Forecasting of the Traffic Situation in the Hannover Region

The main requirement of road traffic participants is to know the current traffic situation. Such data is typically obtained from routing services where the time of many different individual trips is taken into account.

In the context of Data4UrbanMobility tools were developed that allow to predict the traffic situation based on such time series data. The following figure presents an interface to visualize typical time series patterns as well as outliers present in the data:

The prediction of the traffic situation is made available in the form of a map based interface for the end user:

Data4UrbanMobility Data Protection Regulation

The work on the Data4UrbanMobility data protection regulation is completed. The document is publicly available and can be found here.

First Version of MiC-App Available

A first version of the novel MiC-App (Move in the City) App is now available for D4UM-associates as well as a protected group of public users. The mobile MiC-App is a tool to gather data.

MiC was developed by the Institute for Sustainable Urbanism at the University of Braunschweig and the Projektionisten GmbH. MiC links the growing  awareness of  digital citizen rights with the potential of evaluation big datasets. Therefore MiC gives the opportunity to citizen to actively participate in a citizen science project to take part in the development of the mobility of the feature.

MiC gathers data of the users movement, where the user has the about which data should be recorded. All data is pseudonymised such that the privacy of the contributing citizen is ensured.

Current Status:

In the first version of the app, the user can easily start and end the tracking of his/her movement. It is worth to point out, that the user decides when he is tracked and when not. A summary of his/her activity is available for the user as well as the opportunity to issue feedback or even delete all of his contributed data.

Updated System with Dashboard V2

With the new version of our system,  the dashboard will provide even more insights into the impact of public events on the traffic situation.

The coloring and labels let us easily distinguish between the different type of events. By clicking on the label we show the typically affected subgraph for that event type. This allows the user to check what specific routes are typically affected by an event at that location.

Examples: Visualisation of a concert and a football game.

In addition, the graph at the top right gives additional information on how big the impact around the events start time tends to be.

{API}
We enriched the api endpoints with additional information from the data models that were developed as part of the research efforts.

D4UM App Version 1.0

We just released the first Version of the D4UM App. Every project member now has access to the application and can try out its features. Let’s quickly go over some of its main features.
The EFA integration (EFA is a routing engine covering Lower Saxony and Bremen ) allows for quick access to tip information using all available public transport options. Our focus, when designing the application, was on quick and easy navigation to provide a simple and easy to use trip planning tool.

Departures and Connections

On the departure screen we show the user the closes stops for public transportation in his immediate vicinity. On the connection screen the user can fill in his desired starting location( either an address or an existing stop ) and destination and query for what connections are available to him. The provided information contains real time data , meaning we are able to visualized delays for any given connection.

Map

On the map screen you can see and or find all available stops of public transportation. This allows for providing the user with a great way to find out what stops are available in their city. By clicking on any of the shown stops will open the departure screen and provide you with the information mentioned above. To better visualize a selected connection, we show the route you plan to travel on the map.

Menu / Settings

Additional features can be found in the settings menu of the application. Here you can find settings that allow you to customize your routing results for both the departures and connection screen. The best way to let us know what you think about the application is to use the feedback module. This can be found here as well. First click on the emoji that best describe how you feel about the app. And then put in any additional information or ideas or thoughts you may have. Now what is left is just to press send and you will send us an email.

We look forward to hearing from you.

Quantification  and Prediction of Impact of Public Events

Current Data4UrbanMobility research results allow for measuring and prediction of spatial impact on road traffic of public events. Connected, affected street segments nearby public events are identified to measure the spatial impact. The approach is depicted in the following figure:

(Karte von https://www.openstreetmap.org)

An event is marked as yellow dot, affected streets in red and the measured impact in dark blue. Moreover, an approach making use of machine learning algorithms was developed to predict the impact determined in this way, resulting an error-reduction of up to 40% when compared to existing state-of-the-art approaches.

D4UM – Platform V1 Released

The first version of the Data4UrbanMobiltiy platform has been released. The platform was designed and implemented following a 3-tier-architecture. The platform provides RESTfull Web services for mobility applications like dashboards or mobile apps. As a demonstration, an interactive map application has been developed that visualizes the spatial impact of public events. The following figure shows a screenshot of the application.

The figure shows 4 public events in the city of Hannover. The colors represent different types of public events (e.g. concerts, fairs, sport events). The circles visualize the spatial impact on road traffic caused by the public events.

Comprehensive Set of Requirements

The Data4UrbanMobility analysis of requirements includes requirements of the application partners Region Hannover (RH) and Wolfsburg AG (WAG) as well as non functional requirements. The requirements were collected by MOMA. The L3S derived research question for data analysis which are based  on the requirements of RH and WAG. The research question address especially the information needs of end-users.

The current research questions particularly include

1. Automated verification of traffic warnings and prediction of their impact
2. Identification of events and prediction of their impact
3. Investigation of correlation of road traffic data, public transportation query logs, traffic warnings and twitterfeeds
4. Determination of optimal traveling timepoints

Growing Data Collection

ISU create a comprehensive data matrix containing potential source of mobility related data. The Data4UrbanMobility data model describes all project relevant data sets and sets them into context. This makes the data available in a unified manor for both analysis and applications. The selected data sources were transformed according to the Data4UrbanMobility data model by L3S. The data quality of selected data sources (i.e. public transportation query logs and road traffic data) was examined.

