[
  {
    "title": "Schema Inference for NoSQL Databases",
    "type": "Master Thesis",
    "submitted": "2021",
    "keywords": [
      "Schema inference",
      "NoSQL databases",
      "Document-based data stores",
      "JSON"
    ],
    "abstract": "NoSQL databases are becoming increasingly more popular due to their undeniable advantages in the context of storing and processing big data, mainly horizontal scalability and the lack of a requirement to define a data schema upfront. In the absence of explicit schema, however, an implicit schema inherent to the stored data still exists and can be inferred. Once inferred, a schema is of great value to the stakeholders and database maintainers. Nevertheless, the problem of schema inference is non-trivial and is still the subject of ongoing research. We explore the many aspects of NoSQL schema inference and data modeling, analyze a number of existing schema inference solutions in terms of their inner workings and capabilities, point out their shortcomings, and devise (1) a novel horizontally scalable approach based on the Apache Spark platform and (2) a new NoSQL Schema metamodel capable of modeling i.a. inter-entity referential relation- ships and deeply nested JSON constructs. We then experimentally evaluate the newly designed approach along with the preexisting solutions with respect to their functional and performance capabilities.",
    "assignment": "Many NoSQL database management systems do not require an explicit schema for the data they store. Nevertheless, application developers must maintain at least the so-called implicit schema. In certain situations, however, the presence of an explicit schema is still necessary, and so it makes sense to propose methods capable of schema inference just from the structure of the available data. Although many schema inference algorithms have already been proposed, they suffer from various drawbacks. The author first performs an analysis and comparison of selected existing approaches, in particular for JSON document-oriented NoSQL databases. Based on it, a novel approach will be proposed and its prototype implementation then experimentally compared with respect to the selected approaches.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=229611",
    "reviewer": "Martin Svoboda",
    "status": "defended",
    "id": "thesis-01",
    "student": "Ivan Veinhardt Latták",
    "dspace_handle": "20.500.11956/148825",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/148825",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/148825/120396893.pdf?sequence=1&isAllowed=y",
    "grade": 1,
    "dspace": {
      "handle": "20.500.11956/148825",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/148825",
      "sis_id": "229611",
      "defense_date": "13. 9. 2021",
      "grade_raw": "Výborně",
      "grade": "A",
      "reviewer": "Martin Svoboda"
    },
    "defense_date": "13.09.2021",
    "repository_grade": "Výborně",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "229611",
      "issue_academic_year": "2020/2021",
      "assignment_date": "16.10.2020",
      "raw_status": "obhájená, odevzdaná, finalizovaná",
      "scheduled_defense": "13.09.2021 09:00",
      "defense_academic_year": "2020/2021"
    }
  },
  {
    "title": "Experimental Analysis of Query Languages in Modern Database Systems",
    "type": "Bachelor Thesis",
    "submitted": "2024",
    "abstract": "The rise of Big Data has highlighted the limitations of relational databases while handling large datasets, leading to the growth of NoSQL databases. This has made DBMS benchmarking crucial for performance evaluation and decision-making. This thesis compares relational (MySQL, SQLite), graph (Neo4j, ArangoDB), docu- ment (MongoDB), and column-family (Cassandra) databases. We analyze the expressive power of their query languages and their runtime efficiency across varying data sizes. We conclude, that there's no \"number one\" solution for all use cases. The choice depends on factors like data volume, query complexity, and the need for joins. For complex queries and frequent joins, MySQL and SQLite are the most expressive but may struggle with very large datasets. Cassandra and MongoDB excel in perfor- mance and scalability but require efficient schema design and targeted data redundancy. ArangoDB presents a versatile option capable of handling multiple data models but might require further investigation into its performance compared to Neo4j.",
    "assignment": "NoSQL and multi-model systems represent so-called variety of big data, i.e., enables to represent data in different (or combined) logical models and formats. In addition to the relational model, we also distinguish, e.g., hierarchical (document) and graph data, hence the scope and efficiency of querying over these representations differ. The goal of this thesis is to focus only on various data (e.g., document, column, graph, relational) and to compare typical query languages for these data in terms of expressive power and run-time efficiency, taking into account scalability with varying number of stored data. The student first analyzes the current state of knowledge. Then, he/she selects 6-8 candidates for comparison and statically compares the expressive power of the supported query languages. Next, based on the static comparison, the student will propose query scenarios and perform dynamic query comparison over the selected database systems using the proposed queries. Finally, the student will suggest appropriate recommendations or discuss open questions and challenges in querying over various data.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=254987",
    "reviewer": "doc. Irena Holubová, Ph.D.",
    "status": "defended",
    "id": "thesis-02",
    "student": "Martin Čorovčák",
    "dspace_handle": "20.500.11956/192088",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/192088",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/192088/130389873.pdf?sequence=1&isAllowed=y",
    "grade": 1,
    "dspace": {
      "handle": "20.500.11956/192088",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/192088",
      "sis_id": "254987",
      "defense_date": "28. 6. 2024",
      "grade_raw": "Výborně",
      "grade": "A"
    },
    "defense_date": "28.06.2024",
    "repository_grade": "Výborně",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "254987",
      "issue_academic_year": "2023/2024",
      "assignment_date": "29.10.2023",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "28.06.2024 09:00",
      "defense_academic_year": "2023/2024"
    }
  },
  {
    "title": "Experimental Analysis of Querying in Modern Database Systems",
    "type": "Bachelor Thesis",
    "submitted": "2024",
    "assignment": "NoSQL and multi-model systems represent so-called variety of big data, i.e., enables to represent data in different (or combined) logical models and formats. In addition to the relational model, we also distinguish, e.g., hierarchical (document) and graph data, hence the scope and efficiency of querying over these representations differ. The goal of this thesis is to focus on various data (e.g., relational, graph, document, columnar, and array data) and to compare typical query languages for these data in terms of expressive power and run-time efficiency, taking into account scalability with varying number of stored data. The student first analyzes the current state of knowledge. Then, he/she selects 6-8 candidates for comparison and statically compares the expressive power of the supported query languages. Next, based on the static comparison, the student will propose query scenarios and perform dynamic query comparison over the selected database systems using the proposed queries. Finally, the student will suggest appropriate recommendations or discuss open questions and challenges in querying over various data.",
