MENUMENU

Data Utilization (DLMBBD01)

Course No.:

Data Utilization

Course Title:

DLMBBD01

Hours Total:

150 h

Credit Points:

5 ECTS

Course Type: Wahlpflicht

Course Availability: WS, SS

Course Duration: Minimum 1 Semester

Admission Requirements:

None

Course Coordinator / Instructor:

See current list of tutors in the Learning Management System

References to Other Modules:

Please see module description

Course Description:

The course Data Utilization introduces case-based applications that take advantage of regularities and patterns found within continuously generated texts, images, or sensor data. The cases solve issues of pattern recognition, natural language processing, image recognition, detection and sensing, problem solving, and decision support. The cases are related to the application fields of cybersecurity, linguistics, augmented reality, intelligent transportation, problem solving, and decision support.

Course Objectives and Outcome:

Upon successful completion of the course, students are able

  • to understand how identity, similarity and diversity of data can be utilized in problem-solving approaches.
  • to differentiate between complicated and complex systems of investigation.
  • to identify the variability of a problem under investigation.
  • to differentiate between invariant and dynamic features of an investigated system.
  • to synthesize the gained insights to propose a reliable data analytics solution.

Teaching Methods:

The learning materials include printed and online course books, vodcasts, online knowledge tests, podcasts, online tutorials, and case studies. This range of learning materials is offered to students so they can study at a time, place, and pace that best suits their circumstances and individual learning style.

Course Content:

  1. Introduction
    1. The Meaning of Identity, Similarity, and Diversity
    2. Data Patterns and Ontologies
  2. Pattern Recognition
    1. Analysis of User Interaction, Attitude, and Behavior
    2. Predictive Analytics
    3. Preventing the Unknown: User Behavior Analytics in Cybersecurity
  3. Natural Language Processing
    1. Concepts of Natural Language
    2. Speech Recognition and Acoustic Modelling
    3. Discerning the Meaning: Linguistics and Social Media
  4. Image Recognition
    1. Basics of Image Representation
    2. Integral Transforms and Compression
    3. Exploiting the Visual: Image Recognition for Augmented Reality
  5. Detection and Sensing
    1. Sensor Construction and Techniques
    2. Intelligent Agents and Surveillance
    3. Managing the Complex: Sensor Networks in Intelligent Transportation Systems
  6. Problem Solving
    1. Knowledge Sharing and the Cloud
    2. Rule-Based Systems
    3. Learning from Nature: Expert Systems in Business
  7. Decision Support
    1. Invariants, Determinants, and Alternatives in Decision-Making
    2. Correlation and Causality in Strategic Decision-Making
    3. Approaching the Crossroads: Dashboards and Visualization

Literature:

Recommended Literature:

  • Strong, C. (2015). Humanizing Big Data: Marketing at the Meeting of Data, Social Science and Consumer Insight. London: Kogan Page.
  • Wheeler, S.R. (2016). Architecting Experience: A Marketing Science and Digital Analytics Handbook. Singapore: World Scientific Publishing.
  • Farzindar, A., Inkpen, D., Hirst, G. (2017). Natural Language Processing for Social Media. 2nd ed. San Rafael, CA: Morgan & Claypool Publishers.
  • Bajcsy, P., Chalfoun, J., Simon, M. (2017). Web Microanalysis of Big Image Data. Berlin: Springer.
  • Hsu, H., Chang, C., & Hsu, C. (Eds) (2017). Big Data Analytics for Sensor-Network Collected Intelligence. Cambridge, MA: Academic Press.
  • Delen, D. (2015). Real-World Data Mining: Applied Business Analytics and Decision Making. New York: Person.

An actual list with course-specific mandatory reading as well as references to further literature is available in the Learning Management System.

Prerequisites to Qualify for Assessment:

  • Depending on the course: Completion of online knowledge tests (approx. 15 minutes per unit, pass / not pass)
  • Course evaluation

Assessment:

  • Exam, 90 min.

Student Workload (in hours): 150

Self-study: 90 h
Self-testing: 30 h
Tutorials: 30 h