Andrey Tolstikhin

Title: Andrey Tolstikhin: Innovator in Activity Classification Technology

Introduction

Andrey Tolstikhin is a notable inventor based in Montreal, Canada. He has made significant contributions to the field of activity classification technology, holding a total of 7 patents. His work focuses on utilizing advanced algorithms and neural networks to classify human activities based on 2D skeleton data.

Latest Patents

One of his latest patents is a method and system for activity classification. This disclosure is directed to an activity classifier system that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, which comprises scaled, relative joint positions and relative joint velocities. Additionally, it features a gesture classifier that utilizes a first recurrent neural network to identify the most probable of a plurality of gestures. Furthermore, there is an action classifier that employs a second recurrent neural network to identify the most probable of a plurality of actions based on the information received from the gesture classifier.

Career Highlights

Throughout his career, Andrey has worked with prominent companies such as Hinge Health, Inc. and Wrnch Inc. His experience in these organizations has allowed him to refine his skills and contribute to innovative projects in the field of activity classification.

Collaborations

Andrey has collaborated with notable professionals in his field, including Colin J Brown and Thomas D Peters. These collaborations have further enhanced his work and contributed to the development of cutting-edge technology in activity classification.

Conclusion

Andrey Tolstikhin is a distinguished inventor whose work in activity classification technology has made a significant impact. His innovative patents and collaborations with industry professionals highlight his dedication to advancing this field.