    "abstract": "In today's landscape, with a multitude of available database systems, it is often hard to choose which one would fit our needs best. In this thesis we focus on choosing a performant database system from a choice between PostgreSQL, Virtuoso, OrientDB, ScyllaDB, Couchbase, and RavenDB. We compare the static properties and features of said database systems, and we include a brief discussion on data extraction and trans- formation, for which we developed a helper library for Python. We then assess dataset import times into each database system. To determine the most efficient database, we measure query performance across multiple dataset sizes, and finally we offer a recom- mendation based on the results, and discuss further possible considerations.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=254988",
    "reviewer": "Irena Holubová",
    "status": "defended",
    "id": "thesis-03",
    "student": "Ondřej Zálešák",
    "dspace_handle": "20.500.11956/192942",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/192942",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/192942/130401808.pdf?sequence=1&isAllowed=y",
    "grade": 2,
    "dspace": {
      "handle": "20.500.11956/192942",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/192942",
      "sis_id": "254988",
      "defense_date": "5. 9. 2024",
      "grade_raw": "Velmi dobře",
      "grade": "B",
      "reviewer": "Irena Holubová",
      "language": "English",
      "keywords_en": [
        "database systems comparison",
        "data integration",
        "query expressiveness",
        "query performance"
      ]
    },
    "defense_date": "05.09.2024",
    "repository_grade": "Velmi dobře",
    "keywords": [
      "database systems comparison",
      "data integration",
      "query expressiveness",
      "query performance"
    ],
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "254988",
      "issue_academic_year": "2023/2024",
      "assignment_date": "27.10.2023",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "05.09.2024 09:00",
      "defense_academic_year": "2023/2024"
    }
  },
  {
    "title": "A Universal Approach for Anomaly Detection in Log Files",
    "type": "Master Thesis",
    "submitted": "2023",
    "keywords": [
      "anomaly detection",
      "log",
      "network topology",
      "machine learning"
    ],
    "assignment": "There exist a variety of methods to find abnormalities in datasets, whether based on expert models, AI rules, genetic algorithms, etc. However, these solutions are often customized to a particular problem and the general applicability is very limited. A challenging problem is to identify a method that will be suitable for a specific problem. Moreover, if a candidate method is found, it still has to be tuned to the specific problem. The author first performs an analysis and comparison of selected existing methods, e.g., over one or two selected datasets. Based on this, he/she proposes a set of rules to guide the selection of a suitable method to address a particular problem. Finally, the author will implement a prototype that will experimentally validate the set of rules on one or two selected problems.",
    "abstract": "The goal of this thesis is to propose a solution for universal anomaly detection in log files. This thesis first provides theoretical background and overview of related work. Se- lected approaches are then extensively evaluated on multiple data sets. Based on results of evaluation, solution prototype is proposed. This prototype consists of modules respon- sible for detecting different anomaly types. To be specific, anomalous error sequences, anomalous occurrence of log parameters and network topology change can be detected. The error sequence detector integrates selected existing approaches and parameter de- tector utilizes own method based on log parsing and parameter count vector creation. Furthermore, the network topology change detector implements novel minimum span- ning tree based algorithm. Finally, improved log parser that is able to parse logs from different systems and formats is proposed to ensure universality across systems.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=249581",
    "reviewer": "Martin Pilát",
    "status": "defended",
    "id": "thesis-04",
    "student": "Radovan Tomala",
    "dspace_handle": "20.500.11956/181941",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/181941",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/181941/120444695.pdf?sequence=1&isAllowed=y",
    "grade": 1,
    "dspace": {
      "handle": "20.500.11956/181941",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/181941",
      "sis_id": "249581",
      "defense_date": "12. 6. 2023",
      "grade_raw": "Výborně",
      "grade": "A",
      "reviewer": "Martin Pilát",
      "language": "English"
    },
    "defense_date": "12.06.2023",
    "repository_grade": "Výborně",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "249581",
      "issue_academic_year": "2022/2023",
      "assignment_date": "01.09.2022",
      "raw_status": "obhájená, odevzdaná, finalizovaná",
      "scheduled_defense": "12.06.2023 09:00",
      "defense_academic_year": "2022/2023"
    }
  },
  {
    "title": "Nástroj pre konceptuálne modelovanie multi-modelových dát",
    "type": "Bachelor Thesis",
    "submitted": "2023",
    "keywords": [
      "multi-model data",
      "conceptual modeling",
      "CAT",
      "UML"
    ],
    "assignment": "V rámci GAČR projektu Unified Management of Multi-Model Data (č.20-22276S) byl navržen nástroj pro modelování multi-modelových dat. Reprezentace multi-model konceptuálního schématu je založena na teorii kategorií – pro tyto účely byla definována schématická kategorie, jejíž vlastnosti umožňují nahlížet na data v libovolném modelu jako na multigraf. Pro účely zjednodušení pochopení kategorické reprezentace byl navíc navržen pomocný algoritmus pro transformaci klasického ER schématu do schématické kategorie. Cílem tohoto projektu je rozšíření základní funkcionality nástroje MM-cat o modelování schématu jako diagram tříd UML, návrh algoritmu pro převod mezi diagramem tříd a schématickou kategorií a v rámci navazující bakalářské práce implementaci tohoto algoritmu. Výsledkem by měl být uživatelsky přívětivý nástroj, který umožňuje modelování konceptuálního schématu pomocí jazyků UML a CAT a který dále umožňuje překlady těchto schémat.",
    "abstract": "The aim of the bachelor's thesis is to create a tool that supports modeling in the UML and the newly created categorical model (CAT), as well as transla- tion from UML model to CAT model. Thesis contains basic description of UML and CAT, research of popular tools for modeling, programming and user docu- mentation. The appendices contains tests, design pattern and sequence diagrams of selected methods. The outcome of the thesis is functional, user friendly tool available on the Windows operating system. The advantages of the tool are for ex- ample possibility to change grafic properties of objects, save and load file in JSON format or open multiple canvases in one tool window.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=249078",
    "reviewer": "Mgr. Štěpán Stenchlák",
    "status": "defended",
    "id": "thesis-05",
    "student": "Richard Hvizdoš",
    "dspace_handle": "20.500.11956/184453",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/184453",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/184453/130359275.pdf?sequence=1&isAllowed=y",
    "dspace": {
      "handle": "20.500.11956/184453",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/184453",
      "sis_id": "249078",
