Cognitive Internet of Things is about enabling current IoT technologies with human-like intelligence. The end goal is to provide expert advice based on the domains being targeted. Cognitive IoT can be applied on the edge gateway or in the cloud as part of the solution.
Let’s see how we can apply Cognitive IoT technologies for the Sports domain. There are actually three primarily use cases:
- Learning from an expert/coach (or visually) and improving one’s game.
- Personalization: where all information is personalized to improve one’s game.
- Continuous learning to keep a player improving his game based on how is he is playing from current and past records.
I will talk about an example using cricket. The real value that we want to derive is to enable a batsman to understand his game better, help them master various batting strokes — like cover drive, pull shot, etc., and analyze their performance continuously to become an expert batsman.
With respect to a baller, the baller would like to understand how well he is bowling, his speed, his run-up, the way he delivers the ball, and spin variations — all these insights can improve his game continuously (so there is a feedback loop) and how similar he is to bowling like an expert baller.
So let’s talk about how do you go about realizing the plan.
- Embedded device on cricket ball (without increasing form factor).
- Embedded device on cricket bat, pads, gloves.
- A connected stadium.
For an architecture stack perspective, you have the low-powered embedded device installed inside the ball or embedded as part of the design and manufacturing process. It provides at least a six-axis combo sensor for accelerometer and gyroscope reading to identify any movement in 3d space. A Motion SDK is installed on top of the device to identify any movements in general and communicate the reading to the cloud.
In the cloud, we have the learning model or the training data. Basically, we would ask an expert batsman to bat and play various expert strokes, like cover drive, and record their movements from sensors (bats/pads etc) as well as visuals (postures etc), this would be used as the training/test data, and a comparison would be made against it. As we are comparing 3D models, machine learning approaches like dimension reduction can be employed (and many new, innovative approaches) to compare two motion and prediction the similarity. Similar training data is captured from an expert baller, along with other conceptual information like hand movements, pitch angles, etc.
The feedback is continuously captured and the system provides guidance for improving a player’s game. The player tracks all this information on mobile devices and can now look at these insights and suggestions on how he can be an expert. For instance, a player can ask a system, “What does it take to master a cover drive like Sachin?” and the system analyzes the motion information from batting strokes (sensors on bats, pads, etc.), visual information (postures, etc.), then compares it with an expert model and provides an accuracy score and suggestions to improve a player's game. The key here is that the cognitive system understands the domain and is trained on the domain to provide expert advice or suggestion.
The same technique and concept can be applied in any game to get cognitive insights.