iCoSys

Join us at ICDAR 2021 in Lausanne from 5 to 10th of September 2021. As academic sponsor, iCoSys is involved in the organisation of the International Conference on Document Analysis and Recognition. This is the main and biggest conference for the research community active in document analysis and recognition, a field of growing importance in the current age of digital transition.

Machine Learning achieves good success for automatic fall detection based on wearable sensors. Our iCoSys members Nicolas Zurbuchen and Pascal Bruegger, in collaboration with Adriana Wilde from the Centre for Health Technologies at the University of Southampton defined new state of the art results in their publication in Sensors magazine (Sensors 2021, 21(3), 938; https://doi.org/10.3390/s21030938). Congrats to them. […]

iCoSys extends its deep learning micro-services library with Colorizer, a service able to re-colour black and white photographies. Check it out at here. Colorizer includes several interesting features. First, a slick and intuitive web showcase is there to allow you easily drag and drop black and white images and re-colour them in an instant. Second, […]

iCoSys is a proud contributor of Cryfe, the software that analyzes the authenticity of your words. This project is a two years old baby, in partnership with CM Profiling, Idiap Research Institute and funded by Innosuisse. Listen to our collaborators dr. Oussama Zayene and dr. Beat Wolf to know more about the work they have been […]

The project ADVANCe is coming to an end after 2 years of development with CM-Profiling and the IDIAP research institute. Over the course of those 2 years, an innovative solution was developed to assists interviewers during job interviews. Based on machine learning algorithms, a complex data analysis platform has been developed from scratch to detect […]

A really exciting project starts now at iCoSys with our partner Hieronymus AG, Translations by Lawyers for Lawyers : Datalambic ! We will use self-supervised machine learning to collect large quantity – high quality data sets. And then assemble complex NLP data pipelines for AI applications. This data collection will also be used to boost our […]

Planning deep excavations is a long, complex but a very common task for geo-technical engineers. Through a collaboration of iCoSys and iTec, the Optisoil project uses machine learning to greatly speed up the process of evaluating a given deep excavation configuration.  It also enables new possibilities, such as automatically finding the optimal solution to a […]

The deep learning micro-services library of iCoSys is extending with a NLP multilingual sentiment analysis. Check it out at here More precisely, we have built a polarity detection of text. The polarity is a number between 0 and 1 and texts with polarity values closer to 0 are negative, and positive if closer to 1. […]

iCoSys is proud to present SwissCrawl, the largest Swiss German text corpus to date! The tool was built by Lucy Linder with the supervision of Jean Hennebert & Andreas Fischer and is composed of more than half a million sentences, which were generated using a customized web scraping tool that could be applied to other […]

How can iCoSys help researchers and clinicians fight against the COVID-19 ? Our colleague Dr Beat Wolf developed with Phenosystems SA a graphical data analysis tool for genetic data since 2012 : GensearchNGS. He expanded it now to include the SARS-CoV2 virus genome, to help researchers and clinicians work against the virus. GensearchNGS allows geneticists to work with […]