      "defense_date": "7. 9. 2023",
      "language": "Slovak"
    },
    "defense_date": "07.09.2023",
    "curated_title": "A tool for conceptual modelling of multi-model data",
    "sis": {
      "id": "249078",
      "issue_academic_year": "2022/2023",
      "assignment_date": "19.07.2022",
      "raw_status": "obhájená, odevzdaná, finalizovaná",
      "scheduled_defense": "07.09.2023 09:00",
      "defense_academic_year": "2022/2023"
    },
    "grade": 1,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "A tool for querying multi-model data",
    "type": "Bachelor Thesis",
    "submitted": "2023",
    "keywords": [
      "Multi-Model Data",
      "Graphical Querying",
      "Query by Example",
      "Neo4j",
      "Novice Users"
    ],
    "assignment": "V rámci GAČR projektu Unified Management of Multi-Model Data (č.20-22276S) byl navržen framework MM-cat pro správu multi-modelových dat. Reprezentace multi-model konceptuálního schématu je založena na teorii kategorií – pro tyto účely byla definována schématická kategorie, jejíž vlastnosti umožňují nahlížet na multi-modelová data jako na multigraf. Pro účely zjednodušení pochopení kategorické reprezentace byl navíc navržen pomocný algoritmus pro transformaci klasického ER schématu do schématické kategorie. Cílem tohoto projektu je rozšíření základní funkcionality frameworku MM-cat o dotazování se nad kategorickou reprezentací multi-modelových dat. Za tímto účelem bude navržen a experimentálně ověřen jednoduchý grafický dotazovací jazyk. Výsledkem by měl být uživatelsky přívětivý nástroj, který umožňuje dotazování se nad multi-modelovými daty, které jsou reprezentovány pomocí teorie kategorií a pro potřeby prototypu uloženy v grafové databázi Neo4j (tj. využijeme grafové reprezentace schématické a instanční kategorie).",
    "abstract": "Querying over multi-model data is a challenging task even for expert users, as they typically need to master a number of query languages and be aware of the logical repre- sentation of the data. In this thesis, we propose a graphical query language over multi-model data and im- plement it in the form of a prototype application. The proposed query language primarily targets less experienced users, aiming at simple querying over data with only knowledge of its structure. The work includes an attached prototype that represents the data using a categorical representation strikingly similar to a graph. We take advantage of this simi- larity and therefore store the data in the Neo4j graph database. For proof of concept, we translate our proposed language into Cypher and transitively query over the multi-model data stored using the categorical representation in Neo4j.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=249079",
    "reviewer": "Jáchym Bártík",
    "status": "defended",
    "id": "thesis-06",
    "student": "Artem Bakhtin",
    "dspace_handle": "20.500.11956/183089",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/183089",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/183089/130360258.pdf?sequence=1&isAllowed=y",
    "grade": 2,
    "dspace": {
      "handle": "20.500.11956/183089",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/183089",
      "sis_id": "249079",
      "defense_date": "29. 6. 2023",
      "grade_raw": "Velmi dobře",
      "grade": "B",
      "reviewer": "Jáchym Bártík"
    },
    "defense_date": "29.06.2023",
    "repository_grade": "Velmi dobře",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "249079",
      "issue_academic_year": "2022/2023",
      "assignment_date": "21.07.2022",
      "raw_status": "obhájená, odevzdaná, finalizovaná",
      "scheduled_defense": "29.06.2023 09:00",
      "defense_academic_year": "2022/2023"
    }
  },
  {
    "title": "Aplikace metod umělé inteligence pro zlepšení úložné strategie v multi-modelových databázových systémech: Přehled",
    "type": "Bachelor Thesis",
    "submitted": "2023",
    "keywords": [
      "Multi-Model Data",
      "Index Selection",
      "Database Management Systems",
      "Reinforcement Learning",
      "Survey"
    ],
    "assignment": "Multi-Model database systems combine the advantages of traditional and NoSQL database systems. However, the management of these systems is challenging for users, as users have to design an appropriate storage strategy considering (1) the volume and variety of data to be processed and (2) typical user requirements, which include, e.g., sharing or querying over the data. The aim of this bachelor thesis is to analyze the current state-of-the-art in the application of AI (e.g., machine learning, clustering) and other methods for DBMS management and to verify the applicability of the selected approaches to multi-model data. The author will mainly focus on approaches that optimize the storage strategy taking into account the user requirements for manipulating the data. The output of the thesis will be a survey and comparison of the selected methods, including a discussion of theirs applicability to multi-model data.",
    "abstract": "Multi-Model database systems combine the advantages of traditional and NoSQL database systems. However, the management of these systems is challenging, as users have to design an appropriate storage strategy for their data. One of the most influential factors in the storage strategy is the selection of indexes. Indexes can significantly improve query performance, but they require additional storage space and maintenance overhead. Index selection problem is well-studied in the context of single-model Database Management Systems (DBMSs), but there is a lack of research in the context of multi-model database systems. We address this problem by conducting a survey of current state-of-the-art index selection algorithms and evaluating their applicability to other DBMSs. The results reveal the strengths and weaknesses of existing algorithms and highlight the need for specialized algorithms for multi-model database systems. Moreover, we formulate open questions and suggest future research directions in this field. Our research provides a foundation for the development of efficient index selection algorithms for multi-model DBMSs.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=256787",
    "reviewer": "Irena Holubová",
    "status": "defended",
    "id": "thesis-07",
    "student": "Filip Miháľ",
    "dspace_handle": "20.500.11956/183075",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/183075",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/183075/130359430.pdf?sequence=1&isAllowed=y",
    "dspace": {
      "handle": "20.500.11956/183075",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/183075",
      "sis_id": "256787",
      "defense_date": "29. 6. 2023",
      "reviewer": "Irena Holubová",
      "consultant": "Jáchym Bártík",
      "language": "Czech"
    },
    "defense_date": "29.06.2023",
    "curated_title": "An application of AI methods for refining the storage strategy in multi-model database systems: A survey",
    "sis": {
      "id": "256787",
      "issue_academic_year": "2022/2023",
      "assignment_date": "15.02.2023",
      "raw_status": "obhájená, odevzdaná, finalizovaná",
      "scheduled_defense": "29.06.2023 09:00",
      "defense_academic_year": "2022/2023"
    },
    "grade": 1,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "Framework-Agnostic Query Adaptation: Ensuring SQL Compatibility Across .NET Database Frameworks",
    "type": "Master Thesis",
    "submitted": "2025",
