Ideas for Student Projects

Optimization, Artificial Intelligence, Data Science

1. API specification for Optimization Heuristics. Implies:
   • implementation of the specification in a programming language
   • development of at least three user cases, that is, problems eg, simple cases of routing, scheduling, and timetabling
   • implementation of known metaheuristics for these three cases using the specification if time advances: multiobjectives

2. Student Project Assignment with two-sided preferences. Related to the stable marriage problem. Extension of an existing tool that consider preferences only from the side of the students.

3. Peptide design via Active Learning (ML + Optimization): design of cell-penetrating peptides or anti-microbial with desirable properties.
   • Create machine learning model of the biological effectiveness of the siRNA encapsulated in the peptides on the basis of properties like: combinations of parts, fold propensity, disorder, sequence entropy, beta-strand propensity, etc.
   • Find optimal sequence for the model and use that sequence for the next test in the lab
   • Update the machine learning model on the basis of the new results and iterate.

4. Corridor railway optimization for an Italian company with data from a project in Portugal. Optimize the infrastructure interventions aimed at diminishing running times in the corridor by a desired margin while minimizing impact and costs.

5. Capacity Expansion in Energy Production in collaboration with Energinet. Large scale optimization for long term decision making, which plants is best to construct and where, which energy source is likely to give the best performance of the overall system? The optimization problem includes both discrete and continuous variables as well as uncertainty issues.

6. Transport Optimization. Bus line planning and/or estimation of origin destination demand with data from the city of Odense.

7. Bus Map Drawing

8. Vehicle routing

9. Arc routing: applications in salt spreading, garbage collection and unmanned aerial vehicles (UAV, drones) task planning

10. Student sectioning. Starting material: Mads’ speciale, articles.

11. Course Timetabling: exact algorithms (max sat, cp, milp) or black box heuristic solvers

12. Multiple objective solvers for timetabling

13. Exam timetabling: exact algorithms (max sat, cp, milp) or black box heuristic solvers.

14. Fairness in Timetabling. See talk by John Hookoer or tutorial or report

15. Handling preferences in timtabling: collection, elicitation, aggregation, handling in solvers

16. Timetabling: verification and explanation

17. Course timetabling:
    • visualization of room availability integrating with existing system
    • solution post analysis

18. Aiding tools to timetabling construction: interactive optimization (human in the loop)

19. Conversational AI for timetabling (course and exams) requests.

20. Group formation: Heterogeneous within and homogeneous between with or-tools

21. Instructor assignment: matching under preferences with constraints

22. Optimize Binary Neural Networks by heuristics.

23. Optimization in the energy sector (with Energinet)

24. Optimization in film production to reduce CO2 emissions.

25. Comparison of local search solvers: local solver, paradiseo, oscar

26. General Local Search Solver Development. Constraint Based Local Search.

27. Heuristics: black box API, design, implementation, comparison

28. Nurse scheduling

29. Automatic Algorithm Configuration (with Jacopo Mauro)

30. AI for Good

31. Artificial Intelligence for Computational Sustainability

32. Postnord. Daily demand prediction or Route optimization or 3D vehicle packing. Contact and discuss.

33. Predictive maintanance at Sanovo or other companies.

34. Image processing: Dexterity test assessment in children. Automatically assess the goodness of line drawed by children.

35. Design and development of an AI agent for tango deejaying. The selection of songs and their sequence played at milongas (tango events) follow a certain structure, they are grouped in tandas of 4 songs each and must fit well with each others. The task is to extract automatically information from songs and design and implement an AI agent that pleases the dancer on the floor.

36. Traffic Data Analysis and Human Mobility. Data sources:
    • Odense Kommune data. Sensor locations.
    • RejseKort data.
    • Styrelsen for Dataforsyning og Infrastruktur.
    • Human mobility data.
    • Rejseplanen Labs.
    • General Transit Feed Specification (GTFS) Open research questions, the student must contribute to their definitions.

37. Sport analytics: analysis of soccer data in collaboration with DBU and SDU Idræt Institute. Data available: Tracking (25 data per second) + event data: data preparation, alignment, search, pattern mining.

38. Develop an optimization game for educational purposes. The problem could be portfolio optimization or timetabling or others. See beer game and burrito game at Gurobi for examples.

39. Automating carbon footprint calculations in film scripting using large language models.

40. Topics in Flight Planning in collaboration with ForeFlight. Examples:
    • Using computer vision on satellite imagery to detect anomalies in runway data
    • Using computer vision on satellite imagery to detect obstacles
    • Using LiDAR data + AI for obstacle extraction and data verification
    • Extracting meta information and data from airplane flight manual charts

41. App development for web or smartphones

42. LLM for report classification and annotation