An AI model for the mySASY app

For the mySASY training application, we shortened the measurement time from 15 to 4 minutes using advanced artificial intelligence methods.

The mySASY application is intended for everyone who does sports, whether on a professional level or in their free time. With this application you can improve the way you schedule your training. It helps you understand when it is a good time to continue or increase training intensity and when to rest, which helps you prevent injuries or other complications. Simply put, the application evaluates the current state of the autonomic nervous system (ANS) and gives you recommendations based on this data.

Spectral analysis of heart rate variability

To determine the state of the autonomic nervous system, mySASY uses a unique measurement methodology. The algorithm allows to control the athlete's training based on the analysis of ANS activation using the methods of spectral analysis of heart rate variability (HRV). At this stage, we got involved in the development process to help reduce measurement time with AI methods.

Reducing the measurement time

We processed hundreds of thousands of measurements, more precisely 1,041 days of data, and with the help of machine learning methods we managed to shorten the whole process while maintaining the accuracy of a long measurement. It took users 15 minutes to get measured and now it can be done in 4 minutes.

The AI model

We created a model from the collected data, which can extract the same information value from measurements that are three times shorter. "The model we designed using advanced artificial intelligence methods is comparable to the experience of a someone who has been constantly analyzing thousands of people for three years," adds Jaroslav Vážný, who participated in the development of the model.

Gradient Boosting Decision Tree

As with all machine learning applications, the most important part was the processing of raw data and the extraction of useful properties. A key element of this project is the automatic recognition of measurement phases (to activate ANS it is necessary to change the position of the body during the measurement). The correct division into phases that are unique to each individual and various loads on the body is a non-trivial task. We used a combination of methods led by wild binary segmentation (WBS). The data processed in this way was used to train the model. We tested various approaches, including recurrent neural networks, and finally used the Gradient Boosting Decision Tree (GBRT).

An AI model for the mySASY app

Related products and services

Build an AI-driven product
Build an AI-driven product

From an idea to production implementation. We will help define, verify and build your new product and get it to your customer.

More info about Build an AI-driven product
Data integration
Data integration

Data integrations typically combine machine and contextual data, which is available in various structures. We will help you correctly join big dat...

More info about Data integration
Machine learning and automation
Machine learning and automation

Machine learning enables us to introduce higher levels of automation to many business and manufacturing processes across various industries. Artif...

More info about Machine learning and automation

Machine learning and AI

We will advise you too. Let me know.

Jaroslav Vážný
Jaroslav Vážný Big data expert

More case studies

Implementing an AI recommendation engine at Jery
Implementing an AI recommendation engine at Jery

Our recommendation engine is looking to match the best job offers with the best candidates.

More info about Implementing an AI recommendation engine at Jery
Cloudera Workshop for Vodafone
Cloudera Workshop for Vodafone

We prepared for Vodafone a three-day practical training course about big data work on the Cloudera platform.

More info about Cloudera Workshop for Vodafone
Slovak Telekom – Big data infrastructure
Slovak Telekom – Big data infrastructure

Modern data infrastructure for Slovak Telekom and access to new interesting data

More info about Slovak Telekom – Big data infrastructure
Reporting at Tatra banka went from a few hours to a few seconds
Reporting at Tatra banka went from a few hours to a few seconds

We accelerated the generation of reports and trained approximately 30 people at Tatra banka.

More info about Reporting at Tatra banka went from a few hours to a few seconds