    "assignment": "There are numerous .NET frameworks available for accessing database systems, each with its own unique features and methods for executing SQL queries. These frameworks differ in their support for database functionalities, and when an application is migrated from one .NET framework to another, query compatibility issues may arise. For example, certain features or SQL constructs supported by one framework may not be available in another, leading to difficulties in query execution and application performance. The goal of this thesis is to perform a static and experimental comparison of selected .NET frameworks used for database access, focusing on their query execution capabilities and feature support. The student will analyze differences in how these frameworks handle SQL queries and identify potential compatibility issues when switching between frameworks. Based on the findings, the student will design a solution to adapt queries when migrating between frameworks, ensuring smooth transitions even when feature support varies across frameworks.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=277574",
    "reviewer": "Irena Holubová",
    "status": "defended",
    "id": "thesis-08",
    "student": "Milan Abrahám",
    "dspace_handle": "20.500.11956/203083",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/203083",
    "grade": 1,
    "note": "Finalista soutěže",
    "dspace": {
      "handle": "20.500.11956/203083",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/203083",
      "sis_id": "277574",
      "defense_date": "9. 9. 2025",
      "grade_raw": "Excellent",
      "grade": "A",
      "reviewer": "Irena Holubová",
      "language": "English",
      "keywords_en": [
        "ORM comparison",
        "ORM translation",
        "optimization",
        "query performance"
      ],
      "files": [
        {
          "kind": "thesis",
          "name": "120518445.pdf",
          "description": "Text práce"
        },
        {
          "kind": "abstract_en",
          "name": "120518444.pdf",
          "description": "Abstrakt (anglicky)"
        },
        {
          "kind": "attachment",
          "name": "120518447.zip",
          "description": "Příloha práce"
        },
        {
          "kind": "supervisor_review",
          "name": "120524630.pdf",
          "description": "Posudek vedoucího"
        },
        {
          "kind": "referee_review",
          "name": "120522542.pdf",
          "description": "Posudek oponenta"
        },
        {
          "kind": "defense_record",
          "name": "120528192.pdf",
          "description": "Záznam o průběhu obhajoby"
        }
      ]
    },
    "defense_date": "09.09.2025",
    "repository_grade": "Excellent",
    "keywords": [
      "ORM comparison",
      "ORM translation",
      "optimization",
      "query performance"
    ],
    "abstract": "Modern software systems face rapidly evolving requirements that impact both their underlying data and executed queries. While automatic adaptation on the database side has received considerable attention, there is a significant gap regarding how such changes affect application code, particularly in the context of Object-Relational Mapping (ORM). The thesis introduces a unified representation and algorithms for translating ORM configurations and queries across seven .NET ORM frameworks, and an optimization advisor that evaluates translated queries and recommends a suitable framework combination using empirical performance data and integer linear programming.",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "277574",
      "issue_academic_year": "2024/2025",
      "assignment_date": "20.11.2024",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "09.09.2025 09:00",
      "defense_academic_year": "2024/2025"
    }
  },
  {
    "title": "Sběratel informací o výkonu dotazování v multi-modelových databázových systémech",
    "type": "Bachelor Thesis",
    "submitted": "2025",
    "assignment": "There exist a number of optimization techniques for querying over relational data that are built on machine learning. However, there are currently no similar approaches for multi-model data which combine features of multiple data models, not only relational but also e.g. document and graph models. Nevertheless, in order to apply machine learning to multi-model data, it is necessary to have a suitable dataset on which to train the model. Currently, unfortunately, no suitable dataset exists. The objective of this thesis is to create a suitable dataset on which we can train a model to optimize querying over multi-model data. The student will first analyze existing datasets that are used to train approaches for optimizing query evaluation over relational data. Alternatively, the student will analyze existing tools that extract statistical information from database systems and determine their applicability with respect to data collection for model training. Next, he/she will determine the attributes of the dataset and create a tool that will record appropriate data from database systems and store it in a collection for model training.",
    "abstract": "In the world we can encounter many optimization techniques for querying over relational data, but none for multi-model data. To create one, we need to get an adequate dataset over which to train the model. As is the case with the model itself, a suitable dataset has not yet been created. Thus, in this thesis we will focus on creating a tool that can be used to create a dataset that would enable the creation of a machine learning based optimization tool. First, we will analyze the tools that are currently available and allow the collection of statistical metadata from database systems. We then select suitable parameters that would be good to include in the resulting dataset. Finally, we create and describe a tool that automates the whole process of creating the dataset.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=254993",
    "reviewer": "Jáchym Bártík",
    "status": "defended",
    "id": "thesis-09",
    "student": "Josef Holubec",
    "dspace_handle": "20.500.11956/202335",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/202335",
    "dspace": {
      "handle": "20.500.11956/202335",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/202335",
      "sis_id": "254993",
      "defense_date": "4. 9. 2025",
      "reviewer": "Jáchym Bártík",
      "language": "Czech"
    },
    "defense_date": "04.09.2025",
    "curated_title": "Collector of information about query performance in multi-model database systems",
    "sis": {
      "id": "254993",
      "issue_academic_year": "2023/2024",
      "assignment_date": "26.10.2023",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "04.09.2025 09:00",
      "defense_academic_year": "2024/2025"
    },
    "grade": 3,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "Škálovateľná detekcia funkčných závislostí v rozsiahlych multi-modelových dátach",
    "type": "Master Thesis",
    "submitted": "2026",
    "assignment": "Current approaches for detecting functional dependencies (FDs) in relational data are primarily designed with the properties of relational data in mind. As a result, these methods tend to lack scalability, making them suitable only for processing small data samples. Moreover, they often fail to consider other data models where implicit FDs might be hidden, such as in document-oriented, columnar, or key-value data models, where dependencies may be obscured by, e.g., data embedding. The goal of this thesis is to conduct a static analysis and experimental performance evaluation of selected existing FD detection methods to assess their suitability for handling different data formats and large-scale datasets. Based on the analysis, the student will design a new approach for detecting FDs in multi-model data. This approach will focus on scalability, ensuring efficient FD detection across various popular data models, with particular emphasis on big data environments.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=276671",
