SINTEF Open
Not a member yet
11374 research outputs found
Sort by
SINTEF tester våtromsplater og baderomspaneler. Testingen er med på å sikre vanntette vegger i våtrom
Get PDFpublishedVersio
Analysis of spatial and design factors for users’ acceptance of rescue rooms in road tunnels: An exploratory study using Virtual Reality
Get PDFIn emergency fire situations in road tunnels in which vehicles cannot exit the tunnel, evacuation on foot might be the only alternative. In such scenarios, self-rescue using rescue rooms might provide provisional safe shelter to people trapped in tunnel emergencies. Yet, a stay in a rescue room with unsatisfactory design might contribute to higher levels of distress to the users. The present study examines five different designs of rescue rooms via virtual reality, to study how the different design and spatial factors might affect users' acceptance of such rooms. Thirty-seven people participated in the study, in which both objective (Eye-tracking and heart rate measurement) and subjective data was collected. The results suggest that two factors (i.e. lighting and use of separate areas) increased the feelings of safety and users' acceptance of the rescue rooms. In particular, a container room with blue lighting and separate area for injured people was the favourite among the study participants. The outcomes of this study show that design and spatial factors are crucial if rescue rooms are to be implemented and used in road tunnels.publishedVersio
Infotainmentsystemer og oppmerksomhetsfordeling i bil
Get PDFProsjektet har hatt som mål økt forståelse om oppmerksomhetsfordeling ved bruk av berøringsskjerm i bil ved hjelp av eyetracking. Studien avdekker hvordan bruk av berøringsskjerm belaster førerens kjøreprosess og påvirker oppmerksomhetsfordelingen. Det var 44 førerne som skulle utføre flere oppgaver i løpet av en kjøretur i normal trafikk. Resultatene viser at skjermbruk under kjøring krever i noen sammenhenger betydelig oppmerksomhet og distraherer førerne under kjøringen så mye at sikkerheten reduseres.publishedVersio
WindNet: A Mobile Base Station Infrastructure For Maritime Industry
Get PDFThe maritime industry, encompassing sectors such as wind energy, oil rigs, fishing, global logistics, and cruise tourism, is one of the oldest and fastest-growing. However, it faces significant challenges in establishing communication infrastructure, which is crucial for continuous monitoring, safe operations, and data-driven decision-making. Existing communication systems are inadequate and struggle to support real-time data transfer, which is vital for operational efficiency and safety. To address this gap, we propose WindNet, a novel and cost-effective solution that integrates mobile base stations (MBS) with offshore wind turbines, drones, and floating buoys. WindNet aims to provide reliable connectivity across vast oceanic regions by leveraging advanced next-generation network technology. In this paper, we employ a maritime propagation model to evaluate the area covered by the base stations (BS). Our analysis provides key insights into the range, number of BS, and power needed to build a reliable WindNet mobile network along high-density shipping routes. Furthermore, a comprehensive risk analysis highlights WindNet’s potential to enhance maritime connectivity, operational efficiency, and environmental sustainability. By deploying WindNet and tethered drones with floating buoys BS, we aim to create a dynamic mesh network across vast maritime areas, supporting various sectors and driving further advancements in the maritime industry.acceptedVersio
Latency-Aware Node Selection in Federated Learning
Get PDFFederated learning (FL) relies on the frequent exchange of model parameters between clients and the aggregator to achieve efficient model convergence. However, network latency presents a significant challenge, particularly in congested edge/IoT scenarios, hindering the efficiency and effectiveness of distributed machine learning (ML). While existing solutions often depend on hard-coded topologies, addressing this challenge is critical to unlocking FL's full potential in real-world scenarios. This paper proposes a novel approach to mitigate network latency issues by introducing a threefold functionality: latency-aware client selection, latency-aware aggregator assignment, and consistent replication of training progress. Our proof of concept provides a scalable and robust solution to alleviate latency's impact and improve the efficiency of distributed ML operations. Through this research, we aim to advance the field of FL by offering practical solutions that enhance performance and resilience in latency-sensitive environments.acceptedVersio
Characterization of nutrients and contaminants in fish sludge from Atlantic salmon (Salmo salar L.) production sites - A future resource
