Medical studies have intensively demonstrated that sports activity can enhance both the mental and the physical health of practitioners. In recent years, fitness activity became the most common way to motivate and engage people in sports activity. Recently, there have been multiple attempts to elaborate on the “ideal” IoT-based solution to track and assess these fitness activities. Most fitness activities (except aerobic activities like running) involve one or multiple interactions between the athlete’s hand palms and body or between the hand palms and the workout materials. In this work, we present our idea to exploit these biomechanical interactions of the hand palms to track fitness activities via a smart glove. Our smart glove-based system integrates force-sensitive resistor (FSR) sensors into wearable fitness gloves to identify and count fitness activity, by analyzing the time series of the pressure distribution in the hand palms observed during fitness sessions. To assess the performance of our proposed system, we conducted an experimental study with 10 participants over 10 common fitness activities. For the user-dependent activity recognition case, the experimental results showed 88.90% of the
The last decades have seen a growing interest in systems that encourage and support people with regard to the regular practice of physical activity in general and fitness activity in particular. This keen interest in physical activity is mainly due to the results of many research studies which claim that regular practice of physical activity has positive effects on mental and physical health [
With the recent development of wearable computing and sensor technology, a wide range of ubiquitous systems has been developed by researchers and commercial industries to support and motivate people towards physical activity. These systems are designed to track physical activity, evaluate user results, and support decision-making to improve user performances. Fitness workout tracking is important because fitness tracking data provide practitioners with a sense of direction, help them adjust their workout routine, and enhance their motivation and willingness to change their lifestyle [
Thus, the use of such systems tends to limit or constrain the users to perform only within the predefined set of exercises.
For example, the system in [ In general, fitness athletes (with no distinction of their gender, age, or goal) usually wear sports gloves during their workout sessions. They wear the sports gloves for various reasons such as supporting grip pressure, protecting the hands from calluses and blisters, or increasing lift power [ During workout, for most fitness activities (except for aerobics activities like running), there is always one or multiple interactions between the gloves (hands) and the athlete’s body or between the gloves and the workout materials
With that in mind, in this work, we propose a smart glove that can track fitness exercises whenever there is a direct interaction between the athlete’s hands and the workout environment. Figure
Examples of commonly performed fitness exercises.
Our proposed smart glove-based system (Figure
Inside and outside views of the smart glove prototype.
The novelty of our proposed system resides in the approach and data type used to track fitness exercises. Indeed, most common fitness tracking systems rely on inertial sensors such as accelerometers to get information about users’ body positions and movements, whereas our system utilizes data coming directly from the contact surfaces between the users’ hands and the workout environment. Based on this approach, our system could be more suitable to distinguish between exercises of the same type. For example, a classic push-up (Figure
Three distinctive types of push-ups.
Our ultimate goal with the proposed system is to provide fitness athletes with a real-time system that
recognizes the activity being performed counts the number of repetitions (reps) estimates the calorie burned out by each exercise set recommends future exercises to achieve users’ goal
In this paper, we present the design, the activity recognition, and the exercise counting performance of our smart glove system.
The core contributions of this paper are as follows:
flexibility training (e.g., side lunge stretch) dynamic strength training (e.g., squat) static strength training (e.g., plank) circuit training (e.g., push-up + bench dip + lunge)
Through an experiment study, we showed that our smart glove system successfully recognizes 10 frequently performed fitness exercises. We selected 10 different fitness exercise types that target different muscle groups as described in Section
The remainder of this paper is organized into the following sections. Section
There have been much work and many systems on the use of technologies to support and track physical activities. In this section, we restrict the literature review to the area of commercially available systems and research work that use wearable sensors and sensorized equipment to monitor and assess fitness activities.
Commercially available devices such as running watches, fitness wristbands, or trackers are nowadays ubiquitous tools used by thousands of people. Fitbit [
Another well-known commercial system is ActiveLinxx (formerly known as Fitlinxx) [
Google Fit is another widely used activity tracking system which is in the form of an application. It is available for download on any Android device and uses the built-in sensors of that device to track commonly measured fitness data such as the number of steps and calories burned. However, Google Fit’s support website revealed some limitations of the system [
As for research works that use gloves for tracking physical activities, Chang et al. [
Another work presented by Ye et al. [
Sundholm et al. [
A different work introduced by Zhou et al. in [
A state-of-art study, similar to our work is the “RecoFit” system developed by Microsoft Research [
Another more recent work developed by Hassan et al. [
To cope with the limitations of the aforementioned systems, we propose a new type of a smart glove-based system to assess fitness exercises by analyzing hand palm information during workout sessions. Our approach does not require readjusting existing layouts of fitness centers or buying new fitness machines. Table
Comparison with some related work.