Tools for extracting the relevant information from the datasets were developed to enable the integration of the datasets.

• Street and graph extraction from OpenStreetMap
• Bulkloader for public transportation queries
• Integration of “Zentrales Haltestellen Verzeichniss” (central registry of public transportation stops)

The current collection (December 12th 2017) contians

EFA-Logs: 17 million public transportation queries
Road traffic data: 174 thousand street sements with a frequency of 15 minutes
GTFS-data: 90 thousand. public transportation stops, 2.6 thousand routes
Weather: Radolan “Regenraster” (rain grid)
Twitter: 2,5 Mio. Tweets starting at June 2017

OSM: 440 thousand streets 
Events: 21 thousand public events (August 14th 2016-July 17th 2018)

Traffic warnings: 13 thousand warning (since June 2017)

Visualization of Public Transportation Information

In order to allow intuitive analytics of public transportation information, the PROJEKTIONISTEN (PROJ) developed a dashboard web application. First prototypes visualize queries addressed to the regional timetable information system EFA (www.efa.de). The prototypes serve as foundations for exploration analyses as well as the implementation of future versions of the dashboard. The following figure shows an integrated visualization of the most frequent origins and destinations of the queries.

Analysen der EFA-Logs

Analysis of EFA Public Transportation Query Logs

Analyses regarding the impact of public events on public transportation are currently conducted to address early research questions. To this extend, explorative data analyses of the impact of major public events such as football games and medium sized events such as concerts were conducted. Visual analytics were used as a first step towards comprehensive analyses, which show start-like patterns for city center which identify mobility hubs of central importance.

The figure shows the direct connection between origin and destination of public transportation queries. Darker colors correspond to more frequent queried trips. Star-like pattern identify the central train station and the central metro station.

Analyses of single stations reveal weekday dependent patterns.

The figure depicts the average number of queries with the destination “Hannover Stadionbrücke”. Differences emerge between Weekends and workdays.

The impact of public events on the queries can be visualized  as well.

The figure shows the number of queries with the Destination “Hannover Stadionbrücke” for Wednesday, April 26th 2017 (orange) as well as the average number of queries on a Wednesday for the same destination. On this day a concert took place in venue nearby. The concert start at 8 pm. The significant deviations between 5 pm and 7 pm is highly likely to be caused by visitors of the concert. This shows that public transportation queries are a valuable information source to investigate the impact of public events on mobility infrastructure.

• Hair Transplant Innovations: What’s New in the Industry. Grow, Hair Free Hair (2024).
• Exploring the Real-Time Capability of Electrical Impedance Tomography for Hand Sign Recognition in Robotic Hand Control. Ghoul, Bilel; Atitallah, Bilel Ben; Barioul, Rim; Fakhfakh, Ahmed; Kanoun, Olfa (2024). 1–6.

  Electrical impedance tomography (EIT) can monitor the influence of the muscle activity on the conductivity distribution across the forearm and is therefore suitable for Hand Sign Recognition (HSR). However, the method is relatively complex, so realizing real-time classification based on EIT measurements is still considered a major challenge. In addition, the accuracy of EIT for HSR is highly dependent on the injection configuration parameters applied. In this study, we investigate the influence of the injection configuration on the achieved accuracy of the hand robot control and the feasibility of a real-time classification based on EIT measurements. To assess real-time feasibility, experimental data have been collected for a sign set of 36 American Sign Language (ASL) performed by one healthy subject. Moreover, a comparative study of the adjacent, opposite, and cross injection configurations has been conducted on 10 subjects performing the ASL set. An ambiguity study based on the measured signals was performed to assess the discrimination potential between the hand signs. The adjacent EIT configuration exhibited higher sensitivity in discriminating hand signs. For a real-time classification, we propose the use of a Support Vector Machine (SVM) model realizing an overall accuracy of 71.38%. To validate the system's real-time behavior, the classification result is visualized by a robotic hand reproducing 6 different hand signs from the 36 ASL set reaching an accuracy of 80%. The results demonstrate the potential of EIT to facilitate real-time Hand Sign Recognition for robot control applications.
• Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach. Vo, Huy V.; Khalidov, Vasil; Darcet, Timothée; Moutakanni, Théo; Smetanin, Nikita; Szafraniec, Marc; Touvron, Hugo; Couprie, Camille; Oquab, Maxime; Joulin, Armand; Jégou, Hervé; Labatut, Patrick; Bojanowski, Piotr (2024).
• Non-Deterministic and Risk Based Security Services. Doddi, Srinivas Rao; Kotamraju, Akshay Krishna (2024). 22(1) 307–310.
• A pair of possible supernovae Refsdal in the Pantheon+ sample. Sanejouand, Yves-Henri (2024).
• A pair of possible supernovae Refsdal in the Pantheon+ sample. Sanejouand, Yves-Henri (2024).
• A Brain-Inspired Model of Reaching and Adaptation on the iCub Robot. Fietzek, Torsten; Ruff, Christoph; Hamker, Fred H. (2024).

