{"id":7008,"date":"2026-05-18T13:50:05","date_gmt":"2026-05-18T13:50:05","guid":{"rendered":"http:\/\/pstknu.local\/academics\/master\/thesis-topics\/"},"modified":"2026-08-05T15:07:00","modified_gmt":"2026-08-05T12:07:00","slug":"thesis-topics","status":"publish","type":"page","link":"https:\/\/pst.knu.ua\/en\/academics\/master\/thesis-topics\/","title":{"rendered":"Topics of thesis \u2014 Master"},"content":{"rendered":"<p style=\"font-size:17px;line-height:1.65;\">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.<\/p>\n<style>\n.tbs-wrapper { margin: 24px 0; }\n.tbs-group { background:#fff; border:1px solid #e6e3dd; border-radius:8px; padding:20px 24px; margin-bottom:18px; }\n.tbs-supervisor { display:flex; align-items:center; gap:16px; margin-bottom:14px; padding-bottom:14px; border-bottom:1px solid #f0ede5; }\n.tbs-photo { width:72px; height:72px; border-radius:50%; overflow:hidden; background:#fafaf7; flex-shrink:0; display:flex; align-items:center; justify-content:center; }\n.tbs-photo img { width:100%; height:100%; object-fit:cover; }\n.tbs-name { font-family:\"Fraunces\",Georgia,serif; font-size:18px; color:#0c0c0c; font-weight:600; margin:0 0 4px; }\n.tbs-count { font-size:13px; color:#888; font-family:\"JetBrains Mono\",monospace; }\n.tbs-topic { padding:10px 0; border-bottom:1px solid #f0ede5; }\n.tbs-topic:last-child { border-bottom:0; }\n.tbs-topic-title { font-weight:600; color:#0c0c0c; font-size:14.5px; }\n.tbs-topic-desc { font-size:13.5px; color:#666; margin-top:4px; line-height:1.55; }\n.tbs-topic-tags { display:inline-block; font-size:12px; color:#666; margin-top:6px; padding:3px 9px; background:#fafaf7; border-radius:4px; font-family:\"JetBrains Mono\",monospace; }\n.tbs-orphan-title { color:#b85c00 !important; }\n<\/style><div class=\"tbs-wrapper\"><div class=\"tbs-group\"><div class=\"tbs-supervisor\"><div class=\"tbs-photo\"><svg width=\"40\" height=\"40\" viewbox=\"0 0 24 24\" fill=\"#d0cbc0\"><path d=\"M12 12c2.21 0 4-1.79 4-4s-1.79-4-4-4-4 1.79-4 4 1.79 4 4 4zm0 2c-2.67 0-8 1.34-8 4v2h16v-2c0-2.66-5.33-4-8-4z\"\/><\/svg><\/div><div><h3 class=\"tbs-name\"><a href=\"https:\/\/pst.knu.ua\/en\/staff\/bychkov-oleksii\/\" style=\"text-decoration:none;color:inherit;\">Bychkov Oleksii Serhiiovych<\/a><\/h3><div class=\"tbs-count\">12 topics<\/div><\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">(PN) - expansion of the HTN scheduler for a swarm of UAVs with epistemically incompatible prerequisites<\/div><div class=\"tbs-topic-desc\"><p>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.<\/p>\n<\/div><div class=\"tbs-topic-tags\">HTN, planning, (PN)-models<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">FocusedQuestionSelector v3.0: Implementation (PN) -calibrationof specificity bonuses and testing on the medical corps<\/div><div class=\"tbs-topic-desc\"><p>Finalization of the Question Engine module of the Dr.Case system (v2.0). Replacement of empirical bonuses \u00d710\/\u00d75\/\u00d72 with calibrated ones from the theory of possibilities. Experimental evaluation of improvement of diagnostic metrics.<\/p>\n<\/div><div class=\"tbs-topic-tags\">Question Engine, (PN), Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Dr.Case NLP module with medical jargon support and Ukrainian medical NER<\/div><div class=\"tbs-topic-desc\"><p>Extension of the current Dr.Case NLP module (\u2265100 synonyms) to a full-fledged NER for medical terms in Ukrainian. Fine-tuning XLM-RoBERTa or UkrLaBSE. Integration with symptom_extractor.<\/p>\n<\/div><div class=\"tbs-topic-tags\">NLP, NER, Ukrainian, Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Web application of the medical consilium based on the multi-agent Dr.Case architecture<\/div><div class=\"tbs-topic-desc\"><p>Frontend on React\/Next.js to conduct a consultation: the doctor introduces the case \u2192 specialist agents issue a hypothesis \u2192 visualization agreement \u2192 final conclusion. WebSocket for real-time updates.