Related system denomination | Targeted exercises | Type of sensors used | Collected data type | Classification/counting |
---|---|---|---|---|
Tracking free-weight exercises [ |
Weight training exercises | 3-axis accelerometers | Acceleration | Yes/yes |
Force-sensing glove system for measurement of hand forces during motorbike riding [ |
Motorbike riding | FlexiForce tactile sensors | Tactile forces | Yes/no |
Smart mat [ |
Strength and muscular endurance | Resistive pressure sensor matrix | (a) Body weight distribution |
Yes/yes |
Never skip leg day [ |
Leg exercises | Textile FSR sensors | Pressure distribution | Yes/yes |
RecoFit [ |
(a) Weight training |
3-axis accelerometer and 3-axis gyroscope | (a) Acceleration data |
Yes/yes |
Our proposed system | (a) Flexibility training |
FSR sensors | Pressure distribution | Yes/yes |
This section presents the design and architecture of the smart glove system as described in our previous work [
The current prototype of the smart glove system consists of 3 main components: a set of 16 FSR sensors, a data sampling unit (DSU), and a visualization and computation software.
The smart glove contains a set of 16 force-sensitive resistor (FSR) sensors which are mounted on the palm of the glove as depicted in Figure
The sixteen locations on the glove where the force-sensitive sensors are positioned to read the pressure distributions.
Each sensor has an active sensing area of 12.70 mm diameter, with 0.46 mm thickness, and can sense forces up to 20 N. Based on the force applied to the sensors, their electrical resistive values change and the voltage values corresponding to the pressure is read by the DSU. All sensors are separately connected to the DSU using twisted pair cables (Figure
For now, we use only one hand of the fitness glove pair. For this first prototype of our fitness glove, we wanted to ensure the maximum or full coverage of the athlete’s hand palm, in order to get as much as possible pressure distribution data from different areas of the palm. For this reason, we utilized 16 FSR sensors on our first prototype. This number of sensors might be excessive, but it guarantees full coverage of the sensing zone, which is important when studying a first prototype of a wearable sensing device. However, for our final system, we intend to reduce this number of FSR sensors based on the results and observations of this work.
The data sampling and communication unit (DSU) reads the data from the force sensors and sends the data to the computing and visualization unit. The DSU is composed of an Adafruit Feather 32u4 Bluefruit, a 16 channel multiplexer (16chMUX), a resistor of 2 kΩ, and a small 400 mA/h Li-Po battery.
The Adafruit Feather 32u4 Bluefruit is Arduino-compatible+Bluetooth Low Energy (BLE) with a built-in USB and battery charging module [
The visualization and computation software is responsible for logging and displaying the data sent via Bluetooth by the DSU. It provides, through a web-based user interface (UI), a real-time feedback of the activity’s pressure distribution, with the option to save the data into a CSV file (Comma-Separated Values) for further processing. The value of the pressure intensity applied to each sensor is indicated as a heat map-like color distribution on the glove image on the display. Figure
(a) A user performing a knee-pull-in exercise. The real-time visualization laptop and the DSU are indicated by the blue and red circles, respectively. (b) Screenshot of the visualization UI tool for an exercise.
To analyze the system’s capability of recording, classifying, and counting fitness activities, we designed and ran a 1-hour workout session experiment with 10 participants. Participants were informed that they could stop the experiment at any time without losing benefits. Before their enrollment and participation, we obtained written informed consent from each participant. With participants’ consent, we recorded video of the experiment that we used later as ground truth data to evaluate the performance of the system. Out of 40 preselected fitness exercises, we selected 10 exercises for our experiment based on the following two criteria:
For the experiment, we recruited 10 healthy participants aged from 22 to 30 years (
Before their application, it is necessary for force-sensing systems to be calibrated for reducing inaccuracies. Since the resistivity values of the FSR sensors mainly depend on the person’s weight, the curved shape of the hand palm, and the sensors’ position, calibration is needed for each participant. Like with many related works using garments [
Between the end of the warm-up session and the beginning of the experiment, we observed at least a 2-minute break to eliminate any influence of sensor drift and allow the participants to be ready.
