Conference PaperPDF Available

Abstract and Figures

We present a wearable textile sensor system for monitoring muscle activity, leveraging surface pressure changes between the skin and an elastic sport support band. The sensor is based on an 8×16 element fabric resistive pressure sensing matrix of 1cm spatial resolution, which can be read out with 50fps refresh rate. We evaluate the system by monitoring leg muscles during leg workouts in a gym out of the lab. The sensor covers the lower part of quadriceps of the user. The shape and movement of the two major muscles (vastus lateralis and medialis) are visible from the data during various exercises. The system registers the activity of the user for every second, including which machine he/she is using, walking, relaxing and adjusting the machines; it also counts the repetitions from each set and evaluate the force consistency which is related to the workout quality. 6 people participated in the experiment of overall 24 leg workout sessions. Each session includes cross-trainer warm-up and cool-down, 3 different leg machines, 4 sets on each machine. Plus relaxing, adjusting machines, and walking, we perform activity recognition and quality evaluation through 2-dimensional mapping and the time sequence of the average force. We have reached 81.7% average recognition accuracy on a 2s sliding window basis, 93.3% on an event basis, and 85.6% spotting F1-score. We further demonstrate how to evaluate the workout quality through counting, force pattern variation and consistency.
Content may be subject to copyright.
Never Skip Leg Day: A Novel Wearable Approach
to Monitoring Gym Leg Exercises
Bo Zhou, Mathias Sundholm, Jingyuan Cheng, Heber Cruz, and Paul Lukowicz
German Research Center for Artificial Intelligence (DFKI)
and University of Kaiserslautern
Trippstadter Straße 122 , 67663, Kaiserslautern, Germany
{bo.zhou, mathias.sundholm, jingyuan.cheng, heber.cruz zurian, paul.lukowicz}
Abstract—We present a wearable textile sensor system for
monitoring muscle activity, leveraging surface pressure changes
between the skin and an elastic sport support band. The sensor is
based on an 8×16 element fabric resistive pressure sensing matrix
of 1cm spatial resolution, which can be read out with 50fps
refresh rate. We evaluate the system by monitoring leg muscles
during leg workouts in a gym out of the lab. The sensor covers the
lower part of quadriceps of the user. The shape and movement of
the two major muscles (vastus lateralis and medialis) are visible
from the data during various exercises. The system registers the
activity of the user for every second, including which machine
he/she is using, walking, relaxing and adjusting the machines; it
also counts the repetitions from each set and evaluate the force
consistency which is related to the workout quality.
6 people participated in the experiment of overall 24 leg
workout sessions. Each session includes cross-trainer warm-up
and cool-down, 3 different leg machines, 4 sets on each machine.
Plus relaxing, adjusting machines, and walking, we perform
activity recognition and quality evaluation through 2-dimensional
mapping and the time sequence of the average force. We have
reached 81.7% average recognition accuracy on a 2ssliding
window basis, 93.3% on an event basis, and 85.6% spotting
F1-score. We further demonstrate how to evaluate the workout
quality through counting, force pattern variation and consistency.
Index Terms—pressure sensor matrix; wearable garment;
sport science; muscle activity monitoring; gym fitness tracking.
A. Background and Motivation
Muscle activity study is an important topic in life and sport
science. Understanding how muscles move during various
activities and exercises can help us compare the effect of
different exercises, choose more efficient and secure methods
for exercising the muscles and inducing muscle hypertrophy,
which asserts its role in fields such as body building, profes-
sional sport, injury rehabilitation, elderly caring, etc.
Today muscle monitoring is largely restricted to constrained
lab experiments. Long term monitoring under real life condi-
tions is difficult due to lack of unobtrusive mobile systems. As
reviewed in details in Section I-C, most existing approaches
such as EMG, MRI, USI, etc require either bulky hardware
or special attachment of electrodes to the skin, making wide
spread deployment unfeasible. While simpler approaches such
as force sensitive resistors attached to elastic bands [1] or
inertial measurement units that measure skin surface motion
have been studied, they provide only very limited amount of
information about the muscle.
B. Paper Contribution
This work demonstrates an alternative approach based on
textile ressitive pressure mapping sensors, which has been
used for activity recognition with sportmats [2] and tablecloths
[3] during our previous work. We propose a novel wearable
system that can be used in daily environments out of the
laboratories for monitoring muscle activities, and evaluate its
performance in a gym leg workout scenario. The sensor system
is integrated into the form of an elastic sport band, which
is unobtrusive and does not limit the movement freedom of
the user while doing various exercises. At the same time
with an 8×16 elements grid of 1cm pitch, a sampling rate
of 50fps (frames per second) and high dynamic range, the
system provides detailed information about muscle actions.
Thus, the core contributions of this paper are as follows:
Novel wearable sensing approach: The wearable sen-
sor we have designed is an air-permeable fabric matrix
structure that measures force distribution on high spacial
and temporal resolutions. It is integrated into an off-
the-shelf sport band, suitable for most exercises and
everyday use. Compared with current IMU or EMG based
approaches, our sensor acquires information about the
muscle activities without direct skin-electrode contact.
Leg exercise action recognition and quality evaluation:
single action detection: Based on the muscle movement
signature of different exercises, we are able to distin-
guish among the activities of four machine exercises,
adjusting machines, workout pause and walking, on
a fine time granularity. In short, the system knows
exactly each second the user is doing which exercise,
how long the user takes breaks between each sets.
repetition counting: By inspecting the repeating pat-
terns within each workout set, the system automati-
cally counts the repetitions without training templates.
Therefore, applications such as an automatic personal
workout diary can be easily achieved.
Workout Quality Evaluation: Based on the common
gym experience that during an ideal and efficient
workout, the person should perform each action in a
fluent, stable pattern with the targeted muscles. We
abstract information describing the force consistency
among each repetition from every set as quality meters;
then we compare this individual information with the
user’s self report and the observer’s evaluation about
the effort the user puts on each set.
The high framerate muscle force pressure mapping
information can be further used for the study of life
and sport science.
C. Related Work
To the best of our knowledge, state of the art methods for
detecting muscle activities are:
1) Electromyography (EMG) detects the biopotential from
skeletal muscles, which is directly related to the muscle
activity. It is widely used for studying muscles and
considered as the golden standard[4][5]. While traditional
EMG instruments are bulky, the state of the art hardware
has minimal footprint with off-the-shelf components,
which is suitable for wearable applications [6][7]. Main-
stream EMG electrodes need to have direct contact with
the muscle or the skin, and requires stable and minimal
impedance [8] to have reliable signal, which is not prac-
tical concerning conditions such as extreme movement
causing electrode shifting and excessive perspiration that
are common during normal exercises. Recently, contact-
less electrodes that are suitable for EMG signals are being
developed such as the works in [9][10].
2) Magnetic resonance imaging (MRI) forms images of the
body and internal organs. It is typically used before and
after exercise to observe the muscle structural differences.
[11] The MRI equipment is stationary and radioactive,
limiting its use only in lab conditions.
3) Ultrasound imaging (USI) also forms internal organ imag-
ing. While traditional USI equipment is not portable
and can only be used before and after exercise, such
as the study carried out in [12]; recently wearable USI
approaches are being proposed and modeled [13]. In [14],
Sikdar et al. using a single scan element on the wrist,
were able to robustly identify the movement of individual
fingers. Ultrasound therapy is also a versatile treatment
for musculoskeletal conditions, and recently wearable
applications are emerging as in [15].
