Refine
Year of publication
Document type
- Conference Proceeding (1637) (remove)
Keywords
- CD-ROM (41)
- Poster (30)
- Cloud computing (24)
- Security (20)
- Machine learning (16)
- Industry 4.0 (12)
- Posterpräsentation (10)
- Privacy (10)
- Virtual reality (10)
- Manufacturing (9)
As machine learning becomes increasingly pervasive, its resource demands and financial implications escalate, necessitating energy and cost optimisations to meet stakeholder demands. Quality metrics for predictive machine learning models are abundant, but efficiency metrics remain rare. We propose a framework for efficiency metrics, that enables the comparison of distinct efficiency types. A quality-focused efficiency metric is introduced that considers resource consumption, computational effort, and runtime in addition to prediction quality. The metric has been successfully tested for usability, plausibility, and compensation for dataset size and host performance. This framework enables informed decisions to be made about the use and design of machine learning in an environmentally responsible and cost-effective manner.
In this paper, the influence of current sensors of a NILM system is investigated. The current sensors of a classical inductive current transformer and a Rogowski coil are compared. To evaluate the actual influence on the NILM, measurements are performed with two measuring systems with different current sensors. With these measuring systems, 20 different consumers with 50 switch-on and switch-off cycles are measured in parallel. Besides, the influence of the sampling rate on the results of the NILM classification is evaluated. The classification is carried out with features normalized to the performance and without phase information, so only the signal waveform is used to differentiate the devices.
Elevators contribute significantly to the electricity consumption of residential buildings, office buildings and commercial enterprises. In this paper, the electricity consumption is investigated using an elevator system and its individual operating states as example. In addition to analyzing and allocating the energy demand, this work examines how the individual operating states can be determined solely on the basis of the power consumption of the elevator. The knowledge gained from this, such as the usage behavior, the travel profile, or load, is determined independently of the elevator control system. A subsequent installation on any system can be easily realized. In this work, the investigated elevator requires a substantial part of the total annual power consumption in standby (>90 %). This shows an enormous potential for energy savings. The individual elevator states, as well as the load, can be detected very well on the basis of the measured total power consumption. The work thus shows exemplary the potential of an intelligent measurement system for the state detection of elevator systems.
Separation of ventilation and cardiac activity on recorded voltages before EIT image reconstruction
(2023)
Modelability of processes is a recognized and important characteristic of any modeling language. Nevertheless, it is not always purposeful or easy to create process models for every kind of workflow. This article discusses the opportunities and limitations of modeling agile development projects with SCRUM as an example. For this purpose, a BPMN and an S-BPM model for SCRUM are presented. The discussion along recognized rules for good process models shows that both notations provide possible and accurate insights into the process of SCRUM on the one hand. On the other hand, the models raise questions of necessity, added value, and relevance in practice. Practitioners can use the developed models to technically implement agile project management, while researchers benefit from a discourse on opportunities and limitations of modeling agility.
For many practitioners, considering sustainability during a software development project is a challenge. The Sustainability Awareness Framework (SusAF) is a tool for thinking through short, medium-and long-term impacts of socio-technical systems on its surrounding environment. While SusAF has been used by several companies, is not widely adopted in industry yet. In this Vision Paper, we discuss the options for extending the reach of SusAF and what it would take to evolve SusAF into a (de-facto) standard
Digital transformation is now reaching into topics like End-of-life Care, Funeral Culture, and Coping with Grief. Those developments are inevitably accompanied by the growing challenge to design IT systems that are appropriate and helpful for the stakeholders involved. Our aim in this paper is to further introduce the rather new combined research field of Socioinformatics and Thanatology (the scientific study of death and dying) and to present it with the first results on which requirements to consider for the design of digital tools within ‘Thanatopractice’. By using Participatory Design and the Sustainability Awareness Framework (SusAF) in the context of three workshops on socio-technical systems (Online Pastoral Care, Virtual Graveyards, and AI Memory Avatars), we want to sensitize software practitioners to the multidimensional impacts of their products and services in a field, which the participants in the workshops often described as “highly sensitive”.
