Theses

Open Topics

Integrated accelerometry-based Fall Detection System

Background: Falls have an increasing social and economic impact, specially in the developed countries, as life expectancy of our elderly rises dramatically. Fall-related injuries increases morbidity, mortality and premature use of health care services reducing also the time the elderly can live autonomously at their own homes. Fall detection systems may notify emergency responders when no one apart from the injured is present. However, their real-world application is limited by a number of factors such as high false positive rates, low-compliance, poor usability and short battery lifetime. In order to improve these aspects we developed a fall detection algorithm with a low false alarm rate to be used in a miniaturized 3D accelerometer integrated in a belt buckle – the actibelt® – developed at the Sylvia Lawry Center for Multiple Sclerosis Research . The following thesis consist of implementing the fall detection algorithm in the microcontroller of the accelerometer and programming an Android-based application in order to link the actibelt® to a smart phone for fall detection management and notification

Master thesis 1: Customized Android Interface for a fall detection system based on a smart phone and a wireless acceleration sensor – the actibelt®BLU

Tasks: * Use case/Scenario description. Analyze the possible scenarios in which the fall detector can be used and the interaction with the user in order to define the requirements of the system. * Customize Android ROM (e.g., customize the status bar, restrict specific user applications) * User management (authentification, authorization, privacy management) * User-centered design and Android programming of interface adapted to disabled and elderly people. (It can include voice user interface) * Definition of the communication protocol * Fall alarm management (alarm prioritisation, alarm disabling, audible warning, alarm sending) * Emulator programming

Prerequisites: good knowledge of programming (preferably Android)

Master thesis / Bachelor thesis 2: Real-time implementation of an accelerometry-based fall detection algorithm on the MSP430 microcontroller of the actibelt®BLU

Tasks: * Rewrite/ refine the fall detection algorithm written in R-code into C code * Redesign plug-in interface for the communication protocol. Establish connection between actibelt-BLU and mobile phone (authentification, encryption) * Fall alarm management (according to the model which will be described in Master thesis 1)

Prerequisites: Good knowledge of C

References: [1] M. Daumer, K. Thaler, E. Kruis, W. Feneberg, G. Staude, and M. Scholz. Steps towards a miniaturized, robust and autonomous measurement device for the long-term monitoring of the activity of patients - ActiBelt. Biomedizinische Technik/Biomedical Engineering. 2007; 52: 149-155. [2] A new method to estimate the real upper limit of the false alarm rate in a 3D accelerometry-based fall detector for the elderly. C. Soaz, C. Lederer, M. Daumer. In the Proceedings of the 34th IEEE Annual International Conference of the Engineering in Medicine and Biology Society (EMBS). San Diego, California, USA. August 2012. DOI: 10.1109/EMBC.2012.6345915

Supervisors: Cristina Soaz, M.Eng., Lehrstuhl für Datenverarbeitung (Prof. Diepold) E-Mail: cristina.soaz@tum.de , Tel.: +49 (0)89 289 23608

M.Sc. Munish Jassi, Chair of Electronic Design Automation (Prof. Schlichtmann) E-Mail: munish.jassi@mytum.de, Tel.: +49 (89) 289 – 23651

External supervisor : Dr. Martin Daumer Scientific Director of Sylvia Lawry Centre – The Human Motion Institute E-Mail: daumer@slcmsr.org,Tel.: +49 89 2060 269 50

Dr.-Ing. Dmitry Zhelondz Universität der Bundeswehr München

Technology provider: Trium Analysis Online GmbH

Advisor: Prof. Dr.-Ing. Klaus Diepold Lehrstuhl für Datenverarbeitung

Finished Theses

  • Alexander Schaermann, PhD-Thesis with TUM Munich, Dept. for Electrical Engineering and Information Technology, Prof. Marc Zornow: "Systematische Bedatung und Bewertung umfelderfassender Sensormodelle", 2020

  • Christoph Horlebein, Master-Thesis with Rehabilitation Engineering Lab (ETHZ), Prof. Roger Gassert: "Design of an Experimental Setup and Evaluation of Neural Coupling Reflex Detection", 2019

  • Ryan Ramsey Hosn, Bachelor-Thesis with TUM Munich, Dept. for Electrical Engineering and Information Technology, Prof. Klaus Diepold: "Jump Asessment with Mobile Sensors", 2019