4) Inertial Measurement Units (IMU) are nowadays a
standard feature of smartphones, smartwatches, fitness
trackers[16]. IMUs track the linear and angular accelera-
tion, thus can be interpreted into the movement of body
parts where the sensor is fixed, which helps repetition
counting and posture correction. [17] This, however, does
not translate directly into specific muscle activities: e.g.
using a smartwatch, biceps curl with a heavy barbell
results in similar signals as moving arms without weight
in the same speed and pattern; while the muscles undergo
different activities.
5) Force Sensitive Resistors (FSR) are carbon polymer thin
films with printed conductive electrodes, which respond
to pressure force. Previous works include muscle force
evaluation during exercise [18] and gesture recognition
by measuring forearm muscles [19], with one or several
Fig. 1. Wearable leg muscle surface pressure mapping system hardware
(1)prototype components; (2) fixing position and example pressure mapping
data, brighter color indicates higher pressure
FSRs fixed on the corresponding muscles. However, using
discrete sensors limits the level of detail that can be
sensed and creates placement issues (as the sensors need
to always be placed at the same location). Several sensor
systems for robotic sensing skins also offers similar
measurement, such as opto-electronic sensors with sili-
con casting [20]; however, their size and flexibility are
currently not suitable for sport wearable devices.
6) Textile capacitive sensors based on a capacitance change
between two conductive layers have also been used for
muscle monitoring [21]. Proper analog design can achieve
sensing of intense muscle movement as well as minor
tissues changes such as pulse [22].
7) Other medical measurements are used in lab studies such
as vascular and metabolic responses [23], which include
measuring blood flow and taking blood samples before
and after targeted exercises from the specific muscle; or
spectroscopy which attaches optical probes onto skin to
measure tissue oxygen saturation [24].
Our force sensitive resistance matrix sensor is essentially a
carbon-polymer fabric sheet, covered with a group of parallel
stripe electrodes of 1cm pitch on each side; the groups on both
sides are perpendicular to each other, forming a matrix struc-
ture with the intersections from the top-view. The electrodes
are also thin metal fibers, woven into a non-conductive fabric
sheet. The entire sensor is therefore made out of fabrics, and
is flexible and air permeable. We stitch an 8×16 sensor patch
onto an off-the-shelf elastic sportband, which is commonly
used for supporting joints and muscles. As no electrode-skin
contact is required, we cover the sensors with cohesive textile
band to shield it from sweat during intensive workout. The
sensor is wrapped around the leg to cover the lower part of
vastus lateralis and vastus medialis from the quadriceps muscle
group as in Fig. 1(2).
The electrodes are connected to our custom data acquisition
hardware based on our previous work [25]. The hardware
scans the entire matrix at a speed of 50fps by powering
one row electrode with 3.3Veach time, pulling the rest row
electrodes to ground; then measures the local resistance of
the carbon-polymer sheet through a voltage divider at every
column electrode with a 24-bit, 16-channel high performance
ADC. An FPGA controls the logic and offers the scan voltage.
To ensure reliable data-rate, we implement a FIFO-USB
protocol to send the data to a smartphone by a USB-OTG
cable, which also powers the hardware. The smartphone runs
an Android app to save and visualize the data. The hardware
and smartphone can be put inside the user’s pocket during the
workout. Fig. 1(1) shows the sensor system.
A. Experiment Design
To evaluate the system’s capability of recording leg muscle
movement during gym workout, and distinguishing various
workout actions that are focused on different muscles, we
design our experiment as a complete gym leg workout session.
To introduce controlled movement, and for safety concerns,
we avoid exercises with free weights such as barbell squats;
instead, we choose gym machines that are designed to limit the
freedom of movement and hence, in most cases, the movement
of the weight is initiated by the targeted muscles. Each session
includes the following procedures:
1) Warm up with the Cross Trainer ’7-minute warm up’
program (Fig. 2 A);
2) For each machine, perform 3 sets of each 12 repetitions,
followed by one set, in which the participant performs
until failure (if the participant feels confident that failure
will not happen, till only 15 reps). The machines include:
a) Leg Press Machine (Fig. 2 B)
b) Seated Leg Curl Machine (Fig. 2 C)
c) Leg Extension Machine (Fig. 2 D)
3) Cool down with the Cross Trainer ’7-minute warm up’
program, same as step 1.
The participants are free to take pauses, drink, walk around
or any normal activities inside the gym. The system will
record all of those non-workout movements as ”NULL” class.
Every participant recorded four sessions, numbered Day14.
Between every workout day, the participants take several
days off to rest the leg muscles. For Day1and Day3, the
weight of each machine is constant; while for Day2and
Day4, the weight is increased after each set. The actual
constant weight, starting weight and increment are participant
dependent because the subjects have different muscle strength
and their performance actually improves from Day1to Day4.
In Step 2, the order of the three machines are shuffled within
the four days, so that the participants begin and end with a
different machine each day to eliminate the possible bias that
he/she might be already tired upon arriving at the last machine.
The exact wrapping tension and position of the sensor is
not precisely defined; instead, the only standards are (1) the
shapes of the muscles are visible on the app while the users
stand and tighten their legs; (2) the users can fully curl their
legs easily (stand and squat) with the band. The user can adjust
the band if it slides during training.
Class Definition
Workout Activities
Class 1 Cross Trainer
Class 2 Leg Press
Class 3 Seated Leg Curl
Class 4 Leg Extension
Non-workout Activities
Class 5 Mounting/Dismounting/Adjusting machines
Class 6 Pause (on or off machines)
Class 7 walking
B. Participants Demography
Overall 6participants recorded 24 complete sessions, con-
taining 288 sets of the three leg machines and 48 sets of
the cross trainer. To ensure safety while performing those
heavy weight exercises, the participants are regular members
at the gym, and they are aware of how to perform all of the
exercises safely. One participant is a professional gym trainer,
also a university student in sport science. Three participants
are university students who do regular sports or gym exercises,
but are not professional athletes. Two participants are full-time
researchers in the institute and do occasional sports. One of the
three students is female, and the other participants are male.
Their ages range: 21 27, heights range: 171 187cm, and
weights range: 70kg 85kg.
C. Annotation Method
The ground truth is annotated manually, detailed to the
second of the start and end of each set or other movements.
The class definitions are listed in Table I. The single repetition
is not annotated, because (1) counting can be easily imple-
mented by the movement of the weights (e.g. some smart
training machines are commercially available); (2) exercises
with weights are slower, less consistent compared to free-
hand exercises (e.g. push-ups), therefore, usually the exact
separation between adjacent reps is not clear simply by looking
at the person’s movement. Instead, the repetition number and
weight of each set are recorded in the form of a normal
workout diary by the experiment supervisor.
