RERudolf Erdei

Rudolf Erdei

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rudolf Erdei has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Diploid Genetic Algorithms: A Comprehensive Survey of Theory, Applications, and Future Directions

    by Oliviu Matei, Rudolf Erdei, Laura Andreica

    Diploid Genetic Algorithms (DGAs) represent a biologically inspired extension of traditional evolutionary algorithms, leveraging genotype–phenotype separation and dominance mechanisms to enhance adaptability, diversity retention, and long-term learning. This survey provides the first comprehensive, domain-spanning review of DGAs with a focus on practical applications across dynamic optimization, robotics, combinatorial design, bioinformatics, and smart infrastructure. Through a systematic meta-analysis of 160+ peer-reviewed studies, we analyze publication trends, evaluate empirical performance relative to haploid counterparts, and identify domain-specific advantages. The paper introduces a formal mathematical framework for DGAs and categorizes dominance mechanisms, memory behaviors, and diversity-preservation strategies. A comparative performance matrix and detailed case studies illustrate how DGAs consistently outperform classical genetic algorithms in non-stationary and noisy environments. Despite their promise, challenges such as scalability, theoretical modeling, and software support remain. To address these, we outline future directions involving hybrid AI integration, real-time adaptation, and standardized DGA libraries. This survey establishes DGAs as a robust and underutilized paradigm for solving complex, adaptive optimization problems in modern computational systems.

  • Cultivating Sustainable Data: Challenges and Directions in Digital Agriculture

    by Daniela Delinschi, Rudolf Erdei, Emil Marian Pasca, Iulia Baraian, Andrei Curos

  • Open Access

    Trend-Enabled Recommender System with Diversity Enhancer for Crop Recommendation

    by Iulia Baraian, Rudolf Erdei, Rares Tamaian, Daniela Delinschi, Emil Marian Pasca, Oliviu Matei

    Achieving optimal agricultural yields and promoting sustainable farming relies on accurate crop recommendations. However, the applicability of many current systems is limited by their considerable computational requirements and dependence on comprehensive datasets, especially in resource-limited contexts. This paper presents HOLISTIQ RS, a novel crop recommendation system explicitly designed for operation on low-specification hardware and in data-scarce regions. HOLISTIQ RS combines collaborative filtering with a Markov model to predict appropriate crop choices, drawing upon user profiles, regional agricultural data, and past crop performance. Results indicate that HOLISTIQ RS provides a significant increase in recommendation accuracy, achieving a MAP@5 of 0.31 and nDCG@5 of 0.41, outperforming standard collaborative filtering methods (the KNN achieved MAP@5 of 0.28 and nDCG@5 of 0.38, and the ANN achieved MAP@5 of 0.25 and nDCG@5 of 0.35). Significantly, the system also demonstrates enhanced recommendation diversity, achieving an Item Variety (IV@5) of 23%, which is absent in deterministic baselines. Significantly, the system is engineered for reduced energy consumption and can be deployed on low-cost hardware. This provides a feasible and adaptable method for encouraging informed decision-making and promoting sustainable agricultural practices in areas where resources are constrained, with an emphasis on lower energy usage.


  • Open Access

    Similarity-Based Decision Support for Improving Agricultural Practices and Plant Growth

    by Iulia Baraian, Honoriu Valean, Oliviu Matei, Rudolf Erdei

    Similarity-based decision support systems have become essential tools for providing tailored and adaptive guidance across various domains. In agriculture, where managing extensive land areas poses significant challenges, the primary objective is often to maximize harvest yields while reducing costs, preserving crop health, and minimizing the use of chemical adjuvants. The application of similarity-based analysis enables the development of personalized farming recommendations, refined through shared data and insights, which contribute to improved plant growth and enhanced annual harvest outcomes. This study employs two algorithms, K-Nearest Neighbour (KNN) and Approximate Nearest Neighbour (ANN) using Locality Sensitive Hashing (LSH) to evaluate their effectiveness in agricultural decision-making. The results demonstrate that, under comparable farming conditions, KNN yields more accurate recommendations due to its reliance on exact matches, whereas ANN provides a more scalable solution well-suited for large datasets. Both approaches support improved agricultural decisions and promote more sustainable farming strategies. While KNN is more effective for smaller datasets, ANN proves advantageous in real-time applications that demand fast response times. The implementation of these algorithms represents a significant advancement toward data-driven and efficient agricultural practices.


  • Open Access

    A Vulnerable-by-Design IoT Sensor Framework for Cybersecurity in Smart Agriculture

    by Emil Marian Pasca, Daniela Delinschi, Rudolf Erdei, Iulia Baraian, Oliviu Dorin Matei

    Agricultural Internet of Things (IoT) deployments face unique cybersecurity challenges due to resource constraints and direct impact on food production. This paper introduces a vulnerable-by-design, containerized IoT framework simulating both cybersecurity vulnerabilities and sensor health anomalies in agricultural settings. We demonstrate its agricultural relevance through a tomato greenhouse case study where combined DDoS attacks and sensor faults masked critical temperature increases to 43 °C, potentially reducing yields by up to 30%. Our masking analysis revealed counter-intuitive relationships between sensor faults and attack detectability: spike faults enhanced BOLA attack detectability by up to 95.9%, while dropout faults masked command injection attacks by 18.0%. We identified distinctive temporal signatures for each attack type and quantified these relationships through a composite detectability score. Our LSTM-based validation achieved moderate recall (0.5473 average) with significant variation across fault conditions (0.3194–0.8145), while maintaining strong precision (0.8285). The LSTM model performed best with drift fault conditions (0.9749 accuracy), while DDoS attacks were most consistently detectable (avg. score: 0.6886) and resource exhaustion attacks the most difficult (0.3056). These findings challenge conventional approaches that treat sensor health and security as separate domains. Our open-source implementation with systematic dataset generation capabilities addresses reproducibility challenges in agricultural IoT security while demonstrating that integrated health-security monitoring could significantly improve threat detection in smart agriculture deployments.


