catch22
Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-regenerative Life Support System Telemetry
Rewicki, Ferdinand, Gawlikowski, Jakob, Niebling, Julia, Denzler, Joachim
Bio-regenerative Life Support Systems (BLSSs) are artificial ecosystems that consist of multiple symbiotic relationships. BLSSs are crucial for sustaining long-duration space missions by facilitating food production and managing essential material cycles for respiratory air, water, biomass, and waste. The EDEN NEXT GEN Project, part of the EDEN roadmap at the German Aerospace Center (DLR), aims to develop a fully integrated ground demonstrator of a BLSS comprising all subsystems, with the ultimate goal of realizing a flight-ready BLSS within the next decade. This initiative builds upon insights from the EDEN ISS project, which investigated controlled environment agriculture (CEA) technologies for space exploration. EDEN ISS, a near-closed-loop research greenhouse deployed in Antarctica from 2017 to 2021, focused on crop production, including lettuces, bell peppers, leafy greens, and various herbs. To ensure the safe and stable operation of BLSSs, we explore methods to mitigate risks regarding system health, particularly regarding food production and nourishment shortages for isolated crews.
Feature Engineering Methods on Multivariate Time-Series Data for Financial Data Science Competitions
Wong, Thomas, Barahona, Mauricio
Financial data are often available in the form of time series. These time series are often highly dimensional with complex relationships between them. The complexity of financial data can be demonstrated in different aspects. Firstly, training data are often limited and the number of features that researchers can create is often much greater than the number of observations. In some research, such as [1], the ratio of the number of features over the number of observations, defined as model complexity can increase up to hundreds for financial instruments with a limited amount of history. Traditional setups in machine learning are not well-equipped for these data-scarce environments.
Admin & Data Analyst at Catch22 - Southampton, United Kingdom
At Catch22, we are proud of our reputation as a modern and progressive employer. Our 1,300 colleagues and 300 volunteers work at every stage of the social welfare cycle, supporting over 60,000 individuals from cradle to career. In Social Justice, we work with young people and adults in custody and in the community, providing a range of services, including offender management and resettlement, mentoring, veterans in custody, victim services, gangs work, and youth justice. We believe that with effective support mechanisms, and the correct interventions, we can change the ideology of service users, helping them to desist from crime, and reach their true potential. This post presents an exciting opportunity to become an Admin & Data Analyst within our Personal Wellbeing services, in the Hampshire and Isle of Wight region.