Explainable AI - etikk og forretningsverdi?
- Forfattere
- Dorthea Mathilde Kristin Vatn
- År
- 2024
- Type
- Foredrag
The increased complexity of artificial intelligence (AI), machine learning (ML) and deep learning (DL) methods, models, and training data to satisfy industrial application needs has emphasised the need for AI model providing explainability and interpretability. Model Explainability aims to...
Intelligent connectivity at the edge combines wireless communication, edge artificial intelligence (AI), edge computing and internet of things (IoT) technologies to perform machine learning (ML) and deep learning (DL) on connected edge devices. Low latency, ultra-low-energy intelligent IoT devices...
...«Det store brannløftet» var en gave fra Gjensidigestiftelsen til det norske samfunn på 350 millioner kroner. Prosjektet omfatter ulike tiltak som på kort og lang sikt vil trygge hverdagen til befolkningen ytterligere. En del av gaven anvendes på forskning. Konferansen formidlet viktig kunnskap...
A computationally efficient predictive digital twin (DT) of a small-scale greenhouse needs an accurate and faster modelling of key variables such as the temperature field and flow field within the greenhouse. This involves: (a) optimally placing sensors in the experimental set-up and (b) developing...
The human musculoskeletal system is well adapted to use energy-efficient muscle–tendon mechanics during walking and running, but muscle behaviour during on-snow locomotion is unknown. Here, we examined muscle and muscle–tendon unit behaviour during diagonal-style cross-country roller skiing at three...
This study investigates a potential solution to the global challenge of secure, affordable, and low-carbon energy supply: ammonia production from local coal and biomass resources with CO2 capture for negative emissions. Two innovative configurations; an E-gas gasifier with membrane-assisted water...
The molecular characteristics of the food-grade polysaccharide gum acacia may vary depending on source, which could in turn significantly affect its behaviour as thickener, emulsifier and as a wall material in microencapsulation. In this study, five acacia gums (GA) from different sources were...
Growing extraction and usage of rare earth elements and yttrium (REY) for medical and industrial applications has resulted in increased discharges into the marine environment. Using Mytilus spp. Mussels and Tapes spp. clams as bioindicator organisms, we analyzed 15 REY in soft tissues of specimens...
The synthesis of a cheap, nonmetallic and active photocatalyst is the target of this study. Several Carbon loadings (0.2, 0.5 and 1 wt%) were incorporated into the graphitic carbon nitride (g-C3N4) semiconductor by a simple wet impregnation method. Temperature treatment was used for composite...
HYPSO-1 was launched in January 2022, equipped with a novel hyperspectral imaging payload with the main objective of performing marine research. In 2024, HYPSO-2, with an enhanced capture capacity, will be launched. The satellites can point their cameras off-nadir, a capability that is used to...
A good understanding of influencing parameters is required to predict corrosivity in marine and coastal environments. This study investigated the influences of real-time data of (i) air temperature, (ii) sensor surface temperature, (iii) relative humidity, (iv) precipitation, and (v) wind on steel...
This paper reports on computational studies of gas-phase reactions of SiO and Si2O2. The oxidation of SiO can initiate efficient formation of silica or silicate dust particles in a wide range of environments. Both OH radicals and H2O molecules are often present in these environments, and their...
K-RAS is a highly relevant oncogene that is mutated in approximately 90% of pancreatic cancers and 20–25% of lung adenocarcinomas. The aim of this work was to develop a new anti-KRAS siRNA therapeutic strategy through the engineering of functionalized lipid nanoparticles (LNPs). To do this, first, a...