    "reviewer": "Michal Kopecký",
    "status": "defended",
    "id": "thesis-10",
    "student": "Richard Hvizdoš",
    "curated_title": "Scalable Detection of Functional Dependencies in Very Large Multi-Model Data",
    "sis": {
      "id": "276671",
      "issue_academic_year": "2024/2025",
      "assignment_date": "01.11.2024",
      "raw_status": "obhájená, schválená, odevzdaná",
      "scheduled_defense": "03.09.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "03.09.2026",
    "grade": 2,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "Query Rewriting Framework for Translating SQL into Graph Database Query Languages",
    "type": "Master Thesis",
    "submitted": "2026",
    "assignment": "Relational and graph databases operate on fundamentally different data models, and their query languages reflect this distinction. SQL, the standard query language for relational databases, is designed to work with tabular data, while graph databases utilize specialized query languages like Cypher, Gremlin, or SPARQL to traverse and query graph structures. These graph query languages vary in their expressive power, which refers to the range of queries and operations they can perform. Migrating or synchronizing queries between relational and graph databases presents challenges due to differences in query structure, semantics, and the capabilities of these languages. Addressing these differences is essential for enabling effective cross-model query translation. The student will perform a static and experimental comparison of the expressive power of query languages from six selected graph database systems. This analysis will focus on the capabilities of each graph query language in terms of the types of operations and queries they support, comparing these to the expressive power of SQL in relational databases. Following the comparison, the student will design and propose a framework for query rewriting and migration between relational databases and a chosen graph database. This framework will ensure that queries are correctly translated, addressing any language inconsistencies by providing equivalent operations or alternative query formulations when certain features are unsupported in the target graph database system.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=276442",
    "reviewer": "Jakub Lokoč",
    "status": "defended",
    "id": "thesis-11",
    "student": "Ivona Oboňová",
    "sis": {
      "id": "276442",
      "issue_academic_year": "2024/2025",
      "assignment_date": "27.10.2024",
      "raw_status": "obhájená, schválená, odevzdaná",
      "scheduled_defense": "03.09.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "03.09.2026",
    "grade": 1,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "Optimalizace přístupu pro odvozování schématu z multi-modelových dat",
    "type": "Bachelor Thesis",
    "submitted": "2024",
    "assignment": "V rámci diplomové práce Odvozování schématu multi-model dat vznikl v roce 2022 prototyp přístupu MM-infer pro odvozování abstraktního schématu z multi-modelových dat. Aby byl přístup výkonnostně srovnatelný s state-of-the-art přístupy, je nutné provést řadu optimalizací, reflektovat následně objevené nedostatky přístupu a připravit nástroj na integraci se zbývajícími nástroji pro správu multi-modelových dat řešených v projektu Unified Management of Multi-Model Data (GAČR projekt č. 20-22276S). Cílem této bakalářské práce je optimalizace výkonu nástroje MM-infer a vyladění implementace tak, aby byla výkonnostně srovnatelná se state-of-the-art přístupy, a to zvlášť během odvozování schématu z velkých datových kolekcí. Za tímto účelem se řešitel seznámí s nástroji na profilování kódu, s implementací nástroje MM-infer a technologiemi pro distribuované výpočty. Následně řešitel provede optimalizaci a vhodně refaktoruje kód. Nakonec řešitel experimentálně ověří výkon a škálovatelnost optimalizované verze MM-infer a provede jeho integraci se zbývajícími nástroji v rámci projektu Unified Management of Multi-Model Data.",
    "abstract": "With the increasing importance of (multi-model) NoSQL systems without or with partial schema, which would precisely define each attribute in the records, is an option to reverse infer this schema from the data needed for plenty of applications. Project MM-infer created earlier as a master thesis enables to extract this schema. This project however suffers from faults in performance which limited its usability mainly on large and complex data. This thesis continues in MM-infer project and optimizes primaly its speed. It also fixes some bugs, which were inevitably created during its creation. At last it increases precision of the inferred schema by adding new heuristics which identify main elements in the schema from one of its algorithms.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=265066",
    "reviewer": "Mgr. Jáchym Bártík",
    "status": "defended",
    "id": "thesis-12",
    "student": "Jan Šimek",
    "dspace_handle": "20.500.11956/192813",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/192813",
    "legacy_pdf": "https://dspace.cuni.cz/bitstream/handle/20.500.11956/192813/130401294.pdf?sequence=1&isAllowed=y",
    "grade": 1,
    "dspace": {
      "handle": "20.500.11956/192813",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/192813",
      "sis_id": "265066",
      "defense_date": "5. 9. 2024",
      "grade_raw": "Výborně",
      "grade": "A",
      "language": "Czech",
      "keywords_en": [
        "Optimization",
        "Schema inference",
        "NoSQL databases",
        "Profiling"
      ]
    },
    "defense_date": "05.09.2024",
    "repository_grade": "Výborně",
    "keywords": [
      "Optimization",
      "Schema inference",
      "NoSQL databases",
      "Profiling"
    ],
    "grade_scale": "Czech university grading (1 best)",
    "curated_title": "An optimization of an approach for the inference of schema from multi-model data",
    "sis": {
      "id": "265066",
      "issue_academic_year": "2023/2024",
      "assignment_date": "04.11.2023",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "05.09.2024 09:00",
      "defense_academic_year": "2023/2024"
    }
  },
  {
    "title": "Conceptual Graphical Query Language for Multi-Model Data",
    "type": "Master Thesis",
    "assignment": "With the advent of a new generation of database systems, the so-called multi-model database systems, a number of extensions to existing query languages are emerging to make them applicable over multiple data models, e.g. SQL/JSON, SQL/XML, or entirely new multi-model query languages are emerging, e.g. AQL. A common weakness of these languages is that they are often closely related to specific logical data model, and extending them to support multiple data models comes at the cost of increasing user complexity. The author first performs an analysis of existing query languages over multi-model data and compares its expressive power. Based on it, a novel (graphical) query language will be proposed and its prototype implementation then experimentally compared with respect to existing query languages.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=239282",
    "reviewer": "",
    "status": "available",
    "id": "thesis-13"
  },
  {
    "title": "Extraction of business rules from variety of data",
    "type": "Master Thesis",
    "submitted": "2026",
