IND320 Data to Decision

Credits (ECTS):10

Course responsible:Kristian Hovde Liland

Campus / Online:Taught campus Ås

Teaching language:Engelsk

Course frequency:Annually

Nominal workload:Expected workload for 10 credits is 250 hours.

Teaching and exam period:This course has teaching/evaluation in the Autumn parallel.

About this course

The main emphasis will be on end-to-end data handling, analysis, and presentation for monitoring and decision support. Through various use cases, data will be accessed from databases, repositories, and/or sensors, filtered/cleaned, combined/analyzed, and displayed for the end user. Dashboards with plots and key performance indicators will be the main output.

The course supports the UN's sustainability goals 4 (good education - industrial relevance for students), 9 (industry, innovation and infrastructure - better utilization of industrial data, internal and external infrastructure), 10 (less inequality - use of open platforms, programming languages and tools) and 12 (responsible consumption and production - streamlining and improving production processes).

Learning outcome

Knowledge

Theoretical aspects such as database queries, APIs, algorithms, etc. will be highlighted where there is a need, while practical problems are the main topic.

Skills

The student will learn to plan, implement and test a system for data capture, data processing and making it available to the end user. She will learn about current data types, data quality, as well as adopting tools needed to provide decision support and improved automation.

General competence

By using mandatory tasks that build on each other and involve students at intersections through peer review, students will learn about short-term and long-term goals, the use of constructive criticism and continuous improvement of processes and products.

  • Learning activities

    The lectures will be a mixture of theory and practical activities. Discussions of, for example, the consequences of design and implementation choices, goals, and goal achievement can be included in groups and plenary sessions.

    A longitudinal semester project with implementation and documentation is performed as a module-based portfolio (see exam). Milestones related to the topics in the lectures are peer-reviewed along the way, while final approval is made by the teacher.

  • Teaching support
    The teacher will be available at the lectures, and a teaching assistant or teacher will be available at practice lessons. Padlet.com or a similar tool will be used for questions and answers between lectures so that teachers, teaching assistants and fellow students can communicate openly. Canvas and GitHub will be used for sharing plans, lecture material and code.
  • Prerequisites
    Basic programming skills in Python (similar to NMBUs INF120).
  • Recommended prerequisites

    Advanced programming, including version control and object orientation (similar to NMBUs INF201).

    Introductory machine learning (similar to NMBUs DAT200 or MLA210).

    Introductory databases (similar to NMBUs INF230).

  • Assessment method
    Portfolio: Peer-review of modules in semester project. Modules are handed in individually within given deadlines, and the whole portfolio is assessed as passed/failed. The modules build on each other and contain implementation, documentation and theory.

  • Examiner scheme
    The censor will be involved in the development of criteria for quality and assessment structure.
  • Notes
    The number of students who will take the course is very difficult to estimate. Some of the learning activities will have to be adapted to the number of students participating.
  • Teaching hours

    Lectures: approx. 52 hours.

    Exercises: approx. 26 hours.

    Compulsory activity and self-study: approx. 172 hours.

  • Reduction of credits
    The course overlaps 100% with VU-IND320.