The participants were asked to perform the 10 selected fitness exercises while wearing the smart glove. Each exercise is executed 3 times (3 sets for each exercise), at the participant’s natural speed and pace, to make the experiment more realistic. Each set lasts for 30 seconds, and the participants were allowed to take a 1- or 2-minute break between the sets. During the break time, the glove was turned off by the participants to save battery. The ordering of the exercise was randomized, each participant freely chose the order in which he/she wanted to perform the exercise. Table
Selected fitness exercises with their target muscle group.
Exercises | Target muscle group | |
---|---|---|
1 | Bench dips | Triceps, shoulders |
2 | Climber | Hips, legs, quadriceps |
3 | Dumbbell curl | Biceps |
4 | Knee-pull-in | Abdominals |
5 | Knee-twist-in | Abdominals |
6 | Plank leg raise | Lower back, glutes, triceps |
7 | Pilate dips (triceps) | Triceps, biceps, shoulders, back |
8 | Push-up | Chest |
9 | Side-to-side lunge | Glutes, quadriceps, butt |
10 | Wall push-up | Arms, shoulder, chest |
Exercises performed during the experiments, except the side-to-side lunge. Red areas represent the interaction surface between the glove and the workout environment.
At first, each participant is asked to read and sign the informed consent statement. Then, we introduced the experiment as well as the 10 workout exercises to the participant. After filling out the demographic data sheet, the participant is equipped with the smart glove on his/her dominant hand (left or right hand), with nothing attached on the other hand. After that, we ask the participant to warm-up for 3 minutes by freely doing any stretching movements he/she wants. During the experiment, all participants wore the smart glove and the DSU unit to read the pressure distribution on the hand palm and send the data via Bluetooth to the visualization software for displaying and saving of the workout data. If needed, participants were allowed to remove the smart glove during the break time between sets. Once the experiment is over, we ask each participant to take a short after-experiment survey of 2 questions:
How comfortable is the smart glove (rate on a 10-star scale) Any feedback, comments, suggestions, or ideas related to the device and the system
In addition to the smart glove apparatus, we provided participants with a 2 kg dumbbell to perform the dumbbell curl exercise.
The raw data from the smart glove is a stream of time series data of the 16-channel pressure values (each sensor represents a channel). From these pressure values, we extracted a set of features that could be used to distinguish between fitness exercise types. To analyze the pressure values and develop the classification model, we wrote several MATLAB scripts to select the features, compute the features, and validate the obtained results. MATLAB functions such as mean frequency (meanfreq) or root-mean-square (rms) have been exploited. All statistical analyses were performed using the MATLAB software.
For each exercise set performed by a user, we characterize the exercise as a single signal, denoted by
The signal
The computed
All the activities provoke different changes in the pressure distribution and the intensity, at different points on the palm surface, in the temporal domain. Therefore, we computed the following set of time and frequency domain features:
Mean of each channel Standard deviation for each channel Number of above mean crossing of Number of below mean crossing of Number of peaks of Skewness of Kurtosis of Band power of Mean frequency of Max power spectrum of
Overall, 40 features were extracted (32 directly from the sensors and 8 from the signal
To develop our classifier, we tested various classification algorithms, particularly the decision tree, random forest, SVM, k-NN, and ensemble methods. We report the result for the classifier based on the ensemble subspace k-NN method, which achieved the best recognition results. It is well-known that ensemble methods can be used to improve better predictive performance than could be obtained from any of the constituent learning algorithms alone [
Average recognition result for (a) person-dependent and (b) person-independent evaluation.
Average recognition result for leave-one-session-out
Average recognition result for leave-one-participant-out
For both evaluations (leave-one-session-out and leave-one-participant-out), the overall recognition results indicate highly acceptable levels of exercise recognition accuracy which are higher than 80%. Most of the misclassification happens with exercises such as climber and plank leg raise. We also note an inaccurate prediction for pilate dips, where athletes keep the same posture till the end of the exercise.
The decrease in the accuracy rate between the person-dependent and the person-independent evaluation is undoubtedly a result of participants having different workout styles, hand sizes, etc. We believe the system could be more robust against new users if we provided more training data that include more participants. As smart gloves are intended for personal usage, we suppose the optimum recognition accuracy can be obtained for end users that agree to provide training data during their first use.
