1 - 10 of 286
-
PublicationRegression via causally informed Neural Networks( 2024)Neural Networks have been successful in solving complex problems across various fields. However, they require significant data to learn effectively, and their decision-making process is often not transparent. To overcome these limitations, causal prior knowledge can be incorporated into neural network models. This knowledge improves the learning process and enhances the robustness and generalizability of the models. We propose a novel framework RCINN that involves calculating the inverse probability of treatment weights given a causal graph model alongside the training dataset. These weights are then concatenated as additional features in the neural network model. Then incorporating the estimated conditional average treatment effect as a regularization term to the model loss function, the potential influence of confounding variables can be mitigated, leading to bias minimization and improving the neural network model. Experiments conducted on synthetic and benchmark datasets using the framework show promising results.
-
PublicationAttribute-Based Person Retrieval in Multi-Camera Networks( 2024)Attribute-based person retrieval is a crucial component in various realworld applications, including surveillance, retail, and smart cities. Contrary to image-based person identification or re-identification, individuals are searched for based on descriptions of their soft biometric attributes, such as gender, age, and clothing colors. For instance, attribute-based person retrieval enables law enforcement agencies to efficiently search enormous amounts of surveillance footage gathered from multi-camera networks to locate suspects or missing persons. This thesis presents a novel deep learning framework for attribute-based person retrieval. The primary objective is to research a holistic approach that is suitable for real-world applications. Therefore, all necessary processing steps are covered. Pedestrian attribute recognition serves as the base framework to address attribute-based person retrieval in this thesis. Various design characteristics of pedestrian attribute recognition approaches are systematically examined toward their suitability for attribute-based person retrieval. Following this analysis, novel techniques are proposed and discussed to further improve the performance. The PARNorm module is introduced to normalize the model’s output logits across both the batch and attribute dimensions to compensate for imbalanced attributes in the training data and improve person retrieval performance simultaneously. Strategies for video-based pedestrian attribute recognition are explored, given that videos are typically available instead of still images. Temporal pooling of the backbone features over time proves to be effective for the task. Additionally, this approach exhibits faster inference than alternative techniques. To enhance the reliability of attributebased person retrieval rankings and address common challenges such as occlusions, an independent hardness predictor is proposed that predicts the difficulty of recognizing attributes in an image. This information is utilized to remarkably improve retrieval results by down-weighting soft biometrics with an increased chance of classification failure. Additionally, three further enhancements to the retrieval process are investigated, including model calibration based on existing literature, a novel attribute-wise error weighting mechanism to balance the attributes’ influence on retrieval results, and a new distance measure that relies on the output distributions of the attribute classifier. Meaningful generalization experiments on pedestrian attribute recognition and attribute-based person retrieval are enabled for the first time. For this purpose, the UPAR dataset is proposed, which contributes 3.3 million binary annotations to harmonize semantic attributes across four existing datasets and introduces two evaluation protocols. Moreover, a new evaluation metric is suggested that is tailored to the task of attribute-based person retrieval. This metric evaluates the overlap between query attributes and the attributes of the retrieved samples to obtain scores that are consistent with the human perception of a person retrieval ranking. Combining the proposed approaches yields substantial improvements in both pedestrian attribute recognition and attribute-based person retrieval. State-of-the-art performance is achieved concerning both tasks and existing methods from the literature are surpassed. The findings are consistent across both specialization and generalization settings and across the well-established research datasets. Finally, the entire processing pipeline, from video feeds to the resulting retrieval rankings, is outlined. This encompasses a brief discussion on the topic of multi-target multi-camera tracking.
-
PublicationBridging the Gap Between IDS and Industry 4.0 - Lessons Learned and Recommendations for the Future( 2024)The Plattform Industrie 4.0 (PI4.0) and the International Data Spaces Association (IDSA) are two independent, parallel initiatives with clear focuses. While PI4.0 addresses communication and interaction between networked assets in a smart factory and/or supply chain across an asset or product lifecycle, IDSA is about a secure, sovereign system of data sharing in which all stakeholders can realize the full value of their data. Since data sharing between companies requires both interoperability and data sovereignty, the question emerges regarding the feasibility and rationality of integrating the expertise of PI4.0 and IDSA. The IDS-Industrial Community (IDS-I) is an extension of IDSA whose goal is to strengthen the cooperation between IDSA and PI4.0. Two fields of expertise could be combined: The Platform's know-how in the area of Industrie 4.0 (I4.0) and the IDSA's expertise in the areas of data sharing ecosystems and data sovereignty. In order to realize this vision, many aspects have to be taken into account, as there are discrepancies on multiple levels. Specifically, at the reference architecture level, we have the RAMI4.0 model on the PI4.0 side and the IDS Reference Architecture Model (IDS-RAM) on the IDSA side. While the existing I4.0 and IDS specifications are incompatible e.g. in terms of models (i.e., the AAS metamodel and the IDS information model) and APIs, there is also the issue of interoperability between I4.0 and IDS solutions. This position paper aims to bridge the gap between IDS and PI4.0 by not only analyzing how their existing concepts, tools, etc. have been "connected" in different contexts. Rather, this position paper makes recommendations on how different technologies could be combined in a generic way, independent of the concrete implementation of IDS and/or I4.0 relevant technology components. This paper could be used by both the IDS and I4.0 communities to further improve their specifications, which are still under development. The lessons learned and feedback from the initial joint use of technology components from both areas could provide concrete guidance on necessary improvements that could further strengthen or extend the specifications. Furthermore, it could help to promote the IDS architecture and specifications in the industrial production and smart manufacturing community and extend typical PI4.0 use cases to include data sovereignty by incorporating IDS aspects.
-
PublicationSensor-based characterization of construction and demolition waste at high occupancy densities using synthetic training data and deep learning( 2024)Sensor-based monitoring of construction and demolition waste (CDW) streams plays an important role in recycling (RC). Extracted knowledge about the composition of a material stream helps identifying RC paths, optimizing processing plants and form the basis for sorting. To enable economical use, it is necessary to ensure robust detection of individual objects even with high material throughput. Conventional algorithms struggle with resulting high occupancy densities and object overlap, making deep learning object detection methods more promising. In this study, different deep learning architectures for object detection (Region-based CNN/Region-based Convolutional Neural Network (Faster R-CNN), You only look once (YOLOv3), Single Shot MultiBox Detector (SSD)) are investigated with respect to their suitability for CDW characterization. A mixture of brick and sand-lime brick is considered as an exemplary waste stream. Particular attention is paid to detection performance with increasing occupancy density and particle overlap. A method for the generation of synthetic training images is presented, which avoids time-consuming manual labelling. By testing the models trained on synthetic data on real images, the success of the method is demonstrated. Requirements for synthetic training data composition, potential improvements and simplifications of different architecture approaches are discussed based on the characteristic of the detection task. In addition, the required inference time of the presented models is investigated to ensure their suitability for use under real-time conditions.
-
PublicationTowards a Digital Representation of Building Systems Controls( 2024)Energy monitoring and performance optimization processes play a significant role in ensuring energy-efficient building operation. However, the current implementation of these processes requires substantial time and effort due to the fragmented and non-digital nature of technical building equipment information. To address these challenges, we demonstrate the application of the PLCont methodology within an ongoing monitoring process in a real building. PLCont utilizes Semantic Web Technologies and established RDF ontologies to describe the control topology. The digital representation of control functions aligns closely with the IEC standard 61131-3, and the PLCont ontology establishes a connection between the topology and the control functions. We compare the conventional approach and the PLCont methodol-ogy using the supply air temperature control of an Air Handling Unit (AHU) as a use case. A graphical user interface built upon the PLCont backend provides a comprehensive represen-tation of the system's functionality. It displays the system topology as a digital HVAC schema, the function code exported from the PLC, time-series data plots, and textual descriptions of implemented functions. We demonstrate how this approach enhances transparency and facil-itates the identification and elimination of faulty system behavior, ultimately contributing to the optimization and energy efficiency of building systems.
-
PublicationFortschrittsbericht zur Digitalisierung des Energiesystems(Fraunhofer CINES, 2024)
-
PublicationA Concept Study for Feature Extraction and Modeling for Grapevine Yield Prediction( 2024)
-
PublicationCognitive User Modeling for Adaptivity in Serious Games( 2024)Accurate user models that capture information such as needs and knowledge levels are a central part of adaptive e-learning systems, which is all the more important in a post-pandemic world with more individualized learning. In this article, we report on the application of a Bayesian cognitive state modeling approach to adaptive educational serious games. Adaptivity needs information on the users as control variables, e.g., high or low cognitive load. Typically, this information is encoded in user models. One approach to building user models is to use tools from cognitive sciences such as Bayesian cognitive state modeling. However, cognitive modeling tools for adaptivity are sparse and can be difficult to implement. The main research question of this work is how to apply cognitive modeling tools to serious games to control adaptivity. The contribution of this article is the concept of how to implement cognitive modeling for adaptive serious games. Our approach makes use of standardized Experience API (xAPI) tracking data to facilitate applicability. We investigate how to compute quantitative measures of user performance to control adaptive responses. The implemented system has been evaluated in a user study with a serious game for image interpretation. The study results show a moderate correlation between self-assessed and computed variables.
-
PublicationMetrics for the evaluation of learned causal graphs based on ground truth( 2024)The self-guided learning of causal relations may contribute to the general maturity of artificial intelligence in the future. To develop such learning algorithms, powerful metrics are required to track advances. In contrast to learning algorithms, little has been done in regards to developing suitable metrics. In this work, we evaluate current state of the art metrics by inspecting their discovery properties and their considered graphs. We also introduce a new combination of graph notation and metric, which allows for benchmarking given a variety of learned causal graphs. It also allows the use of maximal ancestral graphs as ground truth.
-
