Mining Smartphone data: From smart to cognitive phones

How can smartphones be even smarter?

Smartphones are open and programmable and come with a sensing technology growing at phenomenal pace. Currently embedded sensors such as an accelerometer, camera, Gyroscope, microphone, light sensors and GPS have opened new avenues and enabled a variety of new context-based applications.

These sensing modalities are turning smartphones into cognitive phones capable of understanding our life patterns and reason about our health and well being.  While the idea of cognitive Smartphone is futuristic, early stage prototypes are taking shape in universities and research labs across the world. This seminar offers the opportunity to acquire new knowledge about the current trends towards cognitive phones and approach some of their aspects.

Course description:

  • The first part of the work should be dedicated to an exhaustive search for relevant academic papers and works related to the assigned topic.  The recommended literature should serve as example and starting point to guide the participants in this search.
  • Every participant has to deliver a 12-15 pages scientific paper on the chosen topic. The final version has to be submitted to the adviser both as hard copy and digital version by no later than one week before the presentation. Please use the ACM templates for scientific papers available in Word or LaTeX format.
  • The seminar work can be extended by a practical part, though not mandatory. This will be considered as a Bonus performance and can alleviate the expected scientific paper to 8-10 pages. Working in groups could also be arranged in this case.
  • Each participant is expected to give a presentation in front of all participants. The attendance at all presentations of the seminar is mandatory! There is no standardized Powerpoint template.
  • Each presenter is supposed to "comment" on the talk following it (except for the last presenter who will comment on the first one).  Commenting here means looking over the following topic and preparing 1-2 questions about it


Registration and topic assignment:


  1. Name, surname
  2. Student ID number
  3. Course of study and the number of the current semester
  4.  Email address.
  5.  Preferred Topic(s)
  6.  Including a practical part or not.
  • The topics will be assigned during the first introductory session on

       February the 19th at 3:30 p.m. in B6, 26 A 2.06

  • Please specify your preferred topic(s) in your registration Email. We will follow the “first-come-first-served” policy. The topics could be refined into sub-topics if there are multiple candidates interested.
  • The day and time of the presentations will be agreed on in the first meeting.
  • Even if you have not registered to the course, you can still attend the first meeting and join the seminar as long as free topics are available



Seminar Topics:

From smart to cognitive phones:

  • Trends in sensor-based Smartphone applications
  • Context sensing and context-based applications of smart phones

Example of literature:

  • Campbell, A.; Choudhury, T. "From Smart to Cognitive Phones," Pervasive Computing, IEEE , vol.11, no.3, pp.7-11, March 2012

Smartphone sensing:

  • Embedded sensors and sensing modalities and their respective applications. - Limitations (energy efficiency…) 

Example of literature:

  • A Survey of Mobile Phone Sensing, Nicholas D. Lane, Emiliano Miluzzo, Hong Lu, Daniel Peebles, Tanzeem Choudhury, Andrew T. Campbell, IEEE Communications Magazine, September, 2010

Location and positioning technologies

  • Indoor and outdoor location and positioning using a Smartphone

Example of literature: 

  • Exploiting Smartphone Sensors for Indoor Positioning: A Survey.  W Waqar, Y ChenA Vardy . 2011

Motion and Activity recognition with smart phones

  • State of the art and challenges
  • Sensor modalities and sensor features
  • Classification and recognition approaches
  • Applications

Examples of literature:

  •  Lara, O. D and Labrador M. A. “A survey on Human Activity Recognition using Wearable Sensors”. Accepted for the IEEE Communications Surveys and Tutorials. To appear.
  •  Brezmes, T., J.-L. Gorricho, and J. Cotrina, “Activity Recognition from Accelerometer Data on a Mobile Phone,” in Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living, p. 799, Springer, 2009

Human behaviour modelling and prediction

  • How can a Smartphone sense and understand our life and predict our behaviour and routines?

Example of literature:

  • Javier Gil-Quijano and Nicolas Sabouret. 2010. Prediction of Humans' Activity for Learning the Behaviors of Electrical Appliances in an Intelligent Ambient Environment. In Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02 (WI-IAT '10), Vol. 2. IEEE Computer Society, Washington, DC, USA, 283-286.
  • Xi Long, Steffen Pauws, Marten Pijl, Joyca Lacroix, Annelies Goris, Ronald M Aarts (2009)  Analysis and prediction of daily physical activity level data usingautoregressive integrated moving average models   In: 3rd Workshop on Behaviour Monitoring and Interpretation (BMI'09) Paderborn, Germany
  • Snehal Kumar Chennuru, Peng-Wen Chen, Jiang Zhu, and Ying Zhang, "Mobile Lifelogger - Recording, Indexing, and Understanding a Mobile User’s Life" in the Proceedings of the Second International Conference on Mobile Computing, Applications, and Services. MOBICASE 2010, Santa Clara, USA, Oct. 25-28, 2010

Mood and Emotion detection using a Smartphone

  • State of the art, approaches and technologies to detect emotions and mood using a Smartphone, current applications, challenges and limitations. 

Examples of literature:

  • EmotionSense: A Mobile Phones based Adaptive Platform for Experimental Social Psychology Research, Kiran K. Rachuri, Mirco Musolesi, Cecilia Mascolo, Jason Rentfrow, Chris Longworth, Andrius Aucinas, UbiComp 2010.
  •  Can Your Smartphone Infer Your Mood? Robert LiKamWa (Rice University), Yunxin Liu (Microsoft Research Asia),Nicholas Lane (Microsoft Research Asia), Lin Zhong (Rice University), PhoneSense 2011
  • Margaret E Morris, Qusai Kathawala, Mobile Therapy: Case Study Evaluations of a Cell Phone Application for Emotional Self-Awareness Journal of medical Internet research, 2010, 12, Nr 2

Social context sensing and recognition using a smartphone

  •  Detecting and modelling social context using smartphones
  •  Social context-based Applications

Examples of literature:

  • Rosi, A.; Mamei, M.; Zambonelli, F.; Dobson, S.; Stevenson, G.; Juan Ye; , "Social sensors and pervasive services: Approaches and perspectives," Pervasive Computing and Communications Workshops (PERCOM Workshops), 2011 IEEE International Conference on , vol., no., pp.525-530, 21-25 March 2011
  • Social Sensing to Model Epidemiological Behavior Change, Madan A., Cebrian M., Lazer D. and Pentland A., UbiComp 2010
  • Human Mobility, Social Ties, and Link Prediction Dashun Wang, Dino Pedreschi, Chaoming Song, Fosca Giannotti,Albert-László Barabási

Example application: Healthcare and lifestyle management

Examples of literature: 

  • Activity Sensing in the Wild: A Field Trial of UbiFit Garden, Sunny Consolvo , David W. McDonald , Tammy Toscos , Mike Chen , Jon E. Froehlich , Beverly Harrison , Predrag Klasnja , Anthony LaMarca , Louis LeGrand , Ryan Libby , Ian Smith and James A. Landay, Conference on Human Factors in Computing Systems, 2008.
  • Lane, N.; Mohammod, M.; Lin, M.; Yang, X.; Lu, H.; Ali, S.; Doryab, A.; Berke, E.; Choudhury, T. & Campbell, A. BeWell: A Smartphone Application to Monitor, Model and Promote Wellbeing IEEE, 2012

Tips and remarks:

  1. What's the problem addressed in the paper and why is it important?
  2. What's the proposed solution and why is it novel in comparison to the related work?
  3. Are the assumptions made by the authors reasonable, is the methodology OK?
  4. What are the design tradeoffs?
  5. Present one or two of the more important results
  6. What are your ideas for improving the ideas in the paper?