Refine
Year of publication
- 2023 (163) (remove)
Document type
- Article (peer-reviewed) (163) (remove)
Keywords
Quality assurance (QA) plays a crucial role in manufacturing to ensure that products meet their specifications. However, manual QA processes are costly and time-consuming, thereby making artificial intelligence (AI) an attractive solution for automation and expert support. In particular, convolutional neural networks (CNNs) have gained a lot of interest in visual inspection. Next to AI methods, the explainable artificial intelligence (XAI) systems, which achieve transparency and interpretability by providing insights into the decision-making process of the AI, are interesting methods for achieveing quality inspections in manufacturing processes. In this study, we conducted a systematic literature review (SLR) to explore AI and XAI approaches for visual QA (VQA) in manufacturing. Our objective was to assess the current state of the art and identify research gaps in this context. Our findings revealed that AI-based systems predominantly focused on visual quality control (VQC) for defect detection. Research addressing VQA practices, like process optimization, predictive maintenance, or root cause analysis, are more rare. Least often cited are papers that utilize XAI methods. In conclusion, this survey emphasizes the importance and potential of AI and XAI in VQA across various industries. By integrating XAI, organizations can enhance model transparency, interpretability, and trust in AI systems. Overall, leveraging AI and XAI improves VQA practices and decision-making in industries.
Assessing the impact of a structural prior mask on EIT images with different thorax excursion models
(2023)
Der Rehabilitationsprozess von Patientinnen und Patienten mit neurologischen Langzeitschäden ist eine große Herausforderung. Bei zentralnervalen chronischen Schädigungen arbeiten Therapierende mit Patient*innen und pflegenden Angehörigen mitunter über Jahre intensiv zusammen. Alexa von Bosse hat in einer empirischen Studie die Wichtigkeit einer gelingenden Kommunikation und Beziehungsgestaltung in diesem Beziehungsdreieck verdeutlichen können.
The Industrial Internet of Things (IIoT) holds significant potential for improving efficiency, quality, and flexibility. In decentralized systems, there are no trust based centralized authentication techniques, which are unsuitable for distributed networks or subnets, as they have a single point of failure. However, in a decentralized system, more emphasis is needed on trust management, which presents significant challenges in ensuring security and trust in industrial devices and applications. To address these issues, industrial blockchain has the potential to make use of trustless and transparent technologies for devices, applications, and systems. By using a distributed ledger, blockchains can track devices and their data exchanges, improving relationships between trading partners, and proving the supply chain. In this paper, we propose a model for cross-domain authentication between the blockchain-based infrastructure and industrial centralized networks outside the blockchain to ensure secure communication in industrial environments. Our model enables cross authentication for different sub-networks with different protocols or authentication methods while maintaining the transparency provided by the blockchain. The core concept is to build a bridge of trust that enables secure communication between different domains in the IIoT ecosystem. Our proposed model enables devices and applications in different domains to establish secure and trusted communication channels through the use of blockchain technology, providing an efficient and secure way to exchange data within the IIoT ecosystem. Our study presents a decentralized cross-domain authentication mechanism for field devices, which includes enhancements to the standard authentication system. To validate the feasibility of our approach, we developed a prototype and assessed its performance in a real-world industrial scenario. By improving the security and efficiency in industrial settings, this mechanism has the potential to inspire this important area.
Vertebral motion reveals complex patterns, which are not yet understood in detail. This applies to vertebral kinematics in general but also to specific motion tasks like gait. For gait analysis, most of existing publications focus on averaging characteristics of recorded motion signals. Instead, this paper aims at analyzing intra- and inter-individual variation specifically and elaborating motion parameters, which are consistent during gait cycles of particular persons. For this purpose, a study design was utilized, which collected motion data from 11 asymptomatic test persons walking at different speed levels (2, 3, and 4 km/h). Acquisition of data was performed using surface topography. The motion signals were preprocessed in order to separate average vertebral orientations (neutral profiles) from basic gait cycles. Subsequently, a k-means clustering technique was applied to figure out, whether a discrimination of test persons was possible based on the preprocessed motion signals. The paper shows that each test sequence could be assigned to the particular test person without additional prior information. In particular, the neutral profiles appeared to be highly consistent intra-individually (across the gait cycles as well as speed levels), but substantially different between test persons. A full discrimination of test persons was achieved using the neutral profiles with respect to flexion/extension data. Based on this, these signals can be considered as individual characteristics for the particular test persons.
Keywords: Gait analysis; Human spine; Intra- and interindividual variation; Motion analysis; Rasterstereography; Surface topography; k-means algorithm.
Data processed in context is more meaningful, easier to understand and has higher information content, hence it derives its semantic meaning from the surrounding context. Even in the field of acoustic signal processing. In this work, a Deep Learning based approach using Ensemble Neural Networks to integrate context into a learning system is presented. For this purpose, different use cases are considered and the method is demonstrated using acoustic signal processing of machine sound data for valves, pumps and slide rails. Mel-spectrograms are used to train convolutional neural networks in order to analyse acoustic data using image processing techniques.
In Vehicular Ad Hoc Networks (VANETs), promoting cooperative behavior is a challenging problem for mechanism designers. Cooperative actions, such as disseminating data, can seem at odds with rationality and may benefit other vehicles at a cost to oneself. Without additional mechanisms, it is expected that cooperative behavior in the population will decrease and eventually disappear. Classical game theoretical models for cooperation, such as the public goods game, predict this outcome, but they assume fixed population sizes and overlook the ecological dynamics of the interacting vehicles. In this paper, we propose an evolutionary public goods game that incorporates VANET ecological dynamics and offers new insights for promoting cooperation. Our model considers free spaces, population density, departure rates of vehicles, and randomly composed groups for each data sender. Theoretical analysis and simulation results show that higher population densities and departure rates, due to minimum differences between pay-offs of vehicles, promote cooperative behavior. This feedback between ecological dynamics and evolutionary game dynamics leads to interesting results. Our proposed model demonstrates a new extension of evolutionary dynamics to vehicles of varying densities. We show that it is possible to promote cooperation in VANETs without the need for any supporting mechanisms. Future research can investigate the potential for using this model in practical settings.