Fischer4You2 aims to recommend appropriate alpine skiing equipment based on the skill level of alpine skiers and make them aware of their expertise and level of consistency in performing different alpine skiing techniques. During the Fischer4You project, we will implement a pipeline that collects skiers' data via body-worn sensors embedded into their smartphones, processes the recorded signals to detect their skiing activities, classifies those activities into alpine skiing techniques, monitor user behavior while performing different skiing styles such as speed control and consistency and stability at each turn and acceleration/deceleration after/before each turn, and scores them to provide a level of expertise. This pipeline processes the accelerometer, gyroscope, magnetometer, and GPS signals and detects alpine skiing patterns and insights to build a skill assessment model. The model recognizes the skier’s skill from the generated patterns during skiing using machine learning algorithms, creates a skier performance profile, and assists them with feedback in the form of product and skis recommendations and technique guides.

Ultimately, this system provides users with their skiing profile, supports them to access their own driving quality and choose a proper product, and improves their skiing skills. Further, the goal is that this system runs on a central server and its assessment can be triggered by just using data coming from a mobile phone, which is also used for informing users about their skill level and an appropriate product recommendation.

The Fischer4You2's approach is to build a model based on state-of-the-art methods in sports activity detection, performance and motion analysis, activity identification/classification, and skill level recognition relying on machine learning algorithms. The Fischer4You II pipeline will gather data using IMU and GPS sensors embedded in the smartphone, preprocess recorded signals, detects and analyze alpine skiing activities, and creates a skier profile based on generated patterns. Finally, it will score skiers through a data-driven model that compares each skier with expert users' behavior and their consistency in reproducing similar patterns at consecutive turns. Subsequently, recognized skill levels fused with other general information sources, e.g., demographic information, form an input to the recommendation system to get both ski product and coaching recommendations.

The main goal of the Fischer4You II is to develop a smartphone application to be used by every recreational alpine skier with any level of skiing skill. This recognition pipeline consists of the following components: (i) a sensor fusion module used to create viable sensor ensembles opportunistically as a basis for motion analysis and activity recognition, (ii) performance analysis and activity recognition models to know what each skier does and how well he is performing each technique, (iii) a data-driven model based on expert users profile to be used as a reference for skill assessment (iv) a recommendation module, able to offer the most appropriate equipment to each user, and (v) a feedback trigger module, which will formulate a ski recommendation and potentially also areas of improvements, e.g., like recommending seldom driving techniques. This framework is developed as a distributed application, with a sensing and actuating component, e.g., an application on a smartphone, and a reasoning component, e.g., implemented as a machine learning server component for recognition. For demonstration purposes, the produced application on a smartphone along with the skill assessment framework and recommendation system provides state-of-the-art user assistance to form a standalone, visual support- and guidance system for a targeted personas study and a bigger audience of skiers in the long run.