  Motor learning is an important property for em-bodied agents and a wide variety of approaches has been developed for humanoid robots. One strategy is to study the human brain and replicate the structure and functionality of the brain in neuro-computational models. These models are built at different levels of abstraction to perform a variety of tasks. The presented work integrates a recent system-level neuro-computational model incorporating the motor cortex basal ganglia loops, the cerebellum and central pattern generators with the iCub robot. The iCub is a humanoid robot explicitly developed for cognitive research and well suited for manipulation and other motor tasks due to its high degrees of freedom. To test the performance of the model two experiments are conducted. In the first step a reaching task is carried out. Here, the task is to perform movements from a fixed initial position to different goal locations in the 3D-space. The results are compared to the prior performance of the model to verify the model and code adjustments and the learning abilities. In the second setup a simple motor adaptation task is realized, where an external shift perturbation is introduced to the arm motion, and the adaptation abilities of the model are investigated.
• Optimal feature subset deduction based on possibilistic feature quality classification and feature complementarity. Medhioub, Mouna; Bouhamed, Sonda Ammar; Kallel, Imene Khanfir; Derbel, Nabil; Kanoun, Olfa (2024). 249 123353.
• Digital Trace Data. Jungherr, Andreas (2024).
• Comparative Study of Data Reduction Methods in Electrical Impedance Tomography For Hand Sign Recognition. Ghoul, Bilel; Atitallah, Bilel Ben; Sahnoun, Salwa; Fakhfakh, Ahmed; Kanoun, Olfa (2024). (Vol. 1) 654–658.

  Several studies have shown that electrical impedance tomography (EIT) on the human forearm can be used to classify hand signs without the need for cameras or gloves. However, the amount of measured data is in relatively high, leading to long execution times and high processing complexity. In this study, we investigate the influence of reducing the number of EIT measurements on the classification accuracy. Four different algorithms were used to halve the number of measurements, namely Principal Component Analysis (PCA), Chi-square tests, Minimum Redundancy Maximum Relevance (MRMR) and Laplacian scores. These algorithms were applied to a dataset of forearm EIT measurements corresponding to the practice of American Sign Language (ASL) in a healthy subject. The results show a slight drop in accuracy when using the quadratic support vector machine (SVM) classifier, with accuracy dropping from 95.3% to 93.4% in the best cases. A method based on a genetic algorithm (GA) was also used. This approach exploits the strengths of genetic algorithms in exploring a large solution space and converging on the near-optimal combination. This approach resulted in an increase in accuracy to 96.7%. The study demonstrated that the number of EIT measurements can be reduced without compromising overall accuracy.
• Investigation of Implicit and Contextual Cues for the Facilitation of Cooperative Automated Driving: A Qualitative Analysis. Dettmann, Andre; Berkemeier, Adelina; Felbel, Konstantin; Bullinger, Angelika C. (2024). 319–326.
• EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs. Sapkota, Rupesh; Köhler, Dominik; Heindorf, Stefan (2024).
• Comparative Study of sEMG Feature Evaluation Methods Based on the Hand Gesture Classification Performance. Hellara, Hiba; Barioul, Rim; Sahnoun, Salwa; Fakhfakh, Ahmed; Kanoun, Olfa (2024). 24(11)

  Effective feature extraction and selection are crucial for the accurate classification and prediction of hand gestures based on electromyographic signals. In this paper, we systematically compare six filter and wrapper feature evaluation methods and investigate their respective impacts on the accuracy of gesture recognition. The investigation is based on several benchmark datasets and one real hand gesture dataset, including 15 hand force exercises collected from 14 healthy subjects using eight commercial sEMG sensors. A total of 37 time- and frequency-domain features were extracted from each sEMG channel. The benchmark dataset revealed that the minimum Redundancy Maximum Relevance (mRMR) feature evaluation method had the poorest performance, resulting in a decrease in classification accuracy. However, the RFE method demonstrated the potential to enhance classification accuracy across most of the datasets. It selected a feature subset comprising 65 features, which led to an accuracy of 97.14%. The Mutual Information (MI) method selected 200 features to reach an accuracy of 97.38%. The Feature Importance (FI) method reached a higher accuracy of 97.62% but selected 140 features. Further investigations have shown that selecting 65 and 75 features with the RFE methods led to an identical accuracy of 97.14%. A thorough examination of the selected features revealed the potential for three additional features from three specific sensors to enhance the classification accuracy to 97.38%. These results highlight the significance of employing an appropriate feature selection method to significantly reduce the number of necessary features while maintaining classification accuracy. They also underscore the necessity for further analysis and refinement to achieve optimal solutions.
• Unveiling the invisible: receivers use object weight cues for grip force planning in handover actions. Kopnarski, L.; Rudisch, J.; Kutz, D. F.; Voelcker-Rehage, C. (2024). 242(5) 1191–1202.