After each set, the participant is asked to rate his/her effort
of the past set from difficulty scores of easy (under weight),
normal (the person feels fair effort from the muscles moving
the weight), hard (the person needs to continue focus and self-
motivate moving the weight, movements may be inconsistent),
limit (the person’s movements are close to failure in moving
the weight). Then the experiment supervisor, with a third
person who looks at the recorded video, gives a rating of the
effort based on the participant’s rating, movement consistency
and facial expressions. It is worth mentioning that, the effort is
a subjective score; and the effort does not necessarily increase
as the set proceeds or weight increases. During the experiment,
sometimes if the participant takes a longer pause, he/she might
regain more strength, and the next set can be easier than the
previous one.
Fig. 2. Example of an experiment session’s data was explained in Section IV-A, and example pressure mapping signals of classes C1(A), C2(B), C3(C),
A. Signal Processing and Feature Extraction
The signal from the sensor is essentially a time sequence
(stream) of 2D pressure distributions (frames). We use signal
conditioning schemes similar to the ones introduced in [2] and
[3]. The 2D frame is first spatially up-sampled from 8×16
to 16 ×32. For the training and initial recognition we pre-
segment the data according to the annotation (spotting as in
Section IV-C is done on non-segmented data). We then use
a sliding window (window size 8s, step size 2s) approach to
step through the stream of data, each window is denoted as i.
We extract features from two aspects:
Temporal: For each frame we compute three central
moments (sum wiand centroid xi, yi) and the pixel
value of the pixel (σi) which has the maximum standard
deviation during the current window.
Spacial: We then calculate the inter frames, which are dif-
ference per pixel between every pair of adjacent frames.
They represent the change of the pressure mapping. We
then sum those inter frames within the window, resulting
in a single augmented frame ADi, which represents the
overall 2D pressure change in the window.
Several practical reasons could cause the sensor to have
different offset values, such as the difference in wrapping
tensions and positions, sliding and adjusting of the sensor
band. To make the system more robust against such variations,
we avoid involving absolute values in extracting features. For
each temporal sequence s∈ {wi, xi, yi, σi}, we first normalize
sso the average value is 0, and the standard deviation(SDs)
is 1. We filter the signal to remove DC and high frequency
noise with zero-phase digital filtering. Then we compute the
following features, denoted as Ft(s):
1) magnitude range (max(s)min(s));
2) average absolute of the 1st-order derivatives (avg(|s0|));
3) standard deviation of the 1st-order derivatives (SD(|s0|));
4) range of the 1st-order derivatives (max(s0)min(s0));
5) central frequency of the FFT spectrum (without 0Hz);
6) we divide the spectrum into 5 even portions of frequency
band, use the mean magnitude of each as a feature;
7) we sort the data into a histogram of five bins, and use
the count number of each bin as five features;
8) using half of SDsas minimum peak height, we find the
local maxima and minima. We use the amount of maxima,
minima, and maxima-to-minima ratio as three features.
Again, to make the feature extracted from the augmented
frame translation invariant, instead of directly using ADi,
we look for the maximum pixel within a field that is 4
pixels retracted from the four borders. This pixel represents
the most movement during the window. We select the 9×9
Fig. 3. Leave-1-day-out average result
region, centered at this pixel as the region of interest ROIi.
Then we compute the first three cental moments and Hu’s 7
moments[26] of ROIi, denote those 10 features as Fs(ROIi).
Overall 82 features are extracted from every window:
F(i) = {Ft(wi), Ft(xi), Ft(yi), Ft(σi); Fs(ROIi)}.
B. Window Based and Event Based Classification
First we consider classification results on the basis of
individual windows. We use the confidence-based AdaBoost
algorithm ConfAdaBoost.M1 [27] with decision trees as the
base classifier. We randomly pick an even number of feature
data from every class for balanced training. Since the amount
of data from every class is very unbalanced, 9 classifiers are
trained with such random pick process; the final result is the
majority of the 9 classifiers’ outputs. We perform 10-fold
cross validation of the complete dataset from each person.
This yields over 95% average accuracy; however, this is over
optimistic: the data from the same repetition set have larger
similarity compared with other sets. Therefore, for everyone’s
4 days, we perform leave-1-day-out cross validation.
Fig. 3 (1) shows the average result of all participants
as confusion matrix; the detailed precision, recall, F1and
ACC of every day from every person are listed in Fig. 5.
Among the results, the gym trainer - ID5, has the highest
scores, with minimum daily scores deviation. We speculate
this to be a result of the participant doing the same machine
exercise in a very consistent manner across different sessions,
as his workout experience and body build allow him to easily
Fig. 4. Event-based Leave-1-day-out average result
Fig. 5. Distribution of leave-1-day-out individual day results
control the weights. We then performed leave-one-participant-
out validation to examine the system’s robustness against
encountering unregistered users; the confusion matrix is shown
in Fig. 3 (2).
Next, we elevate classification to event based level. For
every segmented set of C1C4, we use the majority of all
windows’ output as its final class. We combine the remaining
non-workout classes into C57. As shown in Fig. 4, there
exists accuracy improvement in every class, and the resulting
overall F1 scores increase to 0.943 and 0.852, as this process
essentially smooths the window based result.
In this application, it is important to first separate the ma-
chine workout activities (C1C4) from non-workout activities
(C5C7), and then further distinguish which machine the
user is using. From the confusion matrix, it is obvious the most
misclassifications happen within the workout classes, and non-
workout classes; while very little confusion happens between
the two categories. Among the four machines, the cross trainer
is the most distinct from others; while it is misclassified with
walking in some occasions, it is reasonable since the workout
is a stepping action. In the person independent case, the con-
fusions among C2, C3, C 4are increased but not significantly.
The accuracy degradation from person dependent to inde-
pendent case is also a result of the participants’ physiology
variety in terms of muscle size, density, etc. As a baseline,
we speculate the system to be more robust against switching
users with more training data that cover more body types, and
that in practical use case such a personal device can be easily
trained with individual users for optimum accuracy.
C. Activity Detection (Spotting)
As a system that accompanies the user out of the lab
environment, it should be able to automatically spot the user’s
activities in a continuous data stream without annotation. The
challenge is to be able to separate the relevant activities from
aNULL class containing anything that the user can possibly
do in between.
For activity spotting we directly use the same sliding win-
dow istep and size as in Section IV-A to scan through the data
without annotation, and extract the same set of features F(i).
We assume a person dependent use case for optimal accuracy.
For each day’s data, we first train the ConfAdaBoost.M1
classifier with the annotated data from other three days of
the user (leave-1-day-out); during the training we combine
C1C4,C5C7into two classes C14,C57to distinguish
between workout activities and non-workout activities. We test
the classifier with F(i)from every window of this day, and
name the output as the binary spotting result, in which 010
indicates the workout activities. Singular events are removed,
then adjacent 010s are grouped into ’instances’, each with the
start and end points, then instances with less than 10 seconds
gap are merged.
Then, we train two different sets of classifiers: one trained
with data from {C1, C2, C 3, C4}, and tested on the windows
marked as workout instances; another with {C5, C6, C 7}and
tested on the remaining windows. The results within each
workout instance are majority-voted. We compare this final
spotting result with the ground truth on a 2 seconds (window
step) temporal precision. The resulting F1-score is on average
0.779; however, only 31 out of 336 workout sets are not
correctly spotted and classified (error <10%). The major
misses are among C5, C6, C 7, which also do not have a clear
separation during the annotation, for example: when the user
is approaching a machine, he/she might as well starts adjusting
the machine during the last few steps; when a user is relaxing,
he/she might adjust the machine to release his body, or stand
and slightly step around; some adjusting machine movements
might last much shorter than the window size (pulling the
weight pin). After all, the muscles are not actively asserting
force on a workout level. Therefore, we combine C5C7in
the spotting result, reducing the classes from 7 to 5, and the
resulting average F1-score is 0.856.
