EPN-V2

ACIT4530 Data Mining at Scale: Algorithms and Systems Course description

Course name in Norwegian
Data Mining at Scale: Algorithms and Systems
Study programme
Master's Programme in Applied Computer and Information Technology
Weight
10.0 ECTS
Year of study
2022/2023
Curriculum
SPRING 2023
Schedule
Course history

Introduction

The digitalization of medical and health care systems depends on medical devices with perception (i.e., sensing) and control (i.e., actuation) capabilities. To do their work, sensors and actuators require a transduction mechanism, such as that often provided by a mechanical element in the physical sensors. Generally stated, the transduction mechanism converts nonelectrical parameters to electrical ones in a calibrated way.

This course covers the definitions and structure of the sensors and actuators with a focus on medical and health care applications. In addition, the course introduces analytical methods and tools for multivariate calibration and evaluation of sensors and actuators. 

Recommended preliminary courses

  • One written grop project report (2000-3000 words) in group of 1-2 students. This part of the examination counts 35 % of the final grade.
  • One written group project report (4000-5000 words) in group of minimum 4 students. This part of the examination counts 35 % of the final grade.
  • Individual oral examination (20 minutes for each candidate). The oral examination counts 30% of the final grade.

All exams must be passed in order to pass the course.

The oral examination cannot be appealed.

;

New/postponed exam

In case of failed exam or legal absence, the student may apply for a new or postponed exam. New or postponed exams are offered within a reasonable time span following the regular exam. The student is responsible for applying for a new/postponed exam within the time limits set by OsloMet. The Regulations for new or postponed examinations are available in Regulations relating to studies and examinations at OsloMet.

Required preliminary courses

No formal requirements over and above the admission requirements. 

Learning outcomes

The student should have the following outcomes upon completing the course: 

Knowledge 

Upon successful completion of the course, the student should have

  • specialized knowledge to differentiate technologies used for sensors and actuators in medical and health care applications. 
  • an advanced technical understanding of the transduction mechanisms and sensory schemes. 
  • a good understanding about building a sensor and actuator in specific cases involving medical and health care applications. 

Skills

Upon successful completion of the course, the student can:

  • categorize sensors and actuators based on their applications. 
  • calibrate optical and electrical spectra using multivariate calibration. 
  • analyze the performance of sensors and actuators. 

 

General competence

Upon successful completion of the course, the student should:

  • understand the role of sensors and actuators in medical devices. 
  • can explain and discus challenges related to sensors and actuators that are applied medical and health care applications to experts and non-experts alike. 
  • can design a system that is based on sensors and actuators with a specific transduction mechanism.

Content

  • Data mining systems
  • Data mining and machine learning algorithms
  • Deep learning and neural networks for datamining
  • Data stream processing methods, such as, but not limited to, anomaly detection, clustering, association rule learning
  • Distributed reinforcement learning for data mining.
  • Data visualization

Teaching and learning methods

Lectures/tutorials and supervision sessions. The students work in a group of two to four in a human-computer interaction project.

Course requirements

The following coursework must be approved before the student can attend the exam:

  • Semester exercise in a group of 3-4 students, resulting in a report between 7500 and 15000 words. The total working load will be approx. 60 hours per student. 

Assessment

This course covers the state of the art of technology and methods in the research within human-computer interaction and available computer systems.

Permitted exam materials and equipment

No formal requirements over and above the admission requirements.

Grading scale

A student who has completed this course should have the following learning outcomes defined in terms of knowledge, skills and general competence:

Knowledge

On successful completion of this course the student

  • has advanced knowledge of multimodal user interfaces
  • has advanced knowledge of input and output technologies
  • can analyse problems and issues in interactions related to context, such as accessibility in public spaces, mobility problems, and the user's affective state
  • can use knowledge of interaction technology to address new problems in universal design of ICT

Skills

On successful completion of this course the student

  • can independently use appropriate methods of user centred interaction design and evaluation; both heuristic and automatic, in an independent manner
  • can analyse and critically deal with the results from relevant research literature, apply these to structure and formulate scientific arguments, and assess the suitability of published results on new problems and issues
  • can carry out independent, limited research or development projects under supervision and in accordance with applicable ethical standards
  • can present scientific work orally
  • can debate and conduct scientific discussions

General competence

On successful completion of this course the student

  • can apply knowledge and skills in interaction technology on new problems and issues for carrying out advanced facilitation tasks and projects
  • can communicate scientific problems, analysis and conclusions in the field to both specialists and the general public
  • can contribute to original thinking and innovation processes

Examiners

Professor Peyman Mirtaheri

Course contact person

  • Two individual oral presentations of research articles (45 min per presentation including questions).
  • Being opponent against two student presentations.