Refine
Year of publication
- 2022 (77) (remove)
Document type
- Conference Proceeding (77) (remove)
Keywords
- Poster (6)
- Blockchain (2)
- CNN (2)
- CPS (2)
- Convolutional neural network (2)
- Emotion recognition (2)
- ML (2)
- MLOps (2)
- Machine learning (2)
- Measurement environment (2)
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.
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.
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.
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.
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 diesem Vortrag werde ich auf die Programmierumgebungen (ROS) und Schnittstellen (keras/Tensorflow) eingehen, die es ermöglichen Roboter mit Hilfe von maschinellem Lernen zu trainieren. Dabei werde ich insbesondere die Möglichkeiten vorstellen, wie man einen Roboter in der Simulation (gazebo) trainieren kann, um die trainierten Modelle auf echte Roboter zu übertragen. Anhand von praktischen Beispielen mit mobilen Robotern und Greifarmen werden die Konzepte des Reinforcement Learnings, Active Learnings, Transfer Learnings und der Objekterkennung demonstriert. Das Testszenario besteht aus einem Holz-Labyrinth und einem Turtlebot Roboter, der mit Laser Range Scanner und einer 2D-Kamera ausgestattet ist. Dabei soll der Roboter lernen, autonom den Weg zur angegebenen Zielposition zu planen ohne dabei gegen ein Hindernis zu fahren. Es wird hierbei untersucht in wie weit die trainierten Modelle in leicht abgeänderten Szenarien funktionsfähig bleiben.
Unter dem Motto „Technologie bewegt Pflege“ werden Beiträge aus Wissenschaft, Praxis und Industrie präsentiert. In einem abwechslungsreichen Programm werden aus verschiedenen Blickwinkeln die unterschiedlichen Schwerpunkte im Themenfeld Pflege und Technik diskutiert. Die Beiträge auf der 5. Clusterkonferenz, ausgerichtet vom Pflegepraxiszentrum Freiburg, sind im vorliegenden Abstractband ausgeführt.
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.
The Sustainable Development Goals (SDGs) of the United Nations focus on key issues for the transformation of our world towards sustainability. We argue for stronger integration of the SDGs into requirements and software engineering and for the creation of methods and tools that support the analysis of potential effects of software systems on sustainability in general and on SDGs in particular. To demonstrate one way of undertaking this integration, we report on how the Sustainability Awareness Framework (SusAF -- a tool developed by the authors of this paper) can be mapped to the SDGs, allowing the identification of potential effects of software systems on sustainability and on the SDGs. This mapping exercise demonstrates that it is possible for requirements engineers working on a specific system to consider that system's impact with respect to SDGs.
Context: The Software Engineering process can be seen as a socio-technical activity that involves fulfilling one's role as part of a team. Accordingly, software products and services are the result of a specific collaboration between employees (and other stakeholders). In recent years, sustainability, which Requirements Engineers often paraphrase as the ability of a system to endure, is becoming part of the process and thus the responsibility of Software Engineers (SE) as well. Objectives: This study shines the spotlight on the role of the SE: their self-attribution and their awareness for sustainability. We interviewed 13 SEs to figure out how they perceive their own role and to which extent they implement the topic of sustainability in their daily work. By visualizing these two sides, it is possible to debate changes and their possible paths to benefit the Software Engineering process including sustainability design. Results: A discrepancy between the current role and the ideal role of SEs becomes visible. It is characterized in particular by dwelling on their “classic” or time-honored tasks as an executive force, such as coding. At the same time, they point out the still missing necessity of an interdisciplinary, from communication coined working method. According to our interviewees SEs are inefficiently involved in the design process. They do not sufficiently assume their responsibility for the software and its sustainability impacts.
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.
Specification of neck muscle dysfunction through digital image analysis using machine learning
(2022)