Fig. 6 shows the spotting result of the experiment session
in Fig. 2; Fig. 7 shows the distribution of the F1-scores of
every session from every participants. The spotting result of
each person accords with the classification result in Fig. 5.
D. Counting and Workout Quality
To automatically assess not only the type of training, but
also the amount is relevant. We thus next attempt to count the
number of repetitions within each spotted instance. For every
instance, we use the sum w(t)of each frame and run a sliding
window to locate the local maxima with the minimum peak
height criteria of median(w) + SD(w)/2, and local minima
smaller than median(w)SD(w)/2(wis the samples of the
current window instead of the whole instance). Then define the
Fig. 6. Spotting example for the session in Fig. 2, before and after combining
C5, C6, C 7
Fig. 7. Distribution of spotting F1-scores of all participants
smallest minima between two adjacent maxima as the start
of a partition, and end of the previous partition. While this
already defines a naive counting algorithm, it is sensitive to
minor variations in the timing and execution of the individual
repetition. Therefore, we use dynamic time warping (DTW)
to inspect whether the same pattern have been repeated, or
it is an over counting of an locally abnormal peak. In our
previous work [2], we have used DTW for counting body
weight exercises (e.g. push-ups) on a pressure sensitive mat,
one template was chosen as the standard to best represent
Fig. 8. Examples of partition and counting result. Red vertical lines mark the partition separations, orange and dash purple horizontal lines mark the standard
deviation and median of each window.
Fig. 9. Histogram of counting errors
each exercise. Because the repetitions here are not annotated
as explained in Section III-C, rather than choosing a standard
template, we derive a template for each set, by a recursive
1) the partitions are separated into pairs of two;
2) the time series of each pair are warped to have the same
length in time domain to have the optimum distance using
dynamic programming [28];
3) a new time series is calculated as the average of the two
warped series;
4) by generating one new time series from each pair, the
collection of new time series are grouped into pairs of
two and go to step 2 until only one time series is left.
The remaining single time series is then taken as the template
of the current set.
Then, we look for the partitions shorter than half of the
average partition length in the current set, which is an over
counting candidate. We derive three time series for each
candidate: its own partition, the previous partition plus itself,
itself plus the following partition. Then we match each of the
three series with the set’s template, and calculate the mean
value of the difference between the two warped series as the
DTW warping error. The series with the smallest warping error
is the one that best matches the template. Hence, if either the
previous plus itself, or itself plus the next has the smallest
error among the three, the corresponding two partitions are
merged. Compared to our previous work in [2], DTW is
used for correcting the counting results instead of the major
counting criteria. To further save computational time, for cases
that over counting candidates do not exist in a set, or for the
cross trainer with hundreds of repetitions, the DTW correction
process is not performed.
While counting of movement repetitions can be easily done
through wearable IMUs or machines with position sensors on
the weights/cable, the actual meaningful information is how
much effort the user is asserting with the targeted muscles,
and the consistency of the force patterns during the workout.
For each partition’s time series w, we calculate the following
properties to represent the consistency variation:
1) p1length of the partition in seconds
2) p2range of absolute value (max(w)min(w))
3) p3average of absolute value (avg(w))
4) p4DTW distance normalized by warping path as ex-
plained in [2]
5) p5DTW warping error as previously explained.
The template of the DTW is calculated as the same recursive
process, but after removing over counting. Fig. 6 shows
an example of the partitioning process from each machine
workout class, and the according p15. In the end, p15
outliers (within a dataset, points whose distance to the median
is greater than the standard deviation) at the beginning and
end of the set are removed and the number of the remaining
partitions is the final counting result. We compare the counting
results with the ground truth, and show the histogram of errors
in Fig. 9, from which, zero error takes the majority. In Fig.
6, outliers are kept to show how different the pvalues are for
signals out of the set. p15describe the speed, force intensity
and pattern variations, thus can be used as a new measure for
evaluating the workout consistency in future studies.
E. Observation of Warm Up Process
Muscle warm up is an important process for improving
sport performance and safety [29] [30] [31]. In this subsection
we demonstrate the capability of the system for evaluating
the warm up phase. While the skin temperature of the used
muscles indicates the warm up status; muscle warm up is,
by nature, the process of increased blood flow, oxygen,
metabolism and adrenaline in the muscle, which also results
in a muscle volume and strength improvement. With a fixed
elastic band around the muscle, this improvement causes an
increment in the average pressure which can be measured by
our sensor.
In Fig. 2, it is visible that the average w(t)during the
warm up is increasing, while during the cool down phase,
the increment is not as obvious; this difference exists in every
experiment session. While the magnitude range for each step is
smaller during warm up than during cool down in the particu-
lar session of Fig. 2, this does not apply to all workout sessions
(in some sessions the difference is not distinguishable or even
reversed). To quantify this and review all experiment sessions
statistically, we fit each cross-trainer session’s x=w(t)with
the following two functions: (1)y=k×x+bto approximate
the linear increment; (2)y=m×(1 ex/a)to approximate
the start to saturation trend. Fig. 10 shows the resulting k,
b,aand mfor every session(values are normalized for each
coefficient to compare only the difference), from which, it can
be concluded that during the warm up, the average pressure
increases more, with a lower starting value; and the average
pressure saturates faster after the main workout routines, with
a smaller start-to-saturation range.
F. Individual Set Difficulty
As introduced in Section III-C, each workout set has been
rated an effort score. We investigate the relevance between
the subjectively perceived effort and the consistency of the
Fig. 10. Distribution of muscle warm up parameters. x-axis: 1=warm up
sessions, 2=cool down sessions. Higher kmeans more increment; higher b
means more starting tension; higher ameans slower to saturation; higher m
means bigger start-to-saturation range
Fig. 11. Distribution of d9and d10. (before and after grouping easy-normal
and hard-limit; left: 1-easy, 2-normal, 3-hard, 4-limit; right: 1-easy & normal,
2-hard & limit)
force measured by the sensor. To avoid building upon errors
from counting, we do not use p15in Section IV-D; instead,
for every set, we use the same peak detection scheme on the
average pressure data with a sliding window, and also calculate
the standard deviation of the signal within the window SDi.
Then we derive the following pairs of features that describes
the signal consistency:
1) avg (d1) and SD (d2) of local maxima heights;
2) avg (d3) and SD (d4) of local minima heights;
3) avg (d5) and SD (d6) of local maxima distances;
4) avg (d7) and SD (d8) of local minima distances;
5) avg (d9) and SD (d10 ) of SDi;
The last pair of features are shown in Fig. 11, from which the
trend of more significant deviation related to higher difficulty
score is observable. To determine how well those features are
separated among the four rating classes (easy: 1; normal: 2,
hard: 3, limit: 4), we perform 10-fold cross validation with the
ConfAdaBoost.M1 algorithm. The resulting average accuracy
is 42.50%, which is not high, yet still above random (with
four balanced classes, the accuracy of random selection is
25%). We group easy and normal as class 1; hard and limit as
class 2, resulting in a cross validation accuracy of 72.99%. As
the ground truth is subjective, our sensor offers a new aspect
for evaluating the quality of the work out by measuring the
consistency within each repetition set.
