Theses and Projects: Difference between revisions

(2 intermediate revisions by one other user not shown)

Line 3:

See a [https://wiki.net.informatik.uni-goettingen.de/w/images/5/5a/NETGroup_Poster-Jan2021.pdf poster] for a general overview, an [http://www.net.informatik.uni-goettingen.de/?q=research anchor] to our research activities, a list of [https://wiki.net.informatik.uni-goettingen.de/w/images/a/a3/Social_Computing_publications.pdf social computing related] or networking-related publications, and the

[http://www.net.informatik.uni-goettingen.de/?q=news/annual-report-2020-best-wishes-2021 annual report(s)] for our recent activities.

== Joint Thesis Topics with fortiss ==

The following Master's thesis topics are offered in collaboration with Prof. Rute Sofia at fortiss, the Research Institute of the Free State of Bavaria for Software-Intensive Systems, in Munich.

=== * '''New!''' Cognitive Network Intelligence for Energy-Efficient and Deterministic Industrial Communication ===

Industrial applications increasingly rely on heterogeneous networks combining 5G, Wi-Fi, and Time-Sensitive Networking (TSN). This topic investigates energy-aware traffic engineering to reduce network energy consumption while meeting strict latency, jitter, and reliability requirements. Tasks include developing energy models, designing optimization mechanisms, and evaluating them using the ns-3 simulation framework. We expect you to have programming skills in Python or C/C++ and an interest in network optimization. A background in wireless communications, industrial networking, or network simulation is an advantage.

[https://www.fortiss.org/en/career/masters-thesis-cognitive-network-intelligence-for-energy-efficient-and-deterministic-industrial-communication Further information]

=== * '''New!''' Energy-Efficient IoT-Edge-Cloud Infrastructures for Dynamic AI Services ===

Deploying AI inference across heterogeneous edge and cloud resources requires balancing inference quality, latency, and energy consumption. This topic focuses on energy-aware scheduling of small large language models (LLMs), building on the energy monitoring infrastructure in the fortiss Industrial IoT Lab. Tasks include characterizing inference energy consumption and developing scheduling strategies across different hardware configurations and model quantization levels. We expect you to have a background in machine learning, distributed systems, or computer networking, together with programming skills. Familiarity with PyTorch or Hugging Face is an advantage.

[https://www.fortiss.org/en/career/masters-thesis-energy-efficient-iot-edge-cloud-continuum-infrastructures-for-dynamic-ai-service-support Further information]

=== * '''New!''' Decentralised Federated Learning for Semantic Communications ===

Semantic communication aims to reduce communication overhead by transmitting information relevant to a specific inference or control task. This topic investigates decentralised federated learning for training and adapting semantic encoder-decoder models across heterogeneous industrial IoT, edge, and cloud environments. Tasks include developing a distributed learning architecture, addressing non-IID data and device heterogeneity, and evaluating task performance and communication overhead through simulation. We expect you to have programming skills and a background in machine learning or distributed systems. Familiarity with federated learning frameworks or ns-3 is an advantage.

[https://www.fortiss.org/en/career/masters-thesis-decentralised-federated-learning-for-semantic-communications-in-iiot-edge-cloud-environments Further information]

=== * '''New!''' Semantic-Aware Routing for Multi-Hop Industrial IoT Networks ===

Routing decisions in industrial IoT networks can affect how well transmitted information supports an application’s task. This topic investigates routing mechanisms that account for task requirements and semantic distortion across multiple network hops. Tasks include designing a protocol that uses distortion budgets and contextual knowledge to select forwarding paths, implementing it in ns-3, and evaluating it against conventional routing approaches. We expect you to have a background in computer networking or wireless communications and programming skills in Python and C/C++. Familiarity with network simulation is an advantage.

[https://www.fortiss.org/en/career/masters-thesis-semantic-aware-routing-for-multi-hop-iiot-infrastructures Further information]

For more information about joint supervision, please contact Prof. Xiaoming Fu [fu@cs.uni-goettingen.de].

Line 58:

Line 91:

~~=== * '''New!''' Context Specific Self-supervised Pre-Training for Remote Sensing Applications (Semantic Segmentation, Change Detection, Socio-Economic Indicator Estimation, ...) (B/M/P) ===~~

Satellite images in combination with Machine/Deep Learning models have shown to be an effective tool for analysis and monitoring tasks regarding disasters, deforestation, climate change, socio-economic estimation and others. The training of these models usually rely on labelled ground-truth data, which is labour intensive and therefore often scarcely available. To overcome this limitation, models are often trained in self-supervised approaches with unlabelled data, such as Contrastive Learning or Masked Autoencoders. However, these approaches are completely independent and not related to the intended downstream task. In this project/thesis the relationship between the pre-training task and the model performance on the downstream task will be explored and self-supervised training approaches tailored for a selected remote sensing downstream task (semantic segmentation of trees, tree crown share per pixel estimation, change detection of disasters, socio-economic estimation, ...) will be developed.