One goal of our proposed smart glove system is to count how many repetitions a user has performed during an exercise set. To fulfill this goal, we designed a counting algorithm that uses the raw data from the smart glove to count the number of exercise repetitions during fitness sessions. An exercise repetition is characterized by a specific pattern, observed within the time series signal
Figure
Overview of the DTW-based repetition count algorithm.
Algorithm notations.
Notation | Description |
---|---|
The mean of the 16 sensors for each time sample | |
The minimum possible time to perform a repetition | |
Searching zone of 10 seconds to find the repetition pattern | |
Candidate peaks obtained after Step 2 | |
Repetition candidate at index | |
Repetition pattern of an exercise set | |
Smallest normalized distance between matching | |
Threshold value used to accept or deny matching |
The signal
In this step, we exploit the local maxima (peaks) of the signal
Figure
Examples of repetition signals.
Example signal with constant peak amplitude and regular shapes
Example signal with inconstant peak amplitude and irregular shapes
Therefore, our algorithm has to be efficient and global to handle any exercise repetition signal from the smart glove. To that end, in this step, we need to find and reject peaks that are not generated by actual repetitions such as peaks caused by fatigue and subrepetitions.
To filter out false repetition peaks, we primarily compute all the local maxima of the
Finally, after rejecting the candidate peaks lower than the 20th percentile, we filter the remaining candidate peaks based on the time elapsed between successive candidates. We compare the time between a peak candidate and the previously accepted candidate. If the current peak candidate is at least
The value of
After rejecting the false candidate peaks based on the 20th percentile threshold and the time elapsed, the remaining candidate peaks are passed to the next step (Step 3) for the repetition pattern detection.
At the end of the two previously described steps, we already have a naive repetition count algorithm. We could have stopped the algorithm after these two steps. However, this algorithm would be sensitive to variations in timing, speed, and individual repetition style. Therefore, to make our counting algorithm robust against exercise type and speed variations, we incorporated the dynamic time warping (DTW) algorithm to find the repetition pattern of the exercise set, and then, we examined the signal
Dynamic time warping (DTW) is a widely used technique that utilizes dynamic programming to find the optimum distance between time series [
In our counting algorithm, we utilize DTW to
find the repetition pattern ( measure the similarity between a repetition candidate (
Compared to some previous studies as in [
In this phase, we empirically defined a time window of length 10 seconds starting from second 4 to second 14 of
We work with signal sequences between the consecutive candidate peaks (
If reject the candidate peak define a new searching zone repeat the pattern searching process in the new
This new searching zone will include one or more candidate peaks (
Figure
Examples of exercise repetition patterns found in different searching zones. The blue triangles represent all the candidate peaks before running the algorithm. The green circles indicate the accepted candidate peaks from Step 2.
Repetition pattern found in the initial searching zone
Repetition pattern found in the self-generated searching zone
In this phase, we utilize the DTW algorithm to compare each repetition candidate to the exercise repetition pattern
If the normalized DTW distance between a repetition candidate and the exercise repetition pattern is less or equal to the
At the end of this evaluation condition, we sum up the number of similar
To evaluate the efficiency of our repetition counting algorithm, we utilized the set of data collected during the experiment described in Section
For each exercise set, we used the algorithm to compute the number of repetitions for each participant and compared this number with the actual number of repetitions obtained from the recorded videos. Out of the 10 exercises, one exercise (pilate arms) was a noncounting exercise. Therefore, we evaluated the counting algorithm over 9 fitness exercises. Indeed, during the pilate arm exercise, the athlete has to keep the same position during the entire exercise duration without doing any repetitions. We must also note that due to our camera’s battery and memory shortage, we missed the following 4 ground truth videos:
video of P3 performing the knee-twist-in exercise video of P4 performing the plank leg raise exercise video of P7 performing the climber exercise video of P10 performing the climber exercise
We omitted in our evaluation the results obtained from the algorithm for these 4 cases.
To investigate the impact of the DTW in our counting algorithm, we evaluated the algorithm at the end of Step 2 (without DTW) and Step 3 (with DTW) separately.
The results described below are obtained after Step 1 and Step 2. The algorithm counted an overall number of 5280 repetitions for all the exercise sets, whereas the ground truth data showed a total of 5186 repetitions. In general, the algorithm slightly overcounted the number of repetitions.
