Refine
Year of publication
Document type
- Conference Proceeding (1580) (remove)
Has full text
- No (1580) (remove)
Keywords
- CD-ROM (41)
- Poster (27)
- Cloud computing (24)
- Security (19)
- Machine learning (15)
- Industry 4.0 (11)
- Virtual reality (11)
- Posterpräsentation (10)
- Manufacturing (9)
- Privacy (9)
On the way to the smart factory, the manufacturing companies investigate the potential of Machine Learning approaches like visual quality inspection, process optimisation, maintenance prediction and more. In order to be able to assess the influence of Machine Learning based systems on business-relevant key figures, many companies go down the path of test before invest. This paper describes a novel and inexpensive distributed Data Acquisition System, ARTHUR (dAta collectoR sysTem witH distribUted sensoRs), to enable the collection of data for AI-based projects for research, education and the industry. ARTHUR is arbitrarily expandable and has so far been used in the field of data acquisition on machine tools. Typical measured values are Acoustic Emission values, force plate X-Y-Z force values, simple SPS signals, OPC-UA machine parameters, etc. which were recorded by a wide variety of sensors. The ARTHUR system consists of a master node, multiple measurement worker nodes, a local streaming system and a gateway that stores the data to the cloud. The authors describe the hardware and software of this system and discuss its advantages and disadvantages.
ARTHUR – Distributed Measuring System for Synchronous Data Acquisition from Different Data Sources
(2023)
In industrial manufacturing lines, different machines are well orchestrated and applied for their well-defined purpose. As each of these machines must be monitored and maintained in the first place, there are scenarios in which a Data Acquisition system brings enormous benefits. Since the cost of such professional systems is often not appropriate or feasible for research projects or prototyping, a proof of concept is often achieved by applying end-user hardware. In this work, a distributed measurement system for supporting the collection of data is described with respect to AI-based projects for research and teaching. ARTHUR (meAsuRing sysTem witH distribUted sensoRs) is arbitrarily expandable and has so far been used in the field of data acquisition on machine tools. Typical measured values are Accoustic Emission values, force plates X-Y-Z force values, simple PLC switching signals, OPC-UA machine parameters, etc., which were recorded by a wide variety of sensors. The overall ATHUR system is based on Raspberry Pis and consists of a master node, multiple independent measurement worker nodes, a streaming system realized with Redis, as well as a gateway that stores the data in the cloud. The major objectives of the ARTHUR system are scalability and the support for low-cost measuring components while solely applying open-source software. The work on hand discusses the advantages and disadvantages regarding the hard- and software of this TCP/IP-based system.
Transcutaneous Monitoring of pCO2 for the Noninvasive Determination of the Anaerobic Threshold
(1991)
Supervised object detection models are trained to recognize certain objects. These models are classified into two types: single-stage detectors and two-stage detectors. The single-stage detectors just need one pass through the model to anticipate all the bounding boxes, whereas the two-stage detectors require to first estimate the image portions where the object could be located. Due to their speed and simplicity, single-stage anchor-based models are used in many industrial settings. Training such models require bounding boxes that describe the spatial location of an object, which are usually drawn by an expert. However, the question remains, how much area should be considered when drawing the bounding boxes? In this paper, we demonstrate the effects that the size and placement of a rectangular bounding box can have on the performance of the anchor-based models. For this, we first perform experiments on a synthetically generated binary dataset and then on a real-world object detection dataset. Our results show that fixing the size of the bounding boxes can help in improving the performance of the model in the case of single class object detection (approximately 50% improvement in mAP@[.5:.95] for real world dataset). Furthermore, we also demonstrate how freely available tools can be combined for obtaining the best possible semi automated object labeling pipeline.
A simulation-based approach for measuring the performance of human-AI collaborative decisions
(2022)
Despite the widespread adoption of artificial intelligence and machine learning for decision-making in organizations, a wealth of research shows that situations that involve open-ended decisions (novel contexts without predefined rules) will continue to require humans in the loop. However, such collaboration that blends formal machine and bounded human rationality also amplify the risk of what is known as local rationality, which is when rational decisions in a local setting lead to globally dysfunctional behavior. Therefore, it becomes crucial, especially in a data-abundant environment that characterizes algorithmic decision-making, to devise means to assess performance holistically, not just for decision fragments. There is currently a lack of quantitative models that address this issue.
