TY - CHAP A1 - Weidl, Galia A1 - Berres, Stefan A1 - Madsen, Anders L. A1 - Daxenberger, Johannes A1 - Aulbach, Anegret T1 - Exploring Argument Mining and Bayesian Networks for Assessing Topics for City Project Proposals T2 - Proceedings of Machine Learning Research N2 - The digital transformation of cities inspired the city administration of Aschaffenburg, Germany, to apply artificial intelligence to reduce the significant amount of manual administrative effort needed to evaluate citizens’ ideas for potential future projects. This paper introduces a methodology that combines argument mining with Bayesian networks to evaluate the relative eligibility of city project proposals. The methodology involves two main steps: (1) clustering arguments extracted from public information available on the Internet, and (2) assessing and comparing selected urban issues, planning topics, and citizens’ ideas that have been widely discussed to measure public interest in potential candidate projects. The results of the clustering are fed into a Bayesian network, along with scores for several evaluation criteria, to generate a relative eligibility score. The framework was applied to three candidate projects, resulting in the selection of one of them, while the other two were rejected with a given explanation. The latter motivates the decision and provides transparency to all parties involved in the decision process. The methodology is applicable to other cities after adjustments of criteria. KW - Bayesian networks KW - argument mining KW - project evaluation KW - urban planning KW - Projektplanung KW - Stadtverwaltung Y1 - 2024 UR - https://proceedings.mlr.press/v246/weidl24a.html VL - 2024 IS - 246 SP - 438 EP - 451 ER - TY - CHAP A1 - Madsen, Anders L. A1 - Weidl, Galia T1 - Bayes’sche Netze als Methode zur Implementierung transparenter, erklärbarer und vertrauenswürdiger Künstlicher Intelligenz T2 - Vertrauen in Künstliche Intelligenz - Eine multi-perspektivische Betrachtung N2 - Dieser Beitrag betrachtet die Verwendung von Bayes’schen Netzen als Methode zur Implementierung von transparenter, erklärbarer und vertrauenswürdiger Künstlicher Intelligenz (KI). Er beginnt mit einer Darstellung und Diskussion von Schlüsselkonzepten im Zusammenhang mit der Verwendung von Methoden der Künstlichen Intelligenz und der Implementierung von erklärbarer und vertrauenswürdiger KI. Der Beitrag diskutiert mehrere Konzepte aus dem Bereich der Bayes’schen Netze, die für die praktische Anwendung dieser Modelle in Systemen mit KI relevant sind. Zu den betrachteten Konzepten gehören unter anderem der Bayes-Faktor, die wahrscheinlichste Erklärung und die relevanteste Erklärung. Der Beitrag endet mit einem Fallbeispiel aus dem Bereich des automatisierten Fahrens, das veranschaulicht, wie transparente und erklärbare KI mithilfe von Bayes’schen Netzen umgesetzt werden kann, um eine vertrauenswürdige Lösung zu schaffen. KW - Bayes'sche Netze KW - Künstliche Intelligenz KW - Automatisiertes Fahren KW - Mischverkehr KW - Künstliche Intelligenz KW - Bayes-Netz KW - Autonomes Fahrzeug Y1 - 2024 UR - https://link.springer.com/chapter/10.1007/978-3-658-43816-6_8 SP - 139 EP - 162 PB - Springer Verlag ER - TY - CHAP A1 - Raiyn, Jamal A1 - Chaar, Mohamad Mofeed A1 - Weidl, Galia T1 - Analysis of Driving Behavior in Adverse Weather Conditions T2 - IEEE 7th International Conference AND workshop in Óbuda on Electrical and Power Engineering (CANDO EPE 2024) N2 - This paper discusses the impact of Connected Cooperative and Automated Mobility (CCAM) on safety-critical events. The replacement of human drivers by autonomous vehicles (AVs) is promising improved traffic efficiency and reduction of car- crashes to zero using a baseline network traffic. Predicting driving behavior during car-following has been crucial for enhancing road safety while developing advanced driver assistance systems with adaptive cruise control. Human factors significantly influence the driving behavior of a vehicle. Thus, understanding the causal relations between human factors and driving behavior is essential for accurate prediction of vehicle behavior. This is important when autonomous vehicles are expected to behave (cooperatively, according to traffic rules and good praxis) in a human predictable manner, while driving in mixed traffic, involving autonomous, automated, and human driven vehicles. In this paper, we propose a methodology that combines convolutional neural networks (CNNs) with human factors analysis to predict driving behavior during car-following under adverse weather conditions (AWCs). KW - Autonomes Fahrzeug KW - Fahrerassistenzsystem KW - Wetter Y1 - 2024 UR - https://www.researchgate.net/publication/385591980_ANALYSIS_OF_DRIVING_BEHAVIOR_IN_ADVERSE_WEATHER_CONDITIONS ER - TY - INPR A1 - Chaar, Mohamad Mofeed A1 - Raiyn, Jamal A1 - Weidl, Galia T1 - Improving the Perception of Objects under Foggy Conditions in the Surrounding Environment N2 - Autonomous Driving (AD) technology has rapidly advanced in recent years. Some challenges remain, particularly in ensuring robust performance under adverse weather conditions, like heavy fog. To address this, we propose a multi-class fog density classification approach to enhance the