  • Raphael Altmik, Master-Thesis with TUM Munich, Dept. for Electrical Engineering and Information Technology, Prof. Klaus Diepold: "Implementation of the web-based platform 'IndiBelt'", 2018

  • B. Eng. Karl Müller, Master-Thesis with TUM Munich, Dept. for Electrical Engineering and Information Technology, Prof. Klaus Diepold: "Verifizierung eines mobilen Akzelerometers hinsichtlich seiner Messgenauigkeit und Zeitgenauigkeit", 2017

  • Christopher Weber, Master-Thesis with Chair of Data Processing, TUM Electrical and Computer Engineering, Porf. Klaus Diepold: "Die Dezelerationsfläche als prognostischer Parameter des fetalen Outcomes", 2016

  • M. Eng. Cristina Soaz PhD-Thesis with TUM Munich, Dept. for Electrical Engineering and Information Technology, Prof. Klaus Diepold, "Integrated Accelerometetry-Based System for functional Mobility Asessment and Fall Detection", 2015

  • Nicole Ellenrieder, Bachelor-Thesis with Prof. Manfred Wilhelm, Hochschule Ulm, Fakultät Informatik- Medizinische Dokumentation und Informatik: "Statistische Analyse von Laufdaten und Untersuchung möglicher Ansätze für einen Parameter zur Bestimmung der Laufqualität", 2015

  • Florentin Förschler, Bachelor-Thesis with Prof. Matthias Edler-Golla, Hochschule für angewandte Wissenschaften München: "Angewandte User Experience Optimierung am Beispiel 'actibelt' - Bewegungsmessung in klinischen Studien", 2015

  • Paul Subkowski, Bachelor-Thesis with Prof. Klaus Diepold, TU Munich, Institute for Electrical Engineering and Information Technology: "Entwicklung eines Schritterkennungsalgorithmus", 2014

  • Julia Katharina Widl, Dissertation zur Erlangung des Grades eines Doktors der Medizin:"Die Verwendung des actibelt® zur Untersuchung von morbogenen und pharmakogenen Einflüssen auf die körperliche Aktivität bei Patienten mit depressiven Störungen", 2012

  • Julia Christina Endres, Master Thesis with Donau-Universität Krems: "Untersuchung zu funktionellen Parametern, Aktivität und Teilhabe in der Mobilität bei Schlaganfallpatienten", 2012

  • Nele Götze, Dissertation zur Erlangung des Grades eines Doktors der Medizin: "Untersuchung zur Validierung der Messung körperlicher Aktivität von Patienten mit Multipler Sklerose mittels Akzelerometrie/actibelt©", 2012

  • Matthias Fasching, Master Thesis with IMC University of Applied Sciences Krems, Austria: "Exercise therapy in multiple sclerosis: state of research and recommendations for future trials", 2011

  • Michaela Schimpl, Bachelor/Master program in Science in Engineering, Biomedical Informatics; with University of Applied Sciences, Hegenberg, Austria: "Automatic parameter extraction from 3D acceleromic data", 2010

  • Alexandros Kokkalis, Master Thesis with Technical University of Munich: "Spatio-temporal parameter assessment of the human gait using simple biomechanical models", 2010

  • Fabian Franzelin: Bachelor-Thesis with Prof. Nassir Navab, TU Munich "IT-Tools zur On- und Offline Analyse von Einzelschritten, die mit dem hochauflösenden 3D-Akzelerometer actibelt® aufgezeichnet werden", 2009

  • Christoph Türmer, Bachelor thesis, with TU Munich, Institute for Realtime Computersystems, Prof. Färber/Chakraborty: "Ganganalyse fokussiert auf Stolpern mit Hilfe des 3D-Beschleunigungsmesssystems actibelt", 2009

  • Dipl. Stat. Alexandra Thiele with Prof. Dr. Ludwig Fahrmeir, Faculty for Mathematics, Informatics and Statistics, Department of Statistics, LMU Munich, 2009

  • Dipl. Stat. Martin Slawski. "Regularization and sparsity in discrete structures". Diploma Thesis, Faculty for Mathematics, Informatics and Statistics, Department of Statistics, LMU Munich, 2008

  • Dipl. Tech. Math. Gerrit Kreuzer: "Modellierung einer realistischen Raum-Zeit-Trajektorie aufbauend auf elementaren Bewegungseinheiten", Diploma Thesis with Prof. Spohn, Institute for Mathematics, TU Munich, 2008

