The 10 most recently published documents
The evolution of chatbots has been marked by ongoing efforts to bridge the gap between general language understanding and specialized domain knowledge. Previous efforts have primarily focused on improving language models for broader applicability, often overlooking the nuanced requirements of specific domains. A significant step forward is taken in the research by demonstrating how the Retrieval-Augmented Generation methodology can be seamlessly integrated with LangChain and LlamaIndex to overcome this limitation. This integration not only improves chatbot performance in specialized contexts but also sets a new precedent for the adaptability of chatbot technologies. The practical implications are vast, ranging from improved user experience in customer service to increased efficiency in data-sensitive environments such as healthcare and finance. A distinctive contribution to the field of generative Artificial Intelligence is marked by the innovative approach, paving the way for more sophisticated, context-aware chatbot applications.
The introduction of intelligent technologies is shaping the era of digital transformation, while companies face the challenge of evolving in a dynamic environment. Intelligent systems and services are the target of many current digitalization efforts and are part of this digital transformation. Artificial intelligence in particular acts as a key driver of digitalization and has a strong influence on new opportunities for shared value creation. This article presents digital strategy patterns that facilitate the implementation of digital strategies and the effective integration of new technologies in companies. The motivation stems from the need to prepare for the upcoming wave of intelligent systems and services and to develop innovative solutions. The methodology is based on the development of a pattern catalog that supports the implementation of digital strategies. The Digital Strategy Patterns enable organizations to combine digital strategies and artificial intelligence. The findings emphasize the key role of artificial intelligence and offer a structured approach to overcoming future challenges in corporate development.
The volume includes papers presented at the International KES Conference on Human Centred Intelligent Systems 2024 (KES HCIS 2024), held in Madeira, Portugal on June 19-21, 2024. This book highlights new trends and challenges in intelligent systems, which play an important part in the digital transformation of many areas of science and practice. It includes papers offering a deeper understanding of the human-centred perspective on artificial intelligence, of intelligent value co-creation, ethics, value-oriented digital models, transparency, and intelligent digital architectures and engineering to support digital services and intelligent systems, the transformation of structures in digital businesses and intelligent systems based on human practices, as well as the study of interaction and the co-adaptation of humans and systems
Human-centered intelligent systems (HCIS), which are at the forefront of the AI and HCI fields, are dedicated to enhancing human experiences and interactions with technology. HCIS are designed to be intuitive, responsive, and adaptable to human needs and preferences, aiming to empower users and foster positive interactions. By utilizing AI techniques, such as machine learning, natural language processing, and computer vision, HCIS aims to make technology more accessible and beneficial across various industries and domains.
You don't just use software processes, you have to engineer them: a teachers' experience report
(2025)
Software processes are the game plan to develop comprehensive software systems, and there are many ways to teach software processes. Nowadays, the normal approach is to teach students to use software processes correctly, usually by explaining what agile methods are about or by introducing tools that already implement selected processes, and then letting students apply such selected tools and methods in smaller projects or project courses. However, while this approach addresses the application of, e.g., Scrum or Unit Testing, the question of how a company develops its own software process is not answered. With this paper, we address this issue and share our experiences from more than 15 years of teaching the analysis, design, realization, and improvement of software processes in our joint Software Process Engineering course, which is based on a structured Software Process Improvement model. We contribute insights into the process improvement model that builds the foundation of the course, an overview of the course content, and we share our experiences, lessons learned, and recommendations for teachers.
Inductors are critical components in power electronic converters, determining their efficiency and size. A converter's performance is limited by the losses associated with inductors. In lower power applications, commercially available off-the-shelf inductors are usually used, but their losses are often difficult to predict solely based on datasheet values. Therefore, a direct measurement is typically required; here, a separate measurement of the dc and an ac loss is proposed to simplify the measurement process. This paper presents a low-cost setup based on affordable equipment, such as a self-built current probe, and uses simple compensation methods that allow developers to efficiently and cost-effectively measure losses in inductors. The setup is designed to emulate conditions comparable to real-world applications. The proposed procedure and setup are validated through experimental results, and potential sources of error and methods for compensation are discussed.
A circuit structure and operating method for achieving a soft-switching operation of a non-inverting buck-boost converter is proposed. The converter is derived from the two-switch buck-boost converter. It achieves ZVS by replacing a diode with an active switch, driven with a gate signal complementary to the main transistors’ control signals. In this way, the inductor current can be clamped and used to achieve soft-switching transitions of all transistors in the converter. The circuit achieves ZVS by design, and the ZVS range can be adjusted by adding a capacitor parallel to a diode or switch. The converter does not need a complex control or sensor circuit for proper operation. The operating principle and converter design are described in detail. The proposed converter operation is verified using simulations and experimental results.
Ambivalenzerfahrungen sind komplexe Phänomene, die das Denken, Fühlen, Wollen und Handeln betreffen. Im vorliegenden Beitrag soll das subjektive Betroffensein, das, was wir spüren, wenn wir "ambivalent sind", näher betrachtet werden. Auf der Grundlage der Phänomenologie nach Hermann Schmitz wird die "innere" Dynamik, die beim Spüren von Ambivalenzen entsteht, zugänglich gemacht. Als theoretische Rahmung wird auf die Differenz von Körper und Leib in der philosophischen Anthropologie Helmuth Plessners zurückgegriffen, mit deren Hilfe erklärt werden soll, warum Menschen überhaupt Ambivalenzerfahrungen machen können. Die Leiblichkeit wird als der "Ort" hervorgehoben, an dem Ambivalenzerfahrungen als spürbare "Unruhen" auftreten. Anschließend werden Ambivalenzerfahrungen in einer "Struktur des Leibes" rekonstruiert. Die Untersuchung der leiblichen Dynamik des Ambivalenzerlebens lässt hoffen, dass dieses adäquater beschrieben, verstanden und – im Falle eines länger stockenden Lebensvollzugs – auch verändert werden kann.
This article presents a single-phase, single-stage unidirectional inverter derived from a non-inverting buck-boost dc/dc converter combined with a full bridge unfolder circuit. Three different operating modes to achieve zero-voltage switching (ZVS) are discussed and evaluated against each other, demonstrating the feasibility of a soft-switching operation for this converter. The circuit structure and operating principles are discussed in detail. A modular 400 W prototype utilizing GaN devices switching at 500 kHz was built to verify the design, using an input dc voltage range of 100 V to 400 V and delivering an ac output voltage of 230 V at 50 Hz.
Eine Herausforderung der Lehre ist die Vermittlung zwischen Theoriewissen und Praxis. Schon zu Beginn des Studiums sollte in der Lehre ein Bewusstsein für die Bedeutung von Theorien entwickelt werden. Anhand einer Einführungsveranstaltung wird dargestellt, wie Studierende an diese Thematik herangeführt werden können. Wert gelegt wird dabei auf einfache Sprache und eine stetige Bezugnahme auf die Motivation der Studierenden, praktische Arbeit leisten zu wollen