TY - CHAP A1 - Tresp, Volker A1 - Udluft, Steffen A1 - Hein, Daniel A1 - Hauptmann, Werner A1 - Leib, Martin A1 - Mutschler, Christopher A1 - Scherer, Daniel D. A1 - Mauerer, Wolfgang T1 - Workshop Summary: Quantum Machine Learning T2 - 2023 IEEE International Conference on Quantum Computing and Engineering, Bellevue, WA, United States, September 17-22, 2023 Y1 - 2023 U6 - https://doi.org/10.1109/QCE57702.2023.10174 PB - IEEE ER - TY - JOUR A1 - Pozzobon, Enrico A1 - Weiß, Nils A1 - Mottok, Jürgen A1 - Matoušek, Václav T1 - An evolutionary fault injection settings search algorithm for attacks on safe and secure embedded systems JF - Neural Network World (NNW) Y1 - 2023 U6 - https://doi.org/10.14311/NNW.2023.33.020 VL - 33 IS - 5 SP - 357 EP - 374 PB - Czech Technical University in Prague ER - TY - CHAP A1 - Gogeißl, Martin A1 - Safi, Hila A1 - Mauerer, Wolfgang T1 - Quantum Data Encoding Patterns and their Consequences T2 - Q-Data '24: Proceedings of the 1st Workshop on Quantum Computing and Quantum-Inspired Technology for Data-Intensive Systems and Applications, June 9 - 15, 2024, Santiago AA Chile N2 - The use of quantum processing units (QPUs) promises speed-ups for solving computational problems, in particular for discrete optimisation. While a few groundbreaking algorithmic approaches are known that can provably outperform classical computers, we observe a scarcity of programming abstractions for constructing efficient quantum algorithms. A good fraction of the literature that addresses solving concrete problems related to database management concentrates on casting them as quadratic unconstrained binary optimisation problems (QUBOs), which can then, among others, be processed on gate-based machines (using the quantum approximate optimisation algorithm), or quantum annealers. A critical aspect that affects efficiency and scalability of either of these approaches is how classical data are loaded into qubits, respectively how problems are encoded into QUBO representation. The effectiveness of encodings is known to be of crucial importance for quantum computers, especially since the amount of available qubits is strongly limited in the era of noisy, intermediate-size quantum computers. In this paper, we present three encoding patterns, discuss their impact on scalability, and their ease of use. We consider the recreational (yet computationally challenging) Sudoku problem and its reduction to graph colouring as an illustrative example to discuss their individual benefits and disadvantages. Our aim is enable database researchers to choose an appropriate encoding scheme for their purpose without having to acquire in-depth knowledge on quantum peculiarities, thus easing the path towards applying quantum acceleration on data management systems. Y1 - 2024 SN - 979-8-4007-0553-3 U6 - https://doi.org/10.1145/3665225.3665446 SP - 27 EP - 37 PB - ACM ER - TY - INPR A1 - Jung, Matthias A1 - Krumke, Sven O. A1 - Schroth, Christof A1 - Lobe, Elisabeth A1 - Mauerer, Wolfgang T1 - QCEDA: Using Quantum Computers for EDA N2 - The field of Electronic Design Automation (EDA) is crucial for microelectronics, but the increasing complexity of Integrated Circuits (ICs) poses challenges for conventional EDA: Corresponding problems are often NP-hard and are therefore in general solved by heuristics, not guaranteeing optimal solutions. Quantum computers may offer better solutions due to their potential for optimization through entanglement, superposition, and interference. Most of the works in the area of EDA and quantum computers focus on how to use EDA for building quantum circuits. However, almost no research focuses on exploiting quantum computers for solving EDA problems. Therefore, this paper investigates the feasibility and potential of quantum computing for a typical EDA optimization problem broken down to the Min-k-Union problem. The problem is mathematically transformed into a Quadratic Unconstrained Binary Optimization (QUBO) problem, which was successfully solved on an IBM quantum computer and a D-Wave quantum annealer. Y1 - 2024 ER - TY - CHAP A1 - Mauerer, Wolfgang ED - Exman, Iaakov ED - Perez-Castillo, Ricardo ED - Piattini, Mario ED - Felderer, Michael T1 - Superoperators for Quantum Software Engineering T2 - Quantum Software: