Lisää varmuutta syväoppimiseen
Tohtorikoulutettava Lassi Meronen kehittää Saabin tuella syväoppimisen malleja, joita voidaan hyödyntää esimerkiksi tutkissa ja lääketieteen diagnosoinnissa.
Doctoral student Henri Kähkönen integrates antenna arrays and microcircuits made possible by millimeter-wave technology. In addition to wireless data transmission, the technology enables the development of radars for the needs of the automotive and healthcare industries.
Saab's help has been key to advancing research. Among other things, Kähkönen has been able to use a state-of-the-art 3D printing device, which makes it possible to make an accurate and high-quality metallic antenna array prototype. He has also been able to discuss key research issues with Saab engineers.
'Saab's experts have helped us in advancing the research and opened up new perspectives on what is required of future antenna technology,' says Kähkönen.
Doctoral student Jouko Kinnari is researching how positioning would be possible without satellite positioning systems.
Demands for positioning reliability increase as the use of new applications, such as autonomous transport robots, becomes more widespread. However, there are still challenges in satellite positioning technology: for example, tall buildings and vegetation block the signal from the satellite to the position receiver and receiver interference is possible.
Kinnari is exploring how unmanned aerial vehicles can locate themselves using camera and inertial measurement systems, making them independent of satellite positioning systems.
Doctoral student Lassi Meronen is developing deep learning models that know how to estimate their own uncertainty computationally. The models can be used, for example, in radars and medical diagnosis.
Deep learning, machine learning and artificial intelligence offer significant opportunities to solve the challenges of different disciplines and make our lives easier in many ways.
'There is still a lot to be developed in technology modeling, especially in assessing uncertainty. Deep learning models may fail, for example, in situations where the model encounters something new that it has not seen before. Saab offers many fascinating, real-life application challenges that take my research forward', says Meronen.
Tohtorikoulutettava Lassi Meronen kehittää Saabin tuella syväoppimisen malleja, joita voidaan hyödyntää esimerkiksi tutkissa ja lääketieteen diagnosoinnissa.
Langattoman tiedonsiirron lisäksi teknologia auttaa tutkien kehittämisessä.
Tohtorikoulutettava Jouko Kinnari tutkii Saabin tuella, miten paikantaminen olisi mahdollista ilman satelliittipaikannusjärjestelmiä.
Jouko Kinnarin väitöstutkimuksessa dronen sijainti selviää karttatietojen sekä antureiden avulla.