News & Events
Stay informed and engaged with the latest updates, breakthroughs, and community events surrounding the COSA project, your central hub for innovation and collaboration.
A Privacy Assessment Framework For Data Tiers In Multilayered Ecosystem Architectures
A Privacy Assessment Framework For Data Tiers In Multilayered Ecosystem ArchitecturesIonela Chereja, Rudolf Erdei, Emil Pasca, Daniela Delinschi, Anca Avram, Oliviu Matei Abstract. As smart agriculture evolves into an interconnected Internet of Fields, massive amounts...
LLM-Driven, Self-Improving Framework for Security Test Automation: Leveraging Karate DSL for Augmented API Resilience
LLM-Driven, Self-Improving Framework for Security Test Automation: Leveraging Karate DSL for Augmented API ResilienceEmil Marian Pasca, Daniela Delinschi, Rudolf Erdei, Oliviu Matei Abstract. This paper introduces Karate-BOLA-Guard, an LLM-driven, self-improving...
A Proud Achievement for the COSA Team!
Huge congratulations to Rudolf Erdei and Adrian Petrovan for receiving their official doctoral diplomas at the UTCN 2025 Research and Innovation Conference! Out of 74 new PhDs, two belong to our talented COSA team members. Their dedication to research and innovation...
Collaborating for Smarter Agriculture!
🤝 Collaborating for Smarter Agriculture! 🌱 We’re excited to share a work-in-progress glimpse of our bonitation calculation feature from the COSA project! This tool aims to support farmers in evaluating crop quality and productivity through data-driven insights. Our...
Cybersecurity in Smart Agriculture – Emil Pașca at UTCN 2025
🔐 Did you know that cybersecurity plays a vital role in smart agriculture? 🌾 Our team member and PhD student, Emil Marian Pasca, recently presented his research on ‘Intelligent Processes to Improve the Security of Software Applications’ at the UTCN 2025 Research and...
Progress Meeting — Spring 2025 Coordination
The COSA team gathered for a coordination meeting to review progress across work packages and to prepare the deliverables and reporting actions of the period. The agenda included status updates on R&D activities, ongoing publications and the upcoming validation...
Progress Meeting — Starting 2025 with a Clear Roadmap
The COSA project team kicked off 2025 with an internal progress meeting dedicated to reviewing the status of all work packages and setting priorities for the new reporting cycle. The discussion covered ongoing R&D activities, the planning of dissemination actions,...
Optimizing fertilization and crop management for triticale in the Lăpuș depression, Romania
Optimizing fertilization and crop management for triticale in the Lăpuș depression, RomaniaI. Cionca, A. D. Costin, T. Rusu Abstract. Triticale is an important cereal crop in mountainous and hilly areas of Romania, where soil and climatic conditions can limit the...
Using Automation and Artificial Intelligence in the Management of European Social Fund Projects
Using Automation and Artificial Intelligence in the Management of European Social Fund ProjectsMatei Oliviu, Laura Andreica, Faragău Tudor Abstract. The management of European Social Fund (ESF) projects is characterized by complex reporting, monitoring and compliance...
Benefits and limitations of digitalization in managing European Social funded projects
Benefits and limitations of digitalization in managing European Social funded projectsMatei Oliviu, Laura Andreica, Faragău Tudor Abstract. Digitalization is widely promoted as a solution for the administrative complexity of European Social Fund (ESF) projects, yet...
Exciting News from COSA! – Conferences in Salamanca
🎉 Exciting News from COSA! 🌟 Our talented researchers made major contributions in the SOCO-CISIS-HAIS conferences held in Salamanca, Spain! They presented a remarkable 15 research articles based on our groundbreaking COSA project. 📚 Learn about the latest advancements...
The COSA Project is on Fire! – 15 Research Papers
🔥 The COSA Project is on Fire! 🌟 Our incredible team just presented 15 research articles at the SOCO-CISIS-HAIS 2024 conferences based on the groundbreaking COSA project! 📚 From innovative agricultural solutions to cutting-edge technology, we're making significant...
