0.05
(25) (1) (3) (7) (1) (2) (2) (1) (6) (2)
AX9 0.05 0.04 0.13 0.08 0.02 0.10 0.08 0.04 0.03
(26) (3) (2) (8) (3) (1) (3) (3) (2) (1)
The maximum value of Jaccard index is only 0.14 whereas the typical values
are close to the zero. Consequently, there is no significant correlation between
the clusters obtained. This indicates that the measurement axes of each sensor
have their own independent temperature profiles of biases.
All other correlations between different axes of accelerometers and gyro-
scopes, for example, between AX and AZ, GX and GZ, AX and GY etc., were
investigated and the corresponding tables of Jaccard indexes were created. How-
ever, no significant correlation observed.
It should be noted that the number of variations in the shape of the tem-
perature profile is finite, and each temperature profile can be attributed to a
particular cluster by measuring the bias only at several temperatures instead of
measuring over the entire temperature range. Therefore, significant amount of
time might be saved while obtaining thermal profiles.
5 Conclusion
As discussed above, MEMS chips manufacturers denote large error intervals for
produced sensors. Even though it might seem that there is no “family” curve for
a batch of sensors to compensate the thermal dependency, we observed certain
similarity of these curves for a set of chips.
K-means++ clustering algorithm was used to reveal the groups of thermal
curves. It was shown that sensors can be divided in several clusters by the fea-
tures of slopes on 12 temperature intervals. The number of intervals was chosen
experimentally. Further analysis will be done to tune the clustering parameters
for optimum results.
The number of clusters depends on the complexity of the bias thermal profile.
Good group separation for each sensor axis for 250 MPU-9250 chips was achieved
for a number of clusters from 6 to 10.
Also it was shown that there is no correlation between temperature profiles
neither for the different axes (X, Y and Z) of one sensor, nor for different axes
of an accelerometer and a gyroscope within a certain MPU-9250 chip. It means
that temperature dependencies of biases of MEMS formed even on a single die
are not similar to each other.
ACKNOWLEDGEMENTS
This research is supported by the grant 333GR/24464 (IRA-SME program).
References
1. Acar, C., Shkel, A.: MEMS Vibratory Gyroscopes Structural Approaches to Im-
prove Robustness. Springer, New York (2009)
2. Agarwal, P.K., Mustafa, N.H.: K-means projective clustering. In: Proceedings of
the twenty-third ACM SIGMOD-SIGACT-SIGART symposium on Principles of
database systems. pp. 155–165. ACM (2004)
3. Antoniadis, A., Brossat, X., Cugliari, J., Poggi, J.M.: Clustering functional data us-
ing wavelets. arXiv pp. 1–30 (2011). https://doi.org/10.1142/S0219691313500033,
https://arxiv.org/abs/1101.4744
4. Araghi, G., et al.: Temperature compensation model of MEMS inertial sen-
sors based on neural network. In: Position, Location and Navigation Symposium
(PLANS), 2018 IEEE/ION. pp. 301–309. IEEE (2018)
5. Arthur, D., Vassilvitskii, S.: How slow is the k-means method? In: Proceedings of
the twenty-second annual symposium on Computational geometry. pp. 144–153.
ACM (2006)
6. Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. In:
Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algo-
rithms. pp. 1027–1035. Society for Industrial and Applied Mathematics (2007)
7. Butler, J.T., Bright, V.M., Comtois, J.H.: Multichip module packaging of micro-
electromechanical systems. Sensors and Actuators A 70, 15–22 (1998)
8. Dai, G., Li, M., He, X., Du, L., Shao, B., Su, W.: Thermal drift anal-
ysis using a multiphysics model of bulk silicon MEMS capacitive ac-
celerometer. Sensors and Actuators A: Physical 172(2), 369–378 (2011).
https://doi.org/10.1016/j.sna.2011.09.016, http://www.sciencedirect.com/
science/article/pii/S0924424711005309
9. Dickow, A., Feiertag, D.: Partially estimated polynomial mems sensor calibration.
In: Proceedings of SENSOR 2015. pp. 495–499. Association for Sensors and Mea-
surement (2015)
10. Estivill-Castro, V.: Why so many clustering algorithms: a position paper. ACM
SIGKDD explorations newsletter 4(1), 65–75 (June 2002)
11. Ghodssi, R., Lin, P. (eds.): MEMS Materials and Processes Handbook. Springer,
New York (2011)
12. He, J., Xie, J., He, X., Du, L., Zhou, W.: Analytical study and compensation for
temperature drifts of a bulk silicon mems capacitive accelerometer. Sensors and
Actuators A: Physical 239, 174–184 (2016)
13. IEEE: Standard Specification Format Guide and Test Procedure for Linear, Single-
Axis, Non-Gyroscopic Accelerometers. IEEE Std 1293 (1998)
14. IEEE: Standard Specification Format Guide and Test Procedure for Coriolis Vi-
bratory Gyros. IEEE Std 1431 (2004)
15. InvenSense: MPU-9250 Product Specification Revision 1.1. InvenSense Inc (2016)
16. Ketchen, D.J., Shook, C.L.: The application of cluster analysis in strategic man-
agement research: an analysis and critique. Strategic management journal 17(6),
441–458 (1996)
17. Moschevikin, A.P., Sikora, A., et al.: Hardware and software architecture of multi
MEMS sensor inertial module. In: 2017 24th Saint Petersburg International Con-
ference on Integrated Navigation Systems (ICINS). pp. 366–369 (May 2017).
https://doi.org/10.23919/ICINS.2017.7995643
18. Rutkowski, T.M., Cichocki, A., Tanaka, T., Mandic, D.P.: Clustering of spectral
patterns based on emd components of eeg channels with applications to neuro-
physiological signals separation. In: Advances in Neuro-Information Processing,
15th International Conference, ICONIP 2008, Auckland, New Zealand, November
25-28, 2008, Revised Selected Papers, Part I. pp. 453–460 (2008)
19. Schwaab, M., Reginya, S.A., et al.: Measurement analysis of multiple
MEMS sensor array. In: 2017 24th Saint Petersburg International Confer-
ence on Integrated Navigation Systems (ICINS). pp. 392–395 (May 2017).
https://doi.org/10.23919/ICINS.2017.7995650
20. Tarpey, T.: Linear transformations and the k-means clustering algorithm: Appli-
cations to clustering curves. The American Statistician 61(1), 34–40 (February
2007)
21. Wen, M., Wang, W., Luo, Z., Xu, Y., Wu, X., Hou, F., Liu, S.: Modeling and
analysis of temperature effect on MEMS gyroscope. In: Electronic Components and
Technology Conference (ECTC), 2014 IEEE 64th. pp. 2048–2052. IEEE (2014)
22. Zotov, S.A., Simon, B.R., Trusov, A.A., Shkel, A.M.: High quality factor reso-
nant MEMS accelerometer with continuous thermal compensation. IEEE Sensors
Journal 15(9), 5045–5052 (2015)