Dear Students,
You can view the video of the Project Forum 2021 at the following link: https://www.youtube.com/watch?v=m6LN0IGrnyg
A summary of the projects has been collected below. The list also includes projects that have not been presented on the Forum.
1. P4 programok tulajdonságainak elemzése (starts at 00:05:05 in the video)
Goals, Topics, Used Technologies: A P4 egy fiatal, elsődlegesen hálózati csomagok feldolgozását leíró algoritmusok leírására szolgáló nyelv. A projektben P4 programok különböző elemzéseivel (például opcionálisan hibás kódrészletek keresése, optimalizálás, költségbecslés) foglalkozunk.
Static analyzes, Java, Gremlin, P4.
Who are we searching for?: Elsősorban elsőéves MSc vagy végzős BSc magyarul beszélő hallgatókat.
Is it open for students of the Campus of Szombathely?: Igen
How much time a student needs to contribute: Minimum 4-8 óra/hét
Contact person: Tejfel Máté
Contact Information: matej at inf dot elte dot hu
2. Digitalization in agriculture (starts at 00:09:46 in the video)
Goals, Topics, Used Technologies: data science, mashine learning, Iot-technologies, artificial intelligence, application- and webdevelopment
Who are we searching for?: BSc-, MSc-student, PhD-student, young researcher
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: depends on the projects
Contact person: Márta Alexy
Contact Information: abalord02 at inf dot elte dot hu
3. AI for Inertial sensor production (starts at 00:15:15 in the video)
Goals, Topics, Used Technologies: product behavior prediction with tree based AI model
Who are we searching for?: students, dealing with AI solution or digitalization
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: 6-12 months
Contact person: Tamás Fischl
Contact Information: tamas.fischl at hu dot bosch dot com
4. PipeRT – Realtime Scheduling Framework for Digital Signal Processing (starts at 00:19:42 in the video)
Goals, Topics, Used Technologies: development and design of the above mentioned open-source library, C++, Python & Node planned
Who are we searching for?: everyone interested
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: depends, probably 1-4 hours per week
Contact person: Zoltán Gera
Contact Information: gerazo at ik dot elte dot hu
5. RUMBA – Research for Understanding Music, Beat and Acoustics (starts at 00:23:27 in the video)
Goals, Topics, Used Technologies: Math, Digital Signal Processing, Music Theory, Psychoacoustics, Python
Who are we searching for?: motivated people
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: depends, probably 1-4 hours per week
Contact person: Zoltán Gera
Contact Information: gerazo at ik dot elte dot hu
6.a Finding Security Vulnerabilities in Java Code by using Static Analysis (starts at 00:26:39 in the video)
Goals, Topics, Used Technologies: development of open-source SpotBugs detectors, Java
Who are we searching for?: everyone
How much time a student needs to contribute: depends, probably 1-4 hours per week
Contact person: Zoltán Gera
Contact Information: gerazo at ik dot elte dot hu
6.b Finding Security Vulnerabilities in C / C++ Code by using Static Analysis (starts at 00:26:39 in the video)
Goals, Topics, Used Technologies: development of open-source Clang checkers, C / C++
Who are we searching for?: everyone
How much time a student needs to contribute: depends, probably 1-4 hours per week
Contact person: Zoltán Gera
Contact Information: gerazo at ik dot elte dot hu
7. Machine Learning for Software Engineering (starts at 00:32:58 in the video)
Goals, Topics, Used Technologies: Our goal is to teach machines to understand, write, and fix code.
Some currently running projects:
– synthesizing code based on input-output examples (given the inputs and outputs, the system writes code to solve the problem)
– synthesizing code based on natural language (generating code to solve programming assignments automatically)
– idiomatizing code: detecting and fixing non-idiomatic code fragments
– grading programming assignments automatically
– decompilation
Who are we searching for?: First year MSc or BSc, or 2nd year BSc students who are interested in both software engineering and deep learning. Students should have strong skills in both programming and mathematics (mostly linear algebra and some probability and calculus). Having machine learning experience is an advantage but is not necessary.