Aspects of Theory and System Design N2 - As implementations of quantum computers grow in size and maturity, the question of how to program this new class of machines is attracting increasing attention in the software engineering domain. Yet, many questions from how to design expressible quantum languages augmented with formal semantics via implementing appropriate optimizing compilers to abstracting details of machine properties in software systems remain challenging. Performing research at this intersection of quantum computing and software engineering requires sufficient knowledge of the physical processes underlying quantum computations, and how to model these. In this chapter, we review a superoperator-based approach to quantum dynamics, as it can provide means that are sufficiently abstract, yet concrete enough to be useful in quantum software and systems engineering, and outline how it is used in several important applications in the field. KW - quantum computing KW - quantum software engineering KW - software development KW - software engineering Y1 - 2024 U6 - https://doi.org/10.1007/978-3-031-64136-7_3 SN - 978-3-031-64136-7 PB - Springer Nature ER - TY - CHAP A1 - Falter, Sandro A1 - Brunkh, Gerald A1 - Wess, Max A1 - Fischer, Sebastian T1 - Automated Vulnerability Scanner for the Cyber Resilience Act T2 - CLOUD COMPUTING 2024 : The Fifteenth International Conference on Cloud Computing, GRIDs, and Virtualization, 15, 2024, Venice N2 - This paper explores the mitigation of the compliance burdens faced by manufacturers of digital products under the Cyber Resilience Act. After providing a concise overview of the Cyber Resilience Act and pinpointing pivotal areas where tool-based interventions could reduce the regulatory strain on manufacturers, we introduce two prototypes: a digital checklist for product classification and a prototype to streamline the analysis and monitoring of the security state of software along the software development life cycle. As the second prototype is based on Static Application Software Testing and Software Component Analysis, we validate the approach through benchmark tests. While Static Application Software Testing tools show promise in identifying vulnerabilities, additional tests are needed for full compliance with the Cyber Resilience Act. In general, the prototypes serve as an entry point for identifying possible automation potential to alleviate the compliance burdens of manufacturers. KW - cra KW - cyber resilience act KW - vulnerability scanner KW - reporting KW - iot KW - cloud Y1 - 2024 UR - https://www.thinkmind.org/library/CLOUD_COMPUTING/CLOUD_COMPUTING_2024/cloud_computing_2024_1_40_28004.html SN - 978-1-68558-156-5 SP - 13 EP - 18 PB - IARIA ER - TY - CHAP A1 - Buchmann, Thomas A1 - Peinl, René A1 - Schwägerl, Felix T1 - White-box LLM-supported Low-code Engineering: A Vision and First Insights T2 - Proceedings of the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems N2 - Low-code development (LCD) platforms promise to empower citizen developers to define core domain models and rules for business applications. However, as domain rules grow complex, LCD platforms may fail to do so effectively. Generative AI, driven by large language models (LLMs), offers source code generation from natural language but suffers from its non-deterministic black-box nature and limited explainability. Therefore, rather than having LLMs generate entire applications from single prompts, we advocate for a white-box approach allowing citizen developers to specify domain models semi-formally, attaching constraints and operations as natural language annotations. These annotations are fed incrementally into an LLM contextualized with the generated application stub. This results in deterministic and better explainable generation of static application components, while offering citizen developers an appropriate level of abstraction. We report on a case study in manufacturing execution systems, where the implementation of the approach provides first insights. KW - Model-driven engineering KW - large language models KW - low-code KW - semiformal KW - artificial intelligence Y1 - 2024 U6 - https://doi.org/10.1145/3652620.368780 SP - 556 EP - 560 PB - ACM CY - New York, NY, USA ER - TY - CHAP A1 - Füreder, Lukas A1 - Mottok, Jürgen T1 - Assessment of a MACsec-based Security System for Use in Critical Infrastructure Communication T2 - Proceedings of the 12th Prague Embedded Systems Workshop, June 27 - 29, 2024, Horoměřice, Czech Republic N2 - This paper investigates the integration of Media Access Control Security (MACsec) into the communication of critical infrastructure, specifically within power grid applications, such as Substation Automation Systems (SAS) using the IEC 61850 standard. Building on the principles of both standards, this study aims to determine if MACsec can meet the security and performance requirements set by IEC 62351 for power system communications. Furthermore, a test environment containing a number of Intelligent Electronic Devices (IEDs) supporting communication compliant to all IEC 61850 message types is established to evaluate this integration. The results of the measurements executed in this environment indicate that MACsec could secure all types of messages, such as Manufacturing Message Specification (MMS), Sampled-Value (SV) and Generic Object Oriented Substation Events (GOOSE), within the required time periods without significant delays. Even with additional encryption activated in the cipher suite, the resulting transmission times are well below the required times. This suggests that MACsec can enhance the security goals for industrial communication by providing confidentiality in addition to the already mandated assurance of authenticity and integrity to all messages without compromising performance. Only the requirement for end-to-end security cannot be met by MACsec in this configuration, as the security system re-encrypts with every hop of the transmission. For this reason, we propose a hybrid approach of Transport Layer Security (TLS) and MACsec as part of future work. KW - MACsec KW - IEC61850 KW - IEC62351 KW - GOOSE KW - Secure Communication Y1 - 2024 UR - https://pesw.fit.cvut.cz/2024/PESW_2024.pdf SN - 978-80-01-07303-2 SP - 51 EP - 59 ER - TY - INPR A1 - Pagel, Johannes A1 - Vogl, Stefanie A1 - Israel, Laura T1 - Analyzing the Impact of Redaction on Document Classification Performance of Deep CNN Models N2 - Many companies are facing growing data archives leading to an increasing focus on the automated classification of documents in corporate processes. Due to data protection guidelines, development with clear data is often difficult. One way to overcome this difficulty is to desensitize documents using document redaction. The following study, therefore, examines the impact of redaction on the document classification performance of a deep CNN model by analyzing how the classifica- tion performance deteriorates when the model is trained on unredacted documents and evaluated on redacted data (unredacted model) or trained on redacted data and applied to unredacted documents (redacted model). For the former condition, a loss in accuracy of 2.56%P was found and a loss of 2.08%P for the latter. We were also able to show that the loss in performance differed greatly between document classes and was influenced by their proportion of redacted area (unredacted model: r=0.31; redacted model: r=0.87). For the model trained with redacted and evaluated on unredacted data, we also determined that the decrease in classification accu- racy was affected by the intra-class variability of the redacted area (r=0.74). From these results, recommendations for dealing with redacted data in document classification systems are derived. Y1 - 2024 U6 - https://doi.org/10.31219/osf.io/sntb3 PB - OSFPreprints ER - TY - CHAP A1 - Heinz, Florian T1 - Robust Interpolation of Arbitrary-Dimensional Moving Regions in Databases T2 - Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data, October 29th, 2024, Atlanta, USA N2 - Moving Objects Databases are designed to store, process and efficiently search for database objects with attributes that can change over time. Examples are moving points, that change position over time, or, as a more complex data type, moving regions that can also change shape. For moving regions to be practically usable, methods for creating those objects have to be provided. The prevailing method for 2-dimensional moving regions is to create an interpolation of two static regions. Since this