In-situ SEM analysis tool for stretchable metal-elastomer-laminate-membranes for flexible sensors
(2023)
Explainable Artificial Intelligence (XAI) seeks to enhance transparency and trust in AI systems. Evaluating the quality of XAI explanation methods remains challenging due to limitations in existing metrics. To address these issues, we propose a novel metric called Explanation Significance Assessment (ESA) and its extension, the Weighted Explanation Significance Assessment (WESA). These metrics offer a comprehensive evaluation of XAI explanations, considering spatial precision, focus overlap, and relevance accuracy. In this paper, we demonstrate the applicability of ESA and WESA on medical data. These metrics quantify the understandability and reliability of XAI explanations, assisting practitioners in interpreting AI-based decisions and promoting informed choices in critical domains like healthcare. Moreover, ESA and WESA can play a crucial role in AI certification, ensuring both accuracy and explainability. By evaluating the performance of XAI methods and underlying AI models, these metrics contribute to trustworthy AI systems. Incorporating ESA and WESA in AI certification efforts advances the field of XAI and bridges the gap between accuracy and interpretability. In summary, ESA and WESA provide comprehensive metrics to evaluate XAI explanations, benefiting research, critical domains, and AI certification, thereby enabling trustworthy and interpretable AI systems.
3D Computer Vision for the Industrial Metaverse - On the potentials of Neural Radiance Fields
(2023)
The industrial metaverse refers to the use of virtual reality (VR) and augmented reality (AR) technologies in the context of industry and manufacturing. It is envisioned as a shared, immersive digital space where people can interact with and manipulate virtual representations of physical objects and processes. The industrial metaverse has the potential to transform the way products are designed, manufactured, and maintained,
enabling new levels of collaboration, automation, and innovation.
It further includes virtual representations of humans, also known as avatars. These avatars can be used to enable remote collaboration and communication between people in the virtual space. In this way, the industrial metaverse can facilitate virtual meetings, trainings, and other interactive experiences that involve human participants.
Neural Radiance Fields (NeRFs) are a powerful tool for synthesizing photorealistic images of 3D objects, including virtual representations of humans known as avatars. In this talk, we will discuss the potential applications of NeRFs in generating high-fidelity objects and avatars for use in the industrial metaverse.
In several domains of product design - like medical device design -
risk related use scenarios have to be analyzed in an early stage of design process.
Virtual reviews with users make it possible to get early insights in use problems.
Also, situations that are difficult to imitate in reality can be modeled and simulated
in virtual reality without risking the health of user. Therefore, virtual usability
tests are a promising approach which allow testing different scenarios under
controlled conditions. We chose a sample scenario from medical device design
and compare and evaluate different technical systems which can be used for virtual
usability tests. Aim is to derive guidance for virtual usability tests including
systems that can be used for specific conditions and the qualitative and quantitative
data, which can be collected with these systems. A formative test is performed
to evaluate and compare different systems. Also, a summative test is performed
to evaluate the selected systems. Results show that virtual usability tests
make it possible to test scenarios with users in an early stage and thus to encounter
possible interaction problems. But there are also many additional and new
things to consider compared to normal usability tests, such as checking motion
sickness, maintaining presence and the extensive operation of the technology.
Finally, a proposed method for virtual usability testing is described which also
comprises our equipment recommendations for virtual usability tests.
Companies are confronted with the challenge of having to transfer more and more knowledge in a shorter time to fewer available employees. At the same time opportunities based on digitalization and smart services are rising. Digital training offers advantages as flexibility, accessibility, in-teractivity and cost savings. This explorative paper investigates the framework conditions, requirements and opportunities for new approach-es of providing knowledge by smart services for professional users. Fur-ther, the paper will investigate how smart service approaches for knowledge provision can be transferred and integrated into product ser-vice systems and suitable business models.