~~Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]~~

~~=== [Occupied] Tree Growth Detection using Satellite Images and Computer Vision Methods (B/M/P) ===~~

A tree planting project in Madagascar was initiated several years ago. The outcomes of this project shall now be evaluated by analyzing satellite images of the study area with Computer Vision methods. In a first step, very high resolution (VHR) satellite images from 2023 with a resolution of 0.5m will be used to identify trees with object detection / semantic segmentation. In the next step a lower resolution (5m) satellite image time series starting in 2015 will be used for change detection to identify, in which locations the project was (un)successful.

~~Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]~~

=== * '''New!''' Emotional Support Conversation Generation based on LLM (B/M/P)===

Line 83:

Line 104:

Please contact Fei Gao [fei.gao@cs.uni-goettingen.de]

~~=== [Occupied] Image-to-Image Translation of Different Nightlight Image Types (B/M/P) ===~~

Nightlight intensities have been proven to be a good indicator for socio-economic status. However, for long-term temporal analyses their use can be challenging, as different satellites for sensing nightlight intensities operated at different times (DMSP OLS 1992-2014 and VIIRS 2012-2023). Both types differ not only in resolution, but there is also a big discrepancy in the optical appearance and value ranges. To obtain consistent nightlight images for temporal analysis, Image-to-Image Translation methods shall be used in this project/thesis for the conversion between both types. Finally the performance of the translated and original nightlight images for a regression on socio-economic indicators shall be evaluated.

~~Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]~~

~~=== [Occupied] Satellite Image Indices and Machine Learning for Socio-economic Estimation (B/M/P) ===~~

There are several indices, which can be derived from satellite images. For example the Normalized Difference Vegetation Index (NDVI) indicates the presence and condition of vegetation, while the Normalized Difference Built-up Index (NDBI) indicates the presence of built-up areas such as buildings or roads. The distributions of these and other indices may have different explanatory power to estimate the socio-economic status of locations. Therefore in this project/thesis the regression performance of machine learning models - using statistics of these indices as features - to estimate socio-economic indicators shall be evaluated for the individual and also combined indices. Optionally, Convolutional Neural Networks (CNNs) can be applied additionally, which take the derived index images as input.