Get PDFA total of 47 fish sludge samples from commercial land-based Atlantic salmon (Salmo salar) farms in Norway were assessed for their nutrient composition, presence of various legacy contaminants and a wide spectrum of contaminants of emerging concern, veterinary medicines as well as selected salmonid pathogenic bacteria and virus. The aim was to document the levels of desirable and undesirable components in fish sludge in relation to a potential future use of sludge as invertebrate feed. The samples had variable, but relatively high protein and fat contents, indicating a high load of undigested feed in some of the sludge samples. Fatty acid analysis showed the presence of essential omega-3 fatty acids. In terms of undesirable substances, 43% and 84% of the sludge samples contained levels of arsenic and cadmium, respectively, which exceeded the EU Maximum Levels established for complete animal feed. The concentrations of copper, zinc, iron and aluminum were highly variable in the sludge samples. The concentrations of dioxins, sum PCB6, and chlorinated pesticides were all below the Maximum Levels for animal feed. Of the 18 per- and polyfluoroalkyl substances (PFAS) only one compound (L-PFOS) was present at measurable levels. None of the samples had detectable levels of veterinary medicines, salmonid virus or bacteria. Performing a suspect and non-target screening of the sludge samples identified 18 compounds, including four pharmaceuticals, plastic-related products and the UV filter benzophenone, warranting further investigations. Overall, the results from this study show that fish sludge is a nutrient-rich resource; however, undesirable substances, originating from the feed or from treatment of sludge may be present.publishedVersio
Enhancing human activity recognition for the elderly and individuals with disabilities through optimized Internet-of-Things and artificial intelligence integration with advanced neural networks
Get PDFElderly and individuals with disabilities can greatly benefit from human activity recognition (HAR) systems, which have recently advanced significantly due to the integration of the Internet of Things (IoT) and artificial intelligence (AI). The blending of IoT and AI methodologies into HAR systems has the potential to enable these populations to lead more autonomous and comfortable lives. HAR systems are equipped with various sensors, including motion capture sensors, microcontrollers, and transceivers, which supply data to assorted AI and machine learning (ML) algorithms for subsequent analyses. Despite the substantial advantages of this integration, current frameworks encounter significant challenges related to computational overhead, which arises from the complexity of AI and ML algorithms. This article introduces a novel ensemble of gated recurrent networks (GRN) and deep extreme feedforward neural networks (DEFNN), with hyperparameters optimized through the artificial water drop optimization (AWDO) algorithm. This framework leverages GRN for effective feature extraction, subsequently utilized by DEFNN for accurately classifying HAR data. Additionally, AWDO is employed within DEFNN to adjust hyperparameters, thereby mitigating computational overhead and enhancing detection efficiency. Extensive experiments were conducted to verify the proposed methodology using real-time datasets gathered from IoT testbeds, which employ NodeMCU units interfaced with Wi-Fi transceivers. The framework's efficiency was assessed using several metrics: accuracy at 99.5%, precision at 98%, recall at 97%, specificity at 98%, and F1-score of 98.2%. These results then were benchmarked against other contemporary deep learning (DL)-based HAR systems. The experimental outcomes indicate that our model achieves near-perfect accuracy, surpassing alternative learning-based HAR systems. Moreover, our model demonstrates reduced computational demands compared to preceding algorithms, suggesting that the proposed framework may offer superior efficacy and compatibility for deployment in HAR systems designed for elderly or individuals with disabilities.publishedVersio
IAQ and ventilation measurements at the “ZEB Laboratory” office building in Norway
Get PDFThis study aims to assess indoor environmental quality (IEQ) within a Zero Emission Building (ZEB) office in Norway, focusing on occupant impact (CO2, temperature, humidity) and materials/substances influence (formaldehyde, particulate matter (PM2.5), total volatile organic compounds (TVOC)). It presents a detailed data collection spanning 14 months from March 30th, 2022, to June 1st, 2023. Occupancy varied significantly, affecting measured indoor air quality (IAQ) parameters, with the lowest temperatures recorded on the second floor and specific areas like the canteen experiencing temperature drops during low usage times. Relative humidity levels remained over 20 % in winter despite the building's low occupancy, a notable aspect given Norway's dry winters. PM2.5 levels stayed below World Health Organization (WHO) guidelines, indicating effective pollution management. The study also evaluates the impact of reducing the ventilation rates on IAQ, noting no significant IAQ compromise. An analysis correlating IAQ measurements with building occupants' satisfaction post-intervention revealed that temperature is the most significant factor affecting satisfaction levels, excluding acoustic satisfaction. Occupants generally reported satisfaction with the indoor environmental quality (IEQ), with specific dissatisfaction tied to thermal environment and IAQ, suggesting the importance of temperature control in occupant perception. This research not only provides valuable insights into IEQ management in Zero Energy and Zero Emission office buildings but also emphasizes the critical role of indoor temperature and the potential of wooden structures to stabilize humidity levels, contributing to occupant comfort and satisfaction.publishedVersio
SEC-AIRSPACE: Addressing Cyber Security Challenges in Future Air Traffic Management
Get PDFDigitalisation offers many benefits to Air Traffic Management. Yet, with technological innovations come challenges in managing new cyber security threats and risks. This paper presents a comprehensive review over challenges faced in ATM when protecting critical assets, and outlines how the newly established exploratory research project SEC-AIRSPACE will address these challenges.publishedVersio