is a non-trivial task, this is referred to as the "Region Interpolation Problem", which still can not be considered as solved, since several unsolved questions remain. This work strives to give an overview on the Region Interpolation Problem, discuss an extension to 3d and higher dimensions and to present and discuss solutions to address some of the remaining obstacles. Y1 - 2024 U6 - https://doi.org/10.1145/3681769.3698579 SP - 13 EP - 21 PB - ACM CY - New York, NY, USA ER - TY - CHAP A1 - Heinz, Florian T1 - Creating Moving Regions from Satellite Scan Data T2 - SIGSPATIAL '24: Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems, October 29 - November 1, 2024, Atlanta, GA, USA N2 - Moving objects databases are specialized on storing and processing objects with spatial attributes that change over time. An important class of objects are moving regions that can change shape and position over time. Currently, the prevailing method for constructing moving regions is to interpolate them from snapshots. In this paper, an alternative method is proposed, that is better suitable for certain kinds of data as, for example, satellite scans of the earth surface. For instance, the NASA provides datasets with active fire data in near real-time from the Visible Infrared Imaging Radiometer Suite (VIIRS) sensor, attached to satellites as the Suomi NPP and NOAA-20. These satellites orbit earth about 14 times a day and provide full global coverage twice a day. Using these satellites, datasets are compiled that provide locations of active fires on earth as lists of positions and timestamps. This paper describes an alternative, better suitable method for creating moving regions from these lists, which can then be imported into and processed by moving objects databases. KW - spatial data KW - spatiotemporal data KW - moving objects KW - remote sensing Y1 - 2024 SN - 979-8-4007-1107-7 U6 - https://doi.org/10.1145/3678717.3691214 SP - 641 EP - 644 PB - ACM CY - New York, NY, USA ER - TY - CHAP A1 - Schlager, Reinhold A1 - Schildgen, Johannes T1 - A Query-Rewriting-based Implementation for Temporal Data Management T2 - LWDA’24: Lernen, Wissen, Daten, Analysen. September 23–25, 2024, Würzburg, Germany N2 - Temporal data management is used to query historical data, identify trends and changes, and make forecasts for the future. This paper provides a query-rewriting approach to implement temporal data management in the data-warehouse system Exasol by using so-called preprocessor scripts. Preprocessor scripts allow for executing custom Lua code and modifying SQL commands. Our approach does not need to undertake additional manual effort by the user. History tables and associated views are created in the background. Data records are automatically archived if they are updated or deleted, and the SELECT command is extended with the AS OF SYSTEM TIME clause as proposed by the SQL Standard. KW - Temporal data management KW - Data warehouse KW - Exasol KW - Database Y1 - 2024 UR - https://www.informatik.uni-wuerzburg.de/fileadmin/1003-lwda24/LWDA_Paper/DB_LWDA_CRC_164.pdf ER - TY - CHAP A1 - Hassmann, Tobias A1 - Westner, Markus T1 - IS executives and sustainability BT - A literature review T2 - 26th International Conference on Business Informatics (CBI), 09-13 September 2024, Vienna, Austria N2 - The pressing global sustainability challenges, encapsulated in the United Nations’ Sustainable Development Goals (SDGs), require profound transformations across multiple levels. It is imperative for the Information Systems (IS) discipline to engage in addressing these challenges. This paper aims to contribute to this imperative through a scoping literature review, examining factors that enable IS executives to drive sustainability outcomes within organizations, utilizing the Input-Mediator-Outcome (IMO) framework. By analyzing 31 articles from important IS journals and conferences between 2008 and 2024, this review identifies key input factors for sustainability outcomes, such as individual IS executive inputs, the role of the Top Management Team (TMT) setting and organizational contexts, as well as external influences. In addition, it explores how team-specific processes can augment sustainability efforts. The paper concludes by proposing future research