In conclusion, this work has demonstrated a novel wearable
system based on fabric force mapping sensor matrix, which
can measure the muscle movement during various sport activ-
ities. The system is evaluated in a leg workout scenario, which
can be used for not only sport activity recognition, but also
quality evaluation. The major advantages of the system are:
(1) the high amount of sensing points make the device more
robust to fixing variations; (2) its air permeability, flexibility
and possibility to be isolated with sweat absorbing textiles
make it very suitable for sport activities without introducing
uncomfortableness and restriction; (3) the muscle information
can be extracted goes beyond mere movement as shown by
the warm-up and difficulty level analysis.
After the exploratory study, we will put on more engineering
effort to minimize the electronic footprint and implement
battery power and wireless transmission, along with designing
different sizes for different muscle regions, to enable the
system to be evaluated in a wider range of exercises, as well
as other sport activities.
This work was partially supported by the collaborative
project SimpleSkin under contract with the European Commis-
sion (#323849) in the FP7 FET Open framework. The support
is gratefully acknowledged.
The authors would also like to thank the gym Unifit
Kaiserslautern and trainer Robert Gressnich, as well as other
experiment participants Orkhan Amirhslanov, Finja Coerdt,
Sebastian Immel and Patrick Mathy.
[1] P. Lukowicz, F. Hanser, C. Szubski, and W. Schobersberger, “Detecting
and interpreting muscle activity with wearable force sensors,Lecture
Notes in Computer Science, vol. 3968, pp. 101–116, 2006.
[2] M. Sundholm, J. Cheng, B. Zhou, and et al, “Smart-mat: Recognizing
and counting gym exercises with low-cost resistive pressure sensing
matrix,” in UbiComp ’14. ACM, 2014.
[3] B. Zhou, J. Cheng, M. Sundholm, and et al, “Smart table surface: A
novel approach to pervasive dining monitoring,” in PerCom 2015, March
2015, pp. 155–162.
[4] A. P. Marsh and P. E. Martin, “The relationship between cadence and
lower extremity emg in cyclists and noncyclists,Medicine and science
in sports and exercise, vol. 27, no. 2, pp. 217–225, 1995.
[5] S. T. McCaw and D. R. Melrose, “Stance width and bar load effects on
leg muscle activity during the parallel squat,Medicine and science in
sports and exercise, 1999.
[6] W. Huang, M. Kreil, J. Cheng, and et al, “Development of compact
versatile acquisition platform for wireless sensing applications,” in
Applied Mechanics and Materials, vol. 645, 2014, pp. 274–280.
[7] Athos, “
[8] S. Day, “Important factors in surface emg measurement,” Bortec
Biomedical Ltd publishers, pp. 1–17, 2002.
[9] A. Ianov, H. Kawamoto, and Y. Sankai, “Development of a capacitive
coupling electrode for bioelectrical signal measurements and assistive
device use,” in Complex Medical Engineering (CME). IEEE, July 2012,
pp. 593–598.
[10] J. Taelman, T. Adriaensen, C. van der Horst, T. Linz, and A. Spaepen,
“Textile integrated contactless emg sensing for stress analysis,” in
Engineering in Medicine and Biology Society (EMBS). IEEE, Aug
2007, pp. 3966–3969.
[11] T. Abe, C. F. Kearns, and Y. Sato, “Muscle size and strength are
increased following walk training with restricted venous blood flow from
the leg muscle, kaatsu-walk training,” Journal of Applied Physiology,
vol. 100, no. 5, pp. 1460–1466, 2006.
[12] Y. Takai, M. Ohta, R. Akagi, and et al, “Validity of ultrasound muscle
thickness measurements for predicting leg skeletal muscle mass in
healthy japanese middle-aged and older individuals,” in Journal of
Physiological Anthropology, vol. 32, 2013.
[13] M. Tsakallakis and N. Bourbakis, “A wearable ultrasound multi-
transducer array system for abdominal organs monitoring,” in Bioin-
formatics and Bioengineering (BIBE), 2013 IEEE 13th International
Conference on, Nov 2013, pp. 1–5.
[14] S. Sikdar, H. Rangwala, E. Eastlake, I. Hunt, A. Nelson, J. Devanathan,
A. Shin, and J. Pancrazio, “Novel method for predicting dexterous
individual finger movements by imaging muscle activity using a wear-
able ultrasonic system,” Neural Systems and Rehabilitation Engineering,
IEEE Transactions on, vol. 22, no. 1, pp. 69–76, Jan 2014.
[15] G. Lewis, M. Langer, C. Henderson, and R. Ortiz, “Design and evalua-
tion of a wearable self-applied therapeutic ultrasound device for chronic
myofascial pain,” vol. 39, no. 8, 2013, pp. 1429 – 1439.
[16] Gymwatch, “
[17] E. Velloso, A. Bulling, H. Gellersen, W. Ugulino, and H. Fuks, “Qual-
itative activity recognition of weight lifting exercises,” in Proceedings
of the 4th Augmented Human International Conference, ser. AH ’13.
New York, NY, USA: ACM, 2013, pp. 116–123.
[18] M. Kreil, G. Ogris, and P. Lukowicz, “Muscle activity evaluation using
force sensitive resistors,” in Medical Devices and Biosensors, 2008.
ISSS-MDBS 2008. 5th International Summer School and Symposium on,
June 2008, pp. 107–110.
[19] A. Dementyev and J. A. Paradiso, “Wristflex: Low-power gesture input
with wrist-worn pressure sensors,” in Proceedings of the 27th Annual
ACM Symposium on User Interface Software and Technology, ser. UIST
’14. New York, NY, USA: ACM, 2014, pp. 161–166.
[20] M. Donati, N. Vitiello, S. Maria De Rossi, T. Lenzi, S. Crea, A. Per-
sichetti, F. Giovacchini, and B. Koopman, “A flexible sensor technology
for the distributed measurement of interaction pressure,” in Sensors,
vol. 12, 2013.
[21] J. Meyer, P. Lukowicz, and G. Tr¨
oster, “Textile pressure sensor for
muscle activity and motion detection,” in Wearable Computers, 2006
10th IEEE International Symposium on. IEEE, 2006, pp. 69–72.
[22] J. Cheng, O. Amft, G. Bahle, and P. Lukowicz, “Designing sensitive
wearable capacitive sensors for activity recognition,Sensors Journal,
IEEE, vol. 13, no. 10, pp. 3935–3947, Oct 2013.
[23] L. Lawrenson, J. G. Poole, J. Kim, and et al, “Vascular and metabolic
response to isolated small muscle mass exercise: effect of age,American
Journal of Physiology - Heart and Circulatory Physiology, vol. 285,
no. 3, pp. H1023–H1031, 2003.
[24] A. Nygren, K. Rennerfelt, and Q. Zhang, “Detection of changes in
muscle oxygen saturation in the human leg: a comparison of two
near-infrared spectroscopy devices,Journal of Clinical Monitoring and
Computing, vol. 28, no. 1, pp. 57–62, 2014.
