Study Guide

Objectives (course unit)

The student knows what is meant by data collected for data analysis and artificial intelligence. The student knows the techniques used to collect data and knows how to solve challenges related to data collection and processing. The student is able to collect and combine data from various sources and prepare the data in correct format for further exploitation. The student can create processing pipelines for data to enable automated preparation process.

Content (course unit)

- Data sources and data collection techniques
- Data combination and processing methods
- Data collection, conversions and preparation
- Pipeline creation and automation

Assessment criteria, satisfactory (1-2) (course unit)

The student knows about data sources and can use at least one data collection technique. The student can implement a simple data combination and can use an appropriate data processing method for the data. The student can implement a simple data collection, data conversion and data preparation for a data project. The student can use a given pipeline example and automation methods for the given pipeline.

Assessment criteria, good (3-4) (course unit)

The student knows data sources and can use some data collection techniques. The student can implement a data combination and can use appropriate data processing methods for data. The student can implement a data collection, data conversion and data preparation for a data project. The student can create and implement a pipeline and automation for the pipeline.

Assessment criteria, excellent (5) (course unit)

The student knows different data sources and can exploit comprehensively different data collection techniques. The student can implement complex data combinations and can use different data processing methods for data. The student can implement different data collections, data conversions and data preparations for different purposes. The student can create and implement independently pipelines and automation for the pipelines.

Location and time

See the schedule in Moodle and http://lukkarit.tamk.fi.
Part of the lecture/exercise sessions are organized at school, part remotely.

Exam schedules

The evaluation is based on possible small tests, exercises, assignments, and such activities taking place during the course. The normal course sessions can be used for tests.

Assessment methods and criteria

The assessment is based on the final overall number of points one can gather from programming assignments, tests, homework exercises, presentations, and other lecture activities that are submitted or performed in time as instructed. Grading criteria: below 50%: 0, 50%–: 1, 60%–: 2, 70%–: 3, 80%–: 4, 90%–: 5. There may be mandatory tests/assignments one has to pass in order to be able to pass the course. Also, participating in peer assessment as instructed may be required.

Assessment scale

0-5

Teaching methods

Contact/remote sessions (lectures/exercises), self-study, problem-based learning, possibly working in groups.
Teaching is supported by course activities such as homework exercises, practical works / course assignments, tests, peer assessment, and presentations.

N.B. Exercise submissions and such may be subjected to peer assessment/evaluation.

Learning materials

Internet material and lecture slides/notes. Possible book recommendations given during the course.

Student workload

See the semester schedule. The planned average student workload is approximately 135 hours, distributed evenly over the third and fourth periods.

Completion alternatives

Contact the teachers for special arrangements.

Practical training and working life cooperation

Guest lectures are possible but not guaranteed.