  Handover actions are part of our daily lives. Whether it is the milk carton at the breakfast table or tickets at the box office, we usually perform these joint actions without much conscious attention. The individual actions involved in handovers, that have already been studied intensively at the level of individual actions, are grasping, lifting, and transporting objects. Depending on the object's properties, actors must plan their execution in order to ensure smooth and efficient object transfer. Therefore, anticipatory grip force scaling is crucial. Grip forces are planned in anticipation using weight estimates based on experience or visual cues. This study aimed to investigate whether receivers are able to correctly estimate object weight by observing the giver's kinematics. For this purpose, handover actions were performed with 20 dyads, manipulating the participant role (giver/receiver) and varying the size and weight of the object. Due to the random presentation of the object weight and the absence of visual cues, the participants were unaware of the object weight from trial to trial. Kinematics were recorded with a motion tracking system and grip forces were recorded with customized test objects. Peak grip force rates were used as a measure of anticipated object weight. Results showed that receiver kinematics are significantly affected by object weight. The peak grip force rates showed that receivers anticipate object weight, but givers not. This supports the hypothesis that receivers obtain information about the object weight by observing giver's kinematics and integrating this information into their own action execution.
• eSim Guernsey. HolidayeSim (Nusal, ed.) (2024).
• Smoothing Out Smart Tech’s Rough Edges: Imperfect Automation and the Human Fix. Katzenbach, Christian; Pentzold, Christian; Viejo Otero, Paloma (2024). 7 23–43.
• Variable transformations in combination with wavelets and ANOVA for high-dimensional approximation. Potts, Daniel; Weidensager, Laura (2024). 50 53.

  We use hyperbolic wavelet regression for the fast reconstruction of high-dimensional functions having only low-dimensional variable interactions. Compactly supported periodic Chui-Wang wavelets are used for the tensorized hyperbolic wavelet basis on the torus. With a variable transformation, we are able to transform the approximation rates and fast algorithms from the torus to other domains. We perform and analyze scattered data approximation for smooth but arbitrary density functions by using a least squares method. The corresponding system matrix is sparse due to the compact support of the wavelets, which leads to a significant acceleration of the matrix vector multiplication. For non-periodic functions, we propose a new extension method. A proper choice of the extension parameter together with the piecewise polynomial Chui-Wang wavelets extends the functions appropriately. In every case, we are able to bound the approximation error with high probability. Additionally, if the function has a low effective dimension (i.e., only interactions of a few variables), we qualitatively determine the variable interactions and omit ANOVA terms with low variance in a second step in order to decrease the approximation error. This allows us to suggest an adapted model for the approximation. Numerical results show the efficiency of the proposed method.
• Ultra-Fast Edge Computing Approach for Hand Gesture Classification Based on EIT Measurements. Mnif, Mahdi; Sahnoun, Salwa; Kaaniche, Marouene; Atitallah, Bilel Ben; Fakhfakh, Ahmed; Kanoun, Olfa (2024). 1–7.

  Gesture-based robot control offers intuitive interaction between humans and robots, with applications ranging from industrial automation to assistive robotics. However, existing solutions face challenges in achieving real-time requirements while ensuring accurate gesture recognition. This paper presents a new edge computing-based approach for real-time control of robots using Electrical Impedance Tomography (EIT) measurements to classify hand gesture numbers in American Sign Language (ASL). Existing solutions for gesture recognition struggle to achieve real-time performance while maintaining accuracy and energy efficiency. This challenge becomes higher in the case of EIT because of its relative complexity. We focus therefore on leveraging the capabilities of the edge device to implement effectively the Convolutional Neural Network (CNN) acceleration. The proposed solution combines hardware-aware optimization techniques to achieve fast and accurate gesture recognition by enabling rapid inference while minimizing energy consumption on a low-power resource-constrained device with Tiny Machine Learning (TinyML) capabilities. The lightweight CNN model required only 10.2 s to train using the Keras library of TensorFlow and achieved an accuracy of 89.37% for 10 sign language classes, with only 66 μs taken to run inference on the hardware-accelerated microcontroller-based device.
• Flexible Oxide Electronics for Extreme Geometries and Mechanical Deformations. Münzenrieder, Niko; De Souza Oliveira, Hugo; Catania, Federica; Khaanghah, Niloofar Saeedzadeh; Lanthaler, Albert Heinrich; Corsino, Dianne; Cantarella, Giuseppe (2024). 08–11.
• Leading Manufacturer of High-Quality Coir Sheets | WeCoir. WeCoir (WeCoir, ed.) (2024).
• Computing Repairs Under Functional and Inclusion Dependencies via Argumentation. Mahmood, Yasir; Virtema, Jonni; Barlag, Timon; Ngomo, Axel-Cyrille Ngonga (2024).
• Real Time Parameter Estimation for Adaptive OFDM/OTFS Selection. Darghouthi, Amina (2024). 16(4)
• TripoSR: Fast 3D Object Reconstruction from a Single Image. Tochilkin, Dmitry; Pankratz, David; Liu, Zexiang; Huang, Zixuan; Letts, Adam; Li, Yangguang; Liang, Ding; Laforte, Christian; Jampani, Varun; Cao, Yan-Pei (2024).
• The Role of Sea-ice Insulation Effects on the Probability of AMOC Transitions. van Westen, René M.; Jacques-Dumas, Valérian; Boot, Amber A.; Dijkstra, Henk A. (2024).
• The Ladder of Data Citizen Participation: A Sociotechnical Lens for Designing Democratic Digital Services in the Data Economy. Horn, Viktoria; Draude, Claude (2024).
• The Ladder of Data Citizen Participation: A Sociotechnical Lens for Designing Democratic Digital Services in the Data Economy. Horn, Viktoria; Draude, Claude (2024).
• VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models. Han, Junlin; Kokkinos, Filippos; Torr, Philip (2024).
• Pair coalescence times of ancestral lineages of two-dimensional logistic branching random walks. Birkner, Matthias; Depperschmidt, Andrej; Schlüter, Timo (2024).
• The Ladder of Data Citizen Participation: A Sociotechnical Lens for Designing Democratic Digital Services in the Data Economy. Horn, Viktoria; Draude, Claude (2024).