[25] B. Zhou, J. Cheng, M. Sundholm, and P. Lukowicz, “From smart
clothing to smart table cloth: Design and implementation of a large
scale, textile pressure matrix sensor,” in ARCS2014. Springer LNCS,
[26] M.-K. Hu, “Visual pattern recognition by moment invariants,Informa-
tion Theory, IRE Transactions on, vol. 8, no. 2, pp. 179–187, February
[27] A. Reiss and D. Stricker, “Aerobic activity monitoring: towards a
long-term approach,” International Journal of Universal Access in the
Information Society (UAIS), 2013.
[28] H. Sakoe and S. Chiba, “Readings in speech recognition,” A. Waibel and
K.-F. Lee, Eds. San Francisco, CA, USA: Morgan Kaufmann Publishers
Inc., 1990, ch. Dynamic Programming Algorithm Optimization for
Spoken Word Recognition, pp. 159–165.
[29] A. Fradkin, T. Zazryn, and J. Smoliga, “Effects of warming-up on
physical performance: a systematic review with meta-analysis,” in J
Strength Cond Res., 2010.
[30] D. High, E. Howley, and F. Don, “The effects of static stretching and
warm-up on prevention of delayed-onset muscle soreness,” in Research
Quarterly for Exercise and Sport, 1989, pp. 357–361.
[31] M. Mohr, P. Krustrup, L. Nybo, J. Nielsen, and B. J., “Muscle tempera-
ture and sprint performance during soccermatches – beneficial effect of
re-warm-up at half-time,” in Scand J Med Sci Sports, 2004, pp. 156–162.
... Smartphone-based exercise training system COPDTrainer showed the lowest recognition rate for exercising as 77.5% in [34], which is below any other recognition rates in the proposed system. Leg muscles have been monitored using a pressure sensing mechanism in [35] that achieved an accuracy rate of 81.7% for gym exercises recognition. In a filter-based sensor fusion activity recognition system [36], the accuracy achieved using the Kalman filter is 84%. ...
... Activity recognition using 5-s window [33] 61.0 ERICA [9] 70.0 COPDTrainer: lowest recognition rate [34] 77.5 Gym exercises recognition [35] 81.7 Kalman filter based activity recognition [36] 84.0 Automatic exercise detection [37] 85.0 Proposed OPE system 86.0 ...
Full-text available
Due to the recently increased requirements of e-learning systems, multiple educational institutes such as kindergarten have transformed their learning towards virtual education. Automated student health exercise is a difficult task but an important one due to the physical education needs especially in young learners. The proposed system focuses on the necessary implementation of student health exercise recognition (SHER) using a modified Quaternion-based filter for inertial data refining and data fusion as the pre-processing steps. Further, cleansed data has been segmented using an overlapping windowing approach followed by patterns identification in the form of static and kinematic signal patterns. Furthermore, these patterns have been utilized to extract cues for both patterned signals, which are further optimized using Fisher's linear discriminant analysis (FLDA) technique. Finally, the physical exercise activities have been categorized using extended Kalman filter (EKF)-based neural networks. This system can be implemented in multiple educational establishments including intelligent training systems, virtual mentors, smart simulations, and interactive learning management methods.
... Since smart garments are closely connected to users' bodies, different implicit input techniques can be realized. The current posture [152] or movement [284] of the user can be detected as implicit input. Further, assessing the users' biosignals can be realized with smart garments [78,184]. ...
... Examples include clothing that detect the flexion angle of the arm [242] or leg [177]. This information can then be used in different application scenarios such as measuring the exercises a user performs in a gym [284] or provide feedback on the way users perform football kicks [105]. Summing up the flexion angles of different limbs, insights on the posture of the user can be derived as well. ...
Full-text available
Wearable computing is on the brink of moving from research to mainstream. The first simple products, such as fitness wristbands and smart watches, hit the mass market and achieved considerable market penetration. However, the number and versatility of research prototypes in the field of wearable computing is far beyond the available devices on the market. Particularly, smart garments as a specific type of wearable computer, have high potential to change the way we interact with computing systems. Due to the proximity to the user`s body, smart garments allow to unobtrusively sense implicit and explicit user input. Smart garments are capable of sensing physiological information, detecting touch input, and recognizing the movement of the user. In this thesis, we explore how smart garments can enrich mobile interaction. Employing a user-centered design process, we demonstrate how different input and output modalities can enrich interaction capabilities of mobile devices such as mobile phones or smart watches. To understand the context of use, we chart the design space for mobile interaction through wearable devices. We focus on the device placement on the body as well as interaction modality. We use a probe-based research approach to systematically investigate the possible inputs and outputs for garment based wearable computing devices. We develop six different research probes showing how mobile interaction benefits from wearable computing devices and what requirements these devices pose for mobile operating systems. On the input side, we look at explicit input using touch and mid-air gestures as well as implicit input using physiological signals. Although touch input is well known from mobile devices, the limited screen real estate as well as the occlusion of the display by the input finger are challenges that can be overcome with touch-enabled garments. Additionally, mid-air gestures provide a more sophisticated and abstract form of input. We present a gesture elicitation study to address the special requirements of mobile interaction and present the resulting gesture set. As garments are worn, they allow different physiological signals to be sensed. We explore how we can leverage these physiological signals for implicit input. We conduct a study assessing physiological information by focusing on the workload of drivers in an automotive setting. We show that we can infer the driver´s workload using these physiological signals. Beside the input capabilities of garments, we explore how garments can be used as output. We present research probes covering the most important output modalities, namely visual, auditory, and haptic. We explore how low resolution displays can serve as a context display and how and where content should be placed on such a display. For auditory output, we investigate a novel authentication mechanism utilizing the closeness of wearable devices to the body. We show that by probing audio cues through the head of the user and re-recording them, user authentication is feasible. Last, we investigate EMS as a haptic feedback method. We show that by actuating the user`s body, an embodied form of haptic feedback can be achieved. From the aforementioned research probes, we distilled a set of design recommendations. These recommendations are grouped into interaction-based and technology-based recommendations and serve as a basis for designing novel ways of mobile interaction. We implement a system based on these recommendations. The system supports developers in integrating wearable sensors and actuators by providing an easy to use API for accessing these devices. In conclusion, this thesis broadens the understanding of how garment-based wearable computing devices can enrich mobile interaction. It outlines challenges and opportunities on an interaction and technological level. The unique characteristics of smart garments make them a promising technology for making the next step in mobile interaction.
... Les applications sportives, de divertissement et de mode constituent un autre marché intéressant pour l'IoT et les vêtements intelligents, qui sont très utiles lors de l'entraînement [46], de certaines activités ou de la guérison de blessures sportives. Une bonne posture est essentielle tant pour le sport que pour la santé, c'est pourquoi sa reconnaissance a été étudiée par l'utilisation de vêtements intelligents. ...