XAI for Semantic Dependency : How to understand the impact of higher-level concepts on AI results
(2023)
Proactive behaviour of in-vehicle voice assistants is seen as key to develop increasingly intelligent and interactive systems. One of the main questions for proactive voice assistants is when opportune moments for engaging the user are. We present a driving simulator study (N = 32) investigating different situations of proactive interaction during an automated ride. Based on previous findings for opportune moments of interaction during manual driving, the study’s focus is on evaluating the influence of driving situations and the performance of a non-driving related activity (NDRA) on the opportuneness of a proactive interaction. The quantitative and qualitative findings show that most situations do not impact the opportuneness of a proactive interaction during an automated ride. However, an extreme traffic situation with an approaching emergency vehicle is considered as inopportune. Travel time and the current state of the user should also be considered for the selection of an opportune moment. A validation of the results in a real road driving study is planned.
Up until now, it has been shown that big parts of the so called Industry 4.0 are impacted by Machine Learning (ML) in some way or another. In many shopfloor situations, there are different sensors involved and all data is eventually structured, accumulated and prepared for application in various ML-based scenarios, e.g., predictive maintenance of a machine, quality monitoring of manufactured workpieces or handling domain-specific aspect of the respective fabricator or product. As the physical environment of Cyber Physical System (CPS) can change rapidly, the overall Data Acquisition (DAQ) process and ML training is impacted, too. This work focuses on datasets which consist of small amounts of tabular information and how to utilize them in image-based Neural Networks (NN) with respect to meta learning and multimodal transformations. Therefore, the conceptual utilization of an DAQ system in industrial environments is discussed regarding a variety of techniques for preprocessing and generating visual material from multimodal data. The outcome of such operations is a new dataset which is then applied in model training. Therefore, the presented approach is three-fold. In first analysing the concept of predicting the similarity of structured and numerical data in different datasets, indicators of the feasibility when applying the methodology in related but more sophisticated learning scenarios can be gained. Although ongoing time-series data is differing from simple multi-class data in terms of a chronologically dimension, basic classification concepts are applied to it and evaluated. In order to extend the similarity prediction with a temporal component, the discussed methods are extended by multimodal transformations and an subsequent utilization in Siamese Neural Networks (SNN). By discussing the concept of applying visual representations of structured time-series data in a meta-learning context, known trends and historic information can be utilized for generating real-world test-samples and predicting their validity on inference.
Operations within a Cyber Physical System (CPS) environment are naturally diverse and the resulting data sets include complex relations between sensors of the shopfloor devices setup, their configuration respectively. As Machine Learn- ing (ML) can increase the success of industrial plants in a variety of cases, like smart controlling, intrusion detection or predictive maintenance, clarifying responsibilities and operations for the whole lifecycle supports evaluating the potentially feasible scenarios. In this work, the need for highly configurable and flexible modules is demonstrated by depicting the complex possibilities of extending simple Machine Learning Operations (MLOps) pipelines with additional data sources, e.g., sensors. In addition to the particular modules core functionality, arbitrary evaluation logic or data structure specific anomaly detection can be integrated into the pipeline. With the creation of audit-trails for all operational modules, automated reports can be generated for increasing the accountability of the different physical devices and the data related processing. The concept is evaluated in the context of the project Collaborative Smart Contracting Platform for digital value-added Networks (KOSMoS), where a sensor is part of an ML pipeline and audit trails are realized using Blockchain (BC) technology.
Retinopathy of Prematurity (ROP) is the highest cause of childhood blindness globally with babies born preterm having a higher probability of contracting the disease. The disease diagnosis remains an economic burden to many countries, lack of enough ophthalmologists for the disease diagnosis coupled with non-existent national screening guidelines still remains a challenge. To diagnose the disease, a fundus photography is conducted, printout images are analyzed to determine the presence or absence of the disease. With the increase in the development of smartphones having advanced image capturing and processing features, the utilization of smartphones to capture retina image for disease diagnosis is becoming a common trend. For regions where ophthalmologists are few and/or for low resource regions with few or no retina capturing equipment, the use of smartphones to capture retina images for retina diseases is an effective method. This, however, is challenged: different smartphones produce images of different resolutions; some images are darker others lighter and with different resolution. A smartphone retina image capturing has a smaller field of view ranging between 450–900 which is a major limitation. A lens to support a bigger view can be combined with this approach to provide a wide view of 1300. This enlargement however distorts the image quality and may result in losing some image features. To overcome these challenges, this work develops an improved U-Net model to preprocess images captured using smartphones for ROP disease diagnosis. Our focus is to determine the presence or absence of the disease from smartphone captured images. Because the images are captured under a smaller field of view (FOV), we develop an improved U-Net model by adding patches to enhance image circumference and extract all features from the image and use the extracted features to train a U-Net model for the disease diagnosis. The model results outperformed similar recent developments.
