Data analysis and machine learning

Introduction - IoT architecture (e.g. reference models) - Requirements for IOT systems - IOT data transmission protocols - Use of IOT in an industrial context (examples) - Basics of sensor technology - Basics of embedded systems Implementation - Procedure for implementing IOT - Prototypical implementation of IOT - Selection of sensors - Data collection, visualization and evaluation - Challenges in implementation

- Overview of agile process methods - Roles in the agile process - Flow of an agile project (Sprins, Dailies, Demos, Retros) - Coaching of an agile project (e.g. question techniques) - Experiences with agile projects from software development - Challenges in developing smart products - Methods of product development (e.g. FMEA, TRIZ) - Advantages of hybrid process methods - Role of management in the agile process

- Basic terms: Business process, workflow, BPMS, WFMS, RPA, etc. - Selection criteria for workflow engines for process automation - Architecture and integration of workflows for process automation - Overview of interprocess communication - Transactional properties of processes, simulation and code generation - Basics of Microsoft Dynamics 365: Modules and navigation, basic entities and standard workflows - Organizational and technical implementation with configuration and declarative programming

The following content is discussed in the course: - Basics of descriptive statistics - Measurement system analysis - Sample determination - Statistical process monitoring - Process monitoring charts - Process capability analysis - Components of Variants Analysis (COV) - Repetition Basics of inferential statistics - Failure cause determination via hypothesis testing (T-test, Chi-Sq, ANOVA) - Multiple regression analysis

Students are given an overview of common business platforms and cloud computing. In addition, the advantages and disadvantages of the respective platforms are discussed. Students are therefore able to select suitable platforms for a given problem. Students gain practical experience with selected platforms using case studies. In addition, methods for defining interfaces are discussed with the students.

The lecture teaches basic concepts from the field of human-computer interaction (usability, user experience, user interface design) and information visualization. This includes the following focal points: User interface architectures; design criteria, guidelines and standards for the creation and modelling of user interfaces of interactive systems; ap-proaches and methods (quantitative and qualitative) for the evaluation of user interfaces of interactive systems; web style guides and evaluation criteria for websites (e.g. with regard to accessibility); basics of information presentation and data visualization; interactive information visualization; the theoretical lecture contents are prepared in the exercise using practical examples and implemented in a small project (usability evaluation) in a team.

The following content is discussed in the course: - Presentation of different user-oriented analysis platforms (e.g. KNIME, RapidMiner, Grafana) - Presentation of different cloud solutions for data analysis (e.g. Google Cloud, AWS, Azure) - Application of the platforms presented using the example of analysis data sets - Discussion of the different approaches

The following content is discussed in the course: - Reasoning approaches (Roal trees, rule-based expert systems) - Search approaches (depth-first, hill climbing, beam, optimal, branch and bound, A*, games, minimax, and alpha-beta) - Constraint approaches (search, domain reduction, visual object recognition) - Learning approaches (neural nets, back propagation, genetic algorithms, sparse spaces, phonology, near misses, felicity conditions, support vector machines, boosting) - Representation approaches (classes, trajectories, transitions) - Possible applications of artificial intelligence in different contexts - Weak versus strong, artificial intelligence This course is offered together with the Web Communication and Information Systems Master program as an elective course.

Students are introduced to the basic features of Big Data. Special attention is paid to the handling of this data and the knowledge acquired is consolidated with examples. Suitable frameworks for solving Big Data problems are presented and worked on in interactive workshops with case studies. Examples of this are as follows: - Apache Hadoop - Apache Spark - Apache Flink - Apache Storm - Apache Samza - Apache Kafka These frameworks will be explained and used with case studies. For this purpose, the centrally-provided Data Labs can be accessed.

The following content is discussed in the course: - CRM on the strategic level - CRM in process management - CRM on the operative level (CRM software systems) - Operative CRM - Analytical CRM - Communicative CRM This course is offered as an elective course together with the Master's Course in Web Communication and Information Systems.

The following exemplary contents are discussed in the course: - Biology (e.g. genome research, medical diagnostic procedures, etc.) - Physics (e.g. object recognition through image data processing, etc.) - Chemistry (e.g. processing of data-intensive experiments, etc.) - Data-driven maintenance (e.g. predictive maintenance, Digital Twin) - Data-optimized product design (e.g. design of product properties by KNN) - Evaluation of sensor data (e.g. obstacle detection, obstacle avoidance, prediction, etc.) - Cloud-based IoT systems (data storage and collection) - sensor evaluation via Raspberry Pi, Arduino, radio systems

The following content is discussed in the course: - Evaluation tools with visual orientation, e.g. Bl tools such as MS PowerBl, Tableau, QlikView - Display libraries, e.g. matplotlib.pyplot, gglot2 - Rules of visual communication, e.g. Hichert SUCCESSSS