@misc{Schmitt, author = {Schmitt, Ingo}, title = {QLDT+: Efficient Construction of a Quantum Logic Decision Tree}, series = {ICMLT '23: Proceedings of the 2023 8th International Conference on Machine Learning Technologies, SESSION: Session 2 - Data Model Design and Algorithm Analysis}, journal = {ICMLT '23: Proceedings of the 2023 8th International Conference on Machine Learning Technologies, SESSION: Session 2 - Data Model Design and Algorithm Analysis}, publisher = {Association for Computing Machinery}, address = {New York, NY, United States}, isbn = {978-1-4503-9832-9}, doi = {10.1145/3589883.3589895}, pages = {82 -- 88}, abstract = {The quantum-logic inspired decision tree (QLDT) is based on quantum logic concepts and input values from the unit interval whereas the traditional decision tree is based on Boolean values. The logic behind the QLDT obeys the rules of a Boolean algebra. The QLDT is appropriate for classification problems where for a class decision several input values interact gradually with each other. The QLDT construction for a classification problem with n input attributes requires the computation of 2n minterms. The QLDT+ method, however, uses a heuristic for obtaining a QLDT with much smaller computational complexity. As result, the QLDT+ method can be applied to classification problems with a higher number of input attributes.}, language = {en} } @misc{StahlSchmitt, author = {Stahl, Alexander and Schmitt, Ingo}, title = {BBQ-Tree - A Decision Tree with Boolean and Quantum Logic Decisions}, series = {Advances in Databases and Information Systems (ADBIS 2024)}, journal = {Advances in Databases and Information Systems (ADBIS 2024)}, number = {14918}, publisher = {Springer}, pages = {201 -- 214}, abstract = {This study proposes the BBQ-Tree, a new logic-based classifier that combines the two concepts of classical Decision Trees and Quantum-Logic Decision Trees into a generalized model. It thus creates a method that has the power to solve classification problems that incorporate both curved and linear decision boundaries, with a particular focus on interpretability. In addition to the model itself, ways for its efficient training are discussed. Our experimental evaluation demonstrates that our approach is able to produce models that remain compact and provide good insights over trends in data while maintaining an accuracy not worse than Decision Trees alone.}, language = {en} } @misc{Schmitt, author = {Schmitt, Ingo}, title = {Logic interpretations of ANN partition cells}, series = {Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)}, journal = {Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)}, number = {abs/2408.14314}, doi = {10.48550/ARXIV.2408.14314}, abstract = {Consider a binary classification problem solved using a feed-forward artificial neural network (ANN). Let the ANN be composed of a ReLU layer and several linear layers (convolution, sum-pooling, or fully connected). We assume the network was trained with high accuracy. Despite numerous suggested approaches, interpreting an artificial neural network remains challenging for humans. For a new method of interpretation, we construct a bridge between a simple ANN and logic. As a result, we can analyze and manipulate the semantics of an ANN using the powerful tool set of logic. To achieve this, we decompose the input space of the ANN into several network partition cells. Each network partition cell represents a linear combination that maps input values to a classifying output value. For interpreting the linear map of a partition cell using logic expressions, we suggest minterm values as the input of a simple ANN. We derive logic expressions representing interaction patterns for separating objects classified as 1 from those classified as 0. To facilitate an interpretation of logic expressions, we present them as binary logic trees.}, language = {en} } @book{WirschingSchmittWolff, author = {Wirsching, G{\"u}nther and Schmitt, Ingo and Wolff, Matthias}, title = {Quantenlogik, Band 1 : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {2. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-71335-8}, doi = {10.1007/978-3-662-71335-8}, pages = {xiii, 495}, abstract = {Messungen an Quantenobjekten haben eine logische Struktur. Diese schließt die klassische Logik ein, geht jedoch weit dar{\"u}ber hinaus. Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge der Quantenlogik zu vermitteln und technische Anwendungsm{\"o}glichkeiten aufzuzeigen. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden anhand von Beispielen so erl{\"a}utert und motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. Die vorliegende Auflage wurde korrigiert und um zahlreiche Anwendungen, zus{\"a}tzliche Beispiele und Beweise erweitert sowie um ein neues Beispiel zur Mustererkennung erg{\"a}nzt.}, language = {de} } @book{WirschingWolffSchmitt, author = {Wirsching, G{\"u}nther and Wolff, Matthias and Schmitt, Ingo}, title = {Quantenlogik : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {1. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-66779-8}, doi = {10.1007/978-3-662-66780-4}, pages = {XI, 386}, abstract = {Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse auf der Grundlage der klassischen Logik und der Quantenlogik zu entwickeln. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden so dargestellt und anhand von Beispielen motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. - Kompakte logische Darstellung der mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse - Beispiele erl{\"a}utern die Anwendung im Engineering Zielgruppen sind insbesondere Studierende der Ingenieurwissenschaften und der Informatik, aber auch Studierende der Mathematik oder der Physik k{\"o}nnen durch den anwendungsbezogenen Blick ihren Horizont erweitern.