@inproceedings{KnollmeyerCaymazerKovaletal.2024, author = {Knollmeyer, Simon and Caymazer, Oğuz and Koval, Leonid and Akmal, Muhammad Uzair and Asif, Saara and Mathias, Selvine George and Großmann, Daniel}, title = {Benchmarking of Retrieval Augmented Generation: A Comprehensive Systematic Literature Review on Evaluation Dimensions, Evaluation Metrics and Datasets}, booktitle = {Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2024) - Volume 3}, editor = {Gruenwald, Le and Masciari, Elio and Bernardino, Jorge}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-716-0}, doi = {https://doi.org/10.5220/0013065700003838}, pages = {137 -- 148}, year = {2024}, abstract = {Despite the rapid advancements in the field of Large Language Models (LLM), traditional benchmarks have proven to be inadequate for assessing the performance of Retrieval Augmented Generation (RAG) systems. Therefore, this paper presents a comprehensive systematic literature review of evaluation dimensions, metrics, and datasets for RAG systems. This review identifies key evaluation dimensions such as context relevance, faithfulness, answer relevance, correctness, and citation quality. For each evaluation dimension, several metrics and evaluators are proposed on how to assess them. This paper synthesizes the findings from 12 relevant papers and presents a concept matrix that categorizes each evaluation approach. The results provide a foundation for the development of robust evaluation frameworks and suitable datasets that are essential for the effective implementation and deployment of RAG systems in real-world applications.}, language = {en} } @article{KovalKnollmeyerMathiasetal.2024, author = {Koval, Leonid and Knollmeyer, Simon and Mathias, Selvine George and Asif, Saara and Akmal, Muhammad Uzair and Großmann, Daniel and Bregulla, Markus}, title = {Unlocking the Potential of Information Modeling for Root Cause Analysis in a Production Environment: A Comprehensive State-of-the-Art Review Using the Kitchenham Methodology}, volume = {12}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2024.3406020}, pages = {80266 -- 80282}, year = {2024}, abstract = {Data from production environments is now available in unprecedented volumes, making the problem-solving of incidents through root cause analysis straightforward. However, the root cause analysis process remains time-consuming. This study employs the Kitchenham standard systematic literature review methodology to explore how information models and deep learning can streamline this process. By conducting a comprehensive search across four major databases, we evaluate the current technological advancements and their application in root cause analysis. The aim of this study is to assesses the impact of information models for root cause analysis in a production environment. Our findings reveal that integrating knowledge graphs, association rule mining, and deep learning algorithms significantly improves the speed and depth of root cause analysis compared to traditional methods. Specifically, the use of neural networks in recent literature shows substantial advancements in analyzing complex datasets, facilitating large-scale data integration, and enabling automated learning capabilities. Comparing our findings with other recent studies highlights the advantages of using information modeling and deep learning technologies in root cause analysis. This comparison underscores the superior accuracy and efficiency of these advanced methodologies over traditional manual interpretation methods. The effective implementation of these technologies requires a robust foundation of clean, standardized data, giving rise to the concept of "Production IT." Furthermore, it is crucial for this data to be openly available to facilitate academic research, thereby enabling the development of new methods for more efficient and effective root cause analysis.}, language = {en} } @inproceedings{MathiasAsifAkmaletal.2025, author = {Mathias, Selvine George and Asif, Saara and Akmal, Muhammad Uzair and Knollmeyer, Simon and Koval, Leonid and Großmann, Daniel}, title = {Industrial Image Grouping Through Pre-Trained CNN Encoder-Based Feature Extraction and Sub-Clustering}, booktitle = {Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) - Volume 2}, editor = {Rocha, Ana Paula and Steels, Luc and van den Herik, Jaap}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-737-5}, doi = {https://doi.org/10.5220/0013189000003890}, pages = {496 -- 506}, year = {2025}, abstract = {A common challenge faced by many industries today is the classification of unlabeled image data from production processes into meaningful groups or patterns for better documentation and analysis. This paper presents a sequential approach for leveraging industrial image data to identify patterns in products or processes for plant floor operators. The dataset used is sourced from steel production, and the model architecture integrates feature reduction through convolutional neural networks (CNNs) like VGG, EfficientNet, and ResNet, followed by clustering algorithms to assign appropriate labels to the observed data. The model's selection criteria combine clustering metrics, including entropy minimization and silhouette score maximization. Once primary clusters are identified, sub-clustering is performed using near-labels, which are pre-assigned to images with initial distinctions. A novel metric, C-Score, is introduced to assess cluster convergence and grouping accuracy. Experimental re sults demonstrate that this method can address challenges in detecting variations across images, improving pattern recognition and classification.}, language = {en} } @article{MathiasAkmalAsifetal.2024, author = {Mathias, Selvine George and Akmal, Muhammad Uzair and Asif, Saara and Koval, Leonid and Knollmeyer, Simon and Großmann, Daniel}, title = {Pattern Identifications in Transformed Acoustic Signals Using Classification Models}, volume = {2024}, journal = {Procedia CIRP}, number = {130}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2212-8271}, doi = {https://doi.org/10.1016/j.procir.2024.10.061}, pages = {93 -- 99}, year = {2024}, abstract = {Pattern identifications in signals is necessary to discern variations from approved normal values in different scenarios. With machine learning algorithms, it is possible to use hybrid methods of pattern identifications such as feature extractions followed by classifications and/or clustering. This paper presents a pattern identification approach of acoustic signals using their transformations as inputs to classification algorithms. The analysis is carried out on two transformed versions of acoustic emission (AE) hits such as log transformations of peak hits and binary sequencing based on threshold crossing. A comparative analysis using custom data loss metrics is made to determine which inputs provide the best information in predictive methods for identifying commonly occurring patterns while acknowledging significant data loss. The methodology is conducted on transformed versions of a public dataset and the results show that patterns can be discerned to above 90\% accuracy with the transformed datasets. The experimental results yield that actual source signals need not be utilized depending on which transformations suit the practical application.}, language = {en} }