Sensordata in Dierwetenschappen

Sensor data is increasingly used by commercial livestock farmers, feeding companies, breeding companies, and the scientific community. In this course, various sensors in animal production systems that measure animal behaviour will be discussed, including their use in science and for commercial purposes, their possibilities and constraints, and future potential. Emphasis will be put on accelerometer data, feeding station data, and location (tracking) data in livestock farming. This course prepares students in animal sciences for sensor data analysis and interpretation in their future career, by 1) providing knowledge about sensors, their data and use, 2) handling data quality and processing data, 3) analysing animal behaviour over time, and 4) developing basic programming skills in R.

• Discuss main sensors used in animal production systems, and their possibilities and constraints

• Explain how and what kind of data is generated by feeding stations, location sensors and accelerometers in livestock systems

• Apply techniques to visualize and analyze basic features of sensor data

• Engineer new features and create new hypotheses based on sensor data

• Interpret processed results in the context of animal sciences

• Report on data processing, analysis and results

• Assignment oral presentation (20%) A minimum grade of 1.0 is required for the group presentation
• Assignment report (40%)
• Written test with open and closed questions (40%) The (individual and closed-book) exam is half way the course (end of block 1) and about lectures, practicals and provided articles in the first four weeks of the course
• Performance (0%) Active participation in the first part of the course (i.e. attend at least 50% of the practicals and take the exam) and the second part of the course (i.e. contribute to group work) is required. If you don’t actively participate in part one of the course, you cannot participate in the group work in part two. If you cannot participate in the group work, you cannot receive a grade for the group presentation and report.

This course assumes basic working knowledge on mathematics and statistics, and familiarity with computer programming.

• Scientific papers.