https://dasya.itu.dk/tags/ml/ Recent content in ML on DASYA Hugo -- gohugo.io en-us © DASYA, IT University of Copenhagen Thu, 26 Feb 2026 00:00:00 +0000 https://dasya.itu.dk/posts/researchscientist/ Thu, 26 Feb 2026 00:00:00 +0000 https://dasya.itu.dk/posts/researchscientist/ We’re hiring a Research Scientist at IT-Universitetet i København on a project at the intersection of machine learning and operations research, funded by the European innovation community EIT Urban Mobility. Cities across Europe are decarbonising freight - replacing diesel vans with mixed fleets of electric vehicles, cargo bikes, and light electric vehicles. This transition has enormous climate potential, but introduces optimization challenges that existing tools and benchmarks don’t capture. The goal of this project is to build an open benchmark for mixed-fleet vehicle routing grounded in real operational data from European cities, bridging the gap between academic VRP research and the reality of sustainable urban logistics. https://dasya.itu.dk/for-students/proposals/archive/jucp-disco2-camera-control/ Sun, 13 Aug 2023 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/jucp-disco2-camera-control/ The DISCO-2 satellite is an Earth observation satellite in collaboration with the Arctic Research Center in Aarhus and is designed to complement ground based field studies in Greenland. The satellite instrument consists of 2 high quality visible light and 1 infrared cameras, as well as and attitude control system and coral TPU ML coprocessor. In this project you will develop software to control the visible light cameras and interface them with the satellite control system. https://dasya.itu.dk/for-students/proposals/archive/scarecrow/ Tue, 25 Aug 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/scarecrow/ Invasive bird species can be a serious problem in cities, towns and in agriculture. The common pigeon is a very unwelcome guest on many balconies, roofs, terraces. Conventional scarecrows often show no effect, as these birds are known to be quite intelligent, and capable of learning fast. The idea is to built a sensor/camera enhanced scarecrow that - can recognize birds present within its proximity by means of image recognition - perform counting, reporting and statistics and - take event-triggered measures to scare away unwelcome guests, e. https://dasya.itu.dk/for-students/proposals/archive/automl-forecasting-energy/ Thu, 20 Aug 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/automl-forecasting-energy/ With the recent hunger for being “data driven”, many organizations are eager for integrating ML in there decision making process. Unfortunately, competent data scientists are still relatively scarce, and manual model development cannot keep up with the demand for magic AI solutions. This is no less true when it comes to forecasting. Knowing the future is extremely handy when making decisions. AutoML for Time Series Forecasting Subsequently many systems are now developing and integrating AutoML tools for time series forecasting. https://dasya.itu.dk/for-students/proposals/archive/non-intrusive-load-monitoring/ Mon, 06 Jul 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/non-intrusive-load-monitoring/ How much does our smart meter readings disclose about us? Can we disentangle the oven from the washing machine from the kettle? Can we identify demographics and behavior patterns from the stream of electricity data? Most danish homes are now equipped so-called “smart meters” - networked electricity meters that report consumption and load at much higher rate than conventional meters. Currently the meters report data back to a centralized datahub on an hourly basis, but the meters are capable of producing data at a much higher granularity than this. https://dasya.itu.dk/for-students/proposals/archive/reprohpc/ Sat, 20 Jun 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/reprohpc/ Reproducibility is a cornerstone of the scientific method. There are systems available today to build reproducible and sharable data and analysis pipelines including workflow engines (e.g., GWL, Nextflow), package managers (e.g., bioconda), and container systems (e.g., Singularity). However, validating their executions on high-performance computers remains an open issue. Indeed, there are many sources of non-determinism at runtime (e.g., parallelism, scheduling, errors, diverse cores). As a result, static workflow analysis is not enough to guarantee reproducibility. https://dasya.itu.dk/for-students/projects/archive/dpi/ Sat, 01 Feb 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/dpi/ Intel’s oneAPI vs CPP