UNI› F05›
Taras Shevchenko National University of Kyiv · Faculty of Information Technologies

Department of Software Systems and Technologies

Department of Software Systems and Technologies

The list of topical topics of thesis topics is Master's degree. Topics are grouped by supervisors. The student can choose the proposed topic or agree his own with the supervisor.

(PN) - expansion of the HTN scheduler for a swarm of UAVs with epistemically incompatible prerequisites

Implementation of the scheduler based on the Pyhop/SHOP2 library with support for (PN)prerequisites. Integration with swarm simulator. Experiments in scenarios with conflicting information from different agents.

HTN, planning, (PN)-models
FocusedQuestionSelector v3.0: Implementation (PN) -calibrationof specificity bonuses and testing on the medical corps

Finalization of the Question Engine module of the Dr.Case system (v2.0). Replacement of empirical bonuses ×10/×5/×2 with calibrated ones from the theory of possibilities. Experimental evaluation of improvement of diagnostic metrics.

Question Engine, (PN), Dr.Case
Dr.Case NLP module with medical jargon support and Ukrainian medical NER

Extension of the current Dr.Case NLP module (≥100 synonyms) to a full-fledged NER for medical terms in Ukrainian. Fine-tuning XLM-RoBERTa or UkrLaBSE. Integration with symptom_extractor.

NLP, NER, Ukrainian, Dr.Case
Web application of the medical consilium based on the multi-agent Dr.Case architecture

Frontend on React/Next.js to conduct a consultation: the doctor introduces the case → specialist agents issue a hypothesis → visualization agreement → final conclusion. WebSocket for real-time updates.

Web app, React, multi-agent
Dr.Case mobile client for the work of a field medic with offline diagnostics

Development of iOS/Android application with built-in Dr.Case model (model < 50 MB via quantization). Synchronization with the server when reconnecting. Ukrainian localization.

Mobile, offline, Dr.Case
Dr.Case multi-agent architecture with a consilium of specialized diagnostic agents

Development of a prototype of a multi-agent version of Dr.Case: specialist agents (therapist, cardiologist, neurologist) exchange hypotheses and agree on the diagnosis. Implementation of a negotiation protocol based on (PN)models.

Multi-agent, Dr.Case, Mas
Multi-agent reinforcement training (MADDPG/QMIX) to coordinate a group of Dr.Case-agents

A prototype implementation of multi-agent RL for distributed diagnostics, where agents cooperatively decide to whom to ask a clarifying question. Experiments on a synthetic case.

Marl, MADDPG, Dr.Case
Software module for analyzing chest radiographs and its integration into Dr.Case

Implementation of CNN based on transfer learning (ResNet/DenseNet) for the detection of pneumonia, tuberculosis and neoplasms on radiographs. Probability calibration. rest integration with Dr.Case as the 19th module. Experimental evaluation on public datasets (CheXpert, NIH ChestX-ray14).

X-ray analysis, CNN, Dr.Case
Prototype of an epistemic-resistant consensus protocol for the UAV swarm mobile network

Implementation of a PBFT/Raft variant adapted to high mobility and partial channel losses. Experimental study in NS-3 or ROS 2 simulator.

Consensus, Manet, Bft
Prototype of a cooperative SLAM for a heterogeneous swarm of UAVs in the Gazebo simulator

Development of a system for simultaneous localization and mapping for a group of UAVs with different sensors. Experimental assessment of accuracy in environments without satellite navigation.

SLAM, multi-robot, Gazebo
BayesianAnswerProcessor implementation with likelihood calibration on real clinical data

Finalization of the v2.0 module of the Dr.Case system with the replacement of heuristic likelihoods (0.90/0.10/0 .80/0.20, etc.) with calibrated ones according to the data. Experiments with ELC (Expected Likelihood Calibration).

Bayesian, calibration, Dr.Case
Implementation of the complete blood count module in Dr.Case with uncertainty assessment

Development of an ML model for the interpretation of CBC (leukocytes, erythrocytes, platelets, hemoglobin) with the detection of pathognomonic combinations. Integration as a Dr.Case module. Bayesian neural networks to assess uncertainty.

Blood analysis, CBC, BNN