The importance of machine learning (ML) has been increasing dramatically for years. From assistance systems to production optimisation to healthcare support, almost every area of daily life and industry is coming into contact with machine learning. Besides all the benefits ML brings, the lack of transparency and difficulty in creating traceability pose major risks. While solutions exist to make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge, as unnoticed modification of a model is also a danger when using ML. This paper proposes to create an ML Birth Certificate and ML Family Tree secured by blockchain technology. Important information about training and changes to the model through retraining can be stored in a blockchain and accessed by any user to create more security and traceability about an ML model.
In this work, we characterise a flexural mechanical amplifier, which is used for the realisation of a miniaturised piezoelectric inchworm motor designed for large force (some N) and stroke (tens of mm) operation as it is required e.g., for medical implants. The characterisation is based on high precision optical displacement measurements and a force self-sensing approach. An optically measured displacement of 292 nm in lateral direction and 910 nm in vertical direction of the flexural mechanical amplifier has been obtained, corresponding to a deflection attenuation factor of 3.1. Piezoelectric self-sensing of force was used to determine a force amplification factor of 3.43 from the mechanical oval structure.
Die klinische Leistungsfähigkeit von Medizinprodukten rückt bei den Anforderungen moderner Entwicklungsprozesse und den damit verbundenen Regularien immer stärker in den Vordergrund. Die Nachweise für diese Performance können jedoch oft erst sehr spät im Rahmen klinischer Prüfungen bzw. Studien erreicht werden. Ein Lösungsansatz für dieses Problem können virtuellen klinischen Studien darstellen, die auf Simulationsmethoden aufbauen und so helfen, frühzeitig wichtige Weichen in der Entwicklung zu stellen und verschiedene konzeptionelle Ansätze für die Produktentwicklung sowie eine Optimierung spezieller Parameter zu erreichen. Die Nutzung derartiger Techniken wird sowohl durch die Europäisch Kommission im Abschlussreport der Avicenna Alliance als auch gezielt von der FDA im Rahmen verschiedener Guidance-Dokumente vorgestellt und forciert. Das Medical Solution Center-BW greift diese Ansätze auf und strebt an, ein Netzwerk aus Partnern aus Industrie und Wissenschaft aufzubauen, dass die Nutzung von Simulation / HPC im Rahmen der Entwicklung von Medizinprodukten systematisch zu erschließen. Das betrifft insbesondere die Option zur Entwicklung virtueller klinischer Studien in den Bereichen der strukturmechanischen Simulation von Knochen-Implantat-Systemen sowie der strömungsmechanischen Simulation im Bereich der endovaskulären Chirurgie. In unserem Beitrag werden wir einen prinzipiellen Vorschlag zur Implementierung eines Verfahrens vorstellen, welches die Bewertung von Medizinprodukten mit Hilfe biomechanischer Simulationen in virtuellen klinischen Studien ermöglicht und explizite Simulationsanwendungen aus dem Bereich der Knochen-Implantat-Systeme präsentieren.
Digital Transformation, Smart Factories, and Virtual Design: Contributions of Subject Orientation
(2018)
The Elephant in the Room - Educating Practitioners on Software Development for Sustainability
(2021)
Sustainability is a major concern for our society today. Software acts as a catalyst to support different business activities which have an impact on sustainability. Research from software engineering and other academic disciplines have proposed various software sustainability guidelines, tools, and methods to support software sustainability design in industry. However, there are still challenges on how to design and engineer sustainability into software products by software development practitioners in industry using those proposed sustainability guidelines and tools. The goal of this research is to seek understanding on what software sustainability means for software development practitioners and identify how to properly support engineering of sustainability into software design and development through academic research. Data were gathered and analyzed using grounded theory from workshop with different software development practitioners to seek their understanding on what sustainability means in their software systems. The results show economic and technical sustainability dimensions are the most important to software development practitioners for software sustainability. While the social sustainability dimension was not considered for software sustainability. The findings from this study indicates contrast in academia where all sustainability dimensions are treated as an important element to achieve software sustainability. Therefore, there is need for better collaboration between industry and academia to improve understanding of software sustainability and support effective sustainability engineering in software systems.