questions to address underrepresented SDGs, investigate external impact factors more thoroughly, and emphasize the role of individual IS executive inputs. These insights aspire to advance the understanding of IS executives’ potential to influence sustainability in organizational settings. KW - IS executives KW - chief information officer KW - chief digital officer KW - sustainability KW - literature review Y1 - 2024 SN - 979-8-3315-2909-3 U6 - https://doi.org/10.1109/CBI62504.2024.00017 SN - 2378-1971 PB - IEEE ER - TY - INPR A1 - Stragapede, Giuseppe A1 - Vera-Rodriguez, Ruben A1 - Tolosana, Ruben A1 - Morales, Aythami A1 - DeAndres-Tame, Ivan A1 - Damer, Naser A1 - Fierrez, Julian A1 - Ortega-Garcia, Javier A1 - Acien, Alejandro A1 - González, Nahuel A1 - Shadrikov, Andrei A1 - Gordin, Dmitrii A1 - Schmitt, Leon A1 - Wimmer, Daniel A1 - Großmann, Christoph A1 - Krieger, Joerdis A1 - Heinz, Florian A1 - Krestel, Ron A1 - Mayer, Christoffer A1 - Haberl, Simon A1 - Gschrey, Helena A1 - Yamagishi, Yosuke A1 - Saha, Sanjay A1 - Rasnayaka, Sanka A1 - Wickramanayake, Sandareka A1 - Sim, Terence A1 - Gutfeter, Weronika A1 - Baran, Adam A1 - Krzyszton, Mateusz A1 - Jaskóła, Przemysław T1 - Kvc-Ongoing: Keystroke Verification Challenge N2 - This article presents the Keystroke Verification Challenge - onGoing (KVC-onGoing), on which researchers can easily benchmark their systems in a common platform using large-scale public databases, the Aalto University Keystroke databases, and a standard experimental protocol. The keystroke data consist of tweet-long sequences of variable transcript text from over 185,000 subjects, acquired through desktop and mobile keyboards simulating real-life conditions. The results on the evaluation set of KVC-onGoing have proved the high discriminative power of keystroke dynamics, reaching values as low as 3.33% of Equal Error Rate (EER) and 11.96% of False Non-Match Rate (FNMR) @1% False Match Rate (FMR) in the desktop scenario, and 3.61% of EER and 17.44% of FNMR @1% at FMR in the mobile scenario, significantly improving previous state-of-the-art results. Concerning demographic fairness, the analyzed scores reflect the subjects’ age and gender to various extents, not negligible in a few cases. The framework runs on CodaLab. Y1 - 2024 U6 - https://doi.org/10.2139/ssrn.4743934 ER - TY - CHAP A1 - Heinz, Florian A1 - Kluge, Martin ED - Aiello, Marco ED - Barzen, Johanna ED - Dustdar, Schahram ED - Leymann, Frank T1 - Design and Implementation of a High Performance Domain Name Service on Commodity Hardware T2 - Service-Oriented Computing : 18th Symposium and Summer School, SummerSOC 2024, Crete, Greece, June 24-29, 2024, Revised Selected Papers N2 - The internet Domain Name System (DNS) is one of the essential components of the World Wide Web and the whole internet. The core concept is a large distributed and hierarchical database that translates internet domain names into host addresses and other supplemental information. Name servers can serve millions of domains and usually have to answer thousands of requests per second. Because of their vital function for any internet service, domain name servers are regularly target of Denial-of-Service attacks, where millions of queries per second are used to overload the database system. This work describes an approach on how to achieve answer rates in this dimension with a single server built from low-cost commodity hardware. Y1 - 2024 SN - 978-3-031-72577-7 U6 - https://doi.org/10.1007/978-3-031-72578-4_9 SP - 162 EP - 171 PB - Springer Nature CY - Cham ER - TY - CHAP A1 - Safi, Hila A1 - Wintersperger, Karen A1 - Mauerer, Wolfgang T1 - Influence of HW-SW-Co-Design on Quantum Computing Scalability T2 - 2023 IEEE International Conference on Quantum Software (QSW), Chicago, IL, USA, 02-08 July 2023 N2 - The use of quantum processing units (QPUs) promises speed-ups for solving computational problems. Yet, current devices are limited by the number of qubits and suffer from significant imperfections, which prevents achieving quantum advantage. To step towards practical utility, one approach is to apply hardware-software co-design methods. This can involve tailoring problem formulations and algorithms to the quantum execution environment, but also entails the possibility of