    "assignment": "Existing approaches for extracting integrity constraints and business rules from data sets have several limitations. These include, for example, the inability to cover all types of integrity constraints, especially complex business rules involving multiple attributes or entities, efficiency issues when dealing with large datasets where performance degrades dramatically, and last but not least, the detection of random integrity constraints that are only valid on a limited sample of data without having general validity. Moreover, existing approaches are often limited to extracting constraints in the form of functional dependencies or denial constraints, especially over small samples of relational data in CSV format. The aim of this thesis is to propose an approach for extracting integrity constraints that address the aforementioned shortcomings. The approach should be designed to be broadly applicable to different data input formats, e.g. CSV, JSON, XML or RDF, while allowing scalability to work with big data. The solver can appropriately integrate and extend traditional approaches, for example by interacting with large language models (LLMs), which can improve the accuracy and versatility of results. Since a large fraction of the extracted constraints are expected to hold only randomly on the data samples, the solution may include designing a procedure to detect and eliminate these false integrity constraints.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=273667",
    "reviewer": "Michal Kopecký",
    "status": "defended",
    "id": "thesis-14",
    "dspace": {
      "handle": "20.500.11956/209711",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/209711",
      "sis_id": "273667",
      "defense_date": "9. 6. 2026",
      "grade_raw": "Excellent",
      "grade": "A",
      "reviewer": "Michal Kopecký",
      "language": "English",
      "keywords_en": [
        "business rules",
        "integrity constraints",
        "metadata extraction",
        "functional dependencies",
        "apache spark"
      ],
      "files": [
        {
          "kind": "thesis",
          "name": "120542511.pdf",
          "description": "Text práce"
        },
        {
          "kind": "abstract",
          "name": "120542514.pdf",
          "description": "Abstrakt"
        },
        {
          "kind": "abstract_en",
          "name": "120542513.pdf",
          "description": "Abstrakt (anglicky)"
        },
        {
          "kind": "attachment",
          "name": "120542531.zip",
          "description": "Příloha práce"
        },
        {
          "kind": "supervisor_review",
          "name": "120548214.pdf",
          "description": "Posudek vedoucího"
        },
        {
          "kind": "referee_review",
          "name": "120548968.pdf",
          "description": "Posudek oponenta"
        },
        {
          "kind": "defense_record",
          "name": "120550568.pdf",
          "description": "Záznam o průběhu obhajoby"
        }
      ]
    },
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/209711",
    "dspace_handle": "20.500.11956/209711",
    "defense_date": "09.06.2026",
    "grade": 1,
    "repository_grade": "Excellent",
    "keywords": [
      "business rules",
      "integrity constraints",
      "metadata extraction",
      "functional dependencies",
      "apache spark"
    ],
    "title_cs": "Extrakce byznysových pravidel z heterogenních dat",
    "student": "Adam Polický",
    "abstract": "Many datasets outlive the context in which they were created and become difficult to interpret when documentation, schema semantics, or domain assumptions are missing. The thesis proposes a phased approach for extracting metadata, integrity constraints, and business-rule candidates from unknown datasets and storing the results as a queryable metadata footprint in a graph database. A proof-of-concept implementation uses Apache Spark and Neo4j over CSV datasets while keeping the approach extensible toward multi-model data representations.",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "273667",
      "issue_academic_year": "2024/2025",
      "assignment_date": "06.04.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "09.06.2026 09:00",
      "defense_academic_year": "2025/2026"
    }
  },
  {
    "title": "Identification of genuine functional dependencies",
    "type": "Master Thesis",
    "assignment": "Currently, there are a number of approaches for detecting functional dependencies in relational data. These approaches are usually optimized for small data samples, which may lead to the detection of functional dependencies that are only valid on a given sample by chance. In general the set of these functional dependencies may not be valid. The goal of this thesis is to design an approach that not only detects functional dependencies in the data, but more importantly focuses on eliminating spurious functional dependencies that are only valid in a small sample of the data. A key component of the approach will be the use of so-called negative examples - data records that purposely violate the detected functional dependencies but still correspond to potentially real data. The goal is to keep the number of these negative examples as small as possible, yet eliminate spurious functional dependencies as efficiently as possible. Furthermore, interaction with domain experts (e.g., crowdsourcing) can play an important role in assessing whether the proposed negative examples correspond to real data values without accidentally disturbing the actual functional dependencies valid in the domain.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=273668",
    "reviewer": "Pavel Parízek",
    "status": "defended",
    "id": "thesis-15",
    "student": "Taban Attarzadeh",
    "sis": {
      "id": "273668",
      "issue_academic_year": "2025/2026",
      "assignment_date": "18.06.2025",
      "raw_status": "obhájená, schválená, odevzdaná",
      "scheduled_defense": "03.09.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "03.09.2026",
    "submitted": "2026"
  },
  {
    "title": "Transformation of a logical schema into a conceptual schema",
    "type": "Master Thesis",
    "assignment": "Current approaches for extracting schema from data collections can generate schema that faithfully match the logical structure of the data. However, it is often the case that such schemas are unconnected, too complex, or contain repetitive structural elements. These problems are caused, for example, by redundancy in datasets, recursive data structures, or inconsistencies in attribute and entity naming across different datasets. The goal of this thesis is to design approaches that translate the automatically generated logical schema into a conceptual form. The resulting conceptual schema will be comprehensible, compact and usable by the user without losing fidelity to the original data structure. This schema simplification will be achieved through redundancy detection, resolution of inconsistencies in the data, and merging of similar or duplicate elements. Existing methods such as detecting inconsistencies in the data, schema matching based on ontologies and entity or attribute naming, or techniques for detecting recursive structures in the data can be used for this purpose. ",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=273669",
    "reviewer": "",
    "status": "available",
    "id": "thesis-16"
  },
  {
    "title": "Comparison of performance characteristics of ORM frameworks in Java over relational database system",
    "type": "Bachelor Thesis",
    "submitted": "2025",
    "keywords": [],
