Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Development of an Human Activity Recognition Algorithm using Machine Learning Methods
The goal of this project is to find and validate characteristic human action patterns based on real data. This should be achieved by developing an algorithm which recognizes, classifies and predicts human actions in different cognitive challenging surgery or handling tasks.
Keywords: Eye Tracking, Data Mining, Pattern Recognition, Surgery, Automated Workflow Detection, Usability, Process Mining
In order to allow the development of reliable robotic assistive devices, it is indispensable to find and understand the characteristic sequences of action which define these activities.
This project aims to enable these technologies, such as as assistive Augmented Reality (AR) systems in surgery, by providing the algorithm needed to compare and analyze the recorded data.
The student will be asked to use different machine learning approaches to leverage existing real world data, with the goal to correctly classify distinct real world activities.
He/She will have the opportunity to work in an unique environment which combines medicine, product development and state of the art machine learning methods.
In order to allow the development of reliable robotic assistive devices, it is indispensable to find and understand the characteristic sequences of action which define these activities. This project aims to enable these technologies, such as as assistive Augmented Reality (AR) systems in surgery, by providing the algorithm needed to compare and analyze the recorded data.
The student will be asked to use different machine learning approaches to leverage existing real world data, with the goal to correctly classify distinct real world activities.
He/She will have the opportunity to work in an unique environment which combines medicine, product development and state of the art machine learning methods.
- Review on the state of the art
- Improvement of an existing algorithm to extract characteristic process sequences based on real world data
- Application and validation of the algorithm on unlabeled data
- Providing innovative approaches to the problems at hand
- Review on the state of the art - Improvement of an existing algorithm to extract characteristic process sequences based on real world data - Application and validation of the algorithm on unlabeled data - Providing innovative approaches to the problems at hand
- Experience in programming (MATLAB or python) desired - Familiar with basic machine learning methods - Interested in human behavior - Creative and like hands-on work - Highly Motivated and independent
Build Expertise. Create Value.
Success in product development depends heavily on the competence and skills of teams and individuals. This is why we dedicate our research to create knowledge that enables the value-adding use of new technologies - and to make this knowledge tangible and teachable. Industrial and clinical needs are the driving forces for our interdisciplinary research. Our work is distinguished by a variety of methods, ranging from simulation to validation of real applications. Our research changes the way we develop products, and our expertise changes the way we create sustainable value.
Build Expertise. Create Value. Success in product development depends heavily on the competence and skills of teams and individuals. This is why we dedicate our research to create knowledge that enables the value-adding use of new technologies - and to make this knowledge tangible and teachable. Industrial and clinical needs are the driving forces for our interdisciplinary research. Our work is distinguished by a variety of methods, ranging from simulation to validation of real applications. Our research changes the way we develop products, and our expertise changes the way we create sustainable value.