A comparative study of different genetic algorithms approaches to capacitated vehicle routing problem for collection of agricultural products
A comparative study of different genetic algorithms approaches to capacitated vehicle routing problem for collection of agricultural productsCosmin Sabo, Natanael Balogh, Petrică C. Pop, Adrian Petrovan Abstract. In this study, we tackle a local collection challenge,...
Using Machine Learning for Identifying the Intrinsic Economic Specializations of Localities
Using Machine Learning for Identifying the Intrinsic Economic Specializations of LocalitiesOliviu Matei, Laura Andreica, Ioan Alin Danci, Anca Avram, Faragău Tudor Abstract. Identifying the intrinsic economic specialization of localities is a key step in the design of...
Embedding GIS in crop field bonitation computation
Embedding GIS in crop field bonitation computationBogdan Văduva, Oliviu Matei, Anca Avram, Laura Andreica Abstract. Crop field bonitation, the agronomic evaluation of land quality and agricultural potential, traditionally relies on tabular indicators that ignore the...
A comparative study of machine learning models for plant disease identification
A comparative study of machine learning models for plant disease identificationMăcelaru Mara, Petrică Pop, Jose Barata Abstract. Plant disease identification from images is a central task in precision agriculture, but the rapid evolution of machine learning makes it...
A Novel CNN Approach for Accurate Tomato Disease Classification
A Novel CNN Approach for Accurate Tomato Disease ClassificationOvidiu Cosma, Laura Cosma Abstract. Plant diseases pose significant threats to agriculture, leading to substantial yield losses worldwide. Tomato crops are particularly affected by a wide range of...
Design of a collaborative network for mapping digital skills for Industry 5.0
Design of a collaborative network for mapping digital skills for Industry 5.0Maria Gustavsson, Oliviu Matei, Laura Andreica, Agneta Halvarsson Lundkvist, Daniel Persson Thunqvist Abstract. The transition to Industry 5.0 brings new demands for the workforce, where...
Solving the clustered minimum routing tree problem using Prüfer-coding based hybrid genetic algorithms
Solving the clustered minimum routing tree problem using Prüfer-coding based hybrid genetic algorithmsCosmin Sabo, Bogdan Teglaș, Petrică C. Pop, Adrian Petrovan Abstract. The clustered minimum routing tree problem (CluMRTP) extends the classical minimum routing tree...
Augmenting API Security Testing with Automated LLM-Driven Test Generation
Augmenting API Security Testing with Automated LLM-Driven Test GenerationEmil Marian Pasca, Rudolf Erdei, Daniela Delinschi, Oliviu Matei Abstract. API security testing is an essential step in modern software development, but manually crafting comprehensive test...
Data Quality Assessment Methodology
Data Quality Assessment MethodologyDaniela Delinschi, Rudolf Erdei, Emil Pasca, Oliviu Matei Abstract. High-quality data is a precondition for reliable machine learning, analytics and decision support. This paper introduces a methodology for systematic data quality...
Privacy Assessment Methodology for Machine Learning Models and Data Sources
Privacy Assessment Methodology for Machine Learning Models and Data SourcesRudolf Erdei, Emil Pasca, Daniela Delinschi, Anca Avram, Ionela Chereja, Oliviu Matei Abstract. The widespread use of machine learning amplifies privacy risks both at the level of training data...
Aggregation Strategy for Federated Machine Learning Algorithm
Aggregation Strategy for Federated Machine Learning AlgorithmRudolf Erdei, Daniela Delinschi, Iulia Băărăian, Oliviu Matei Abstract. Federated learning allows multiple parties to collaboratively train a model without sharing their raw data, but the quality of the...
Using Markov chains for determining the proximity contagion of smart specialization of localities
Using Markov chains for determining the proximity contagion of smart specialization of localitiesOliviu Matei, Laura Andreica, Ioan Alin Danci, Anca Avram, Bogdan Văduva Abstract. Smart specialization strategies depend on understanding how economic specialization...