NET Wiki

Seminar on Internet Technologies (Summer 2024): Difference between revisions

← Older edit
Stong (talk | contribs)
28 edits
Stong (talk | contribs)
28 edits
 
(11 intermediate revisions by 4 users not shown)
Line 4: Line 4:
{{CourseDetails
{{CourseDetails
|credits=5 ECTS (BSc/MSc AI); 5 (ITIS)
|credits=5 ECTS (BSc/MSc AI); 5 (ITIS)
|module=M.Inf.1124
|lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu]
|lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu]
|ta =[http://www.net.informatik.uni-goettingen.de/?q=people/jiaquan-zhang MSc. Jiaquan Zhang];
|ta = Tong Shen[shen.tong@cs.uni-goettingen.de]
|'''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|ta = Dr. Tingting Yuan [tingting.yuan@informatik.uni-goettingen.de]
|time='''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|time='''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|univz=[https://studip-ecampus.uni-goettingen.de/dispatch.php/course/details/?cid=9d41fd6cc504b43ebbe4b1c33eef46bb]
}}
}}


Line 61: Line 61:
|-
|-
|-
|-
|AI painter
| How to do efficient offline training
| In this topic, you will study how AI has been used for painting. e.g. GAN.
| In this topic, you will study how to do efficient offline training for reinforcement learning
| Basic programming knowledge, Basic machine learning knowledge, need coding work
| Basic programming knowledge, Basic machine learning knowledge, need coding work
| [Tingting Yuan, tingt.yuan@hotmail.com]
| [Tingting Yuan, tingting.yuan@cs.uni-goettingen.de]
|[https://topten.ai/ai-painting-generators/]
|
| Yes
| Yes
|-
|-
|-
|-
|OCR (Optical Character Recognition) and Annotation Transfer
| Disaster Monitoring
| The aim of the project is to develop a tool/software that can convert a printed paper with annotations and text into electronic versions with text highlighting and annotations
| In this topic, you will study methods to monitor disaster scenarios (e.g. floodings) with aerial images.
| Basic machine learning knowledge
| Basic machine learning knowledge
| [Tingting Yuan, tingt.yuan@hotmail.com]
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
|[https://medium.com/analytics-vidhya/opencv-perspective-transformation-9edffefb2143] [https://www.cameralyze.co/blog/how-can-i-detect-lines-in-images-or-pdfs] [https://developer.adobe.com/document-services/apis/pdf-services/]
|
| Yes
| No
|-
|-
|-
| Change Detection in Satellite Image Time Series
| Biomass estimation from Satellite Images
| In this topic, you will study methods to detect changes in land-use, vegetation, etc. in Satellite Image Time Series.
| In this topic, you will study methods to estimate the biomass of trees from satellite images.
| Basic machine learning knowledge
| Basic machine learning knowledge
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
Line 85: Line 85:
|-
|-
|-
|-
| Satellite Image Pixel Clustering for Change Estimation
| Explainable AI(XAI) / graph neural network (XGNN)
| In this topic, you will study pixel clustering methods for satellite images and apply their outputs for regression-based estimation of changes between different points in time.
| In this topic, student will study how AI models / GNNs are explained by SOTA papers.
| Basic machine learning knowledge
| Basic AI / GNN knowledge
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
|
| Yes
| Yes
|-
|-
|-
|-
| Explainable AI(XAI) / graph neural network (XGNN)
| Anomaly Detection in Graphs
| In this topic, students study how AI models / GNNs are explained with SOTA papers.
| In this topic, student will read papers to learn how to detect anomaly edge/graph/subgraph… with the help of GNN.
| Basic AI / GNN knowledge
| Basic AI / GNN knowledge
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
Line 102: Line 102:
|-
|-
| Social Media Comments Network (Intern/Project/Thesis possible)
| Social Media Comments Network (Intern/Project/Thesis possible)
| In this topic, you will study methods to crawl the dataset from social networks(e.g. YouTube) and utilize social science network analysis in any topic you are interested in (science/education/language…) to find out the network structure and compare the difference among different topics.
| In this topic, student will study methods to crawl the dataset from social networks(e.g. X, YouTube) and utilize social network analysis in any topic you are interested in (science/education/language…) to find out the network structure and compare the difference among different topics.
| Python(Data crawling, cleaning, statistical data analysis, modeling and visualization), basic graph knowledge
| Python(Data crawling, cleaning, statistical data analysis, modeling and visualization), basic graph knowledge would be a plus
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
|
| No
| No
|-
|-
| Influence of LLM robots in social networks (Intern/Project/Thesis possible)
| In this topic, student will study methods to crawl the data of LLM robots from social networks(e.g. X, Facebook) and utilize NLP and SNA to evaluate the influence of LLM robots in a specific topic.
| Python(Data crawling, cleaning, statistical data analysis, modeling and visualization), basic graph knowledge would be a plus
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
| Yes
|-
|-
|-
|-
| The life-circle of vanished scientific journals (Intern/Project/Thesis possible)
