arXiv subjects

Javad Zarrin

Publications and source records attributed to Javad Zarrin.

6 recordsLinked to original sources

arXiv2026

Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring System

This paper is an extension of a paper presented at the ICAART 2026 conference, which introduced LEA (Learning Engagement Assistant), an adaptive AI tutoring agent combining course-specific Retrieval-Augmented Generation (RAG) with structured Knowledge Component (KC) models across integrated Chat, Tutor, and Quiz modes. That prior work validated LEA on a single STEM course (CMP511) exclusively through simulation, using synthetic learner agents. This paper extends that work by reporting the first classroom deployment of LEA with real students (n = 8, CMP511) and the first empirical test of its cross-course scalability, deploying the system across three courses spanning two academic levels and two disciplinary domains. The study reveals a divergence from simulation predictions across modes, showing that synthetic evaluation alone cannot anticipate all aspects of real deployment. A RAGAS-based cross-course scalability evaluation (660 questions) finds Answer Relevancy and Context Precision broadly stable across courses (0.88-0.94 and 0.88-0.90 respectively), while Faithfulness declines with curriculum distance from the system's original course (0.69 to 0.50), a preliminary finding that may reflect generation logic tuned to the system's original subject rather than a scalability limitation. These findings suggest that while the orchestration layer requires no modification, full course-agnosticism of all downstream components requires further investigation.

cs.CY↗

arXiv2025

Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study

The ability to discriminate between generative graph models is critical to understanding complex structural patterns in both synthetic graphs and the real-world structures that they emulate. While Graph Neural Networks (GNNs) have seen increasing use to great effect in graph classification tasks, few studies explore their integration with interpretable graph theoretic features. This paper investigates the classification of synthetic graph families using a hybrid approach that combines GNNs with engineered graph-theoretic features. We generate a large and structurally diverse synthetic dataset comprising graphs from five representative generative families, Erdos-Renyi, Watts-Strogatz, Barab'asi-Albert, Holme-Kim, and Stochastic Block Model. These graphs range in size up to 1x10^4 nodes, containing up to 1.1x10^5 edges. A comprehensive range of node and graph level features is extracted for each graph and pruned using a Random Forest based feature selection pipeline. The features are integrated into six GNN architectures: GCN, GAT, GATv2, GIN, GraphSAGE and GTN. Each architecture is optimised for hyperparameter selection using Optuna. Finally, models were compared against a baseline Support Vector Machine (SVM) trained solely on the handcrafted features. Our evaluation demonstrates that GraphSAGE and GTN achieve the highest classification performance, with 98.5% accuracy, and strong class separation evidenced by t-SNE and UMAP visualisations. GCN and GIN also performed well, while GAT-based models lagged due to limitations in their ability to capture global structures. The SVM baseline confirmed the importance of the message passing functionality for performance gains and meaningful class separation.

cs.LG↗

arXiv2025

Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications

Recent advancements in Large Language Models (LLMs) have transformed Natural Language Processing (NLP), enabling complex information retrieval and generation tasks. Retrieval-Augmented Generation (RAG) has emerged as a key innovation, enhancing factual accuracy and contextual grounding by integrating external knowledge sources with generative models. Although RAG demonstrates strong performance on unstructured text, its application to structured knowledge graphs presents challenges: scaling retrieval across connected graphs and preserving contextual relationships during response generation. Cross-encoders refine retrieval precision, yet their integration with structured data remains underexplored. Addressing these challenges is crucial for developing domain-specific assistants that operate in production environments. This study presents the design and comparative evaluation of multiple Retriever-Reranker pipelines for knowledge graph natural language queries in e-Commerce contexts. Using the STaRK Semi-structured Knowledge Base (SKB), a production-scale e-Commerce dataset, we evaluate multiple RAG pipeline configurations optimized for language queries. Experimental results demonstrate substantial improvements over published benchmarks, achieving 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank (MRR). These findings establish a practical framework for integrating domain-specific SKBs into generative systems. Our contributions provide actionable insights for the deployment of production-ready RAG systems, with implications that extend beyond e-Commerce to other domains that require information retrieval from structured knowledge bases.

