
General Claim detection model - mDeBERTa V3
mDeBERTa V3 model which was trained during experiments in order to create models capable of detecting check-worthy claims in the widest achievable range.
A tourist falls ill and needs to go to the hospital in a city, she has not visited before. When she crosses the hospital entrance, a likeable robot approaches her and immediately asks about the reason for visiting the hospital. Thereafter the robot accompanies her to the reception desk where an AI receptionist avatar is waiting. She has a fever and is coughing, suspecting she has the COVID-19 virus. The AI receptionist registers her and asks some questions about the symptoms. Then the AI asks the robot to accompany the patient to the radiologist room where additional tests will be done. A medical doctor with the help of an AI diagnostic system identifies the illness and prescribes the treatment.
In this futurist example, “Collaborative AI” (CAI) appears in different moments in the hospital episode, when the robot approaches the patient; when the robot accompanies the patient to the AI receptionist avatar; when the AI avatar talking with the person refers her to a specialist medical doctor; when the robot accompanies the patient to the radiologist room; and when the medical doctor makes a diagnosis with the help of the AI diagnostic system.
mDeBERTa V3 model which was trained during experiments in order to create models capable of detecting check-worthy claims in the widest achievable range.
The Load Forecast Model is distinguished by its precision in predicting energy load demands, owing to its integration of advanced machine learning algorithms. Its cloud-hosted nature ensures scalability and adaptability, catering to both centralized and e...
Agriculture productivity maps based on satellite images at the field level are revolutionizing the way farmers manage their crops. These maps provide detailed insights into the health and performance of individual fields, enabling farmers to make data-dri...
This asset is the open dataset used for the experiment and for develop the proof of concept. It is an open dataset of SCADA data for Energy Management Systems.
XLM-RoBERTa model which was trained during experiments in order to create models capable of detecting check-worthy claims in the widest achievable range.
Hourly wind power production data in MWh/h from 69 wind farms in Norway.
Docker image containing the script to execute a Grid2Op agent training while using the PowSyBl Backend on a dataset.
The development of solutions and models for the analysis, early detection and mitigation of vessel collision events is a significant step towards ensuring future maritime safety. In this context, a synthetic vessel proximity event dataset is created using...
The Kaspar AI Natural Language Media Indexing Engine (NLMIE) is an application for MacOS machines with M1/M2/M3 chips, which allows for fast and natural video search within Adobe Premiere Pro.
A pipeline generation to get and process images from Sentinel-2 for a specific ROI (Region of interest) to display and rescale NVDI values.