Is it open for students of the Campus of Szombathely?: no
How much time a student needs to contribute: 10-20 hours weekly, probably more at first to learn deep learning and get started.
Contact person: Tibor Gregorics, Balázs Pintér
Contact Information: gt at inf dot elte dot hu, pinter at inf dot elte dot hu
8. Artificial open-ended evolution, Artificial intelligence is the machine realization of intelligence. (starts at 00:37:18 in the video)
Goals, Topics, Used Technologies: Artificial intelligence is the machine realization of intelligence. But what does intelligence mean?
Intelligence is difficult to define precisely, but it
– has the ability to learn;
– adapts to its environment;
– collaborates with others;
– is creative, ie able to create new (and working) things.
Recently, AI primarily means machine learning, using the method of (deep) artificial neural networks. However, this is not the only method based on a biological analogy that can be interesting and effective in creating intelligent systems. Especially, if we not only consider the training of a single machine for a single, relatively narrow task.
Another successful biological example is evolution, that has created a great variety of living beings that successfully adapt to ever changing conditions. Both diversity and adaptation are remarkable. Adaptation means that the species that provides the best solution for the available opportunities at the given time survives. This is the work of natural selection, which has many engineering applications already and is a very effective optimization tool.
The ability to create diversity is just as important, however. Natural evolution has created an extremely diverse multitude of species (living today or already extinct but known to us) from one (or a few) initial life forms. Diversity is also important from an engineering point of view because it is the basis of adaptability and creativity. The basic mechanisms are well known: we learned about mutation and cross aver in high school already.
The balance between diversity and selection within a single artificial system is currently an open question. We can create diversity, but selection-based methods converge very effectively to the optimal solution at a given moment and ‘kill’ other, less solutions. The creation of open-ended evolutionary systems is currently an open research task.
Programming knowledge is required. Java or Python is a plus.
Who are we searching for?: Senior BSc students. Master students. Students looking for TDK topics. Possibly, students contemplating Phd.
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: To be discussed. Minimum 4 hours a week.
Contact person: László Gulyás
Contact Information: lgulyas at inf dot elte dot hu
9. Conductor vibration in transmission lines, Dynamic problems of wind turbine blades (starts at 00:42:05 in the video)
Who are we searching for?: BSc students, PhD candidates
Is it open for students of the Campus of Szombathely?: yes
How much time a student needs to contribute: BSc students: half a year – one year, PhD project: 4 years
Contact person: Prof. László Kollár
Contact Information: kl at inf dot elte dot hu
10. Machine Learning for Signal Processing (starts at 00:46:42 in the video)
Goals, Topics, Used Technologies: Machine learning is a rapidly developing field with numerous applications in computer science and technology. In this project, we develop agorithms which combine the advantages of data-driven deep learning methods and model-based signal processing approaches. We have several ongoing projects:
– Biomedical signal processing: heartbeat classification in ECG signals, epileptic seizure detection in EEGs
– Digital signal processing: skidding detection by wheel sensor data, encoding/decoding signals in telecommunication, beat and rythm detection in audio signals
– Thomographic imaging: nondestructive testing by thermal imaging, artifact reduction in CT images
– Developing model-driven machine learning algorithms
Udes technologies: Python, Matlab
Who are we searching for?: 3rd year BSc and MSc students interested in Mathematical Modeling, Signal and Image Processing, and Artificial Intelligence are welcome.
Is it open for students of the Campus of Szombathely?: 3rd year BSc and MSc students interested in Mathematical Modeling, Signal and Image Processing, and Artificial Intelligence are welcome.