  • Dipl. Math Celiné Schöne: "Hidden-Markov-Modell und Autokorrelationsfunktion zur Bewegungs- und Gangklassifikation dreidimensionalen Beschleunigungsdaten". Diploma Thesis with Prof. Spohn, Institute for Mathematics, TU Munich, 2008

  • Dipl. Stat. Birgit Schrödle: "Multi-state models for interval censored event history data: An analysis of multiple sclerosis progression", with Prof. Dr. Ludwig Fahrmeir, Faculty for Mathematics, Informatics and Statistics, Department of Statistics, LMU Munich, 2008

  • Dipl. Stat. Christine Porzelius: "Microarray-based prediction with emphasis on clinical parameters". Prof. Tutz, Department of Statistics, LMU and Prof. Strimmer, Institute for Medical Informatics, Statistics and Epidemiology, University of Leipzig. In Cooperation with Prof. Kappos, University of Basel, 2007

  • Dipl. Stat. Elisabeth Gnatowski: "Stability of methods for the analysis of differential gene expression". Diploma thesis with with Prof. Fahrmeir, Department of Statistics, LMU Munich and Prof. Strimmer, Institute for Medical Informatics, Statistics and Epidemiology, University of Leipzig. In Cooperation with Welcome Trust Sanger Institute, University of Cambridge / National Blood Service and International School of Technical Medicine and Clinical Bioinformatics / Porticus foundation., 2007

  • Dipl. Sport Science Lorenz Lachmann: "Machbarkeit für Aktivitätsstudie bei MS Patienten". Dr. Tusker, Institute for Biomechanics, TU Munich, 2007

  • Dipl. Inf. Christof Niedermayr: "Detection and removal of facial features in volume MRI scans" diploma thesis with Prof. Navab, TU Munich, in cooperation with Rinnecker proton therapy centre, 2007

  • Dipl. Math. Franziska Bayer: "Mathematische Aspekte der nichtlinearen intensitaetsbasierten Bildregistrierung", diploma thesis with Prof. Hoffmann, Institute for Mathematics, TU Munich and Prof. Wolinsky, Houston, 2007

  • B.Sc. Nadja Harner: "Modellierung von Verweildauern für Patienten mit Multipler Sklerose (MS)"; Master Thesis with Prof. Fahrmeir, LMU Munich, 2007

  • Dipl. Phys. Thomas Goßner: "Design of a motion model and validation using different tracking systems for continuous MS patient monitoring", TU Physics, with Prof. Navab, Computing Faculty and Computer Aided Medical Procedures, TU Munich, 2007

  • Dipl. Math. Katrin Noack, "Klassifikation von Dezelerationen" diploma thesis with Prof. Spohn, Institute for Mathematics, TU Munich und University of Fortaleza, Brasilien, 2007

  • Dipl. Math. Oec. Martina Güntner: "Predicting the natural history of multiple scoerosis in patients seen from disease onset"; diploma thesis with Prof. Unwin, Institute for Mathematics, University of Augsburg, 2007

  • Dipl. Math. Tech. Kathrin Thaler: "Acquisition, preprocessing and analysis of high-resolving, 3-dimensional accelerator-data for the determination of the activities of MS-patients", with Prof. Spohn, Centre for Mathematics, Applied Probability Theory / Statistical Physics, TU Munich, 2006

  • Dipl.-Stat. Moritz Heinz: "Validation Processes of Results in Biomedical Research Centres" (german), with Prof. Ickstadt, Dept. of Statistics, University of Dortmund, 2005

  • Dr. med. F. Seiffert: "An internet based system to assess the inter- and intraobserver variability of biosignals", with Prof. Schneider and Prof. Neiß, Obstetrics & Gynecology/Medical Statistics, Technical University of Munich, 2005

  • Master Stat. Nadja Harner, Bachelor thesis: "Validation and Optimization of the FIGO Criteria for CTG Analysis", with Prof. Dr. Ludwig Fahrmeir, Faculty for Mathematics, Informatics and Statistics, Department of Statistics, LMU Munich, 2004

  • Dipl.-Stat. Anneke Neuhaus: "Modelling time to progression", with Prof. Küchenhoff, Dept. of Statistics, LMU Munich, 2003