The box plot in Figure
Average exercise repetition count from the ground truth and count without and with the DTW.
Furthermore, for each participant, we computed the average repetition count per exercise (remember that each exercise has been performed 3 times), from the ground truth (
Table
Average
Exercise types | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | Average | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Bench dip | Without DTW | +1.7 | -2.7 | +1.0 | -1.7 | -3.3 | -3.7 | -1.3 | -7.7 | -3.1 | ||
With DTW | -2.3 | +0.3 | -1.0 | +0.7 | +0.7 | -1.7 | -1.0 | +1.0 | -3.0 | -3.0 | -0.9 | |
Climber | Without DTW | 0.0 | +1.0 | -1.7 | 2.7 | -1.3 | -0.7 | NaN | +1.3 | -3.3 | NaN | -0.3 |
With DTW | +0.7 | +2.7 | +0.7 | +2.0 | +2.3 | +2.0 | NaN | +1.0 | -2.3 | NaN | +1.1 | |
Dumbbell | Without DTW | +0.7 | +4.0 | -3.3 | -1.7 | -3.7 | +2.3 | +0.7 | -1.0 | -2.0 | +0.2 | |
With DTW | +0.7 | +2.7 | +4.3 | -1.0 | -0.7 | +1.0 | +2.7 | +1.7 | +0.3 | -0.3 | +1.1 | |
Knee-pull-in | Without DTW | +0.3 | -2.0 | -0.3 | +2.0 | +0.3 | +4.7 | +1.3 | +2.3 | +1.0 | +0.3 | |
With DTW | +0.7 | -1.0 | -1.7 | +1.3 | +0.7 | +2.7 | +0.0 | +2.7 | -2.3 | +0.3 | +0.3 | |
Knee-twist-in | Without DTW | -3.3 | -3.7 | NaN | +1.7 | +2.0 | +8.0 | +1.7 | +1.7 | +0.7 | ||
With DTW | -0.7 | +1.3 | NaN | +4.7 | +3.7 | +4.0 | +3.0 | +1.3 | -3.7 | +2.0 | +1.7 | |
Side lunge | Without DTW | +2.3 | -0.7 | +0.7 | +16.7 | -1.3 | +5.7 | |||||
With DTW | +1.0 | +1.0 | +4.5 | +3.3 | -2.3 | +4.0 | +4.0 | -0.3 | +2.8 | |||
Plank leg raise | Without DTW | +1.0 | -1.3 | -1.0 | NaN | -1.7 | -3.0 | +5.0 | -0.3 | -5.7 | -0.7 | -0.9 |
With DTW | +2.0 | -0.3 | +0.7 | NaN | +4.0 | +0.3 | +3.3 | +0.3 | -3.0 | +1.0 | +0.9 | |
Push-up | Without DTW | -1.3 | -2.3 | -1.7 | +4.7 | -2.0 | +2.0 | -2.7 | -3.0 | -1.8 | ||
With DTW | -3.3 | -1.0 | -1.0 | -0.7 | +3.7 | -3.0 | -3.3 | -2.0 | -0.9 | |||
Wall push-up | Without DTW | +0.7 | -0.3 | -1.0 | -0.3 | -0.7 | +0.7 | +0.3 | -2.4 | |||
With DTW | -1.7 | +0.7 | +0.3 | -0.7 | +0.3 | -2.3 | -0.6 | +0.7 | -3.0 | 0.0 | -0.6 |
The high overcounting and undercounting repetition numbers are presented in bold.
Although the peak count and time-elapsed approach can count well without looking into the pattern, this approach only is not sufficient for counting exercise repetitions. One way to improve it is to utilize the DTW algorithm to find the repetition pattern of each exercise set and then use this pattern to count the exercise repetitions.
At the end of Step 3, the algorithm counts 5053 total repetitions, whereas the ground truth showed a total of 5186 repetitions. The average repetition count obtained after using DTW is almost equal to the number of repetitions observed in the ground truth data. The box plot in Figure
Table
The difference in the results obtained before and after integrating the DTW algorithm shows that the DTW makes our counting algorithm more robust and accurate.
In evaluating our algorithm, we computed another parameter: error rate in percent. The error rate is calculated as the absolute value of the mis_count over the actual count (
For each exercise and participant, we calculated the error rate by using the average repetition count obtained after integrating the DTW (Step 3). Figure
Average error rate by exercise and by participant.