| The life-circle of vanished scientific journals (Intern/Project/Thesis possible)
| In this topic, students will mine the information of vanished/(ongoing)/top journals, try to find out the difference features(manually/ML-based method) between journals facing different destinies.
| In this topic, student will mine the information of vanished/(ongoing)/top journals, try to find out the difference features(manually/ML-based method) between journals facing different destinies.
| Python(Data Crawling, Cleaning, EDA, Modeling). Basic graph, XAI knowledge is a plus.
| Python(Data Crawling, Cleaning, EDA, Modeling). Basic graph, XAI knowledge is a plus.
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
Line 118: Line 126:
|-
|-
| Traffic prediction with GNN (Intern/Project/Thesis possible)
| Traffic prediction with GNN (Intern/Project/Thesis possible)
| In this topic, students will study how to use XGNN to predict traffic volumn.
| In this topic, student will study how to use XGNN to predict traffic volumn.
| Python(Modeling and Visualization). Graph and XAI knowledge.
| Python(Modeling and Visualization). Graph and XAI knowledge.
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
Line 126: Line 134:
|-
|-
| ML/DL based industrial equipment predictive maintenance (Intern/Project/Thesis possible)
| ML/DL based industrial equipment predictive maintenance (Intern/Project/Thesis possible)
| In this topic, students will study how to use cutting-edge machine learning models to predict when industrial equipment need to be maintained before crashing.
| In this topic, student will study how to use cutting-edge machine learning models to predict when industrial equipment need to be maintained before crashing.
| Python(Cleaning, EDA, Modeling and Visualization). XAI knowledge is a plus.
| Python(Cleaning, EDA, Modeling and Visualization). XAI knowledge is a plus.
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
Line 138: Line 146:
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|  
|  
| Yes
| No
|-
|-
|-
|-
| Open topics
| Lidar-based traffic flow analysis
| Open topics in Data Science & Applied Statistics, especially XAI
| In this topic, you will study methods to analyze traffic usage on roads, e.g., in terms of traffic flow, speed, and density to identify patterns and trends.
| Depends
| Basic point cloud processing & ML knowledge
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
| Yes
|-
|-
| Vision-based pedestrian distribution monitoring
| In this topic, you will study methods to do macroscopic pedestrian detection aims to estimate crowd density without distinguishing each pedestrian.
| Basic CV & ML knowledge
| [Yanlong Huang, yanlong.huang@cs.uni-goettingen.de]
| [Yanlong Huang, yanlong.huang@cs.uni-goettingen.de]
|  
|  
Line 157: Line 157:
|-
|-
|-
|-
| Vision-based traffic usage analysis
| Personalized chatbot based on ChatGPT
| In this topic, you will study methods to analyze traffic usage on roads and highways, e.g., in terms of traffic flow, speed, and density to identify patterns and trends.
| In this topic, you will learn about ChatGPT and learn to use OpenAI ChatGPT API to create a personalized chatbot.
| Basic CV & ML knowledge
| NLP & ChatGPT
| [Yanlong Huang, yanlong.huang@cs.uni-goettingen.de]
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
|  
|  
| Yes
| Yes
|-
|-
|-
|-
| Personalized chatbot based on ChatGPT
| Multimodal Large Language Model Evaluation for Multimodal Tasks
| In this topic, you will learn about ChatGPT and learn to use OpenAI ChatGPT API to create a personalized chatbot.
| This topic focuses on assessing the performance and effectiveness of large language models in handling tasks that involve multiple modalities, such as text, images, and audio. It involves the evaluation of these large models using specialized multimodal datasets, considering both quantitative metrics and qualitative analysis. In this topic, you will gain insights into various large models, including GPT-4, and acquire knowledge about a wide range of multimodal tasks. Additionally, you will become proficient in implementing evaluations related to these tasks.
| NLP & ChatGPT
| Large Language Model & multimodal setting
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
|  
|  
Line 173: Line 173:
|-
|-
|-
|-
| Performance of real 5G communication
| Knowledge Graph Completion
| What are the key QoS requirements for future applications and scenarios? What are the shortcomings of today's 5G network? Where are the bottlenecks? How can performance be improved? In this topic, you will build an open-source 5G communication network from the core to the edge, test and analyze the real performance of 5G.
| What are the Knowledge Graph (KG) requirements for future applications and scenarios? What is the task of Knowledge Graph Completion? What is the correlation between KGs and NLP? How to use popular large language models (LLMs) to assist in the implementation of knowledge graph completion? In this topic, you will learn about KGs and learn to use LLMs to perform a KGC task.
| Network protocol stack & 5G architecture
| Knowledge Graph & NLP
| [Wanghong Yang, wanghong.yang@cs.uni-goettingen.de]
| [Tong Shen, shen.tong@cs.uni-goettingen.de]
|  
|  
| Yes
| Yes
Retrieved from "https://wiki.net.informatik.uni-goettingen.de/wiki/Seminar_on_Internet_Technologies_(Summer_2024)"