Staff
Dr.-Ing. Karsten Wendt
Contact information
| Email: |
 |
| Phone: |
(+49) 351 463 38608 |
| Fax: |
(+49) 351 463 38459 |
| Address: |
Zi. APB 2080, 2. Stock, Westflügel
Nöthnitzer Str. 46
01187 Dresden |
| Consultation: |
Mail me! |
My main research topics of interest are:
- Model-Based Machine Learning
- Data-Driven Software Engineering
- Multi-Objective Optimization
- Software Product Lines (for Digital Health Systems)
- Adaptive & Emergent Software Systems
Publications
List of last publications
Publications 2020-2018
[
less]
No papers to display!
Publications 2017-2015
[
less]
No papers to display!
Publications 2014-2012
[
less]
No papers to display!
Publications 2011-2009
[
less]
No papers to display!
Publications 2008-2006
[
less]
No papers to display!
Publications - older
[
less]
No papers to display!
Research projects
List of last projects
All projects
[
less]
-
GUIDES - Generalized Support and Investigation Design for Nested Systems
Smart Factory is a central concept in Industry 4.0, national high-tech development strategy. Physical processes, which occur at such a factory are monitored and are translated to a virtual model. Size and complexity of this model makes an analysis, both manual and automated, extremely costly. The model can be presented as a number of high-dimensional elements, e.g., tasks that should be finished by specific deadlines, machines that are required to perform specific tasks, employees with various shifts and access to a limited amount of machines, etc.
The goal of Generalized Support and Investigation Design for Nested Systems~(GUIDES) project is an effective enterprise resource planning, which presumes construction of a schedule, i.e., allocation of tasks on respective machines at the same time minimizing computation time, operational cost, etc. From the research point of view such a scheduling introduces the following challenges: treatment of data's high-dimensionality and avoidance of a local optima, which is a frequent result for various optimization heuristics.
To achieve this goal, we tackle the aforementioned problems separately. First, we reduce the model's dimensionality by the means of Multi-Dimensional Scaling, whose task is to transpose a high number features of a respective element to a low-dimensional equivalent (e.g., position on a plane) based on user-defined comparison operators, whilst still preserving dependencies between the elements. Significantly simplified model, in contrast to high-dimensional one, can be analyzed by global optimum search approaches such as Cluster Analysis or Nearest Neighbor Search to couple similar elements. Such a coupling, in turn, can be treated as either a near-optimal scheduling recommendation or can be further refined in order to find a global optima.
-
OpenLicht
Lighting systems should work with sensors and actuators of arbitrary vendors and with arbitrary configurations and amount.
Furthermore, an automatic configuration based on user preferences as well as intuitive and easy interaction should be ensured.
However, today's systems can not deliver those features, as they are vendor specific, incompatible, difficult to automate and/or not scalable.
The goal of this project is to research scalable mechanisms for a self-adaptive control of open, intelligent lighting systems.
Light is then able to be apperceptive, easy to use and adaptive.
To reach this goal, reference attribute grammars will be used for context models, which promise scalability through incremental computation.
Interoperability is being targeted to create a system which abstracts from vendor and communication specific details.
To achieve this, a self-adaptive system architecture will be used, to enable reconfigurations at runtime and the integration of self-learning algorithms to further enhance user experience.
Wearables -- sensors and actuators worn by the user -- will be used for a new interaction form to enable an intuitive, direct and context sensitive interaction with those adaptive systems.
