Institutes
-
Mathematik
(383)
-
Informatik
(1759)
Refine
Year of publication
Document Type
- Doctoral Thesis (92)
- Article (79)
- Bachelor Thesis (18)
- Book (16)
- Master's Thesis (10)
- Conference Proceeding (4)
- Contribution to a Periodical (4)
- Habilitation (2)
- Preprint (2)
- Diploma Thesis (1)
Has Fulltext
- yes (228)
Is part of the Bibliography
- no (228)
Keywords
- Machine Learning (5)
- NLP (5)
- large language models (5)
- mathematics education (4)
- ALICE (3)
- Annotation (3)
- Machine learning (3)
- MathCityMap (3)
- Text2Scene (3)
- TextAnnotator (3)
Institute
We construct an algorithm for computing the cycle classes of the spin components of a stratum of differentials in the moduli space of stable curves. In addition, we implement it within the Sage package admcycles. Our main strategy is to reconstruct these cycles by their restrictions to the boundary via clutching maps.
We compute the rational cohomology of the moduli space of non-singular genus 4 curves with $1$ marked point, using Gorinov-Vassiliev's method.
Generalized strata of meromorphic differentials are loci in the usual strata of differentials, where certain sets of residues sum up to zero. They appear naturally in the boundary of the multi-scale compactification of the usual strata. We will classify the connected components of generalized strata in genus different from one.
Truck platooning is a promising approach for reducing fuel consumption, improving road safety, and optimizing transport logistics. This paper presents a drone-based decentralized truck platooning system that leverages the advantages of Ultra-Wideband (UWB) technology for precise positioning, robust communication, and real-time control. Our approach integrates UWB sensors on both trucks and drones, creating a scalable and resilient platooning system that can handle dynamic traffic conditions and varying road environments. The decentralized nature of the proposed system allows for increased flexibility and adaptability compared to traditional centralized platooning approaches. The core platooning algorithm employs multi-objective optimization, taking into account fuel efficiency, travel time, and safety. We propose a strategy for the formation and management of platoons based on UWB sensor data with an emphasis on maintaining optimal inter-vehicle secure distances and compatibility between trucks. Simulation results demonstrate the effectiveness of our approach in achieving efficient and stable platooning while addressing the challenges posed by real-world traffic scenarios. The proposed drone-based decentralized platooning system with UWB technology paves the way for the next generation of intelligent transportation systems that are more efficient, safer, and environment friendly.
In this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predictions into another set of NN. Our exploration starts from an initial preliminary study and extends to various ensemble techniques including bagging, stacking, and finally cascading. The cascading ensemble involves training a second layer of models on the predictions of the first. This cascading structure, combined with ensemble voting for the final prediction, aims to exploit the strengths of multiple models while mitigating their individual weaknesses. Our results demonstrate significant improvement in prediction accuracy, providing a compelling case for the potential utility of these techniques in healthcare applications, specifically for prediction of diabetes where we achieve compelling model accuracy of 91.5% on the test set on a particular challenging dataset, where we compare thoroughly against many other methodologies.
The increasing complexity of Multi-Agent Systems (MASs), coupled with the emergence of Artificial Intelligence (AI) and Large Language Models (LLMs), have highlighted significant gaps in our understanding of the behavior and interactions of diverse entities within dynamic environments. Traditional game theory approaches have often been employed in this context, but their utility is limited by the static and homogenous nature of their models. With the transformative influence of AI and LLMs on business and society, a more dynamic and nuanced theoretical framework is necessary to guide the design and management of MASs. In response to this pressing need, we propose an Extended Coevolutionary (EC) Theory in this paper. This alternative framework incorporates key aspects of coevolutionary dynamics, adaptive learning, and LLM-based strategy recommendations to model and analyze the strategic interactions among heterogeneous agents in MASs. It goes beyond game theory by acknowledging and addressing the diverse interactions (economic transactions, social relationships, information exchange) and the variability in risk aversion, social preferences, and learning capabilities among entities. To validate the effectiveness of the EC framework, we developed a simulation environment that enabled us to explore the emergence of cooperation and defection patterns in MASs. The results demonstrated the potential of our framework to promote cooperative behavior and maintain robustness in the face of disruptions. The dynamics and evolution of the Multi-Agent System over time were also visualized using advanced techniques. Our findings underscore the potential of harnessing LLMs to facilitate cooperation, enhance social welfare, and promote resilient strategies in multi-agent environments. Moreover, the proposed EC framework offers valuable insights into the interplay between strategic decision making, adaptive learning, and LLM-informed guidance in complex, evolving systems. This research not only responds to the current challenges faced in modeling MASs, but also paves the way for future research in this rapidly developing field.