performance of AD systems. By dividing the fog density into multiple classes (25\%, 50\%, 75\%, and 100\%) and generating separate data-sets for each class using the Carla simulator, we can independently improve perception for each fog density and examine the effects of fog at each level. This approach offers several advantages, including improved perception, targeted training, and enhanced generalizability. The results show improved perception of objects from the categories: cars, buses, trucks, vans, pedestrians, and traffic lights. Our multi-class fog density approach is a promising step towards achieving robust AD system performance under adverse weather conditions. KW - Autonomes Fahrzeug KW - Wetter KW - Sicht Y1 - 2024 U6 - https://doi.org/https://doi.org/10.21203/rs.3.rs-3821656/v1 PB - Research Square Platform LLC ER - TY - CHAP A1 - Raiyn, Jamal A1 - Weidl, Galia T1 - Assessing Inattentiveness and Human Elements in Critical Driving Safety Events T2 - 9th European Congress on Computational Methods in Applied Sciences and Engineering 3-7 June 2024, Lisboa, Portugal N2 - Road accidents, with their potential for severe consequences, pose an ongoing global challenge. Within the multitude of factors contributing to these incidents, inattentiveness and the intricate human elements inherent in driving behaviors stand out as pivotal. As indicated by reports and studies on traffic safety, a significant share of accidents can be attributed to driver inattentiveness, encompassing activities such as texting, talking on the phone, or simply being distracted by the surrounding environment. Beyond these observable behaviors lie complex human elements, influenced by factors ranging from cognitive processes to emotional states, which significantly contribute to the occurrence and severity of critical safety events. Inattentiveness is defined as a state in which a driver's eye gaze behavior deviates from attentive driving patterns. It can be influenced by human factors and adverse weather conditions, serving as an indicator of an increased risk of inattentiveness and the potential to contribute to safety-critical events on the road. Recognition of inattentiveness occurs when the average gaze duration on the road or critical areas falls below a specified threshold. The driver's response time is crucial to the braking process of the vehicle and, therefore, has a significant impact on safety in critical situations. KW - Fahrerassistenzsystem KW - Aufmerksamkeit Y1 - 2024 UR - https://www.researchgate.net/publication/381283484_Assessing_Inattentiveness_and_Human_Elements_in_Critical_Driving_Safety_Events ER - TY - CHAP A1 - Talluri, Kranthi Kumar A1 - Weidl, Galia T1 - Impact of Accidents on Traffic Congestions: A Bayesian Network Approach Using Real City Data T2 - Advances in Transdisciplinary Engineering N2 - Traffic congestion has been a major concern in urban areas due to its strong impact on various social, economic, and human safety sectors. Understanding the relationship and analyzing the trends and patterns between congestion and accidents can strengthen the strategy for reducing traffic congestion. Research on causes of accidents and their impact on congestion has recently been explored on a greater scale, but there is still a lot of scope for vast areas of improvement. To tackle this issue, we built a Bayesian Network (BN) model for analyzing and predicting congestion probability that can occur due to accidents. In this work, the complexity of handling real data obtained from Darmstadt city is described in detail. The accidents and congestion are correlated by introducing a novel threshold-based approach, which identifies congestion based on the change in vehicle density immediately following an accident. Different thresholds are explored to determine the most reliable measure of congestion, with the T4 threshold emerging as the optimal choice. Moreover, the proposed BN model is evaluated against several machine learning models, demonstrating competitive performance and its ability to understand the root cause of traffic congestion. KW - Verkehrsstau KW - Verkehrsunfall KW - Bayes-Netz KW - Maschinelles Lernen Y1 - 2024 SN - 9781643685601 U6 - https://doi.org/10.3233/ATDE241181 SN - 2352-751X IS - 63 SP - 64 EP - 78 PB - IOS Press ER - TY - CHAP A1 - Talluri, Kranthi Kumar A1 - Stang, Christopher A1 - Weidl, Galia T1 - Green Wave as an Integral Part for the Optimization of Traffic Efficiency and Safety: A Survey T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) N2 - Green Wave provides practical and advanced solutions to improve traffic efficiency and safety through network coordination. Nevertheless, the complete potential of Green Wave systems has yet to be explored. Utilizing emerging technologies and advanced algorithms, such as AI or V2X, would aid in achieving more robust traffic management strategies, especially when integrated with Green Wave. This work comprehensively surveys existing traffic control strategies that enable Green Waves and analyzes their impact on future traffic management systems and urban infrastructure. Understanding previous research on traffic management and its effect on traffic efficiency and safety helps explore the integration