adapting physical properties of the QPU to specific applications. In this work, we follow the latter path, and investigate how key figures— circuit depth and gate count—required to solve four cornerstone NP-complete problems vary with tailored hardware properties. Our results reveal that achieving near-optimal performance and properties does not necessarily require optimal quantum hardware, but can be satisfied with much simpler structures that can potentially be realised for many hardware approaches.m Using statistical analysis techniques, we additionally identify an underlying general model that applies to all subject problems. This suggests that our results may be universally applicable to other algorithms and problem domains, and tailored QPUs can find utility outside their initially envisaged problem domains. The substantial possible improvements nonetheless highlight the importance of QPU tailoring to progress towards practical deployment and scalability of quantum software. KW - quantum computing KW - software engineering KW - hardware-software co-design KW - quantum algorithm performance analysis KW - scalability of quantum applications Y1 - 2023 SN - 979-8-3503-0479-4 U6 - https://doi.org/10.1109/QSW59989.2023.00022 SP - 104 EP - 115 PB - IEEE ER - TY - JOUR A1 - Wintersperger, Karen A1 - Dommert, Florian A1 - Ehmer, Thomas A1 - Hoursanov, Andrey A1 - Klepsch, Johannes A1 - Mauerer, Wolfgang A1 - Reuber, Georg A1 - Strohm, Thomas A1 - Yin, Ming A1 - Luber, Sebastian T1 - Neutral Atom Quantum Computing Hardware: Performance and End-User Perspective JF - EPJ Quantum Technology N2 - We present an industrial end-user perspective on the current state of quantum computing hardware for one specific technological approach, the neutral atom platform. Our aim is to assist developers in understanding the impact of the specific properties of these devices on the effectiveness of algorithm execution. Based on discussions with different vendors and recent literature, we discuss the performance data of the neutral atom platform. Specifically, we focus on the physical qubit architecture, which affects state preparation, qubit-to-qubit connectivity, gate fidelities, native gate instruction set, and individual qubit stability. These factors determine both the quantum-part execution time and the end-to-end wall clock time relevant for end-users, but also the ability to perform fault-tolerant quantum computation in the future. We end with an overview of which applications have been shown to be well suited for the peculiar properties of neutral atom-based quantum computers. KW - Neutral atom quantum computers KW - Review KW - Quantum computing platforms KW - Performance metrics KW - Benchmarks Y1 - 2023 U6 - https://doi.org/10.1140/epjqt/s40507-023-00190-1 VL - 10 PB - Springer Nature ER - TY - CHAP A1 - Greiwe, Felix A1 - Krüger, Tom A1 - Mauerer, Wolfgang T1 - Effects of Imperfections on Quantum Algorithms BT - A Software Engineering Perspective T2 - 2023 IEEE International Conference on Quantum Software (QSW), Chicago, IL, USA, 02-08 July 2023 N2 - Quantum computers promise considerable speedups over classical approaches, which has raised interest from many disciplines. Since any currently available implementations suffer from noise and imperfections, achieving concrete speedups for meaningful problem sizes remains a major challenge. Yet, imperfections and noise may remain present in quantum computing for a long while. Such limitations play no role in classical software computing, and software engineers are typically not well accustomed to considering such imperfections, albeit they substantially influence core properties of software and systems. In this paper, we show how to model imperfections with an approach tailored to (quantum) software engineers. We intuitively illustrate, using numerical simulations, how imperfections influence core properties of quantum algorithms on NISQ systems, and show possible options for tailoring future NISQ machines to improve system performance in a co-design approach. Our results are obtained from a software framework that we provide in form of an easy-to-use reproduction package. It does not require computer scientists to acquire deep physical knowledge on noise, yet provide tangible and intuitively