Lecture Notes in Informatics

Permanent URI for this communityhttps://dl.gi.de/handle/20.500.12116/21

Die „GI-Edition: Lecture Notes in Informatics" (LNI) ist eine eigene Veröffentlichungsreihe der GI mit den Strängen: Proceedings, Dissertations, Seminars und Thematics. Alle in den LNI herausgegebenen Bände werden von GI-Gliederungen unterstützt und verantwortet.

Information und Ansprechpartner zur Reihe finden sich auf den Webseiten der GI unter https://gi.de/service/publikationen/lni

News

Authors with most Documents

Schroeder, Ulrik

Lucke, Ulrike

Busch, Christoph

Thomas, Oliver

Theuvsen, Ludwig

Browse

Search Results

1 - 10 of 84

Cloud-Based Data Classification Framework for Cultural Heritage Conservation
(Gesellschaft für Informatik e.V., 2024) Rashid, Shaimaa; Qasha, Rawaa; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
Nineveh is one of ancient cities of Iraq, ruled by various civilizations throughout the ages. As a result, Nineveh retains different types of tangible and intangible cultural heritage with different values that show its importance. This research contributes to the digital archiving process of the culture heritage of Nineveh by suggesting a cloud-based framework that classifies the text data obtained from various heterogonous data sources according to the type, values, civilization, and time to which they belong. We used four classical machine learning algorithms to train the classifier, such as Multinomial Naive Bayes, Support Vector Machines, Random Forest, and K Nearest Neighbors. We then chose the classifier with the highest accuracy to classify the obtained texts automatically. The finding showed that the K-Nearest Neighbors classifier is the best classifier to be adopted in the classification process.
Understanding and addressing user needs for annotation of simple sensor data: Bridging the gap between human sensemaking and machine interpretation
(Gesellschaft für Informatik e.V., 2024) Kurze, Albrecht; Reuter, Christin; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
The increasing presence of sensors in smart homes generates vast amounts of data, which require effective interpretation to be useful, often along with data annotation. While automatic approaches can automatically analyze sensor data but require strict and clean annotations, they often neglect the complex, multidimensional nature of human sensemaking. We explore this gap and propose an approach to bridge this gap. We present preliminary findings from three directions: lay user annotations of sensor data collected in a field study using our Sensorkit solution, analysis of existing annotation tools, and a human-centered design process for a new annotation solution. Our goal is to develop a more integrated approach to sensor data interpretation that benefits both humans and machines.
Automated Reasoning for Conflict Solving in Knowledge Graphs
(Gesellschaft für Informatik e.V., 2024) Fähndrich, Johannes; Wischow, Maik; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
Forensic application of Methods of AI depends on the level of trust towards automated reasoning. Automated reasoning leads necessarily to conflicts, and with that to the need for adaptation. Knowledge Graphs are an existential part of formalization in complex systems, e.g. as representation of beliefs of an AI. Strong AI, and with that one of the two main research areas of the early 21st century in Computer Science, struggles with the representation of conflicting beliefs, as well as with strategies for their resolution. We present a template based approach with an implementation on detecting and resolving conflicts in belief systems leading to a deeper insight into AI and its ability of self reflection. Without the understanding of how beliefs are handled in strong AI systems, the application to forensics is hurdled.
AI Defenders: Machine learning driven anomaly detection in critical infrastructures
(Gesellschaft für Informatik e.V., 2024) Nebebe, Betelhem; Kröckel, Pavlina; Yatagha, Romarick; Edeh, Natasha; Waedt, Karl; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
Previous studies have evaluated the suitability of different machine learning (ML) models for anomaly detection in critical infrastructures, which are pivotal due to the potential consequences of disruptions that can lead to safety risks, operational downtime, and financial losses. Ensuring robust anomaly detection for these systems within a company is vital to mitigate risks and maintain continuous operation. In this paper, we utilize a time-series labeled dataset obtained from a hydraulic model simulator (ELVEES simulator) to conduct a comprehensive and comparative analysis of various ML models. The study aims to demonstrate how different models effectively identify and respond to anomalies, underscoring the potential artificial intelligence (AI) driven systems to mitigate attacks. With the chosen approach, we expect to achieve the best performance in detecting two types of anomalies: point anomaly and contextual anomaly.
Data Analytics as a Service – Challenges and Opportunities: An Introduction to DAS-24
(Gesellschaft für Informatik e.V., 2024) Keller, Barbara; Möhring, Michael; Augenstein, Friedrich; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
Data Analytics is an important topic in current and future services. Different opportunities and challenges occur when implementing it. The paper describes some core aspects of Data Analytics Services as well as concrete application domains. Furthermore, an overview of the workshop and specifics of Analytic Services as well as future research streams are provided.
Comparison of Classifiers for Eye-Tracking Data
(Gesellschaft für Informatik e.V., 2024) Landes, Jennifer; Köppl, Sonja; Klettke, Meike; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