Context: It is impossible to imagine our everyday and professional lives without software. Consequently, software products, especially socio-technical systems, have more or less obvious impacts on almost all areas of our society. For this purpose, a group of scientists worldwide has developed the Sustainability Awareness Framework (SusAF) which examines the impacts on five interrelated dimensions: social, individual, environmental, economic, and technical. According to this framework, we should design software to maintain or improve the Sustainability Impacts. Designing for sustainability is a major challenge that can profoundly change the field of activity – particular for Software Engineers. Objectives: The aim of the thesis work is to analyze the current role of Software Engineers and relate it to Sustainability Impacts of Software Products in order to contribute to this paradigm shift. This should provide a basis for follow-up works. The question in which direction exactly the Software Engineer should develop and how exactly this path can be followed is still owed by the scientific community. Perhaps universities will have to adapt the curriculum in the training of Software Engineers, politics could possibly initiate support programs in the field of sustainability for software companies, or maybe software sustainability certifications could emerge. In any case, Software Engineers must adapt to the times and acquire the necessary knowledge, the skills and the competencies. Results: The results of the dissertation are a better understanding of the needed paradigm shift of Software Engineers and comeplement the SusAF that to better support sustainability design. The extended SusAF is intended for both training and corporate use.
Shapley Values based Regional Feature Importance Measures Driving Error Analysis in Manufacturing
(2022)
Development of mHealth-Apps for Hearing Aids – Requirements and Assessments of a First Prototype
(2022)
Comparison of Visual Attention Networks for Semantic Image Segmentation in Reminiscence Therapy
(2022)
Due to the steadily increasing age of the entire population, the number of dementia patients is steadily growing. Reminiscence therapy is an important aspect of dementia care. It is crucial to include this area in digitization as well. Modern Reminiscence sessions consist of digital media content specifically tailored to a patient’s biographical needs. To enable an automatic selection of this content, the use of Visual Attention Networks for Semantic Image Segmentation is evaluated in this work. A detailed comparison of various Neural Networks is shown, evaluated by Metric for Evaluation of Translation with Explicit Ordering (METEOR) in addition to Billingual Evaluation Study (BLEU) Score. The most promising Visual Attention Network consists of a Xception Network as Encoder and a Gated Recurrent Unit Network as Decoder.
Pflegeinnovationen in der Praxis: Erfahrungen und Empfehlungen aus dem "Cluster Zukunft der Pflege"
(2022)
Enormous potential of artificial intelligence (AI) exists in numerous products and services, especially in healthcare and medical technology. Explainability is a central prerequisite for certification procedures around the world and the fulfilment of transparency obligations. Explainability tools increase the comprehensibility of object recognition in images using Convolutional Neural Networks, but lack precision.
This paper adapts FastCAM for the domain of detection of medical instruments in endoscopy images. The results show that the Domain Adapted (DA)-FastCAM provides better results for the focus of the model than standard FastCAM weights.
Innovationsverhalten von Lowtech-Unternehmen und Innovationskooperation mit Hightech Partnern
(2009)
AAL applications are designed for elderly people and collecting personally identifiable information (PII), e.g. health data. During normal operations, these data should be kept private. But during emergency situations, the information is critical for helpers and emergency doctors. This paper discusses the results of a survey conducted for PII in AAL and proofs the requirement of special access control rules for systems in situations of emergency.
In edge/fog computing infrastructures, the resources and services are offloaded to the edge and computations are distributed among different nodes instead of transmitting them to a centralized entity. Distributed Hash Table (DHT) systems provide a solution to organizing and distributing the computations and storage without involving a trusted third party. However, the physical locations of nodes are not considered during the creation of the overlay which causes some efficiency issues. In this paper, Locality aware Distributed Addressing (LADA) model is proposed that can be adopted in distributed infrastructures to create an overlay that considers the physical locations of participating nodes. LADA aims to address the efficiency issues during the store and lookup processes in DHT overlay. Additionally, it addresses the privacy issue in similar proposals and removes any possible set of fixed entities. Our studies showed that the proposed model is efficient, robust and is able to protect the privacy of the locations of the participating nodes.
Mobility management is a key feature of mobile edge
computing. We present an edge cloud infrastructure testbed to
explore various mobility scenarios. The design objection of this testbed has been a flexible open platform based on commodity hardware that can easily be scaled with more edge devices and compute resources to perform various edge cloud experiments. As first experiments on our testbed, we have investigated the feasibility of task migration among edge devices caused by edge device overload and unpredictable user movements. We describe the migration process and present some measurements to demonstrate the feasibility.