  In the data economy digital services of democratic value such as news platforms are embedded into unjust power imbalances and the intertwining of economic and civic objectives. The authors argue, to design proficient democratic digital services, power structures of the data economy and empowerment stages of data citizenship need to be made visible initially. To do so, a combination of Arnstein’s ‘Ladder of Citizen Participation’ and Rocha’s ‘Ladder of Empowerment’ is translated into the field of the data economy. A small interview study with niche actors from the field of online journalism is conducted to identify phenomena of their embedding into the sociotechnical landscape of the data economy. As a result, the Ladder of Data Citizen Participation is presented. Eventually, this article closes with implications for the sociotechnical design of democratic digital services and suggestions for future research.
• SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement. Boss, Mark; Huang, Zixuan; Vasishta, Aaryaman; Jampani, Varun (2024).
• Towards Realistic Results for Instrumentation-Based Profilers for JIT-Compiled Systems. Burchell, Humphrey; Larose, Octave; Marr, Stefan in MPLR’24 (2024).

  Profilers are crucial tools for identifying and improving application performance. However, for language implementations with just-in-time (JIT) compilation, e.g., for Java and JavaScript, instrumentation-based profilers can have significant overheads and report unrealistic results caused by the instrumentation. In this paper, we examine state-of-the-art instrumentation-based profilers for Java to determine the realism of their results. We assess their overhead, the effect on compilation time, and the generated bytecode. We found that the profiler with the lowest overhead increased run time by 82x. Additionally, we investigate the realism of results by testing a profiler’s ability to detect whether inlining is enabled, which is an important compiler optimization. Our results document that instrumentation can alter program behavior so that performance observations are unrealistic, i.e., they do not reflect the performance of the uninstrumented program. As a solution, we sketch late-compiler-phase-based instrumentation for just-in-time compilers, which gives us the precision of instrumentation-based profiling with an overhead that is multiple magnitudes lower than that of standard instrumentation-based profilers, with a median overhead of 23.3% (min. 1.4%, max. 464%). By inserting probes late in the compilation process, we avoid interfering with compiler optimizations, which yields more realistic results.
• Casimir Effect in MEMS: Materials, Geometries, and Metrologies—A Review. Elsaka, Basma; Yang, Xiaohui; Kästner, Philipp; Dingel, Kristina; Sick, Bernhard; Lehmann, Peter; Buhmann, Stefan Yoshi; Hillmer, Hartmut (2024). 17(14) 3393.

  Casimir force densities, i.e., force per area, become very large if two solid material surfaces come closer together to each other than 10 nm. In most cases, the forces are attractive. In some cases, they can be repulsive depending on the solid materials and the fluid medium in between. This review provides an overview of experimental and theoretical studies that have been performed and focuses on four main aspects: (i) the combinations of different materials, (ii) the considered geometries, (iii) the applied experimental measurement methodologies and (iv) a novel self-assembly methodology based on Casimir forces. Briefly reviewed is also the influence of additional parameters such as temperature, conductivity, and surface roughness. The Casimir effect opens many application possibilities in microelectromechanical systems (MEMS) and nanoelectromechanical systems (NEMS), where an overview is also provided. The knowledge generation in this fascinating field requires interdisciplinary approaches to generate synergetic effects between technological fabrication metrology, theoretical simulations, the establishment of adequate models, artificial intelligence, and machine learning. Finally, multiple applications are addressed as a research roadmap.
• Through the Lens of Google CrUX: Dissecting Web Browsing Experience Across Devices and Countries. Sengupta, Jayasree; Shreedhar, Tanya; Kramer, Robert; Bajpai, Vaibhav (2024). 509–514.

  User quality of experience in the context of Web browsing is being researched widely, with plenty of developments occurring alongside technological advances, not seldom driven by big industry players. With Google's huge reach and infrastructure, the Chrome User Experience Report (CrUX) provides quantitative real-life measurement data of a vast magnitude. Analysis of this steadily expanding dataset aggregating different user experience metrics, yields tangible insights into actual trends and developments. Hence, this paper is the first to study the CrUX dataset from the viewpoint of relevant metrics by quantitative evaluation of users' Web browsing experience across three device types and nine European countries. Analysis of data segmented by connection type in the device dimension shows desktops outperforming other device types for all metrics. Similar analysis in the country dimension, shows North European countries (Sweden, Finland) having maximum 4G connections (85.99%, 81.41% respectively) and steadily performing 25%-36% better at the 75th percentile across all metrics compared to the worst performing country. Such a high-level longitudinal analysis of real-life Web browsing experience provides an extensive base for future research.
• The Effect of Implicit Cues in Lane Change Situations on Driving Discomfort. Felbel, Konstantin; Dettmann, André; Bullinger, Angelika C. in Lecture Notes in Computer Science, H. Krömker (ed.) (2023). (Vol. 14049)
• Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction. Huang, Zhixin; He, Yujiang; Sick, Bernhard (2023). 99–105.

  RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.
• Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network. Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Nather, Rüdiger; Thomas, Josephine (2023). 1–7.

  Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.
• FSD: A novel forged document dataset and baseline. Jaiswal, Ankit Kumar; Singh, Shiksha; Tripathy, Santosh Kumar (2023). 1–6.

  Forgery detection in multimedia is an emerging research area in the field of digital content security. The current research focuses on finding several solutions to digital image forgery detection but a small number of works have been reported for scanned document forgery detection. The reason would be the unavailability of a forged scanned document (FSD) dataset. A scanned document can be manipulated in different ways: deleting a region, copy paste a region of the document either in the same document or in another document. Detection of these manipulations becomes arduous when a post-processing operation is performed on the manipulated region. To advance research in this field, we created a large dataset for the FSD. To generate such a dataset, we collected scanned documents from the FUNSD dataset (Publicly Available). The resolution of each sample of the dataset is of size 755x1000. The samples of the dataset are forged using different post-processing operations. The dataset comprises 6656 instances of manipulated scanned documents with their ground truth masks. To build the baseline for forged scanned document detection, we evaluated state-of-the-art object segmentation algorithms on the FSD dataset. Experiments demonstrate that the FSD well represents forged scanned documents and is quite challenging.
• A Novel Inexpensive Camera-Based Photoelectric Barrier System for Accurate Flying Sprint Time Measurement. Uhlmann, Tom; Bräuer, Sabrina; Zaumseil, Falk; Brunnett, Guido (2023). 23(17)

  This paper introduces a novel approach to addressing the challenge of accurately timing short distance runs, a critical aspect in the assessment of athletic performance. Electronic photoelectric barriers, although recognized for their dependability and accuracy, have remained largely inaccessible to non-professional athletes and smaller sport clubs due to their high costs. A comprehensive review of existing timing systems reveals that claimed accuracies beyond 30 ms lack experimental validation across most available systems. To bridge this gap, a mobile, camera-based timing system is proposed, capitalizing on consumer-grade electronics and smartphones to provide an affordable and easily accessible alternative. By leveraging readily available hardware components, the construction of the proposed system is detailed, ensuring its cost-effectiveness and simplicity. Experiments involving track and field athletes demonstrate the proficiency of the proposed system in accurately timing short distance sprints. Comparative assessments against a professional photoelectric cells timing system reveal a remarkable accuracy of 62 ms, firmly establishing the reliability and effectiveness of the proposed system. This finding places the camera-based approach on par with existing commercial systems, thereby offering non-professional athletes and smaller sport clubs an affordable means to achieve accurate timing. In an effort to foster further research and development, open access to the device’s schematics and software is provided. This accessibility encourages collaboration and innovation in the pursuit of enhanced performance assessment tools for athletes.
• Reconstruction of incomplete X-ray diffraction pole figures of oligocrystalline materials using deep learning. Meier, David; Ragunathan, Rishan; Degener, Sebastian; Liehr, Alexander; Vollmer, Malte; Niendorf, Thomas; Sick, Bernhard (2023). 13(1) 1–12.

  X-ray diffraction crystallography allows non-destructive examination of crystal structures. Furthermore, it has low requirements regarding surface preparation, especially compared to electron backscatter diffraction. However, up to now, X-ray diffraction has been highly time-consuming in standard laboratory conditions since intensities on multiple lattice planes have to be recorded by rotating and tilting. Furthermore, examining oligocrystalline materials is challenging due to the limited number of diffraction spots. Moreover, commonly used evaluation methods for crystallographic orientation analysis need multiple lattice planes for a reliable pole figure reconstruction. In this article, we propose a deep-learning-based method for oligocrystalline specimens, i.e., specimens with up to three grains of arbitrary crystal orientations. Our approach allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. In contrast to other methods, the pole figure is reconstructed based on only a single incomplete pole figure. To speed up the development of our proposed method and for usage in other machine learning algorithms, we introduce a GPU-based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.
• The impact of bionic prostheses on users’ self-perceptions: A qualitative study. Bretschneider, Maximilian; Meyer, Bertolt; Asbrock, Frank (2023). 241 104085.
• Optimizing a superconducting radio-frequency gun using deep reinforcement learning. Meier, David; Ramirez, Luis Vera; Völker, Jens; Viefhaus, Jens; Sick, Bernhard; Hartmann, Gregor (2022). 25(10) 104604.

  Superconducting photoelectron injectors are promising for generating highly brilliant pulsed electron beams with high repetition rates and low emittances. Experiments such as ultrafast electron diffraction, experiments at the Terahertz scale, and energy recovery linac applications require such properties. However, optimizing the beam properties is challenging due to the high number of possible machine parameter combinations. This article shows the successful automated optimization of beam properties utilizing an already existing simulation model. To reduce the required computation time, we replace the costly simulation with a faster approximation with a neural network. For optimization, we propose a reinforcement learning approach leveraging the simple computation of the derivative of the approximation. We prove that our approach outperforms standard optimization methods for the required function evaluations given a defined minimum accuracy.
• A Philosophy of Software Design Osterhout, John (2021). (2nd ed.) Yaknyam Press.
• Learning Transferable Visual Models From Natural Language Supervision. Radford, Alec; Kim, Jong Wook; Hallacy, Chris; Ramesh, Aditya; Goh, Gabriel; Agarwal, Sandhini; Sastry, Girish; Askell, Amanda; Mishkin, Pamela; Clark, Jack; Krueger, Gretchen; Sutskever, Ilya (2021).
• HISTSFC: Optimization for ND Massive Spatial Points Querying. Liu, Haicheng (2020). 12(3) 07–28.