Grâce aux progrès de marché des objets connectés ces dernières années, la conception de réseaux intelligents, tels que les réseaux centrés sur les personnes (Body Area Network en anglais ou WBAN) a connu une croissance très élevée, qui explique le grand engouement des industriels autour de cette nouvelle technologie. De nouveaux concepts d'applications émergentes capables de détecter des phénomènes physiologiques, environnementaux et plus particulièrement des applications centrées sur l'homme en utilisant des capteurs et des antennes susceptibles de communiquer et de collecter des informations en temps réel afin d'assurer une interaction intelligente du corps humain et son environnement grâce à la mise au point d'une interface physique capable de détecter, de réagir et de s'adapter, comme les vêtements intelligents. Dans ce cadre, nous nous sommes attachés dans ce travail de recherche à la conception et la réalisation d’antennes textiles susceptibles d’être intégrées dans des vêtements pour les applications de l’internet des objets (IoT), ces antennes sont conçues pour fonctionner dans la bande Wi-Fi (2.45 GHz, 5.8GHz) et la bande 5G inférieure à 6 GHz (3.5 GHz). Nous avons également utilisé des structures métamatériaux de type bande interdite électromagnétique (BIE) afin d’augmenter leurs performances en rayonnement et diminuer le couplage avec le corps humain. Puis récemment la bande millimétrique a été mise en avant pour le développement des réseaux de communication sans fil. L’intérêt de cette bande pour les applications 5G et IoT s'explique par les avantages qu'elle bénéficie par rapport aux bandes de fréquence plus basses (possibilité de débits de données supérieurs à 10 Gbit/s, réduction des interférences avec les réseaux voisins, compacité des dispositifs, etc.). Dans la deuxième étude, la première antenne textile destinée à la bande de fréquence 5G-26 GHz a été présentée. Une amélioration du gain et une limitation des interactions avec le corps ont été obtenues grâce à une nouvelle technique d'amélioration en utilisant des surfaces BIE. Les résultats de mesure effectués ont bien validé les conceptions développées et ont démontré qu'il existe de nombreuses possibilités d'exploitation de ces prototypes pour les futures applications IoT.
... A MOPET [3] is an example of a wearable system aimed at supervising a physical fitness activity. Activity recognition is also one important domain where custom wearable devices are developed [2], [6], [8], [9]. ...
Full-text available
Computational Intelligence methods for automatic generation of sport training plans in individual sport disciplines have achieved a mature phase. In order to confirm their added value, they have been deployed into practice. As a result, several methods have been developed for generating well formulated training plans on computers automatically that, typically, depend on the collection of past sport activities. However, monitoring the realization of the performed training sessions still represents a bottleneck in automating the process of sport training as a whole. The objective of this paper is to present a new low-cost and efficient embedded device for monitoring the realization of sport training sessions that is dedicated to monitor cycling training sessions. We designed and developed a new bike computer, i.e. the AST-Monitor, that can be mounted easily on almost every bicycle. The aforementioned bike computer is based on the Raspberry Pi device that supports different external sensors for capturing the data during the realization of sport training sessions. An adjusted GUI tailored to the needs of athletes is developed, along with the hardware. The proof of concept study, using the AST-Monitor in practice, revealed the potential of the proposed solution for monitoring of realized sport training sessions automatically. The new device also opens the door for the future utilization of Artificial Intelligence in a wide variety of sports.
... Wearable devices are also used to record movement data for other applications. Zhou at al [42] present a wearable e-textile device for monitoring muscle activity, using a fabric-based pressure sensor. The sensor is embedded into an elastic sport band, commonly used for support during exercise. ...
... In this study, a similar methodology was applied. Additional dynamic tasks that were classified utilizing the pressure recorded at the knees as a reference were added (Zhou et al. 2016). Specifically, this study proposed an experimental methodology for investigating the restriction and discomfort of EOD suits with respect to pressure at the interface of the human body and the suit. ...
Full-text available
Soldiers working in the field of explosive ordnance disposal (EOD) wear cumbersome personal protective equipment (PPE) that may affect their performance in the field, limit their mobility, and cause discomfort. The objective of this study was to develop a test methodology to identify the relationship between EOD suit interface loads and mission-critical performance metrics. The physical interactions between an EOD suit and human subjects were monitored using a distributed pressure sensor network to investigate the interface load distribution during EOD-related physical positions and activities. More specifically, a Med-Eng brand Model EOD 8 suit was utilized to evaluate shoulder discomfort and leg mobility restriction. Thirty-four college aged adults of varying athletic abilities completed a test course and walked on a treadmill for 2 min while wearing the EOD 8. Demographic information was collected before testing via a survey and qualitative observations were collected at the end of testing with a questionnaire. After each test course repetition, participants ranked their perceived exertion using the Borg scale. Overall, the time it took participants to complete the test course increased by 17% and participants experienced a 60% increase in perceived exertion while wearing the EOD 8. The region that experienced the most pain and discomfort was the top of the shoulders (59%) and there was a negative correlation (r = − 0.5, p < 0.05) between participants’ body mass index (BMI) and the max shoulder pressure. The groin protector was found to restrict hip rotation when the subject squatted to pick up an object, producing a pressure 30-times higher than without the EOD 8. These results suggest that a range of motion evaluation method for EOD suits and other protective ensemble can be successfully developed using a combination of user feedback and strategically placed pressure sensors. This study implements the largest pressure region ever recorded on the human body and is the first of its kind to investigate the movement restriction of PPE for various practical tasks.
... Another force-sensitive approach proposed by Zhou et al. [27] introduces a real-time assisted training feedback system. Their system uses a smart textile on a shirt as a fabric sensor [28] to track muscle activities by measuring the pressure on the fabric. Using data acquired from the shirt sensor, the system can classify anaerobic exercise such as push-ups, bicep curls, handstands, and so on. ...
Full-text available
There is growing consumer demand for digital technologies that help users track, motivate, and receive coaching for both aerobic and anaerobic activities. In this article, we provide a review of existing technological advances in tracking, coaching, and motivating users during indoor training in contexts such as gymnasiums. This study lists the advantages and limitations of various apparatuses and applications used for this purpose. Our review and discussion are intended to help entrepreneurs and engineers improve their products to better meet users? needs and aid researchers in identifying potential new areas.
Fine-grained, unobtrusive monitoring of gym exercises can help users track their own exercise routines and also provide corrective feedback. We propose W8-Scope, a system that uses a simple magnetic-cum-accelerometer sensor, mounted on the weight stack of gym exercise machines, to infer various attributes of gym exercise behavior. More specifically, using multiple machine learning models, W8-Scope helps identify who is exercising, what exercise she is doing, how much weight she is lifting, and whether she is committing any common mistakes. Real world studies, conducted with 50 subjects performing 14 different exercises over 103 distinct sessions in two gyms, show that W8-Scope can, at the granularity of individual exercise sets, achieve high accuracy–e.g., identify the weight used with an accuracy of 97.5%, detect commonplace mistakes with 96.7% accuracy and identify the user with 98.7% accuracy. By incorporating an additional, simple IR sensor on the weight stack, the exercise classification accuracy (across the 14 exercises) further increases from 96.93% to 97.51%. Moreover, by adopting incremental learning techniques, W8-Scope can also accurately track these various facets of exercise over longitudinal periods, in spite of the inherent natural changes in a user’s exercising behavior. Our comprehensive analysis also reveals open challenges, such as adapting to the expertise level of individuals or providing in-situ, early feedback, that remain to be addressed.