-
LINC - Lean Innovation Center
[p]Integrationsplattform für das Management von agilen Prozessen, insbesondere Innovationsprozessen. Aktuell besteht die Plattform aus folgenden Tools:
[ul]
[li] Taiga: Aufgabenmanagement
[li] WatchOurIdeas: Ideen-Inkubator
[li] fridolean: Digitale Canvases
[li] CodiMD: Kollaboratives Markdown
[li] RocketChat: Chat+Messaging
[li] Keycloak: Single Sign-On
[/ul]
[/p]
[p]Die Plattform dient experimentellen Zwecken und wird ständig weiter entwickelt.[/p]
-
ConSens Data Glasses 4 SME
[p]"Pilot Application for Context-Sensitive Data Glasses for Smart Medical Environments"[/P]
[p][str]Abstract:[/str][/p]
[p]With regard to the increasing digitalization of medical information and the lack of adaptive systems to provide these information in an appropriate, mobile manner during the daily clinical business, a system is to be designed and analyzed to close this gap. For this purpose a software and hardware prototype based on smart glasses is to be developed to cover several basic use cases and to provide a platform to investigate and extend this approach.[/p]
[p][str]Medical need & background:[/str][/p]
[p]Despite the increasing digitization of healthcare and the increasing availability of electronic medical data, access to clinically relevant information and medical expertise is often limited by spatial and technical constraints. During inpatient care, a large spectrum of data is continuously generated, forming the base for treatment and care concepts. Nearly all medical-relevant information are electronically recorded in different primary systems and exchanged via increasingly standardized interfaces and data formats within the protected hospital networks. By providing information "at the right time, in the right place" and without barriers, it would be possible to increase the quality of care and patient safety, to improve the utilization of human resources and to reduce the mental effort of the medical staff.[/p]
[p]At the bedside, access devices such as laptops or tablets to request electronic information resources are limited due to hygienic requirements and due to the need for high interaction flexibility with the patient 1). Thus, it is necessary to develop mobile assistance (and communication) systems based on adaptive and wearable technologies that are capable of detecting contexts and situations based on static information and current sensor output to provide relevant medical data to multi-professional user groups. These assistance solutions must not interfere with human interaction with the patient, which requires the development of
intelligent control logic that takes into account the specific needs and context of healthcare professionals. Compared to existing solutions, a broad range of advanced presentation and interaction techniques, mobile hardware, heterogeneous sensor and data networks, and learning and flexible software technologies must be integrated to create a scalable multi-user system for
clinical operations.[/p]
[p]The project aims to cooperate with the tooz technologies GmbH, which provides hardware and software for the development of the smart glasses.[/p]
[p][str]Aims of the project:[/str][/p
[p] In the scope of the project, the technological basics for a mobile information and communication system based on the tooz smart glasses are to be developed. First, static medical data from external data sources should displayed dynamically with regard to the current location context. Secondly, the scope of the context is extended by integrating complex sensor input and user control by voice or gestures, forming a smart medical environment.[/p]
[p]Aims of the project are:
[ul]
[li] the analysis of the concept and the technologies in a clinical environment
[li] the development of a functional and demonstrable prototype, providing basic anonymized medical data (e.g. patient information, main diagnosis summary, last actions / results) in a test scenario
[li] preparation and support of aligned EKFZ project ideas & living Lab
[/ul]
[/p]
Teaching
Academic Year 2019/2020
| Winter Semester |
Summer Semester |
|
|
|
Academic Year 2018/2019
[
less]
| Winter Semester |
Summer Semester |
|
|
|
Academic Year 2017/2018
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2016/2017
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2015/2016
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2014/2015
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2013/2014
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2012/2013
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2011/2012
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2010/2011
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2009/2010
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Academic Year 2008/2009
[
less]
| Winter Semester |
Summer Semester |
- No given subjects in this semester
|
- No given subjects in this semester
|
Students' theses
Current students' theses
| Kind |
Topic |
Student |
| FM |
Evaluate and integrate model based AR applications in Hospital Contexts |
Uwe Schmidt |
| Forschungsmodul |
LINC: CriticalPath |
Martin Welcker |
| MA |
Enhancement of navigation maps for autonomous navigating AGVs by environmental observations |
Oleksandr Zaloznyi |
Past students' theses
| Kind |
Topic |
Student |
| FM |
Data Transformation Quality Metrics based on Information Theory |
Simon Tobies |
| BA |
Implementation and Analysis of a Software Framework for the Evaluation of Machine Learning required Data Transposition Technology Evaluation |
Amir Rahimi |
| MA |
Investigation of Domain Transposition and Pattern Recognition Technologies for Correlation Detection and Analysis in the Context of Big Data |
Moritz Haeusler |
| DA |
Entwicklung eines Frameworks zur Konzeptbestätigung ortsbasierter Fahrzeugdienste und derer Abbildbarkeit auf Fog Architekturen |
Benjamin Zerche |
[
show all]
Here is nothing more to display than this above!
About this page
Sebastian Götz
Last modified:
Dec 18, 2017