}, language = {de} } @misc{GuptaPaulSchmittetal., author = {Gupta, Vipul and Paul, Jonathan David Heaton and Schmitt, Ingo and Pyczak, Florian}, title = {SciLitMiner : an intelligent system for scientific literature mining and knowledge discovery}, series = {Advanced intelligent systems}, journal = {Advanced intelligent systems}, publisher = {Wiley}, address = {Weinheim}, issn = {2640-4567}, doi = {10.1002/aisy.202501235}, pages = {1 -- 20}, abstract = {Recent advances in data mining have enabled automation in literature-based discovery (LBD), allowing synergistic evaluation of experimental findings reported in scientific publications. However, existing tools and digital libraries fall short in generating relevant literature collections and evaluating them for highly specific questions. This article presents SciLitMiner, an intelligent system to address this gap. SciLitMiner enables federated ingestion of literature from digital libraries; applies advanced retrieval techniques, including dataset-aware retrieval from visual elements, to identify relevant studies; and leverages retrieval-augmented generation (RAG) tailored to domain-specific knowledge reasoning. The system is applied in materials science to study the creep behavior of γ-TiAl alloys, revealing the intricate interplay between material, process, microstructure, and creep rate, represented through knowledge graphs. Two domain experts rate responses from the knowledge reasoning workflow with OpenAI large language models (LLMs) as the backbone above "good" (3 on a 5-point Likert scale) in over 90\% across qualitative criteria, indicating strong performance. In a case study, the workflow also outperforms gpt-4.5-turbo with web search and other leading tools in reliability. A second case study benchmarks open-source LLMs as drop-in replacements for proprietary models, demonstrating comparable-to-superior performance. The system's flexibility enables its use in automated LBD across diverse research domains.}, language = {en} } @misc{SchmittSowoidnichGosswamietal., author = {Schmitt, Ingo and Sowoidnich, Kay and Gosswami, Tapashi and Sumpf, Bernd and Maiwald, Martin and Wolff, Matthias}, title = {PCA-based peak feature selection for classification of spectroscopic datasets}, series = {Journal of chemometrics}, volume = {39}, journal = {Journal of chemometrics}, number = {11}, publisher = {John Wiley \& Sons Ltd.}, address = {New York, NY}, issn = {0886-9383}, doi = {10.1002/cem.70074}, pages = {1 -- 14}, abstract = {Reducing feature dimensionality in spectroscopic data is crucial for efficient analysis and classification. Using all available features for classification typically results in an unacceptably high runtime and poor accuracy. Popular feature extraction methods, such as principal component analysis (PCA), linear discriminant analysis (LDA), and autoencoders, reduce feature dimensionality by extracting latent features that can be challenging to interpret. To enable better human interpretation of the classification model, we avoid extraction methods and instead propose applying feature selection methods. In this work, we develop an innovative PCA-based feature selection method for spectroscopic data, providing an essential subset of the original features. As an important advantage, no prior knowledge about the characteristic signals of the respective target substance is required. In this proof-of-concept study, the proposed method is initially characterized using simulated Raman and infrared absorption datasets. From the top five PCA eigenvectors of spectroscopic data, we identify a set of three top peaks each at specific wavenumbers (features). The compact set of selected features is then used for classification tasks applying a decision tree. Based on two well-defined spectroscopic datasets, our study demonstrates that our new method of PCA-based peak finding outperforms selected other approaches with regard to interpretability and accuracy. For both investigated datasets, accuracies greater than 97\% are achieved. Our approach shows large potential for accurate classification combined with interpretability in further scenarios involving spectroscopic datasets.}, language = {en} } @misc{SchmittStahl, author = {Schmitt, Ingo and Stahl, Alexander}, title = {BBQ-Tree : a unified classifier and regressor combining Boolean and quantum logic decisions}, series = {Information systems}, volume = {136}, journal = {Information systems}, publisher = {Elsevier BV}, address = {Amsterdam}, issn = {0306-4379}, doi = {10.1016/j.is.2025.102632}, pages = {1 -- 10}, abstract = {This article provides a detailed explanation of the BBQ-Tree, a unified logic-based model that integrates both classical Decision Trees and Quantum-Logic Decision Trees into a generalized framework for classification and regression. As it combines these paradigms, the BBQ-Tree effectively addresses problems with both linear and curved decision boundaries while prioritizing interpretability. We provide a detailed description of the underlying concepts, a possible training algorithm, experimental evaluations and the incorporation of regression functionality, broadening its applicability beyond classification tasks. Strategies for efficient training and model optimization are also presented. Experimental results demonstrate that the BBQ-Tree produces compact, interpretable models capable of revealing data trends, while achieving accuracy comparable to Decision Trees. Furthermore, its new regression capabilities highlight its versatility and performance across a wider range of tasks.}, language = {en} }