Full-text available
Important Factors in Surface EMG Measurement is a customer support paper that was requested by several researchers using the Bortec Octopus EMG measurment system. The technical specifications for the Octopus were developed by Dr. Day with systems design and fabrication conducted by electronics engineer Boris Kacmar to meet the need for a full EMG bandwidth system that did not chop out significant power from the EMG signal, as was/is the problem with other systems on the market. The Octopus met the needs of 1) ease of use, 2) reliability, 3) full signal measurement and 4) affordability. The support paper is helpful for any student or researcher that wants a concise overview of important factors in recording the surface EMG during static or dynamic muscle activity, regardless the brand of recording system. It has proven to be a very popular article, in part, because it was not designed to push product sales: unlike this abstract :)
Full-text available
In this paper we present WristFlex, an always-available on-body gestural interface. Using an array of force sensitive resistors (FSRs) worn around the wrist, the interface can distinguish subtle finger pinch gestures with high accuracy (>80 %) and speed. The system is trained to classify gestures from subtle tendon movements on the wrist. We demonstrate that WristFlex is a complete system that works wirelessly in real-time. The system is simple and light-weight in terms of power consumption and computational overhead. WristFlex's sensor power consumption is 60.7 uW, allowing the prototype to potentially last more then a week on a small lithium polymer battery. Also, WristFlex is small and non-obtrusive, and can be integrated into a wristwatch or a bracelet. We perform user studies to evaluate the accuracy, speed, and repeatability. We demonstrate that the number of gestures can be extended with orientation data from an accelerometer. We conclude by showing example applications.
Conference Paper
Full-text available
We describe the design and implementation of an unobtrusive, cheap, large scale, pressure sensor matrix that can be used for a variety of applications ranging from smart clothing, through smart furniture, to an intelligent table cloth or carpet. The specific functionality and with it most of the complexity lies in the electronics and the processing software. We propose a scalable, modular architecture for such electronics, describe a prototype implementation, and present the results of its application to three different scenarios.
Full-text available
We present a novel sensor system for the support of nutrition monitoring. The system is based on smart table cloth equipped with a fine grained pressure textile matrix and a weight sensitive tablet. Unlike many other nutrition monitoring approaches, our system is unobtrusive, non privacy invasive and easily deployable in every day life. It allows the spotting and recognition of food intake related actions, such as cutting, scooping, stirring, etc., the identification of the plate/container on which the action is executed, and the tracking of the weight change in the containers. In other words, we can determine how many pieces are cut on the main dish plate, how many are taken from the side dish, how many sips are taken from the drink, how fast the food is being consumed and how much weight is taken overall. In addition, the distinction between different eating actions, such as cutting, scooping, poking, provides clues to the type of food taken and the way the meal is consumed. We have evaluated our system on 40 meals (5 subjects) in a real life living environment: for seven eating related actions (cutting, scooping, stirring, etc.), resulting in above 90% average recognition rate for person dependent cases, and spotting each action out of continuous data streams (average F1 score 87%).
Full-text available
There is a large class of routine physical exercises that are performed on the ground, often on dedicated "mats" (e.g. pushups, crunches, bridge). Such exercises involve coordinated motions of different body parts and are difficult to recognize with a single body worn motion sensors (like a step counter). Instead a network of sensors on different body parts would be needed, which is not always practicable. As an alternative we describe a cheap, simple textile pressure sensor matrix, that can be unobtrusively integrated into exercise mats to recognize and count such exercises. We evaluate the system on a set of 10 standard exercises. In an experiment with 7 subjects, each repeating each exercise 20 times, we achieve a user independent recognition rate of 82.5% and a user independent counting accuracy of 89.9%. The paper describes the sensor system, the recognition methods and the experimental results. Copyright
Full-text available
Research on activity recognition has traditionally focused on discriminating between different activities, i.e. to predict which activity was performed at a specific point in time. The quality of executing an activity, the how (well), has only received little attention so far, even though it potentially provides useful information for a large variety of applications. In this work we define quality of execution and investigate three aspects that pertain to qualitative activity recognition: specifying correct execution, detecting execution mistakes, providing feedback on the to the user. We illustrate our approach on the example problem of qualitatively assessing and providing feedback on weight lifting exercises. In two user studies we try out a sensor- and a model-based approach to qualitative activity recognition. Our results underline the potential of model-based assessment and the positive impact of real-time user feedback on the quality of execution.
Ultrasound imaging (USI) or Medical Sonography (MS) as it is formally called is widely used in biomedical applications over the last decades. Form the Intensive Care Unit (ICU) minimally invasive monitoring to the recent point of care testing besides the patient's bed. US imaging outcomes can provide clinicians with a thorough view of the internal parts of the human body at a very low expense. In this paper, we insinuate an alternative approach compared to already existing ones of capturing US images. We propose a wearable ultrasound system composed of an array of ultrasound circular 2D transducers, integrated in a belt, for point of care monitoring of the abdominal region and particularly the liver for critical ill subjects. The configuration of the array and the type of the transducers will entail a system capable of providing clinicians with high resolution 2D imaging of the region of interest (ROI) as well as 3D representation of whole organs without theirs assistance.
In this paper we present a compact and versatile acquisition platform designed by modularized method, which is useful and flexible for various sensing applications (such as mechanic detection and ubiquitous computing) thanks to the combination of high resolution analog-to-digital converter (ADC), low power consumption and exchangeable wireless transmission. The 31*45 mm2 module supports simultaneous acquisition on maximum 8 channels with an effective number of bits (ENOB) of 20.9 at most and a sampling rate of up to 32KSPS each. Also we implement two popular modes of wireless transmission featuring high data rate and low power, namely a transmission rate of 21.3Kbps using Bluetooth low energy (BLE, power consumption 30mW) and 263Kbps using WiFi (723mW). Additionally, two typical wireless sensing applications, floor vibration detection and electrocardiograph (ECG) signal acquisition, are tested to demonstrate the performance of this platform. Results show that the characteristic of this platform can primely satisfy the requirements of these applications featuring high resolution, low power and high-efficient wireless data transmission, which is greatly helpful for exploring-stage experiments in wireless sensing application cases.
Conference Paper
The human body is known to produce several different electrical patterns and signals derived from bioelectrical activity. Bioelectrical signals such as the cardioelectrical and myoelectrical signals have several medical applications. In order to acquire those signals, low impedance contact electrodes are commonly used. However, because these sensors require skin preparation or application of conductive gels, placing these sensors can be difficult, time consuming and uncomfortable task for the patient. Moreover the presence of body hair and sweat can be a source of noise and cause signal depletion. This paper proposes a noncontact capacitively coupled electrode based on high impedance input, required to detect weak electrical fields. Noncontact capacitively coupled electrodes rely on reacting to electrical field variations caused by bioelectrical activity, therefore eliminating the need to maintain resistive contact between the skin and the electrode. The sensor high impedance input of 1 teraohms allowed only 0.3 to 1 picoampere input current to flow between the sensor plate and the preamplifier unit. Experiments focused on the recording of electromyogram and electrocardiograms over clothing. Data was collected and compared with data from resistive electrodes. We confirmed that our electrodes are capable of collecting bioelectrical data that can be used for assistive devices interfacing without direct contact with the skin of the subject. Such electrodes can replace currently used resistive contact electrodes improving the reliability of collected signals and increasing user-friendliness of systems that require daily, long term bioelectrical signal monitoring.