How much time a student needs to contribute: 10 hours / week
Contact person: Dr. Peter Kovacs
Contact Information: kovika at inf dot elte dot hu
11. Human-machine, human-robot interaction and related applications (starts at 00:55:51 in the video)
Goals, Topics, Used Technologies: Applicatios include monitoring, help, personality estimation (Barcelona University), memory estimtion in online meetings (Delft Technical University) diagnosis (Rush Medical School, Chicago), therapy (Radboud University, Netherlands), drowsiness estimation (Bosch, Budapest), avatar in banking, avatar in hiring)
Used Technologies:
– Multimodal (audio-visual-textual) information processing using deep learning
– OpenBot with Jensen and 3D camera
– Semantic mapping and semantic matching between human and robot partners
Who are we searching for?: Students who
a) have excellent programming skills and have a solid background in math — the key elements in deep learning technologies
b) want to deal with such tasks for over one year at least, e.g., to continue for MSc
c) are quick learners
d) who have about 20 hours/week for R+D+I and want to compete in student competitions and want to publish
e) can work with us during the summer(s) alike students in the US and in China
In other words, I am looking for students from the top 5%
Is it open for students of the Campus of Szombathely?: –
How much time a student needs to contribute: 20 hours/week
Contact person: András Lőrincz
Contact Information: lorincz at inf dot elte dot hu
12. CodeCompass (starts at 1:07:14 in the video)
Goals, Topics, Used Technologies: CodeCompass: For the purpose of new feature development, bug fixing or just effective work, the programmer has to completely understand the code under work. Unfortunately, it is a frequent issue with large software projects developed for decades that after years nobody really understand the system on the whole. Code comprehension tools help to find important parts in the source, navigate inside large projects and provide a better understanding via various visual and textual summaries. CodeCompass https://github.com/Ericsson/codecompass is such an open source tool using static analysis developed by Eötvös Loránd University and Ericsson. We are developing new features and enhancing the existing ones, like analyzing new languages, creating better visualizations and navigation, enriching the web gui, etc.
Used technologies: C++, Java, Javascript, Python, LLVM/Clang
Who are we searching for?: Students who have stable programming knowledge in C++, know version control basics, interested in static analysis or compiler technology and want to learn/master their knowledge in programming languages and other fields. They have the opportunity to create a BSc/MSc thesis, mandatory practice, TDK and they can work on a tool which would be useful for their own.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: Weekly 4-20 hours, depending on the engagement
Contact person: Zoltán Porkoláb
Contact Information: gsd at inf dot elte dot hu
13. Static/dynamic source code analysis and transformations for Erlang — RefactorErl. (starts at 1:17:30 in the video)
Goals, Topics, Used Technologies: Static program analysis is a well-known technique in computer-aided software development when we can help to check certain properties of the software without running the applications and wasting the time of a developer. With the techniques of static and dynamic analyses, we can check the quality/security of the software, the optimal usage of resources, energy consumption, or able to improve our development and maintenance processes. In our research project, we are focusing on the Erlang programming language. Erlang is a functional programming language designed for implementing highly concurrent and distributed applications. Just Cisco ships more than 2 million of devices per year with Erlang on board. Thus the 90% of the internet traffic goes through devices controlled by Erlang applications.
https://www.inf.elte.hu/content/ericsson-szoftvertechnologiai-labor.t.1040?m=123
http://plc.inf.elte.hu/erlang/
Who are we searching for?: BSc, MSc, PhD students who are willing to learn new technologies and tools and want to work on interesting R&D tasks.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: 4 hours/week is a minimum in a Lab like RefactorErl, but if you want to achieve nice result, you should find a bit more time for the project.
Contact person: Melinda Tóth, István Bozó
Contact Information: {toth_m, bozo_i}@inf.elte.hu
14. Quantum computing (not in the video)
Goals, Topics, Used Technologies: Quantum computing: algorithms benefiting from quantum computers; techniques and languages which facilitate programming quantum computers; development of a quantum computer simulator. Linear algebra, Python, C++, GPU/FPGA
Who are we searching for?: Comp.Sci. / Math / Physics students who want to know more about quantum computing, have a solid mathematical background (esp. linear algebra), and are not afraid of programming.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: 8 hours per week
Contact person: Tamás Kozsik
Contact Information: –
15. Artificial Neural Networks and Network Science (not in the video)
Goals, Topics, Used Technologies: The original motivation of Artificial Neural Networks (ANNs) stems from biology: ANNs were modelled on our knowledge (at the time) of human neural networks.