In this paper, we introduce an innovative approach to handling the multi-armed bandit (MAB) problem in non-stationary environments, harnessing the predictive power of large language models (LLMs). With the realization that traditional bandit strategies, including epsilon-greedy and upper confidence bound (UCB), may struggle in the face of dynamic changes, we propose a strategy informed by LLMs that offers dynamic guidance on exploration versus exploitation, contingent on the current state of the bandits. We bring forward a new non-stationary bandit model with fluctuating reward distributions and illustrate how LLMs can be employed to guide the choice of bandit amid this variability. Experimental outcomes illustrate the potential of our LLM-informed strategy, demonstrating its adaptability to the fluctuating nature of the bandit problem, while maintaining competitive performance against conventional strategies. This study provides key insights into the capabilities of LLMs in enhancing decision-making processes in dynamic and uncertain scenarios.
The increasing demand for efficient and safe transportation systems has led to the development of autonomous vehicles and vehicle platooning. Truck platooning, in particular, offers numerous benefits, such as reduced fuel consumption, enhanced traffic flow, and increased safety. In this paper, we present a drone-based decentralized framework for truck platooning in highway monitoring scenarios. Our approach employs multiple drones, which communicate with the trucks and make real-time decisions on whether to form a platoon or not, leveraging Model Predictive Control (MPC) and Unscented Kalman Filter (UKF) for drone formation control. The proposed framework integrates a simple truck model in the existing drone-based simulation, addressing the truck dynamics and constraints for practical applicability. Simulation results demonstrate the effectiveness of our approach in maintaining the desired platoon formations while ensuring collision avoidance and adhering to the vehicle constraints. This innovative drone-based truck platooning system has the potential to significantly improve highway monitoring efficiency, traffic management, and safety. Our drone-based truck platooning system is primarily designed for implementation in highway monitoring and management scenarios, where its enhanced communication and real-time decision-making capabilities can significantly contribute to traffic efficiency and safety. Future work may focus on field trials to validate the system in real-world conditions and further refine the algorithms based on practical feedback and evolving vehicular technologies.
X-ray photoelectron spectroscopy (XPS) remains a fundamental technique in materials science, offering invaluable insights into the chemical states and electronic structure of a material. However, the interpretation of XPS spectra can be complex, requiring deep expertise and often sophisticated curve-fitting methods. In this study, we present a novel approach to the analysis of XPS data, integrating the utilization of large language models (LLMs), specifically OpenAI’s GPT-3.5/4 Turbo to provide insightful guidance during the data analysis process. Working in the framework of the CIRCE-NAPP beamline at the CELLS ALBA Synchrotron facility where data are obtained using ambient pressure X-ray photoelectron spectroscopy (APXPS), we implement robust curve-fitting techniques on APXPS spectra, highlighting complex cases including overlapping peaks, diverse chemical states, and noise presence. Post curve fitting, we engage the LLM to facilitate the interpretation of the fitted parameters, leaning on its extensive training data to simulate an interaction corresponding to expert consultation. The manuscript presents also a real use case utilizing GPT-4 and Meta’s LLaMA-2 and describes the integration of the functionality into the TANGO control system. Our methodology not only offers a fresh perspective on XPS data analysis, but also introduces a new dimension of artificial intelligence (AI) integration into scientific research. It showcases the power of LLMs in enhancing the interpretative process, particularly in scenarios wherein expert knowledge may not be immediately available. Despite the inherent limitations of LLMs, their potential in the realm of materials science research is promising, opening doors to a future wherein AI assists in the transformation of raw data into meaningful scientific knowledge.