Average error rate for each exercise
Average exercise count from the ground truth and count after Step 3 of the algorithm
Independently of the participant and exercise type, there is no result of an error rate higher than 20%. With most participants, the push-up exercise has the highest error rate of 17.70%. This is explicable since the push-up exercise is the most exhausting exercise to be performed over 30 sec. Some participants pause and resume while in the middle of the push-up exercise, before the time out. Two participants performed the “lady push-up” style because they felt incapable of doing the standard push-up for 30 sec. Two other participants performed the push-up in a different style, which consists of making a subrepetition movement after each normal repetition. This style (a.k.a. “military push-up”) is generally performed by nonamateurs to boost up the effect of the standard push-up.
Only two exercises (knee-twist-in and push-up) have their error rate higher than 10%. The average counting error rate for all exercises is 9.84% and the participant average counting error rate is 9.78%. The worst error rate by participants was obtained with P9 (19.38%), followed by P6 (12.26%). These high error rates might be related to the fact that P9 and P6 did not practice any sports activity in the last six months before the experiment day.
Overall, the results indicate that our repetition counting approach is an acceptable way to make a smart glove that can also count exercise repetitions. The system might work better with regular gym-goers than irregular practitioners. However, we need more testing with experimented fitness practitioners to confirm or deny this hypothesis.
In our short exit survey, participants were asked to assess the comfort level of the smart glove on a scale from 0 to 10, with 0 being not comfortable and 10 being comfortable. Figure
Score of the 10-star scale comfort level for each participant.
The second question of the survey (do you have any feedback, comments, suggestions, or ideas related to the device and the system?) revealed that participants want the smart glove to be adjustable, for fitting their hand size. In fact, our current prototype was designed to be “gender neutral with a unique size.” Therefore, some participants felt like the smart glove was slightly big, while others said that it was small. For example, P1 said, “It would be nice if the width could be adjustable to fit it (the glove) to my arm,” whereas P9 reported, “It (the glove) fits well on my hand but sometimes slides (during the workout).” Another participant (P3) mentioned, “I want to have better tight on my fingers.” From this feedback, we agree that our next prototype should follow the fabrication designs of ordinary fitness gloves already available on the market, in terms of materials, sizes, and appearances.
As mentioned in Section
By analyzing the data collected during the experiment, it appears that some sensors can be removed without drastically altering the activity recognition and exercise counting results.
For each activity, we got 30 exercise sets (10 participants × 3 sets per activity). From these 30 sets per activity, we computed the average force applied to each sensor, to determine whether or not a sensor is activated (used) during that particular exercise. For this evaluation, we used the absolute force applied to the sensors, without normalization.
Table higher than or equal to lower than less than
Average sensor values for each exercise.
Sensors position | Bench dip | Climb. | Dumb. | Knee-pull-in | Knee-twist-in | Side lunge | Pilate dip | Plank leg raise | Push-up | Wall push-up |
---|---|---|---|---|---|---|---|---|---|---|
1 | 54.28 | 240.54 | 6.62 | 91.89 | 230.71 | 201.88 | 219.04 | 343.82 | 275.98 | 56.13 |
2 | 231.81 | 511.77 | 2.10 | 227.78 | 337.49 | 318.30 | 248.62 | 633.29 | 467.15 | 71.70 |
3 | 341.95 | 718.57 | 3.35 | 331.44 | 732.16 | 648.41 | 745.87 | 724.94 | 708.25 | 226.36 |
4 | 274.48 | 595.46 | 9.31 | 381.60 | 641.78 | 580.58 | 673.91 | 552.13 | 644.16 | 267.11 |
5 | 50.39 | 4.72 | 81.48 | 0.41 | 6.00 | 1.89 | 0.54 | 17.66 | 18.95 | 0.00 |
6 | 244.08 | 198.89 | 34.53 | 34.99 | 132.48 | 121.25 | 151.06 | 158.61 | 124.59 | 1.71 |
7 | 478.40 | 365.18 | 8.62 | 81.24 | 280.89 | 262.61 | 314.31 | 332.83 | 301.13 | 8.10 |
8 | 540.44 | 405.72 | 1.19 | 135.53 | 365.07 | 379.80 | 373.25 | 348.93 | 369.32 | 71.27 |
9 | 0.28 | 0.28 | 0.06 | 1.80 | 0.53 | 0.62 | 0.03 | 3.06 | 1.27 | 0.00 |