Another important and hot topic of research of the past two decades is network science: the study of real world systems using the mathematical abstraction of a graph (network). An important lesson from network science is that networks from vastly different systems (e.g., biology, social systems, engineering, etc.) have important similarities, many of them share important structural properties and that useful statements can be made about their workings based on lessons learnt from networks from different domains, but with similar structural properties.
Among the many real world networks analyzed by network scientists, one can find works studying the neural networks of living organisms. These works suggest that real neural networks may have special structural properties, not unknown to network science, that may suggest that the network is a result of optimization.
This research connects network science to ANN, analyzing and optimizing the structure of ANNs, informed by network science.
Used technologies: To be discussed. Programming knowledge is essential.
Who are we searching for?: Master students, Students looking for TDK research topics, Students contemplating PhD studies
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: To be discussed. Min. 4 hours a week
Contact person: László Gulyás – Artificial Intelligence Department
Contact Information: lgulyas at inf dot elte dot hu
16. Design and analysis of open adaptive systems of autonomous systems (not in the video)
Goals, Topics, Used Technologies: As a result of the ‘artificial intelligence revolution’ of the last decade, applications optimized for special tasks and learning to solve them with the methods of machine learning (deep learning) are becoming more and more successful. Some of them are so-called autonomous systems that perform their function without direct human control, based on information obtained from its environment, adapting to it.
As a result of the increasingly widespread application, it is inevitable that the areas of operation of autonomous, ‘intelligent’ systems will overlap, thus the ‘interference’ of autonomous systems. This means that other autonomous systems (‘agents’) are part of the operating environment of an autonomous system. In such cases, the two systems naturally affect each other. Especially when the autonomous systems involved are adaptive, ie they modify (learn) their operation based on feedback from their environment. This is the case of social learning, co-evolution, which can lead to interesting but sometimes also to dysfunctional, learning cycles.
In the case of an open system, the number or the types of autonomous systems (agents) found in the system is not known in advance. For example, we do not know what other autonomous vehicles our vehicle will meet, and whether these vehicles are produced by another manufacturers, possibly operating on different principles and serving different purposes. In general, it cannot be guaranteed that the other agent will not violate the conventional rules of the system – due to self-interest, malice or malfunction.
The design and investigation of autonomous systems in such open systems (eg verification of its correctness and robustness) is a difficult but important topic for which the methods and tools of several fields can be informative (eg dynamic systems, certain areas of game theory, auction theory, evolutionary technology, agent-based modeling, multi-agent systems, etc.).
Programming knowledge necessary.
Who are we searching for?: Master Students, Students looking for TDK topics, Students contemplating PhD
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: To be discussed. Min. 4 hours a week
Contact person: László Gulyás – Artificial Intelligence Department
Contact Information: lgulyas at inf dot elte dot hu
17. Feedback self-organisation (not in the video)
Goals, Topics, Used Technologies: Feedback is an essential tool for the stability of dynamical systems and for self-regulation in general. This is true for different man-made engineering systems as well as for different (dynamically) stable systems in the physical world, including biological populations (e.g., food webs of species feeding on each other). However, how the spontaneous, self-organizing development of feedback may result in stable systems is still an open question. Exploring and examining this can be an important new tool for the development of autonomous, adaptive systems.
The fundamental problem is that a single feedback alone either strengthens (positive feedback) or weakens (negative feedback) the process. These, although in opposite directions, are the same in that in the absence of other factors, e.g. other feedbacks, they both lead to exponential change, and thus to the collapse and exhaustion of the system. Thus, feedback cannot appear on its own in a self-organizing (learning or evolving) system. In fact, non-equilibrium (at least in the sense of a dynamic equilibrium) states can only be transient: self-organization must take place successfully before the imbalance leads to the collapse of the system.
