1. Please introduce yourself to the readers (how you started in the profession, education,
My name is Giuseppe Vannozzi and I'm a Computer Engineer, and I hold a PhD in Bioengineering. My thesis focused on the analysis of how the human body functions and moves with a special emphasis on the application of soft computing techniques to extract information from biomechanics data. I then held a post-doc position at the University of Rome “Foro Italico”, which specializes in sports and movement analysis, and now I am an Assistant Professor in Biomechanics. In these 15 years of activity, I have worked close to industrial partners as well as physical educators, clinicians and coaches to propose quantitative methods for capacity and performance assessment. Since 2009, I started my activity in swimming biomechanics in close collaboration with Dr. Giorgio Gatta and his staff at the University of Bologna. Mainly, we aimed at promoting the use of wearable technology devices to assess swimmer performance and monitor his/her activity.
2. You recently published an article on wearable inertial sensors in swimming. Could you explain what those are?
Miniaturized inertialmeasurement units (often called IMUs), commonly found today in trendy wearable technology, are an increasingly popular alternative to 3D video analysis. An IMU typically comprises a 3-axial linear accelerometer and an angular rate sensor, also called gyroscope. Output of the IMU are the 3D linear acceleration and the 3D angular velocity of the body segment to which it is attached. The physical quantities provided by each sensor are measured with respect to the axes of a unit-embedded frame, generally aligned with the edges of the unit case. Through smart algorithms, able to fuse the redundant information available and to compensate for sensor drift, 3D body segment orientation can be also obtained. IMU sensors are typically wireless, allowing for in-field quantitative measurements, easy to use and generally cheap.
3. What did your study look at?
Since an increasing range of inertial sensors and protocols have been proposed in the scientific literature for swimming performance assessment, we deemed of interest to examine how they were used and how well they performed with respect to traditional swimming motion analysis techniques. Therefore, our aim was to provide a systematic review regarding the current status of inertial and magnetic sensors for swimming performance assessment (Magalhaes et al, 2014). The main objective of this review was to provide a framework to fully exploit the recent advances in miniaturized wearable technologies to obtain biomechanical data related to sport performance.
4. What were the results of your study?
We found that IMUs are potentially capable of helping us evaluate the performance of swimmers throughout the swimming pool and for a whole duration of a training session; this overcomes the various limitations of traditional video analysis. For instance, in looking at the stroke patterns, while video analysis limits its observation to a single stroke cycle, depending upon the real capture volume of the cameras, IMUs can generally acquire continuously without specified spatial limitations. Thus, for instance, changes with fatigue may be potentially captured using IMUs. These results were supported by a comprehensive overview of the existing applications of inertial sensors in swimming science.
5. What were the practical implications for coaches and swimmers from your study?
Nowadays, there is a lively interest about IMUs in swimming motion analysis and researchers working in this area are continuously proposing new methods to estimate variables potentially useful for coaches and swimmers practice. We discovered that inertial sensors, including accelerometers and gyroscopes, can be invaluable in a multidisciplinary environment, in which sport biomechanists and engineers can work together to calculate the scores and indices – widely used by swimming practitioners –with the aim of progressively meeting the desires of coaches and trainers. Based on specific objectives of the analysis, you can appropriately select the sensor to include in your setup: an accelerometer to estimate linear kinematics (velocity) and body inclination; a gyroscope to estimate angles and body orientation; both sensors to estimate task phases, time parameters (durations, stroke frequency).
6. What inertial sensors do you use or recommend?
It is really hard to recommend any specific brand or product available on the market. Your best starting point to conduct your research is really any IMU device that possesses the appropriate sensor requirements (Picerno et al, 2011) and the suggested guidelines to improve outcome accuracy (Bergamini et al, 2014). Personally, I have used the technology offered by Newsens, which included a spin-off of our laboratory with which I have started to work on this topic.