Einsatz eines Aktivitätstisches in der Akutversorgung : Erfahrungen und Ergebnisse aus der Praxis
(2023)
Potenzial eines Echtzeit-Patientenmonitoring-Systems zur Unterstützung einer bedarfsgerechten Pflege
(2023)
Are Muscles In Musculoskeletal Pain Syndromes Objectively Stiffer Than Normal? - An Evidence Map
(2023)
Bei der Entwicklung von Anwendungen der künstlichen Intelligenz (KI) im klinischen Setting ist es besonders wichtig zukünftige Nutzer*innen einzubeziehen. Denn gerade klinisches Personal benötigt sowohl zur Akzeptanz als auch zur effektiven Nutzung zukünftiger KI-Anwendungen ein tiefergehendes Verständnis der KI-Modelle und derenFunktionsprinzipien. In diesem Sinne wurde im Projekt KIDELIR, dessen Ziel es ist, ein KI Unterstützungssystem zur Delirprädiktion zu entwickeln, ein partizipativer Ansatz gewählt.
Um eine praxistaugliche Gestaltung und Entwicklung des KI-Systems zu erreichen, werden Pflegefachpersonen und Ärzt*innen fortlaufend in den Forschungs- und Entwicklungsprozess einbezogen. Im Folgenden wird berichtet, wie der Partizipationsprozess im Projekt KIDELIR bislang gestaltet wurde und welche weiteren Schritte geplant sind. Der Fokus liegt auf der Reflexion der Methoden, die zur Bedarfserhebung bezüglich der Delirversorgung aus pflegerischer Sicht und dem Nutzen eines KI-Systems zur Delirprädiktion herangezogen wurden. Konkret wird die Kombination von Fallvignetten, Health Information Mapping, Techno-Mimesis sowie Cognitive-Affective-Mapping und einer Gruppendiskussion betrachtet. Im weiteren Verlauf des Projekts sind vertiefende leitfadengestützte Interviews mit den Teilnehmenden sowie Ärzt*innen geplant.
Zusätzlich sind weitere partizipative Formate vorgesehen, unter anderem gemeinsam mit Ärzt*innen und Pflegefachpersonen.
Evolutionary strategy is increasingly used for optimization in various machine learning problems. It can scale very well, even to high dimensional problems, and its ability to globally self optimize in flexible ways provides new and exciting opportunities when combined with more recent machine learning methods. This paper describes a novel approach for the optimization of models with a data driven evolutionary strategy. The optimization can directly be applied as a preprocessing step and is therefore independent of the machine learning algorithm used. The experimental analysis of six different use cases show that, on average, better results are attained than without evolutionary strategy. Furthermore it is shown, that the best individual models are also achieved with the help of evolutionary strategy. The six different use cases were of different complexity which reinforces the idea that the approach is universal and not depending on specific use cases.
Data scientists, researchers and engineers want to understand, whether machine learning models for object detection work accurate and precise. Networks like Yolo use bounding boxes as a result to localize the object in the image.
The principal aim of this paper is to address the problem of a lack of an effective metric for evaluating the results of bounding box regression in object detection networks when boxes do not overlap or lie completely within each other.
The standard known metrics, like IoU, lack of differentiating results, which do not overlap but differ in the distance between predicted bounding box and label.
To solve this challenge, we propose a new metric called UIoU (Unified Intersection over Union) that combines the best properties of existing metrics (IoU, GIoU and DIoU) and extends them with a similarity factor. By assigning weight to each component of the metric, it allows for a clear differentiation between the three possible cases of box positions (not overlapping, overlapping, boxes inside each other).
The result of this paper is a new metric that outperforms the existing metrics such as IoU, GIoU and DIoU by providing a more understandable measure of the performance of object detection models. This provides researchers and users in the field of explainable AI with a metric that allows the evaluation and comparison of prediction and label bounding boxes in an understandable way.
Transcultural Student Research on SDGs - A Higher Education Project for Sustainable Development
(2023)
Prototyp eines Controllers und eine Simulationsumgebung für VR-basierte laparoskopische Trainings
(2023)
Prophylaxis in pink: Susceptibility of human oral bacteria to roseoflavin, a vitamin B2 analogue
(2023)
As industrial networks continue to expand and connect more devices and users, they face growing security challenges such as unauthorized access and data breaches. This paper delves into the crucial role of security and trust in industrial networks and how trust management systems (TMS) can mitigate malicious access to these networks.
The TMS presented in this paper leverages distributed ledger technology (blockchain) to evaluate the trustworthiness of blockchain nodes, including devices and users, and make access decisions accordingly. While this approach is applicable to blockchain, it can also be extended to other areas. This approach can help prevent malicious actors from penetrating industrial networks and causing harm. The paper also presents the results of a simulation to demonstrate the behavior of the TMS and provide insights into its effectiveness.
Health informatics plays a crucial role in modern healthcare provision. Training and continuous education are essential to bolster the healthcare workforce on health informatics. In this work, we present the training events within EU-funded DigNest project. The aim of the training events, the subjects offered, and the overall evaluation of the results are described in this paper.
The YOLO series of object detection algorithms, including YOLOv4 and YOLOv5, have shown superior performance in various medical diagnostic tasks, surpassing human ability in some cases. However, their black-box nature has limited their adoption in medical applications that require trust and explainability of model decisions. To address this issue, visual explanations for AI models, known as visual XAI, have been proposed in the form of heatmaps that highlight regions in the input that contributed most to a particular decision. Gradient-based approaches, such as Grad-CAM, and non-gradient-based approaches, such as Eigen-CAM, are applicable to YOLO models and do not require new layer implementation. This paper evaluates the performance of Grad-CAM and Eigen-CAM on the VinDrCXR Chest X-ray Abnormalities Detection dataset and discusses the limitations of these methods for explaining model decisions to data scientists.
In this paper, we present a study on the utilization of smart medical wearables and the user manuals of such devices. A total of 342 individuals provided input for 18 questions that address user behavior in the investigated context and the connections between various assessments and preferences. The presented work clusters individuals based on their professional relation to user manuals and analyzes the obtained results separately for these groups.
This poster presents a Montenegrin Digital Academic Innovation Hub aimed to support education, innovations, and academia-business cooperation in medical informatics (as one of four priority areas) at national level in Montenegro. The Hub topology and its organisation in the form of two main nodes, with services established within key pillars: Digital Education; Digital Business Support; Innovations and cooperation with industry; and Employment support.
A Review on Digital Wallets and Federated Service for Future of Cloud Services Identity Management
(2023)
In today’s technology-driven era, managing digital identities has become a critical concern due to the widespread use of online services and digital devices. This has led to a fragmented landscape of digital identities, burdening individuals with multiple usernames, passwords, and authentication methods. To address this challenge, digital wallets have emerged as a promising solution. These wallets empower users to store, manage, and utilize their digital assets, including personal data, payment information, and credentials. Additionally, federated services have gained prominence, enabling users to access multiple services using a single digital identity. Gaia-X is an example of such a service, aiming to establish a secure and trustworthy data infrastructure. This paper examines digital identity management, focusing on the application of digital wallets and federated services. It explores the categorization of identities needed for different cloud services, considering their unique requirements and characteristics. Furthermore, it discusses the future requirements for digital wallets and federated identity management in the cloud, along with the associated challenges and benefits. The paper also introduces a categorization scheme for cloud services based on security and privacy requirements, demonstrating how different identity types can be mapped to each category.
The charge response of a force applied to piezoelectric stack actuators was characterized in the range of 0 N – 20 N for application in piezoelectric self-sensing. Results show linear behavior between ap-plied force and collected charge for both actuators tested in this study. One actuator exhibits a 3.55 times higher sensitivity slope than the other related to its larger capacitance. An error analysis reveals a reduction of relative error in charge measurement with rising forces applied to the actuators.