  Space Filling Curve (SFC) mapping-based clustering and indexing works effectively for point clouds management and querying. It maps both points and queries into a one-dimensional SFC space so that B+- tree could be utilized. Based on the basic structure, this paper develops a generic HistSFC approach which utilizes a histogram tree recording point distribution for efficient querying. The goal is to resolve the issue of skewed data querying. Besides, the paper proposes an agile method to compute a continuous Level of Detail (cLoD), and integrates it into HistSFC to support smooth rendering of massive points. Results indicate that for range queries, HistSFC decreases the False Positive Rate (FPR) of selection by maximally 80%, compared to previous approaches. It also performs significantly faster than the state-of- the-art Oracle SDO_PC solution. With improved performance on visualization and k Nearest Neighbour (kNN) search, HistSFC can therefore be used as a new standard solution.
• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Mildenhall, Ben; Srinivasan, Pratul P.; Tancik, Matthew; Barron, Jonathan T.; Ramamoorthi, Ravi; Ng, Ren (2020).
• Annette von Droste-Hülshoff: Die Judenbuche (1842). Huszai, Villö Dorothea; Fehlmann, Ralph (2020). 112–116.
• "Mutter, lügen die Förster?". Judith Kuckarts dramatische Adaption der "Judenbuche" als Versuch über den Umgang mit Alteritäten. Morrien, Rita (2019). 12 239–253.
• Die Judenbuche. Ein Sittengemälde aus dem gebirgigten Westphalen. Korten, Lars J. G. Cornelia Blasberg (ed.) (2018). 505–529.
• Auf den Spuren der "Judenbuche". Voloj, Julian (2015). 15(3) 20–21.
• "Ein zweites Recht". Oder: Die Möglichkeiten der Fiktion. Zur fiktionstheoretischen Basis unzuverlässigen Erzählens in Annette von Droste-Hülshoffs "Judenbuche". Meixner, Sebastian R. Babel (ed.) (2014). 109–121.
• Blutlese. Annette von Droste-Hülshoffs "Die Judenbuche". Helfer, Martha (2013). 126–170.
• "Bei uns zulande auf dem Lande" und "Die Judenbuche" von Annette von Droste-Hülshoff (1797-1848). Gössmann, Wilhelm (2012). 134–135.
• "Die Judenbuche" und ihr Mörder. Kritik an einem kanonisierten Vorurteil. Heine, Marcel Thomas (2011). 8 53–63.
• "Die Judenbuche" und die Narbe des Odysseus. Zur Vorgeschichte des Realismus. Calhoon, Kenneth Scott K. S. Michael Neumann (ed.) (2011). 337–347.
• Annette von Droste-Hülshoff "Die Judenbuche". Ein Sittengemälde aus dem gebirgichten Westphalen (1842). Doering-Manteuffel, Sabine H. Z. Günter Butzer (ed.) (2010). 109–125.
• Kapitalverbrechen und familiäre Vergehen. Zur Struktur der Verdoppelung in Droste-Hülshoffs "Judenbuche". Wortmann, Thomas I. H. Claudia Liebrand (ed.) (2010). 315–337.
• Ein Spruch, der wahr sei. Hans Grimms Verarbeitung eines Motivs aus Annette von Droste-Hülshoffs "Judenbuche". Pakendorf, Gunther (2010). 38 9–22.
• Überhörtes Leid – ungeahndete Verbrechen. Annette von Droste-Hülshoffs "Die Judenbuche". Schmitz-Burgard, Sylvia (2010). 8 63–103.
• Eine Familiengeschichte in neuer Version: Die Judenbuche. Liebrand, Claudia (2008). 195–232.
• Ironie und Ethik in Annette von Droste-Hülshoffs "Judenbuche" Schaum, Konrad (2004). Winter, Heidelberg.
• "[...] ich habe Euch ein schweres Gewissen zu danken". Eine psychoanalytische Interpretation der "Judenbuche". Greve, Gisela H. E. H. Gisela Greve (ed.) (2003). 11–33.
• Annette von Droste-Hülshoff: "Die Judenbuche, 1831/42". Wittkowski, Wolfgang (2002). 167–192.
• Die Kriminalgeschichte als sozialer und religiöser Modellfall. Droste-Hülshoff, "Die Judenbuche", 1842. Borchmeyer, Dieter C. K. Klaus-Michael Bogdal (ed.) (2000). 70–73.
• Bayesian Theory Bernardo, José M.; Smith, Adrian F. M. in Wiley Series in Probability and Statistics (2000). Wiley, Chichester.
• Die Wirklichkeit des Frauenlebens: "Die Judenbuche". Yi, Mi-Seon (2000). 103–119.
• Bellersen. Das Dorf B. der "Judenbuche" von Annette von Droste-Hülshoff. Krus, Horst-Dieter (2000). 6 32–32.