accessible means of interpreting the influence of noise on common software quality and performance indicators. KW - noisy quantum computing KW - NISQ systems KW - quantum software engineering KW - HW-SW co-design Y1 - 2023 U6 - https://doi.org/10.1109/QSW59989.2023.00014 SP - 31 EP - 42 PB - IEEE ER - TY - CHAP A1 - Yue, Tao A1 - Mauerer, Wolfgang A1 - Ali, Shaukat A1 - Taibi, Davide T1 - Challenges and Opportunities in Quantum Software Architecture T2 - Software Architecture: Research Roadmaps from the Community N2 - Quantum computing is a relatively new paradigm that has raised considerable interest in physics and computer science in general but has so far received little attention in software engineering and architecture. Hybrid applications that consist of both quantum and classical components require the development of appropriate quantum software architectures. However, given that quantum software engineering (QSE) in general is a new research area, quantum software architecture–a subresearch area in QSE is also understudied. The goal of this chapter is to provide a list of research challenges and opportunities for such architectures. In addition, to make the content understandable to a broader computer science audience, we provide a brief overview of quantum computing and explain the essential technical foundations. KW - Quantum Computing KW - Software Architecture KW - Quantum Applications KW - Quantum Software Engineering Y1 - 2023 SN - 978-3-031-36847-9 U6 - https://doi.org/10.1007/978-3-031-36847-9_1 SP - 1 EP - 23 ER - TY - CHAP A1 - Schildgen, Johannes A1 - Heinz, Florian T1 - Interactive SQL Queries and Program Code in Presentations T2 - Datenbanksysteme für Business, Technologie und Web (BTW2023), 06.-10. März 2023, Dresden N2 - Nowadays, most database lectures are performed with an accompanying visual presentation that further illustrates the conveyed facts. Conventional presentation software allows dynamic elements up to a certain level, for example revealing or changing parts of the slide step by step, or even an interaction with the viewers by means of polls or similar mechanisms. Recently, HTML-and browser-based frameworks for presentations have emerged, which allow an even higher degree of flexibility due to the manifold possibilities of HTML5 and JavaScript. This paper presents an approach of how to interactively modify parts of a slide during the presentation, like SQL-based queries or program code snippets, and show the results pretty-printed on the corresponding slide in real-time. This enables the lecturer to easily show more examples, and answer and illustrate side questions, which they did not prepare in advance. KW - Lecture Slides KW - SQL Y1 - 2023 SN - 978-3-88579-725-8 U6 - https://doi.org/10.18420/BTW2023-39 SP - 687 EP - 693 PB - Gesellschaft für Informatik e.V. CY - Bonn ER - TY - CHAP A1 - Bittner, Dominik A1 - Hendricks, Ricky-Ricardo A1 - Horn, Luca A1 - Mottok, Jürgen T1 - In-depth Benchmarking of Transfer Learning Techniques for Improved Bottle Recognition T2 - 2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS), Guayaquil, Ecuador, 04-07 July 2023 N2 - An immense diversity in bottle types requires high accuracy during sorting for recycling purposes by breweries. This extremely complex and time-consuming procedure can result in enormous additional costs for them. This paper presents transfer learning-based algorithms for classifying beer bottle brands using camera images, applicable in individual sorting solutions for different use cases. The problem is tackled using customised EfficientNet, InceptionResNet and VGG models along with an augmented dataset. In addition, a detailed analysis of different model and parameter combinations is performed, enabling tailor-made technologies for specific conditions and resource limitations. In accompanying validations and subsequent tests, a test accuracy of 100% in the recognition of beer brands could be achieved, proving the proposed method fully contributes to the solution of the problem. KW - Analytical models KW - Costs KW - Transfer learning KW - Benchmark testing KW - Cameras KW - Pattern recognition KW - Recycling Y1 - 2023 SN - 979-8-3503-3337-4 U6 - https://doi.org/10.1109/ICPRS58416.2023.10178995 SP - 1 EP - 6 PB - IEEE ER -