Weekly outline

  • Mobile Sensing

    The course investigates the use of sensors, embedded in mobile computation devices (e.g. smartphones, smartwatches, etc.), for understanding a user’s context, modelling a user’s behaviour, and devising novel applications based on the acquired information. The course covers the historical, theoretical, and research ground in order to help students understand modern mobile sensing approaches. Further, the course equips students with tools for a practical realisation of mobile sensing. The framework of choice is Android, the most popular mobile operating system. Within Android, the course investigates methods for one-off and periodic sensing of different sensors, data pre-processing, and on-device machine learning. Equipped with the theory, best practices, and the tools needed for application development, the course empowers students to develop their own state-of-the-art mobile sensing solutions. The solutions will be developed in small (two people) teams, will be continuously guided by the instructors, progress will be checked via two in-class presentations, and the final report, in the form of a workshop paper, that will be written for each of the projects. Lectures are accompanied by labs, where students will implement theoretical concepts in practice. Certain labs will be based on the analysis of publicly available mobile sensing research datasets, some will cover Android programming concepts, while some labs will be focused on specific issues that emerge during the students’ project development.

  • 30 September - 6 October

    Introduction, Course goals and organisation, Evolution of mobile sensing, Types of sensing devices, Mobile sensing app scales, Example apps, Mobile sensing pipeline.
    No labs this week.
  • 7 October - 13 October

    Obtaining sensor data. Sampling fundamentals. Signal filtering.
    • Lab 1 - Sensing with AWARE File Uploaded 10/10/19, 16:11
    • activity main File Uploaded 10/10/19, 10:49
    • strings File Uploaded 10/10/19, 16:36
  • 14 October - 20 October

    Machine learning pipeline: data collection, inspection, feature engineering, model construction, and model evaluation. Machine learning approaches on Android.

  • 21 October - 27 October

    Advanced learning from sensor data. Deep learning fundamentals. Deep neural networks on mobile devices.

    NOTE: Labs on Tuesday (4:15pm), lectures on Wednesday (4:15pm), student paper presentation on Thursday (4:15pm)

  • 28 October - 3 November

    Health and wellbeing. Depression monitoring using mobile sensing. Digital behaviour change interventions.

    Note: Labs on Monday 5:15pm, Lectures on Tuesday 4:15pm, Student paper presentations on Wednesday 4:15pm

  • 4 November - 10 November

    Mandatory project progress check. Please attend your assigned meeting slot with Martin.

    No regular labs and lectures this week!

    • 11 November - 17 November

      Midsemester presentations! Each team will give a five minute presentation of their project, followed by a ten minute slot for questions. Please refer to the guidelines for the midterm presentation in order to prepare for your talk.

      Tuesday 4:15pm - presentations (we will probably finish around 6:30pm)

      Wednesday 4:15pm - mandatory feedback meeting (please attend your assigned slot)

    • 18 November - 24 November

      Physiological signal sampling and processing.

    • 25 November - 1 December

      Location sensing: location determination and prediction.

    • 2 December - 8 December

      Lectures: Location prediction
      Labs: continuation of the geofencing lab (if you have finished this lab, please come to the session anyways and get potential questions about your project answered).
      Paper presentation: wireless sensing

    • This week

      9 December - 15 December

      Not available