Open PhD Position @ ETH Zurich “Indoor Localization and Context Recognition for Patients with Parkinson’s Disease”

=== Background ===
The Wearable Computing Laboratory at ETH Zurich ( develops methods to recognize human activities and context from data captured from sensors placed on-body, such as those found in mobile phones.

One of the uses of context and activity recognition methods is to support independent living for people in need, such as elderly or people with disabilities.

=== CuPiD: “Closed-loop system for personalized and at-home rehabilitation of people with Parkinson’s Disease” ===

CuPiD is a European funded project with 8 partners distributed in 6 EU countries during a 3 year period (2011-2014). Partners include 2 universities, 2 medical centers, 3 enterprises and one research foundation.

The objective of CuPiD is to develop a system to support the rehabilitation of persons with Parkinson’s diseases. The project considers three issues commonly faced by Parkinson’s disease patients:
* Freezing of gait: while walking, the person suddenly “freezes” and is unable to pursue walking. This may last a few seconds up to a minute. The person is conscious of this, but unable to resume walking. This happens more oftenwhen performing sharp turns, entering narrow areas, or when faced with cognitive load or social pressure.
* Motor control: fine motor control used for manipulative gestures is often negatively affected with the progression of Parkinson’s disease
* Balance: loss of balance is common and may lead to falls, or difficulties in appropriately shifting the body weight in sit-to-stand transitions.

The aim of the CuPiD project is to devise wearable and ambient devices to perform at-home rehabilitation for these issues. The principle consists in providing pre-emptive feedback to the user, shortly before the onset of an issue, and to rely on neural plasticity for the user’s behavior to unconsciously adapt to avoid situations leading to these issues algogether.

CuPiD makes use of sensors such as movement sensors placed on body, physiological sensors, location awareness, etc, in order to recognize the onset of an issue. Feedback includes audio and vibrotactile feedback, and virtual reality. The CuPiD system allows logging of data to monitor the user’s rehabilitation progress by care personnel.

At ETH Zürich we focus within this project on the issue of the freezing of gait, but close collaboration is foreseen between all project partners as an integrated rehabilitation system is the ultimate goal of the project.

=== Job description ===

We offer a PhD position within the framework of the 3 year long (2011-2014) European-funded CuPid project.
In this position you will be responsible for one of the project’s work package. This work package consists in devising context and indoor localization methods to deliver specific feedback to the user as part of the rehabilitation programme. Specifically the work package comprises:
* Devising a localization method for use in unknown indoor environment. This uses sensors such as those available on mobile phones or custom wearable sensor nodes, and uses techniques inspired from simultaneous localization and mapping (SLAM).
* Recognition pre-defined activities and gestures in the home environment from wearable sensors to deliver feedback to the user in specific situations.
* Implementation of the localization and context recognition methods in embedded platforms or mobile phones.

Your work environment will be multinational, both in Zürich and with project partners within Europe, with frequent travels to the partner’s location.

Within this project, your research topics will include (but are not limited to):
* Simultaneous Localization and Mapping (SLAM) with Body-Worn sensors: identification of the user’s position in unknown indoor environment on mobile phones or custom sensors (e.g. Wifi fingerprints to indentify re-occurring locations, dead-reckoning from acceleration and compass sensors to estimate path).
* Context recognition with body-worn sensors with streaming signal processing and machine learning techniques in embedded platforms
* Wireless sensor networks
* Multimodal data fusion
* Mobile phone and embedded platform implementations

Starting date: ASAP

=== Requirements ===

The candidate has a diploma, MSc, or equivalent in electrical engineering, micro-engineering, computer science or mathematics.
He has strong interests in mobile computing, machine learning/pattern recognition, signal processing, adaptive and learning systems, and in the combination of theoretical and experimental research.

Fluent spoken and written English is mandatory.

=== Contact and application ===
For further information about the CuPiD project and your contribution within it, please contact Dr. Daniel Roggen.

If you are interested and believe that you qualify, please send your application to Prof. Gerhard Tröster. Include:
* Curriculum Vitae with the names and contact details of at least 2 references
* a list of exams and grades obtained
* a cover letter explaining how your skills and research interests fit the project

For more information: