Internship / Student Assistant / Thesis Active - Dresden, Deutschland - Fraunhofer-Gesellschaft

Fraunhofer-Gesellschaft

Geprüftes Unternehmen

Dresden, Deutschland

vor 3 Wochen

Geschrieben von:

Lena Wagner

beBee Recruiter

PraktikumSHIP

Beschreibung

Adaptivity is an indispensable characteristic for the networked world of tomorrow.

Intelligent components can detect and evaluate changes in the environment or in the system itself and adapt to them independently.

As a partner of industry, Fraunhofer IIS/EAS develops key technologies for adaptive systems with about 110 employees at Dresden and offers innovative technologies and robust solutions.

The department Distributed Analysis and Control Systems develops algorithms for the monitoring of wireless industrial networks. Todays Smart production concepts heavily rely on the availability and reliability of wireless communication systems.

To counteract interferences from the increasing number of wireless systems, innovative algorithms provide information about the connection quality and existing transmission problems.

You are interested in the improvement of deep learning based object detection methods for analysis and monitoring of wireless networks?

Then we have the right position for you:

To improve the spectral analysis, machine learning is used to detect individual packets of different wireless technologies and calculate detailed statistics automatically and in real time.

Therefore, an extensive emulation pipeline has been developed to generate training data. But adding more RF-standards can be a time consuming task.

What you will do
The human-in-the-loop approach is going to help to accelerate the training of new RF-standards.

An Active Learning algorithm will help detecting unknown spectral appearances within real measurements and present the human expert only the most meaningful examples for manually labelling.

The following tasks will be covered:

State of the art survey regarding Active Learning for object detection tasks
Transfer learning for newly labelled RFpackets
Evaluate the performance of the algorithm and make adjustments as needed
Validation of results in the laboratory

What you bring to the table
- are a student of computer science, engineering, physics or mathematics (with technical focus) or similar
- have knowledge in machine learning
- have experience using tools like Python
- provide solid skills in English or German

What you can expect

A challenging project with a high degree of realworld applicability
Support in the familiarization phase so that you can quickly work productively
An open and friendly work atmosphere
Flexible hours that allow you to balance your work and study activities

- an innovative and exciting topic, with the chance to contribute your own ideas

The leeway to develop your own interests and skills

Remuneration according to the general works agreement for employing assistant staff.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process.

As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Interested?

We look forward to getting to know you
Fraunhofer Institute for Integrated Circuits IIS

Requisition Number: 63558

Application Deadline:
none