  • Open Access

    Privacy-Conducive Data Ecosystem Architecture: By-Design Vulnerability Assessment Using Privacy Risk Expansion Factor and Privacy Exposure Index

    by Ionela Chereja, Rudolf Erdei, Daniela Delinschi, Emil Pasca, Anca Avram, Oliviu Matei

    The increasing complexity of data ecosystems demands advanced methodologies for systematic privacy risk assessment. This work introduces two complementary metrics—the privacy risk expansion factor (PREF) and the privacy exposure index (PEI)—to evaluate how architectural decisions influence the exposure and distribution of sensitive data. Several representative use cases validate the methodology, demonstrating how the metrics provide structured insights into the privacy impact of distinct design choices. By enabling comparative analysis across architectures, this approach supports the development of privacy-first data ecosystems and lays the groundwork for future research on dynamic, AI-driven risk monitoring.


  • Open Access

    Guide in Designing an Asynchronous Performance‐Centric Framework for Heterogeneous Microservices in Time‐Critical Cybersecurity Applications. The BIECO Use Case

    by Daniela Delinschi, Rudolf Erdei, Emil Marian Pasca, Iulia Bărăian, Oliviu Matei

    This article presents the architecture, design and validation of a microservice orchestration approach that improves the flexibility of heterogeneous microservice‐based platforms. Improving user experience and interaction for time‐critical applications are aspects that were primary objectives for the design of the architecture. Each microservice can provide its own embedded user interface component, also decentralising it and, in consequence, improving the loosely coupled approach to the architecture. Obtained results are promising, with high throughput and low response times. Also, a key finding was the introduction of benchmarking as a new step in the development lifecycle of performance‐critical software components, with an example of how it can be applied within an Agile methodology. Further research is proposed to improve the results and raise the final technology readiness level of the system. Obtained results already make the approach a candidate and viable alternative to classical service composers.

  • Open Access

    A Privacy Assessment Framework for Data Tiers in Multilayered Ecosystem Architectures

    by Ionela Chereja, Rudolf Erdei, Emil Pasca, Daniela Delinschi, Anca Avram, Oliviu Matei

    Data-centric operational systems, machine learning (ML), and other analytical and artificial intelligence (AI) pipelines are becoming increasingly imperative for organizations seeking to increase the protection of sensitive data while satisfying customer expectations. This paper proposes a novel methodology to assess the level of vulnerability assigned to each of the data storage components in complex multilayered data ecosystems through a nuanced assessment of data persistence and content metrics. The suggested methodology introduces a new and effective way to address the issues of determining perceived privacy risk across data storage layers and informing necessary security measures for an ecosystem by calculating an ecosystem vulnerability score. This offers a comprehensive overview of data vulnerability, aiding in the identification of high-risk components and guiding strategic decisions for enhancing data privacy and security measures. With consistent and generalized assessment of risk, the methodology can properly pinpoint the most vulnerable storage systems and assist in directing efforts to mitigate them.


  • Open Access

    LLM-Driven, Self-Improving Framework for Security Test Automation: Leveraging Karate DSL for Augmented API Resilience

    by Emil Marian Pasca, Daniela Delinschi, Rudolf Erdei, Oliviu Matei

    Modern software architectures heavily rely on APIs, yet face significant security challenges, particularly with Broken Object Level Authorization (BOLA) vulnerabilities, which remain the most critical API security risk according to OWASP. This paper introduces Karate-BOLA-Guard, an innovative framework leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques to automate security-focused test case generation for APIs. Our approach integrates vector databases for context retrieval, multiple LLM models for test generation, and observability tools for process monitoring. Initial experiments were carried out on three deliberately vulnerable APIs (VAmPI, Crapi, and OWASP Juice Shop), with subsequent validation on fifteen additional production APIs spanning diverse domains including social media, version control systems, financial services, and transportation services. Our evaluation metrics show Llama 3 8B achieving consistent performance (Accuracy: 3.1-3.4, Interoperability: 3.7-4.3) with an average processing time of 143.76 seconds on GPU. Performance analysis revealed significant GPU acceleration benefits, with 20-25x improvement over CPU processing times. Smaller models demonstrated efficient processing, with Phi-3 Mini averaging 69.58 seconds and Mistral 72.14 seconds, while maintaining acceptable accuracy scores. Token utilization patterns showed Llama 3 8B using an average of 36,591 tokens per session, compared to Mistral’s 25,225 and Phi-3 Mini’s 31,007. Our framework’s effectiveness varied across APIs, with notably strong performance in complex platforms (Instagram: A=4.3, I=4.4) while maintaining consistent functionality in simpler implementations (VAmPI: A=3.6, I=4.3). The iterative refinement process, evaluated through comprehensive metrics including Accuracy (A), Complexity (C), and Interoperability (I), represents a significant advancement in automated API security testing, offering an efficient, accurate, and adaptable approach to detecting BOLA vulnerabilities across diverse API architectures.