cs.IR↗

arXiv2023

Enhancing Road Safety through Accurate Detection of Hazardous Driving Behaviors with Graph Convolutional Recurrent Networks

Car accidents remain a significant public safety issue worldwide, with the majority of them attributed to driver errors stemming from inadequate driving knowledge, non-compliance with regulations, and poor driving habits. To improve road safety, Driving Behavior Detection (DBD) systems have been proposed in several studies to identify safe and unsafe driving behavior. Many of these studies have utilized sensor data obtained from the Controller Area Network (CAN) bus to construct their models. However, the use of publicly available sensors is known to reduce the accuracy of detection models, while incorporating vendor-specific sensors into the dataset increases accuracy. To address the limitations of existing approaches, we present a reliable DBD system based on Graph Convolutional Long Short-Term Memory Networks (GConvLSTM) that enhances the precision and practicality of DBD models using public sensors. Additionally, we incorporate non-public sensors to evaluate the model's effectiveness. Our proposed model achieved a high accuracy of 97.5\% for public sensors and an average accuracy of 98.1\% for non-public sensors, indicating its consistency and accuracy in both settings. To enable local driver behavior analysis, we deployed our DBD system on a Raspberry Pi at the network edge, with drivers able to access daily driving condition reports, sensor data, and prediction results through a monitoring dashboard. Furthermore, the dashboard issues voice warnings to alert drivers of hazardous driving conditions. Our findings demonstrate that the proposed system can effectively detect hazardous and unsafe driving behavior, with potential applications in improving road safety and reducing the number of accidents caused by driver errors.

cs.LG↗

arXiv2020

Blockchain for Decentralization of Internet: Prospects, Trends, and Challenges

Blockchain has made an impact on today's technology by revolutionizing the financial industry in its utilization on cryptocurrency and the features it provided on decentralization. With the current trend of pursuing the decentralized Internet, many methods have been proposed to achieve decentralization considering different aspects of the current Internet model ranging from infrastructure and protocols to services and applications. This paper focuses on using Blockchain to provide a robust and secure decentralized computing system. The paper conducts a literature review on Blockchain-based methods capable for the decentralization of the future Internet. To achieve that decentralization, two research aspects of Blockchain have been investigated that are highly relevant in realizing the decentralized Internet. The first aspect is the consensus algorithms, which are vital components for decentralization of Blockchain. We have identified three consensus algorithms being PoP, Paxos, and PoAH to be more adequate for reaching consensus in Blockchain-enabled Internet architecture. The second aspect that we investigated is the impact of future Internet technologies on Blockchain, where their combinations with Blockchain would help to make it overcome its established flaws and be more optimized and applicable for Internet decentralization.

cs.NI↗

arXiv2017

Decentralized Resource Discovery and Management for Future Manycore Systems

The next generation of many-core enabled large-scale computing systems relies on thousands of billions of heterogeneous processing cores connected to form a single computing unit. In such large-scale computing environments, resource management is one of the most challenging, and complex issues for efficient resource sharing and utilization, particularly as we move toward Future ManyCore Systems (FMCS). This work proposes a novel resource management scheme for future peta-scale many-core-enabled computing systems, based on hybrid adaptive resource discovery, called ElCore. The proposed architecture contains a set of modules which will dynamically be instantiated on the nodes in the distributed system on demand. Our approach provides flexibility to allocate the required set of resources for various types of processes/applications. It can also be considered as a generic solution (with respect to the general requirements of large scale computing environments) which brings a set of interesting features (such as auto-scaling, multitenancy, multi-dimensional mapping, etc,.) to facilitate its easy adaptation to any distributed technology (such as SOA, Grid and HPC many-core). The achieved evaluation results assured the significant scalability and the high quality resource mapping of the proposed resource discovery and management over highly heterogeneous, hierarchical and dynamic computing environments with respect to several scalability and efficiency aspects while supporting flexible and complex queries with guaranteed discovery results accuracy. The simulation results prove that, using our approach, the mapping between processes and resources can be done with high level of accuracy which potentially leads to a significant enhancement in the overall system performance.

cs.DC↗