• Das magische Gesetz der hebräischen Sprache. Drostes "Judenbuche" und der spätromantische Diskurs über die jüdische Magie. Kilcher, Andreas B. (1999). 118(2) 234–265.
• "Ist er kein Jude, so verdient er einer zu sein". Droste-Hülshoff’s "Die Judenbuche" and Religious Anti-Semitism. Donahue, William Collins (1999). 72(1) 44–73.
• "Was ist die Liebe?". Ein problemgeschichtliches Rätsel in der Prosa der Restaurationszeit und im Werk der Droste. Köhn, Lothar E. Ribbat (ed.) (1998). 71–93.
• Hinter den Spiegeln: Mergels Uhr und Aarons Risiko. Schmidt, Michael B. W. Johannes Heil (ed.) (1997). 171–192.
• The "Bauernhochzeit" in Droste’s "Die Judenbuche". A contemporary reading. Pickar, Gertrud Bauer L. Bodi (ed.) (1995). 68–93.
• Bayesian Theory Bernardo, José M.; Smith, Adrain F. M. in Wiley Series in Probability and Mathematical Statistics (1994). (First ) Wiley, Chichester.
• The Specter of Anti-Semitism in and around Annette von Droste-Hülshoff’s "Judenbuche". Doerr, Karin (1994). 17(3) 447–471.
• "Friedrich Mergel, geboren 1738 im Dorfe B.". Von den Namen in Annette Droste-Hülshoffs Novelle "Die Judenbuche". Rölleke, Heinz (1991). 209–216.
• Where the Devil leads: Peasant superstitions in George Sand’s "Petite fadette" and Droste-Hülshoff’s "Judenbuche". Godwin-Jones, Robert (1983). 10(1) 221–238.
• Zur Deutungsproblematik der "Judenbuche" - semiotisch gesehen. Zeller, Hans (W. Woesler, ed.) (1982). 1978-1982(5) 95–104.
• Die Judenbuche. Erläuterungen und Dokumente Droste-Hülshoff, Annette in Universal-Bibliothek, (W. Huge, ed.) (1981). Reclam, Stuttgart.
• Die Literarisierung eines Kriminalfalls. Woesler, Winfried (1980). 99 5–21.
• The Real Mystery in Droste-Hülshoff’s "Die Judenbuche". Brown, Jane K. (1978). 73(4) 835–846.
• Der Verbrecher in der deutschen Prosaliteratur des ausgehenden achtzehnten und des neunzehnten Jahrhunderts. Technical Report (PhD dissertation), Barsch, Maria Benedikta (1978).
• Die Narbe des Friedrich Mergel. Zur Aufklärung eines literarischen Motivs in Annette von Droste-Hülshoffs "Die Judenbuche". Oppermann, Gerard (1976). 50(3) 449–464.
• Kann man das Wesen gewöhnlich aus dem Namen lesen? Zur Bedeutung der Namen in der "Judenbuche" der Annette von Droste-Hülshoff. Rölleke, Heinz (1976). 70(4) 409–414.
• Annette von Droste-Hülshoff: Die Judenbuche. Freund, Winfried (1975). 63–73.
• Das Doppelgängermotiv in der Judenbuche. Murakami, Fumihiko (1975). (16) 78–86.
• Miszelle zur Judenbuche. Rölleke, Heinz (W. Woesler, ed.) (1973). 1972-1973(2) 139–140.
• Der Algerier. Der Stoff zur Novelle "Die Judenbuche" von Annette von Droste-Hülshoff, nach August von Haxthausen. Kiepke, Rudolf (1972). 22(9) 138–139.
• "Die Judenbuche" and English Literature. Thomas, L. H. C. (1969). 64(2) 351–354.
• "Die Judenbuche. Von der lebenden Gegenwärtigkeit einer "historischen" Novelle. Kleinwächter, Johannes (1963). 18–20.
• Erläuterungen zu Annette von Droste-Hülshoffs "Die Judenbuche" Woyte, Oswald in Wilhelm Königs Erläuterungen zu den Klassikern (1957). Bange, Hollfeld/Oberfranken.
• Die Vorfabel der "Judenbuche". Flaskamp, Franz (1956). 10–14.
• Bildsymbole in der deutschen Novelle. von Wiese, Benno (1955). 24(1) 131–158.
• Droste-Hülshoff, "Die Judenbuche". Silz, Walter (1954). 36–51.
• Studie zum Erzählstil der Judenbuche. Hoffmann, Lore (1950). 2 137–147.
• Ueber eine Oertlichkeit der Judenbuche von Annette Droste. Oeke, Wilhelm (1934). (121) 504–504.
• Die Örtlichkeiten in der "Judenbuche" der Annette von Droste. Oeke, Wilhelm (1927). (26)
• Vom Realismus der Droste. Antz, Joseph (1912). 25(6) 308–310.
• Der Weg zur Form. Ästhetische Abhandlungen vornehmlich zur Tragödie und Novelle Ernst, Paul (1906). Bard, Berlin.
• Eine Novelle und ihre Quellen III. Franzos, Karl Emil (1897). 61(53) 632–633.
• Der Westfälische Antiquarius. Schücking, Levin (1866). (5)
• Der Westfälische Antiquarius. Schücking, Levin (1866). (4)