Obermaisser, Roman
Now showing 1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , A Distributed and Secure Self-Sovereign-Based Framework for Systems of SystemsSecurity and privacy are among the main challenges in the systems of systems. The distributed ledger technology and self-sovereign identity pave the way to empower systems and users’ security and privacy. By utilizing both technologies, this paper proposes a distributed and self-sovereign-based framework for systems of systems to increase the security of such a system and maintain users’ privacy. We conducted an extensive security analysis of the proposed framework using a threat model based on the STRIDE framework, highlighting the mitigation provided by the proposed framework compared to the traditional SoS security. The analysis shows the feasibility of the proposed framework, affirming its capability to establish a secure and privacy-preserving identity management system for systems of systems.Source Type:Article5 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , A Reliable System-of-Systems Healthcare Monitoring FrameworkSystem-of-systems (SoS) have recently been used in several applications and scenarios in the field of safety, defense, and healthcare. In an SoS environment, the entire system is divided into sub-systems, which provides more flexibility and reduces the management cost of the entire system. SoS have been widely used in healthcare monitoring services, where patients are provided with medical sensors that send their medical measurements to a remote unit for further processing and decision-making. These sensors communicate with an access point using the wireless channel, which gives patients flexibility in mobility and makes the monitoring system more convenient and comfortable. However, sending data over the wireless channel presents several challenges, such as contention between the different sensors in accessing the channel and the bit errors associated with the noisy wireless channel. In this paper, an SoS healthcare monitoring framework is proposed, where a wireless communication protocol is proposed that addresses the sensors’ node network access contention and mitigates the bit errors of the communication channel by providing forward error correction bits to the transmitted packets. In addition, the protocol takes into consideration the sensors’ importance and criticality, such that more important sensors are given more network access time and more error correction bits, which in turn results in a robust transmission process with low transmission delay. The simulation results show the proposed wireless communication protocol’s effectiveness in lowering the packet loss, giving higher priority and having higher throughput for the more critical sensors.Source Type:Article1 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Time-Efficient Identification Procedure for Neurological Complications of Rescue Patients in an Emergency Scenario Using Hardware-Accelerated Artificial Intelligence ModelsDuring an emergency rescue operation, rescuers have to deal with many different health complications like cardiovascular, respiratory, neurological, psychiatric, etc. The identification process of the common health complications in rescue events is not very difficult or time-consuming because the health vital symptoms or primary observations are enough to identify, but it is quite difficult with some complications related to neurology e.g., schizophrenia, epilepsy with non-motor seizures, or retrograde amnesia because they cannot be identified with the trend of health vital data. The symptoms have a wide spectrum and are often non-distinguishable from other types of complications. Further, waiting for results from medical tests like MRI and ECG is time-consuming and not suitable for emergency cases where a quick treatment path is an obvious necessity after the diagnosis. In this paper, we present a novel solution for overcoming these challenges by employing artificial intelligence (AI) models in the diagnostic procedure of neurological complications in rescue situations. The novelty lies in the procedure of generating input features from raw rescue data used in AI models, as the data are not like traditional clinical data collected from hospital repositories. Rather, the data were gathered directly from more than 200,000 rescue cases and required natural language processing techniques to extract meaningful information. A step-by-step analysis of developing multiple AI models that can facilitate the fast identification of neurological complications, in general, is presented in this paper. Advanced data analytics are used to analyze the complete record of 273,183 rescue events in a duration of almost 10 years, including rescuers’ analysis of the complications and their diagnostic methods. To develop the detection model, seven different machine learning algorithms-Support Vector Machine (SVM), Random Forest (RF), K-nearest neighbor (KNN), Extreme Gradient Boosting (XGB), Logistic Regression (LR), Naive Bayes (NB) and Artificial Neural Network (ANN) were used. Observing the model’s performance, we conclude that the neural network and extreme gradient boosting show the best performance in terms of selected evaluation criteria. To utilize this result in practical scenarios, the paper also depicts the possibility of embedding such machine learning models in hardware like FPGA. The goal is to achieve fast detection results, which is a primary requirement in any rescue mission. An inference time analysis of the selected ML models and VTA AI accelerator of Apache-TVM machine learning compiler used for the FPGA is also presented in this research.Source Type:Article1
