Air quality recommender system for commuting


Jump to: navigation, search

Air quality recommender system for commuting

by Eivind Engesæter
Supervisor(s) Josef Noll, Nuria Castell Balaguer
Due date 2015/08/01
Status Finished
Problem description: The Norwegian Institute for Air Pollution monitoring has initiated the project CITI-SENSE-MOB on Mobile Air Pollution measurements. Mobile sensor platforms are going to be installed on busses, cars and bicycles to achieve a wider distribution of measurements, as compared to the limited number of fixed stations.

The goal of this thesis is to develop a recommender system for air quality while travelling. Travelling to work might happen by foot, bicycle, public transportation or other means. The thesis will address the variability of measured air quality indicators both in time and space, e.g. indicating the variation from major roads to smaller roads or from cycling along major roads towards cycling through green cycling tracks. The mobile data will be combined with sensor data from other sources, e.g. the meteorological office or from the fixed air quality stations in order to establish the model of variability. Predictions of air quality, taking into account correlation of certain measurements and predictions, will then provide an estimated value for air pollution along the way.

Methods and Tools: The tools and methods in this thesis are based on
  • A set of scenario, describing the challenges
  • A list of requirements being extracted from the scenarios
  • A description and evaluation of technologies and tools being candidates for solutions
  • A functional architecture/description of the envisaged system
  • An implementation of the core concepts
  • A demonstration of the solution
  • An evaluation of the solution, including a critical review of the descisions taken earlier
  • Conclusions
  • References
Time schedule was followed
Pre-Knowledge This thesis includes a reasonable amount of programming. The envisaged thesis is based on radio communications, thus expects the user to have followed at least two radio-related courses
Approved Approved by May Helen Varøy
Keywords Air pollution, Air quality, Sensor Networks, Linked open data

this page was created by Special:FormEdit/Thesis, and can be edited by Special:FormEdit/Thesis/Air quality recommender system for commuting

The thesis is finished, and can be downloaded here (17.8MB pdf)

Meeting notes


  • focus on variability and integration with other sources
  • potential evaluation of prediction versus real measurements

First steps

  • literature review on models predicting variability of air pollution data
  • correlation between air quality data and meteorological data - note: contact with Nuria
  • reference data for air pollution (in cities) - note: contact with Nuria
  • data sources and formats, e.g. GEOS (note: Sintef work with Dumitru Roman)

Second step

  • correlation between camera (Go Pro) and sensing data (capture special air pollution events)

This page provides hints on what to include in your master thesis.


Suggested TOC from Nuria: File:TOC Air quality recommener system.docx

Title page, abstract, ...

1. Introduction, containing: short intro into the area, what is happening
1.1 Motivation, containing: what triggered me to write about what I'm writing about
1.2 Methods, containing: which methods are you using, how do you apply them
2. Scenario, optional chapter for explaining some use cases
2.1 user scenario, (bad name, needs something bedre)
2.2 Requirements/Technological challenges
3. State-of-the art/Analysis of technology, structure your content after hardware/SW (or other domains). Describe which technologies might be used to answer the challenges, and how they can answer the challenges
3.1 technology A
3.2 technology B
4. Implementation
4.1 Architecture, functionality
5. Evaluation
6. Conclusions


Red line

Your thesis should have a "red line", which is visible throughout the whole thesis. This means you should mention in the beginning of each chapter how the chapter contributes to the "goals of the thesis".

Use of scientific methods

A thesis follows a standard method:

  • describe the problem (problemstilling)
  • extract the challenges. These challenges should be measurable, e.g. method is too slow to be useful to voice handover.
  • Analyse technology with respect to challenges. Don't write & repeat "everything" from a certain technology, concentrate on those parts (e.g. protocols) which are of importance for your problem


  • Wikipedia is good to use to get an overview on what is happening. But there is not scientific verification of Wikipedia, thus you should use wikipedia only in the introduction of a chapter (if you use text from wikipedia). Use scientific literature for your thesis.
  • Scientific library is "at your hand", you can get there directly from UiO: [[How to get access to IEEE, Springer and other scientific literature -> Unik/UiOLibrary]]
  • I suggest that references to web pages, e.g. OASIS, W3C standards, are given in a footnote. Only if you find white papers or other .pdf documents on a web page then you refer to them in the reference section.

Evaluation of own work

Perform an evaluation of your own work. Revisit the challenges and discuss in how you fulfilled them. Provide alternative solution and discuss what should be done (or what could have been done).