AI Controlled Wireless Mesh Networks for Medical Applications in Crisis Situations (AWESOME)
Mentored by Frank Fitzek & Stefanie Speidel
at Deutsche Telekom Chair for Communication Networks, National Center for Tumor Diseases Dresden/TU Dresden
The purpose is to develop a wireless mesh network control system that utilizes artificial intelligence (AI) to optimize network performance and enable remote medical assistance in crisis situations, such as telemedical diagnosis, patient monitoring or connected ambulances.
Figure: Wireless mesh network with fixed and wireless communication nodes for crisis situations controlled by AI
The intended system will use machine learning algorithms to analyze network data and automatically adjust network parameters in real-time, resulting in improved network efficiency, reduced downtime, and enhanced user satisfaction. This is especially important for communication networks in crisis situations, where networks have to be established on the fly and react to disruptive changes (e.g. earthquake in Turkey or flooding in Germany).
Objectives: The objectives of this project are to i.) develop a wireless mesh network control system that utilizes AI to optimize network performance, ii.) implement machine learning algorithms that analyze network data and adjust network parameters in real-time and iii.) evaluate the performance of the proposed system on real COTS hardware and compare it to existing wireless network control systems within the use case of remote medical assistance.
Methods: The proposed wireless network control system will include a centralized control module that collects data from network devices and uses machine learning algorithms to analyze the data and adjust network parameters in real-time. The system will be designed to operate in a heterogeneous network environment, supporting different types of wireless access technologies and devices. The control module will use a combination of supervised and unsupervised learning techniques to identify patterns in network data and predict network behavior. The proposed system will be implemented using tested in a laboratory environment. The laboratory environment is equipped with several commercial off the shelf (COTS) devices that are installed at the chair. Furthermore, several mobile nodes will be used to investigate the impact of mobility. The performance of the system will be evaluated by comparing it to existing wireless network control systems, using metrics such as network throughput, latency, and packet loss.
Expected Outcomes: The proposed wireless network control system is expected to provide several benefits, including i.) improved network performance: by using machine learning algorithms to optimize network parameters, the proposed system is expected to improve network efficiency, reduce downtime, and enhance user experience, ii.) scalability: the proposed system is designed to be scalable, supporting different types of wireless access technologies, and devices, and iii.) cost-effectiveness: the proposed system is expected to be cost-effective, as it will utilize open-source software and require minimal hardware upgrades.
Impact: The proposed wireless network control system that utilizes AI has the potential to significantly improve wireless mesh network performance and enhance user experience for medical applications in crisis situations. This project will contribute to the development of advanced wireless network control systems that utilize machine learning algorithms to optimize network performance. The results of this project will have broad implications for the wireless communications industry and could lead to new opportunities for innovation and growth.
Work environment
You will work at the Deutsche Telekom Chair for Communication Networks. You will have access to a full wireless mesh network with over 50 fixed communication nodes and several mobile communication nodes such as Boston Dynamics’ Spot. You will also have the chance to work with a startup from the chair called Meshmerize. Meshermize provides the operating system of the communication nodes of the testbed. In addition, NCT Dresden located at the medical campus will provide access to infrastructure, data, and knowledge regarding the medical use case.
Prerequisites
The candidate will need a solid background in communication systems and should have strong programming skills. A master’s degree (or equivalent) in electrical engineering, computer science, or applied mathematics will be needed to apply for the PhD school. Prior expertise in machine learning or general AI techniques will be an advantage. The ability to collaborate well in an interdisciplinary environment is appreciated.
Topics All Topics
Adaptive / Context Sensitive Data Provision in Mobile Applications
AI Controlled Wireless Mesh Networks for Medical Applications in Crisis Situations (AWESOME)
Artificial Intelligence in the Context of Biomedical Signals
Explainable AI for reliable computer assisted surgery
External Systems Biology Knowledge Integration in Large Language Models
Features of Fitness Landscapes
From protein structure prediction to explainable AI in Oncology
GeoSOP: Geometry for surgical outcome prediction
Natural Neural networks inspire Artificial Neural Networks in Therapeutic Design
Reinforcement Learning for Mechanical Ventilation
StochasticAI – Integrating Stochastic Modeling with AI
SuperTouch - Data-driven tactile sensing for robot-assisted cancer surgery
Teaching artificial intelligence conformational dynamics of proteins
The Use of AI by the Civil Service in Light of the Principles of Democracy and the Rule of Law