In the current, first phase of the research, we will deal with evolutionary technology among the possible forms of self-organization. We will examine the possibilities for creating stable, self-organizing feedbacks using evolutionary methods. In doing so, it is also important to understand the theoretical and practical problems that stand in the way of successful self-organization.
Who are we searching for?: Master students. Students looking for TDK topics. Students contemplating Phd.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: To be discussed. Min. 4 hours a week
Contact person: László Gulyás – Artificial Intelligence Department
Contact Information: lgulyas at inf dot elte dot hu
18. Robot Soccer (not in the video)
Goals, Topics, Used Technologies: Robot Soccer (RoboCupSoccer Simulation, https://www.robocup.org/leagues/23, https://ssim.robocup.org/)
RoboCup is an international scientific initiative with the goal to advance the state of the art of intelligent robots. To fulfill this goal RoboCup proposed several different competitions (leagues) in different domains. The RoboCup Soccer Simulation League (SSim) is one of the oldest leagues, focusing on artificial intelligence and team strategy. Independently moving software players (agents) play soccer on a virtual field inside a computer.
There are 2 subleagues: 2D and 3D.
Our long term goal is to build the competences (team of students and researchers) necessary to participate in the regular international RoboSoccer Simulation competitions. We are currently at the first steps, setting up the team and infrastructure. Be prepared for intense learning, strategizing, but also for a lot of configuration tasks.
Who are we searching for?: BSc students. Master students.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: To be discussed. Min. 4 hours a week
Contact person: László Gulyás – Artificial Intelligence Department
Contact Information: lgulyas at inf dot elte dot hu
19. Task Management System (TMS) (not in the video)
Goals, Topics, Used Technologies: The aim of the project is the development of the Task Management System (TMS), an open source web-based assignment and examination management system for universities, primarily focused on programming and computer science related courses. The main features of the application are the integrated evaluation, automatized testing, version control and plagiarism check of the student submissions. TMS also integrates with the Canvas LMS.
Used technologies: Backend: REST, MVC, ORM, PHP, Yii, Docker
Frontend: TypeScript, React
Who are we searching for?: Students who already completed the Software Technology course in their BSc training and have knowledge, experience (or at least interest) in web technologies and the mentioned programming languages.
Is it open for students of the Campus of Szombathely?: Yes
How much time a student needs to contribute: 8 hours / week
Contact person: Máté Cserép
Contact Information: mcserep at inf dot elte dot hu, https://mcserep.web.elte.hu/site/projects
20. Geoinformatics and Remote Sensing Laboratory (not in the video)
Goals, Topics, Used Technologies: Use cases of geoinformatics and remote sensing range widely nowadays from classical carthopgraphic applications through the agricultural industry, civil engineering and urban planning to environmental use cases. Most recently navigation of autonomous systems and augmented reality applications highly depend on spatial and remote sensing sensors and algorithms. The evolution and spreading of data capturing methods ranging from simple GPS devices like smart-phones to large scale imaging equipment – including very high resolution and hyperspectral cameras and LiDAR – resulted in an exponential growth in the amount of spatial data maintained by companies and organizations. At the same time methods for extracting information efficiently from such datasets raise challenges from a computer science aspect.
Current topics in the laboratory are focused on object recognition, change detection, model reconstruction and classification based on 3D LiDAR point clouds and multispectral aerial and satellite imagery.
Used technologies: LiDAR, point clouds, digital elevation models, PCL, PDAL, GDAL, OpenCV
Who are we searching for?: MSc or PhD students with programming competence mainly in C++ and/or C#. Specialized knowledge on remote sensing technologies and algorithms are not mandatory beforehand, but completing the relevant courses in the MSc programme is a benefit.
MSc students can also register for the Software Technology Lab course (group: 4) and gain credits for participating in the research and development.
Is it open for students of the Campus of Szombathely?: No
How much time a student needs to contribute: 8-10 hours / week
Contact Information Contact person: Máté Cserép
Contact Information: mcserep at inf dot elte dot hu, https://mcserep.web.elte.hu/site/projects