10 | 21.33 | 63.72 | 5.56 | 13.78 | 21.98 | 54.41 | 32.46 | 59.86 | 24.44 | 1.77 |
11 | 29.70 | 52.35 | 19.78 | 16.10 | 22.57 | 70.18 | 31.49 | 28.70 | 18.70 | 0.04 |
12 | 7.05 | 22.94 | 0.54 | 21.07 | 28.75 | 46.87 | 36.86 | 8.28 | 1.04 | 0.00 |
13 | 4.89 | 29.09 | 150.03 | 2.62 | 35.28 | 36.05 | 28.96 | 21.48 | 39.90 | 0.18 |
14 | 66.69 | 87.37 | 116.34 | 25.93 | 77.09 | 74.55 | 54.34 | 89.54 | 102.87 | 7.30 |
15 | 1.37 | 3.81 | 201.49 | 1.13 | 51.67 | 20.29 | 6.17 | 22.33 | 45.05 | 1.03 |
16 | 3.12 | 82.12 | 4.16 | 9.42 | 76.11 | 106.57 | 51.42 | 71.28 | 76.45 | 7.56 |
Mean | 146.89 | 211.41 | 40.32 | 86.05 | 190.03 | 182.77 | 185.52 | 213.55 | 201.20 | 45.02 |
14.89 | 21.14 | 4.03 | 8.60 | 19.00 | 18.27 | 18.55 | 21.35 | 20.12 | 4.50 |
Sensor activation status during fitness exercise.
The intuition behind this reasoning is that if a value is 10 times less than the average of all values, then this value is significantly low and negligible. From the results of this analysis, we can suggest a new design of the proposed smart glove, without the sensors at position 5 and 9. Indeed, at these positions, the sensor values are negligible for most exercises. The sensors on the fingers (positions 13, 14, 15, and 16) can also be removed or slightly moved down because they are frequently inactivated or activated only a few times for most exercises except for the dumbbell curl exercise. Sensors on positions 1, 2, 3, 4, 7, and 8, which are generally highly activated, should remain in the same spots for the next prototype.
One limitation of our current system is the tracking of exercises such as running that does not produce pressure variation in the palm. To overcome this issue, we intend to integrate inertial sensors such as accelerometers or gyroscopes into the DSU (data sampling and communication unit) of our next smart glove prototype. By adding such inertial sensors into our system, we will be able to track pressureless exercises, as well as improve the exercise recognition and counting performance of the proposed system.
Another limitation of the present work was the low number of participants during the experiment, which meant we could not determine whether the obtained results of the current prototype are statistically significant. However, these results confirmed our intuition and idea that it is possible to use biomechanical data from the hand palms to monitor fitness activity. Moreover, the current experimental results provide valuable information and orientation that could be employed to improve the overall system performance. Notwithstanding the above, in our future work, we intend to validate the proposed methods with a larger number of participants.
In this work, we investigated a novel smart glove-based system for tracking indoor fitness activity. Our approach exploits the interactions between the hand palm and the working environment to assess fitness activities. The system integrates 16 FSR sensors into a fitness glove to identify fitness activities and count the repetition of an exercise, by analyzing a time series of the pressure distribution applied to the hand palm during the exercise.
We presented the design of the smart glove and evaluated the exercise recognition performance and the accuracy of the repetition counting algorithm of the system. Our validation experiment with 10 healthy participants over 10 common fitness exercises showed an overall exercise recognition accuracy of 88.00% for the person-dependent evaluation and 82.00% for the person-independent evaluation. The evaluation of the repetition counting algorithm achieved an average counting error rate of 9.85%. Based on our results, we concluded that a smart glove that collects and analyzes hand palm pressure could be used to track and assess fitness activities.
Clearly, in its current design, the system alone is not enough for tracking exercises that do not generate pressure in the hand palms. However, it provides valuable results that can be combined with the data from inertial sensors, to develop more complete systems for supporting fitness practitioners.
The smart glove data (in .csv format) used to support the findings of this study have been deposited in the “FSR-Smart-glove-data” public repository on Github and are accessible via the following link:
The authors declare that they have no conflicts of interest.
This work was partly supported by JST PRESTO and JSPS KAKENHI Grant Number JP16H01721.