    "assignment": "Motivací této práce je analyzovat výkonnostní charakteristiky vybraných Java ORM (Object-Relational Mapping) frameworků při práci s relačním databázovým systémem. ORM technologie jsou široce používané při návrhu podnikových aplikací, ale jednotlivé přístupy se mohou výrazně lišit z hlediska výkonu, flexibility a složitosti použití. Úkolem studentky bude nejprve navrhnout a implementovat experimentální aplikaci, jejímž jádrem bude sada mikroservis, přičemž každá služba bude využívat jiný ORM framework pro přístup k jednotnému relačnímu databázovému systému. Aplikace bude zahrnovat minimálně šest rozdílných ORM technologií dle volby řešitelky. Pro účely registrace služeb bude použit framework Eureka. Nad těmito službami bude vytvořen frontend (např. v TypeScriptu), který umožní vizualizaci výsledků testování a porovnání výkonu. Výsledkem práce bude nejen funkční aplikace, ale i systematické statické a dynamické porovnání jednotlivých ORM přístupů z hlediska výkonu, efektivity a vhodnosti pro různé typy použití. Tato srovnávací analýza může pomoci vývojářům s výběrem vhodného nástroje pro specifické nasazení ve firemní praxi.",
    "abstract": "This thesis presents a benchmarking system to compare the performance of six Java ORM frameworks, namely JDBC, Spring Data JPA, Ebean, jOOQ, MyBatis, and Cayenne, over a relational database system MySQL using a microservices architecture. The system executes a diverse set of SQL queries, partially taken from the TPC-H benchmark, and collects metrics such as execution time and memory usage. A web interface allows users to configure experiments and visualize results. The software solution is modular, extensible and allows ORM selection decisions to be made based on data in real-valued applications.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=283931",
    "pdf": "",
    "reviewer": "Martin Nečaský",
    "status": "defended",
    "id": "thesis-17",
    "student": "Valeriia Kurinna",
    "dspace_handle": "20.500.11956/211483",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/211483",
    "grade": 2,
    "dspace": {
      "handle": "20.500.11956/211483",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/211483",
      "sis_id": "283931",
      "defense_date": "4. 9. 2025",
      "grade_raw": "Velmi dobře",
      "grade": "B",
      "reviewer": "Martin Nečaský",
      "language": "English"
    },
    "defense_date": "04.09.2025",
    "repository_grade": "Velmi dobře",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "283931",
      "issue_academic_year": "2025/2026",
      "assignment_date": "05.06.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "04.09.2025 10:00",
      "defense_academic_year": "2024/2025"
    }
  },
  {
    "title": "Webová aplikace pro analýzu a predikci výsledků ve sportovním tanci",
    "type": "Bachelor Thesis",
    "submitted": "2026",
    "keywords": [],
    "assignment": "Sportovní tanec je estetická a subjektivně hodnocená disciplína, v níž hraje zásadní roli lidský faktor rozhodování. Přestože existuje přesně definovaný systém hodnocení, tzv. skating systém, jeho výstupy jsou silně ovlivněny individuálními preferencemi porotců. Taneční veřejnost tak často vnímá hodnocení jako netransparentní a neprůhledné. Vzniká tak potřeba nástroje, který by umožnil přehlednou analýzu hodnocení a podpořil transparentnost celého systému. Cílem práce je navrhnout a implementovat webovou aplikaci umožňující uživatelům přístup k analýze a predikci soutěžních výsledků ve sportovním tanci. Aplikace bude postavena na modulární architektuře a rozdělena na frontendovou část pro interaktivní vizualizaci dat, backend poskytující REST API a výpočetní a sběrné moduly pro analýzu a získávání dat. Součástí řešení bude infrastruktura pro automatizované stahování a zpracování výsledků, například z webu Českého svazu tanečního sportu (ČSTS), jejich uložení do databáze a následná prezentace statistik a souvisejících informací uživatelům. Vedle analýzy historických dat bude aplikace také poskytovat funkcionalitu pro odhad možných výsledků budoucích soutěží na základě dostupných údajů, jako jsou předchozí výkony soutěžních párů, profily porotců nebo složení startovní listiny. Cílem této části je nabídnout uživatelům nástroj pro prediktivní pohled na soutěže. Celý systém bude navržen s důrazem na přehlednost, efektivitu a budoucí rozšiřitelnost.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=284949",
    "pdf": "",
    "reviewer": "",
    "status": "defended",
    "id": "thesis-18",
    "student": "Viktor Helmich",
    "dspace": {
      "defense_date": "18. 6. 2026",
      "status_verified": "defended",
      "repository_discovery": "DSpace record located; exact handle not yet resolved"
    },
    "defense_date": "18.06.2026",
    "curated_title": "Web Application for Analysis and Prediction of Competitive Dance Results",
    "sis": {
      "id": "284949",
      "issue_academic_year": "2025/2026",
      "assignment_date": "02.07.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "18.06.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "grade": 1,
    "grade_scale": "Czech university grading (1 best)",
    "grade_source": "supervisor-provided"
  },
  {
    "title": "Design and implementation of an item positioning management system",
    "type": "Bachelor Thesis",
    "submitted": "2026",
    "keywords": [
      "inventory system",
      "interactive editors",
      "spatial organization"
    ],
    "assignment": "Efektivní správa a lokalizace předmětů je výzvou v menších firmách, které nedisponují profesionálním systémem pro správu inventáře. S rostoucím množstvím předmětů, zejména těch méně často používaných, se zvyšuje riziko jejich nesystematického ukládání a obtížného dohledání. Implementace digitálního nástroje pro správu položek by mohla pomoci menším podnikům nebo maloobchodním provozovnám, kde by bylo možné efektivně sledovat umístění produktů a usnadnit tak jejich vyhledávání. Cílem této práce je návrh a implementace aplikace umožňující uživatelům spravovat a vyhledávat umístění jejich položek. Systém bude zahrnovat uživatelskou autentizaci, správu knihovny sdílených objektů, editory tvarů, nábytku a podlah, které umožní uživatelům modelovat své prostory. Klíčovou funkcionalitou bude správa položek v rámci vytvořeného modelu, včetně jejich přidávání, přesouvání a vyhledávání. Výstupem práce bude funkční aplikace s intuitivním uživatelským rozhraním, která umožní efektivní organizaci předmětů v různých prostředích.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=281520",
    "pdf": "",
    "reviewer": "Jakub Klímek",
    "status": "defended",
    "id": "thesis-19",
    "grade": 3,
    "student": "Lukáš Holub",
    "dspace_handle": "20.500.11956/207202",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/207202",
    "defense_date": "13.02.2026",
    "repository_grade": "Dobře",
    "dspace": {
      "handle": "20.500.11956/207202",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/207202",
      "sis_id": "281520",
      "defense_date": "13. 2. 2026",
      "grade_raw": "Dobře",
      "grade": "C",
      "reviewer": "Jakub Klímek",
      "language": "English",
      "keywords_en": [
        "inventory system",
        "interactive editors",
        "spatial organization"
      ]
    },
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "281520",
      "issue_academic_year": "2024/2025",
      "assignment_date": "12.03.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "13.02.2026 09:00",
      "defense_academic_year": "2025/2026"
    }
  },
  {
    "title": "Interactive tool for detecting redundant rows in datasets",
    "type": "Bachelor Thesis",
    "submitted": "2025",
    "keywords": [
      "data redundancy",
      "redundancy detection",
      "data profiling",
      "functional dependencies",
      "interactive data analysis"
    ],