of Green Wave solutions with smart city initiatives for effective traffic signal coordination. This paper also discusses the advantages of using Green Wave strategies for emission reduction and considers road safety issues for vulnerable road users, such as pedestrians and cyclists. Finally, the existing challenges and research gaps in building robust and successful Green Wave systems are discussed to articulate explicitly the future requirement of sustainable urban transport. KW - Verkehrsregelung KW - Smart City Y1 - 2025 U6 - https://doi.org/10.1109/IV64158.2025.11097706 SP - 2422 EP - 2429 PB - IEEE ER - TY - CHAP A1 - Talluri, Kranthi Kumar A1 - Weidl, Galia A1 - Kasuluru, Vaishnavi T1 - Accident-Driven Congestion Prediction and Simulation: An Explainable Framework Using Advanced Clustering and Bayesian Networks T2 - IEEE 102nd Vehicular Technology Conference N2 - Traffic congestion due to uncertainties, such as accidents, is a significant issue in urban areas, as the ripple effect of accidents causes longer delays, increased emissions, and safety concerns. To address this issue, we propose a robust framework for predicting the impact of accidents on congestion. We implement Automated Machine Learning (AutoML)-enhanced Deep Embedding Clustering (DEC) to assign congestion labels to accident data and predict congestion probability using a Bayesian Network (BN). The Simulation of Urban Mobility (SUMO) simulation is utilized to evaluate the correctness of BN predictions using evidence-based scenarios. Results demonstrate that the AutoML-enhanced DEC has outperformed traditional clustering approaches. The performance of the proposed BN model achieved an overall accuracy of 95.6%, indicating its ability to understand the complex relationship of accidents causing congestion. Validation in SUMO with evidence-based scenarios demonstrated that the BN model's prediction of congestion states closely matches those of SUMO, indicating the high reliability of the proposed BN model in ensuring smooth urban mobility. KW - Verkehrsstau KW - Verkehrsunfall KW - Maschinelles Lernen Y1 - 2025 UR - https://www.researchgate.net/publication/394121957_Accident-Driven_Congestion_Prediction_and_Simulation_An_Explainable_Framework_Using_Advanced_Clustering_and_Bayesian_Networks U6 - https://doi.org/10.48550/arXiv.2507.22529 ER - TY - CHAP A1 - Talluri, Kranthi Kumar A1 - Madsen, Anders L. A1 - Weidl, Galia T1 - Enhancing Safety Standards in Automated Systems Using Dynamic Bayesian Networks T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) N2 - Cut-in maneuvers in high-speed traffic pose critical challenges that can lead to abrupt braking and collisions, necessitating safe and efficient lane change strategies. We propose a Dynamic Bayesian Network (DBN) framework to integrate lateral evidence with safety assessment models, thereby predicting lane changes and ensuring safe cut-in maneuvers effectively. Our proposed framework comprises three key probabilistic hypotheses (lateral evidence, lateral safety, and longitudinal safety) that facilitate the decision-making process through dynamic data processing and assessments of vehicle positions, lateral velocities, relative distance, and Time-to-Collision (TTC) computations. The DBN model's performance compared with other conventional approaches demonstrates superior performance in crash reduction, especially in critical high-speed scenarios, while maintaining a competitive performance in low-speed scenarios. This paves the way for robust, scalable, and efficient safety validation in automated driving systems. KW - Unfallverhütung KW - Schnellfahrstrecke KW - Autonomes Fahrzeug Y1 - 2025 UR - https://www.researchgate.net/publication/391461422_Enhancing_Safety_Standards_in_Automated_Systems_Using_Dynamic_Bayesian_Networks U6 - https://doi.org/10.48550/arXiv.2505.02050 ER - TY - CHAP A1 - Chaar, Mohamad Mofeed A1 - Raiyn, Jamal A1 - Weidl, Galia T1 - Predicting Depth Maps from Single RGB Images and Addressing Missing Information in Depth Estimation T2 - Proceedings of the 11th International Conference on Vehicle Technology and Intelligent Transport Systems N2 - Depth imaging is a crucial area in Autonomous Driving Systems (ADS), as it plays a key role in detecting and measuring objects in the vehicle’s surroundings. However, a significant challenge in this domain arises from missing information in Depth images, where certain points are not measurable due to gaps or inconsistencies in pixel data. Our research addresses two key tasks to overcome this challenge. First, we developed an algorithm using a multi-layered training approach to generate Depth images from a single RGB image. Second, we addressed the issue of missing information in Depth images by applying our algorithm to rectify these gaps, resulting in Depth images with complete and accurate data. We further tested our algorithm on the Cityscapes dataset and successfully resolved the missing information in its Depth images, demonstrating the effectiveness of our approach in real-world urban environments. KW - Autonomes Fahrzeug KW - Tiefenbild Y1 - 2025 U6 - https://doi.org/10.5220/0013365900003941 SP - 549 EP - 556 PB - SCITEPRESS - Science and Technology Publications ER -