This paper delves into the initial stages of data analysis, focusing on the classification of eye-tracking data. Six machine learning algorithms, namely XGBoost, Random Forest, Naive Bayes, Logistic Regression, Gradient Boosting Machines, and Neural Networks, were employed to predict cheating behavior based on a dataset comprising records from 25 students. Their performance was evaluated using metrics such as accuracy, precision, recall, F1 score, confusion matrix, and feature importance. Results indicate that Random Forest and its optimized version exhibit balanced performance, making them promising candidates for cheating prediction. The overarching research project investigates academic misconduct in the realm of online assessments, seeking to comprehend the behaviors and methodologies involved. An eye-tracking experiment was conducted to gain deeper insights into the timing and mannerisms of students engaging in academic misconduct.
Methods and techniques for plant and weed detection creating a database for future computer vision systems in weed control and practical implementations: Insights from the KIdetect project, funded by the BMEL
(Gesellschaft für Informatik e.V., 2024) Noori, Faryal; Hopf, Lucas; Flierl, Philipp; Zimmermann, Alexander; Niedermeier, Michael; Holst, Gerhard; Schmailzl, Anton; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
This paper explores weed detection methodologies in vertical farming systems using Short Wave Infrared (SWIR) and Visual (VIS) camera technology, alongside computer vision techniques and Artificial Intelligence (AI). It investigates pixel-matching techniques for stereo-image processing to enhance imaging accuracy and reliability in agriculture. Classical methods like SIFT FLANN Matcher, Epiline Matcher, and Partial Epiline Matcher are evaluated. The paper also examines the integration of AI with classical pixel-matching methods to streamline pixel pair identification. Real-world accuracy assessments demonstrate promising results, facilitating practical applications. Additionally, it covers camera calibration and image rectification tasks on VIS cameras to support 3D reconstruction for plant structure analysis, alongside Stereo pixel matching. Overall, it provides valuable insights into stereo image analysis in agriculture, fostering future research and practical implementations in precision agriculture and computer vision systems.
Towards Sustainable Machine Learning: Analyzing Energy-Efficient Algorithmic Strategies for Environmental Sensor Data
(Gesellschaft für Informatik e.V., 2024) Cetkin, Berkay; Begic Fazlic, Lejla; Guldner, Achim; Naumann, Stefan; Dartmann, Guido; Klein, Maike; Krupka, Daniel; Winter, Cornelia; Gergeleit, Martin; Martin, Ludger
This study evaluates the energy efficiency of machine learning (ML) classification models across 49 test setups, each representing different conditions derived from a set of scenarios. Utilizing internet of things (IoT) technology with an ESP8266 microcontroller, we collected and analyzed environmental data including temperature, humidity, and CO2 levels from a simulated room environment. We measured energy consumption for data preprocessing, model training, and testing, alongside energy efficiency metrics that consider output, processing time, and F1 score. The study also performed correlation analyses to explore the relationship between energy consumption and performance metrics. Furthermore, it assessed the trade-offs between accuracy and energy efficiency by comparing an ensemble model to its constituent algorithms. The measurements, conducted according to the Green Software Measurement Model (GSMM), provide essential insights into selecting energy-efficient algorithms for a broad spectrum of IoT applications.
Turning Tenders into Tinder: How AI and Open Data can spark Bidding Matches
(Gesellschaft für Informatik e.V., 2024) Klassen, Gerhard; Bauer, Luca T.; Fritzsche, Robin; Kordyaka, Bastian; Weber,Sebastian; Niehaves, Björn; Wimmer, Maria A.; Räckers, Michael; Hünemohr, Holger
Public procurement in Germany, accounting for 15% of GDP, is plagued by inefficiencies, high costs, and lack of transparency. This study investigates how Open Data can enhance competitive bidding and streamline the identification of suitable companies. Using the German public procurement market, we propose a web-based portal employing machine learning to automate tender and bidder matchmaking. Our methodology includes data collection, company profiling, and NLPbased similarity searches. Results indicate that integrating Open Data can increase competition, improve bid quality, and enhance procurement efficiency. This research provides a scalable framework for more transparent and effective public procurement practices, with potential applications in other regions and sectors.
Model-Driven Engineering for Machine Learning Code Generation using SysML
(Gesellschaft für Informatik e.V., 2024) Rädler, Simon; Rupp, Matthias; Rigger, Eugen; Rinderle-Ma, Stefanie; Michael, Judith; Weske, Mathias
The complexity of engineering products increases due to more functions, components, and the number of involved disciplines. In this respect, Data-Driven Engineering (DDE) aims to integrate machine learning to support product development and help manage the increasing complexity of engineered systems. Still, the potential and opportunities of DDE are not entirely reflected in practice, which among others originate from the rarely available machine learning experts on the market and the effort for the implementation in practice. In this respect, this work depicts an approach based on model-driven engineering, allowing to automatically derive executable machine learning code based on machine learning task formalization using the general-purpose modeling language SysML. The main focus of the approach is on the generality of the model transformation using templates so that extensions and changes to the code generation can be integrated without requiring profound modifications to the code generator. The approach is evaluated in a use case in the domain of Cyber-Physical Systems, i.e., weather forecast prediction based on data from a Cyber-Physical weather system. The derived executable code promises to reduce the time for the implementation and supports the standardization of machine learning implementations within a company due to templates.