Motion Interface technology is incorporated today in leading consumer electronics products such as smartphones, tablets, game systems, and smart TV remotes. Following this trend, highly accurate, low cost MEMS motion sensor devices such as accelerometers have already found their way into wearable sensors to perform basic tasks such as step counting to monitor overall activity levels. The next generation of wearable sensors will include a complete, integrated, intelligent Motion Tracking device through the addition of gyroscopes, compasses and pressure sensors to collect even more complex data sets that allow for automatic activity recognition and for other activity monitoring such as jump height, swing plane analysis, ball rotation, reaction time, impact energy, speed and distance. This data opens a tremendous number of interesting possibilities for professional sports training, personal fitness tracking, and will likely open the sports viewer in the stadium or at home to an incredible array of new statistics that can be used to track their favorite athletes. Motion Tracking devices will be explained in more detail later in this paper.
Data and statistics have long been a big part of sports and fitness. In professional sports, we have traditionally tracked metrics such as batting average, rushing yards, driving distance off the tee, goals scored, and ERA to gauge the quality of the athlete. However, the desire to win and the prospective financial gains for those players and teams who can get an edge over the competition are changing the way athletes train and the way teams scout and evaluate players. Access to large amounts of data and advanced statistical analysis are raising the competitive bar. Billy Bean, GM of the Oakland A’s, as told in the book “Moneyball” used advanced statistical analysis to scout for and find “diamond in the rough” players on the cheap to give his team a boost and get into the baseball playoffs. Cyclists monitor VO2 max (max oxygen consumption) levels and power output metrics to optimize their energy output over long rides. Many athletes these days are using advanced data sets collected during their training to find that razor thin edge over their opponents.
In personal fitness, the Quantified Self movement is taking us beyond simply tracking the time and distance of our runs or bike rides. Casual athletes are becoming much more data driven and access to more sophisticated data sets from wearable sensing devices and advanced statistical analysis are taking this to the next level. By using motion sensor subsystems, we now have the data to analyze our activity throughout the day. How much time did I spend sitting, walking, exercising and sleeping? How does this match to the activity goals I’ve set for myself? While exercising, did I expend more calories on my 30 minute run or that pickup game of basketball?
Figure 2: Quantified Self concept (image credit: quantifiedself.com)
Personal fitness is also going social as friends and peer pressure sometimes serve as our best motivator. Did I run further than my friend today? Did he or she beat my time on our favorite mountain biking trail? This data can now be automatically collected and shared by our smartphones and companion wearable sensing devices and can bring a sense of motivation and competition to personal fitness.