~~Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]~~

=== * 3D natural hazard simulator ===

@@ Line 3: / Line 3: @@
 See a [https://wiki.net.informatik.uni-goettingen.de/w/images/5/5a/NETGroup_Poster-Jan2021.pdf poster] for a general overview, an [http://www.net.informatik.uni-goettingen.de/?q=research anchor] to our research activities, a list of [https://wiki.net.informatik.uni-goettingen.de/w/images/a/a3/Social_Computing_publications.pdf social computing related] or networking-related publications, and the
 [http://www.net.informatik.uni-goettingen.de/?q=news/annual-report-2020-best-wishes-2021 annual report(s)] for our recent activities.
+== Joint Thesis Topics with fortiss ==
+The following Master's thesis topics are offered in collaboration with Prof. Rute Sofia at fortiss, the Research Institute of the Free State of Bavaria for Software-Intensive Systems, in Munich.
+=== * '''New!''' Cognitive Network Intelligence for Energy-Efficient and Deterministic Industrial Communication ===
+Industrial applications increasingly rely on heterogeneous networks combining 5G, Wi-Fi, and Time-Sensitive Networking (TSN). This topic investigates energy-aware traffic engineering to reduce network energy consumption while meeting strict latency, jitter, and reliability requirements. Tasks include developing energy models, designing optimization mechanisms, and evaluating them using the ns-3 simulation framework. We expect you to have programming skills in Python or C/C++ and an interest in network optimization. A background in wireless communications, industrial networking, or network simulation is an advantage.
+[https://www.fortiss.org/en/career/masters-thesis-cognitive-network-intelligence-for-energy-efficient-and-deterministic-industrial-communication Further information]
+=== * '''New!''' Energy-Efficient IoT-Edge-Cloud Infrastructures for Dynamic AI Services ===
+Deploying AI inference across heterogeneous edge and cloud resources requires balancing inference quality, latency, and energy consumption. This topic focuses on energy-aware scheduling of small large language models (LLMs), building on the energy monitoring infrastructure in the fortiss Industrial IoT Lab. Tasks include characterizing inference energy consumption and developing scheduling strategies across different hardware configurations and model quantization levels. We expect you to have a background in machine learning, distributed systems, or computer networking, together with programming skills. Familiarity with PyTorch or Hugging Face is an advantage.
+[https://www.fortiss.org/en/career/masters-thesis-energy-efficient-iot-edge-cloud-continuum-infrastructures-for-dynamic-ai-service-support Further information]
+=== * '''New!''' Decentralised Federated Learning for Semantic Communications ===
+Semantic communication aims to reduce communication overhead by transmitting information relevant to a specific inference or control task. This topic investigates decentralised federated learning for training and adapting semantic encoder-decoder models across heterogeneous industrial IoT, edge, and cloud environments. Tasks include developing a distributed learning architecture, addressing non-IID data and device heterogeneity, and evaluating task performance and communication overhead through simulation. We expect you to have programming skills and a background in machine learning or distributed systems. Familiarity with federated learning frameworks or ns-3 is an advantage.
+[https://www.fortiss.org/en/career/masters-thesis-decentralised-federated-learning-for-semantic-communications-in-iiot-edge-cloud-environments Further information]
+=== * '''New!''' Semantic-Aware Routing for Multi-Hop Industrial IoT Networks ===
+Routing decisions in industrial IoT networks can affect how well transmitted information supports an application’s task. This topic investigates routing mechanisms that account for task requirements and semantic distortion across multiple network hops. Tasks include designing a protocol that uses distortion budgets and contextual knowledge to select forwarding paths, implementing it in ns-3, and evaluating it against conventional routing approaches. We expect you to have a background in computer networking or wireless communications and programming skills in Python and C/C++. Familiarity with network simulation is an advantage.
+[https://www.fortiss.org/en/career/masters-thesis-semantic-aware-routing-for-multi-hop-iiot-infrastructures Further information]
+For more information about joint supervision, please contact Prof. Xiaoming Fu [fu@cs.uni-goettingen.de].
@@ Line 58: / Line 91: @@
-===  * '''New!''' Context Specific Self-supervised Pre-Training for Remote Sensing Applications (Semantic Segmentation, Change Detection, Socio-Economic Indicator Estimation, ...) (B/M/P) ===
-Satellite images in combination with Machine/Deep Learning models have shown to be an effective tool for analysis and monitoring tasks regarding disasters, deforestation, climate change, socio-economic estimation and others. The training of these models usually rely on labelled ground-truth data, which is labour intensive and therefore often scarcely available. To overcome this limitation, models are often trained in self-supervised approaches with unlabelled data, such as Contrastive Learning or Masked Autoencoders. However, these approaches are completely independent and not related to the intended downstream task. In this project/thesis the relationship between the pre-training task and the model performance on the downstream task will be explored and self-supervised training approaches tailored for a selected remote sensing downstream task (semantic segmentation of trees, tree crown share per pixel estimation, change detection of disasters, socio-economic estimation, ...) will be developed.
-Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]
-===  [Occupied] Tree Growth Detection using Satellite Images and Computer Vision Methods (B/M/P) ===
-A tree planting project in Madagascar was initiated several years ago. The outcomes of this project shall now be evaluated by analyzing satellite images of the study area with Computer Vision methods. In a first step, very high resolution (VHR) satellite images from 2023 with a resolution of 0.5m will be used to identify trees with object detection / semantic segmentation. In the next step a lower resolution (5m) satellite image time series starting in 2015 will be used for change detection to identify, in which locations the project was  (un)successful.
-Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]
 ===  * '''New!''' Emotional Support Conversation Generation based on LLM (B/M/P)===
@@ Line 83: / Line 104: @@
 Please contact Fei Gao [fei.gao@cs.uni-goettingen.de]
-===  [Occupied]  Image-to-Image Translation of Different Nightlight Image Types (B/M/P) ===
-Nightlight intensities have been proven to be a good indicator for socio-economic status. However, for long-term temporal analyses their use can be challenging, as different satellites for sensing nightlight intensities operated at different times (DMSP OLS 1992-2014 and VIIRS 2012-2023). Both types differ not only in resolution, but there is also a big discrepancy in the optical appearance and value ranges. To obtain consistent nightlight images for temporal analysis, Image-to-Image Translation methods shall be used in this project/thesis for the conversion between both types. Finally the performance of the translated and original nightlight images for a regression on socio-economic indicators shall be evaluated.
-Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]
-===  [Occupied] Satellite Image Indices and Machine Learning for Socio-economic Estimation (B/M/P) ===
-There are several indices, which can be derived from satellite images. For example the Normalized Difference Vegetation Index (NDVI) indicates the presence and condition of vegetation, while the Normalized Difference Built-up Index (NDBI) indicates the presence of built-up areas such as buildings or roads. The distributions of these and other indices may have different explanatory power to estimate the socio-economic status of locations. Therefore in this project/thesis the regression performance of machine learning models - using statistics of these indices as features - to estimate socio-economic indicators shall be evaluated for the individual and also combined indices. Optionally, Convolutional Neural Networks (CNNs) can be applied additionally, which take the derived index images as input.
-Please contact Fabian Wölk [fabian.woelk@cs.uni-goettingen.de]
 ===  * 3D natural hazard simulator  ===