n today’s complex economic environment, individuals and households alike grapple with the challenge of financial planning. This paper introduces novel methodologies for both individual and cooperative (household) financial budgeting. We firstly propose an optimization framework for individual budget allocation, aiming to maximize savings by efficiently distributing monthly income among various expense categories. We then extend this model to households, wherein the complexity of handling multiple incomes and shared expenses is addressed. The cooperative model prioritizes not only maximized savings but also the preferences and needs of each member, fostering a harmonious financial environment, whether they are short-term needs or long-term aspirations. A notable innovation in our approach is the integration of recommendations from a large language model (LLM). Given its vast training data and potent inferential capabilities, the LLM provides initial feasible solutions to our optimization problems, acting as a guiding beacon for individuals and households unfamiliar with the nuances of financial planning. Our preliminary results indicate that the LLM-recommended solutions result in budget plans that are both economically sound, meaning that they are consistent with established financial management principles and promote fiscal resilience and stability, and aligned with the financial goals and preferences of the concerned parties. This integration of AI-driven recommendations with econometric models, as an instantiation of an extended coevolutionary (EC) theory, paves the way for a new era in financial planning, making it more accessible and effective for a wider audience, as we propose an example of a new theory in economics where human behavior can be greatly influenced by AI agents.
In this paper, we address the research gap in efficiently assessing Generative Adversarial Network (GAN) convergence and goodness of fit by introducing the application of the Signature Transform to measure similarity between image distributions. Specifically, we propose the novel use of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) Signature, along with Log-Signature, as alternatives to existing methods such as Fréchet Inception Distance (FID) and Multi-Scale Structural Similarity Index Measure (MS-SSIM). Our approach offers advantages in terms of efficiency and effectiveness, providing a comprehensive understanding and extensive evaluations of GAN convergence and goodness of fit. Furthermore, we present innovative analytical measures based on statistics by means of Kruskal–Wallis to evaluate the goodness of fit of GAN sample distributions. Unlike existing GAN measures, which are based on deep neural networks and require extensive GPU computations, our approach significantly reduces computation time and is performed on the CPU while maintaining the same level of accuracy. Our results demonstrate the effectiveness of the proposed method in capturing the intrinsic structure of the generated samples, providing meaningful insights into GAN performance. Lastly, we evaluate our approach qualitatively using Principal Component Analysis (PCA) and adaptive t-Distributed Stochastic Neighbor Embedding (t-SNE) for data visualization, illustrating the plausibility of our method.
The colonization of Mars poses unprecedented challenges in developing sustainable and efficient transportation systems to support inter-settlement connectivity and resource distribution. This study conducts a comprehensive evaluation of two proposed transportation systems for Martian colonies: a ground-based magnetically levitated (maglev) train and a low-orbital spaceplane. Through simulation models, we assess the energy consumption, operational and construction costs, and environmental impacts of each system. Monte Carlo simulations further provide insights into the cost variability and financial risk associated with each option over a decade. Our findings reveal that while the spaceplane system offers lower average costs and reduced financial risk, the maglev train boasts greater scalability and potential for integration with Martian infrastructural development. The maglev system, despite its higher initial cost, emerges as a strategic asset for long-term colony expansion and sustainability, highlighting the need for balanced investment in transportation technologies that align with the goals of Martian colonization. Further extending our exploration, this study introduces advanced analysis of alternative transportation technologies, including hyperloop systems, drones, and rovers, incorporating dynamic environmental modeling of Mars and reinforcement learning for autonomous navigation. In an effort to enhance the realism and complexity of our navigation simulation of Mars, we introduce several significant improvements. These enhancements focus on the inclusion of dynamic atmospheric conditions, the simulation of terrain-specific obstacles such as craters and rocks, and the introduction of a swarm intelligence approach for navigating multiple drones simultaneously. This analysis serves as a foundational framework for future research and strategic planning in Martian transportation infrastructure.