<\/p>\n<\/div><div class=\"tbs-topic-tags\">Web app, React, multi-agent<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Dr.Case mobile client for the work of a field medic with offline diagnostics<\/div><div class=\"tbs-topic-desc\"><p>Development of iOS\/Android application with built-in Dr.Case model (model &lt; 50 MB via quantization). Synchronization with the server when reconnecting. Ukrainian localization.\n<\/p>\n<\/div><div class=\"tbs-topic-tags\">Mobile, offline, Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Dr.Case multi-agent architecture with a consilium of specialized diagnostic agents<\/div><div class=\"tbs-topic-desc\"><p>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.<\/p>\n<\/div><div class=\"tbs-topic-tags\">Multi-agent, Dr.Case, MAS<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Multi-agent reinforcement training (MADDPG\/QMIX) to coordinate a group of Dr.Case-agents<\/div><div class=\"tbs-topic-desc\"><p>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.<\/p>\n<\/div><div class=\"tbs-topic-tags\">MARL, MADDPG, Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Software module for analyzing chest radiographs and its integration into Dr.Case<\/div><div class=\"tbs-topic-desc\"><p>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).<\/p>\n<\/div><div class=\"tbs-topic-tags\">X-ray analysis, CNN, Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Prototype of an epistemic-resistant consensus protocol for the UAV swarm mobile network<\/div><div class=\"tbs-topic-desc\"><p>Implementation of a PBFT\/Raft variant adapted to high mobility and partial channel losses. Experimental study in NS-3 or ROS 2 simulator.<\/p>\n<\/div><div class=\"tbs-topic-tags\">Consensus, MANET, BFT<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Prototype of a cooperative SLAM for a heterogeneous swarm of UAVs in the Gazebo simulator<\/div><div class=\"tbs-topic-desc\"><p>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.<\/p>\n<\/div><div class=\"tbs-topic-tags\">SLAM, multi-robot, Gazebo<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">BayesianAnswerProcessor implementation with likelihood calibration on real clinical data<\/div><div class=\"tbs-topic-desc\"><p>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).<\/p>\n<\/div><div class=\"tbs-topic-tags\">Bayesian, calibration, Dr.Case<\/div><\/div><div class=\"tbs-topic\"><div class=\"tbs-topic-title\">Implementation of the complete blood count module in Dr.Case with uncertainty assessment<\/div><div class=\"tbs-topic-desc\"><p>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.<\/p>\n<\/div><div class=\"tbs-topic-tags\">Blood analysis, CBC, BNN<\/div><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>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.<\/p>","protected":false},"author":1,"featured_media":0,"parent":7002,"menu_order":5,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-7008","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/pages\/7008","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/comments?post=7008"}],"version-history":[{"count":1,"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/pages\/7008\/revisions"}],"predecessor-version":[{"id":7629,"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/pages\/7008\/revisions\/7629"}],"up":[{"embeddable":true,"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/pages\/7002"}],"wp:attachment":[{"href":"https:\/\/pst.knu.ua\/en\/wp-json\/wp\/v2\/media?parent=7008"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}