7. What other technical advances do you see beneficial for swimmers?
As a swimmer-centric monitoring technology, these devices can increase the amount of information available to the athlete/coach. IMU technology can potentially put the coaches and athletes in a position to benefit from numerical feedback almost in real time. This is especially valuable if a swimmer or a coach wants to detect and correct specific performance-related concerns. Moreover, coaches at poolside can have individual indicators of the swimmer’s performance such as velocity, attitude and position of the swimmer for the length of the swimming pool (Le Sage et al., 2010b).
The engineering literature started also to consider the development of real-time feedback methods, even if these approaches are not ready for the everyday practical application. The main advantage of these methods is the low computational effort required. Therefore, once the communication protocols reach a useful real-time performance and the sensor fusion algorithms become more reliable in the aquatic environment, it would be reasonable to expect a decrease in the time gap between laboratory and training environments. In this manner, swimmer performance analysis based on biomechanics method can be carried out almost instantaneously after a swim trial.
8. How can a coach use inertial sensors for a large age-group (40 kids), a more elite high school group (20 kids), or an elite college group (10 kids)?
Inertial sensors have several advantages and allow for quick data acquisitions without cumbersome setups as you may experience using video-cameras, which makes it applicable to athletes of medium level and not only to élite swimmers. Depending on the team size, the coach may consider to include only one IMU device per swimmer to monitor cycle durations, stroke frequency and related parameters or to include additional sensors to monitor more complex indicators. A coach might consider partnering with an analyst who can then implement the right mathematical procedures following the scientific literature. Currently, there are no commercially available devices that directly implement some of the mentioned performance indexes.
9. Who is doing the most interesting research currently in your field? What are they doing?
There really aren’t many laboratories working on swimming biomechanics using IMU sensors. Groups from Australia, Switzerland and UK are very active carrying out the most interesting work about the topic as widely cited in our review article. Adding to our review, Farzin Dadashi from Lausanne (SW) recently published an interesting paper about the estimation of front-crawl energy expenditure using IMUs (Dadashi et al, 2014), which is one of the most promising application we foresaw at the end of our review article. In his study, he used a set of four waterproofed IMUs worn on forearms, sacrum, and right shank of eighteen swimmers and validated their methodology using indirect calorimetry and blood lactate concentration.
10. Which teachers have most influenced your research?
I had the privilege to work with Professor Aurelio Cappozzo, recognized internationally as one of the main experts in the biomechanics of human movement. In his laboratory in Rome, I had the opportunity to learn how biomechanical methods can be applied and used to assess the performance and capacity of human motion. Working with several sports science colleagues, I had the opportunity to approach the field and to better understand the needs of coaches and sport professionals; the collaboration with my colleague Giorgio Gatta was determinant for me to open to the swimming field which is one, currently, of my main scientific interest.
11. What research or projects are you currently working on or should we look from you in the future?
I am always looking at how I can help coaches and athletes benefit from rich numerical feedback at the swimming pool. Currently, I am evaluating the feasibility of using IMUs to characterize block starts and turning mechanics, this will add yet another layer to my previous research and answer some of the questions coming out of the swimming community.
- Bergamini E, Ligorio G, Summa A, Vannozzi G, Cappozzo A, Sabatini AM, (2014). Estimating orientation using magnetic and inertial sensors and different sensor fusion approaches: accuracy assessment in manual and locomotion tasks. Sensors (Basel): 14(10):18625-49.
- Dadashi F, Millet GP, Aminian K, (2014). Estimation of Front-Crawl Energy Expenditure Using Wearable Inertial Measurement Units. IEEE Sensors Journal, 14(4): 1020 – 1027.
- Le Sage T, Bindel A, Conway P, Justham L, Slawson S, & West A, (2010). Development of a real time system for monitoring of swimming performance. Procedia Engineering, 2, 2707–2712.
- Magalhaes FA, Vannozzi G, Gatta G, Fantozzi S, (2014).Wearable inertial sensors in swimming motion analysis: a systematic review. Journal of Sports Sciences, Epub ahead of print, pp. 1-14.
- Picerno P, Cereatti A, Cappozzo A, (2011). A spot check for assessing static orientation consistency of inertial and magnetic sensing units. Gait and Posture, 33(3):373-8.