    "assignment": "Redundance v datech se přirozeně objevuje při práci s velkými datovými sadami z různých nezávislých zdrojů. Může mít různé formy - nejen v denormalizovaných datech dokumentových databází, kde vnořené dokumenty mohou obsahovat duplicitní informace, což může zvyšovat výkon dotazů, ale komplikuje aktualizace. Redundance může být úplná (dvě sady obsahují stejná data) nebo částečná (překrývají se jen některé atributy, řádky či jejich kombinace). Pro efektivní integraci dat je proto klíčové rozpoznat, kde se redundance vyskytuje. Cílem této práce je využít metody profilování dat (např. detekci identifikátorů, referencí, funkčních či inkluzivních závislostí) k návrhu a implementaci nástroje, který efektivně identifikuje redundantní řádky ve vstupních CSV souborech (s rozumným omezením na maximální počet řádků a sloupců). Současně bude analyzována možnost využití LLM (např. ChatGPT) k detekci redundance, identifikována jeho omezení a případně začleněno do implementovaného workflow, pokud přinese zlepšení.",
    "abstract": "Redundancy is a common feature of large and heterogeneous datasets, often arising from data integration, denormalization, or performance-oriented design. It can take various forms, such as partial duplicates, repeated rows, or overlapping attributes. Rather than being an issue to eliminate outright, redundancy can support faster access patterns, provide fault tolerance, or offer alternative paths for interpreting data. To take advantage of these benefits, it is essential to detect and understand redundancy in a structured and explainable way. This bachelor’s thesis introduces an interactive tool for detecting redundant rows in CSV files. It relies on data profiling methods such as identifier detection, reference analysis, and functional dependency discovery to find and describe different types of redundancy. The developed prototype offers users an intuitive interface for exploring, checking, and interpreting redundancy.",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=281425",
    "pdf": "",
    "reviewer": "Michal Kopecký",
    "status": "defended",
    "id": "thesis-20",
    "student": "Mariia Chinkova",
    "dspace_handle": "20.500.11956/202440",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/202440",
    "grade": 1,
    "dspace": {
      "handle": "20.500.11956/202440",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/202440",
      "sis_id": "281425",
      "defense_date": "4. 9. 2025",
      "grade_raw": "Výborně",
      "grade": "A",
      "reviewer": "Michal Kopecký",
      "language": "English",
      "keywords_en": [
        "data redundancy",
        "redundancy detection",
        "data profiling",
        "functional dependencies",
        "interactive data analysis"
      ]
    },
    "defense_date": "04.09.2025",
    "repository_grade": "Výborně",
    "grade_scale": "Czech university grading (1 best)",
    "sis": {
      "id": "281425",
      "issue_academic_year": "2024/2025",
      "assignment_date": "03.03.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "04.09.2025 09:00",
      "defense_academic_year": "2024/2025"
    }
  },
  {
    "id": "thesis-21",
    "title": "Platform for renting advertising space on cars",
    "type": "Bachelor Thesis",
    "student": "Lukáš Hellesch",
    "status": "defended",
    "abstract": "Personal cars drive through Czech and Slovak cities every day, yet their exterior remains an unused advertising surface that no local platform rents per kilometer driven. The thesis presents Ad-on-Wheels, a platform in which drivers earn per kilometer with an advertisement mounted and companies create and pay for campaigns themselves. The solution uses Spring Boot microservices, a Spring Cloud gateway, SwiftUI and React clients, Apache Cassandra for GPS samples, and MySQL for ride and earnings data.",
    "grade": 1,
    "grade_scale": "Czech university grading (1 best)",
    "reviewer": "Jakub Klímek",
    "repository": "https://dspace.cuni.cz/handle/20.500.11956/210754",
    "dspace_handle": "20.500.11956/210754",
    "dspace": {
      "handle": "20.500.11956/210754",
      "url": "https://dspace.cuni.cz/handle/20.500.11956/210754",
      "sis_id": "285134",
      "defense_date": "18. 6. 2026",
      "grade_raw": "Výborně",
      "grade": 1,
      "reviewer": "Jakub Klímek",
      "language": "English",
      "keywords_en": [
        "two-sided marketplace",
        "vehicle advertising",
        "microservices",
        "GPS ride tracking",
        "iOS"
      ],
      "files": [
        {
          "kind": "thesis",
          "name": "130460732.pdf",
          "description": "Text práce"
        },
        {
          "kind": "abstract_en",
          "name": "130460688.pdf",
          "description": "Abstrakt (anglicky)"
        },
        {
          "kind": "attachment",
          "name": "130460731.zip",
          "description": "Příloha práce"
        },
        {
          "kind": "supervisor_review",
          "name": "130468986.pdf",
          "description": "Posudek vedoucího"
        },
        {
          "kind": "referee_review",
          "name": "130467536.pdf",
          "description": "Posudek oponenta"
        },
        {
          "kind": "defense_record",
          "name": "130470996.pdf",
          "description": "Záznam o průběhu obhajoby"
        }
      ]
    },
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=285134",
    "sis": {
      "id": "285134",
      "issue_academic_year": "2025/2026",
      "assignment_date": "02.07.2025",
      "raw_status": "obhájená, schválená, odevzdaná, finalizovaná",
      "scheduled_defense": "18.06.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "18.06.2026",
    "submitted": "2026"
  },
  {
    "id": "thesis-22",
    "title": "Universal Object Mapping Assistant: LLM-Assisted Migration of Application Persistence Layers",
    "type": "Master Thesis",
    "student": "Martin Čorovčák",
    "status": "defended",
    "reviewer": "Irena Holubová",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=297273",
    "sis": {
      "id": "297273",
      "issue_academic_year": "2025/2026",
      "assignment_date": "26.06.2026",
      "raw_status": "obhájená, schválená, odevzdaná",
      "scheduled_defense": "03.09.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "03.09.2026",
    "submitted": "2026"
  },
  {
    "id": "thesis-23",
    "title": "Workload-aware data representation and placement advisor for polyglot persistence environments",
    "type": "Master Thesis",
    "student": "Bedřich Mazourek",
    "status": "defended",
    "reviewer": "Tomáš Faltín",
    "consultant": "Jáchym Bártík",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=297810",
    "sis": {
      "id": "297810",
      "issue_academic_year": "2025/2026",
      "assignment_date": "26.06.2026",
      "raw_status": "obhájená, schválená, odevzdaná",
      "scheduled_defense": "03.09.2026 09:00",
      "defense_academic_year": "2025/2026"
    },
    "defense_date": "03.09.2026",
    "submitted": "2026"
  },
  {
    "id": "thesis-24",
    "title": "Graphle: Graph-oriented file management system",
    "type": "Bachelor Thesis",
    "student": "Filip Bubák",
    "status": "ongoing",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=285131",
    "sis": {
      "id": "285131",
      "issue_academic_year": "2025/2026",
      "assignment_date": "02.07.2025",
      "raw_status": "schválená, odevzdaná",
      "scheduled_defense": "09.09.2026 09:00"
    },
    "planned_defense_date": "09.09.2026 09:00"
  },
  {
    "id": "thesis-25",
    "title": "Comparison of Performance Characteristics of ODM Frameworks over Document Database Systems",
    "type": "Bachelor Thesis",
    "student": "Michal Šindler",
    "status": "ongoing",
    "ref": "https://is.cuni.cz/studium/dipl_st/index.php?id=&tid=&do=main&doo=detail&did=295226",
    "sis": {
      "id": "295226",
      "issue_academic_year": "2025/2026",
      "assignment_date": "08.04.2026",
      "raw_status": "schválená, odevzdaná",
      "scheduled_defense": "10.09.2026 12:00"
    },
    "planned_defense_date": "10.09.2026 12:00"
  }
]