VeranstaltungsortHörsaal 3Veranstalter Institut für Innovationsmanagement und UnternehmensgründungBeschreibungKontaktInstitut für Innovationsmanagement und Unternehmen (innovation@aau.at)

Veranstaltungsorthttps://join.skype.com/fW14TGoEdd4ConlineVeranstalter Institut für Vernetzte und Eingebettete SystemeBeschreibungDear Uni-People,despite the Corona situation we continue to do research. As a special event I would like to invite everybody who is interested in the topics of energy management and technology to join our online meeting on the topic of energy forecasting. We have external and internal presentations on the topic.The meeting will take place on Wednesday, April 22, 2020 from 12:00-13:30. You can join the meeting using this link: https://join.skype.com/fW14TGoEdd4CAgenda:1. Welcome2. Short term load forecasting (Aida Mehdipourpirbazari, University of Stavanger, Norway)3. Machine learning techniques for power forecasting (Prof. Marco Mussetta, Politecnico di Milano)4. Towards a decentralized smart energy sharing: The ARTICONF approach (Nishant Saurabh)5. Investigating the impact of data quality on the energy yield forecast using data mining techniques (Ekanki Sharma)Vortragende(r)Aida MehdipourpirbazariProf. Marco MussettaNishant SaurabhEkanki SharmaKontaktWilfried Elmenreich (wilfried.elmenreich@aau.at)

Veranstaltungsort https://classroom.aau.at/b/anw-ezd-k9gVeranstalter Institut für MathematikBeschreibungTitel:Computation of eigenvalues for operators in an all-at-once formulationAbstract:The all-at-once formulation for inverse problems has recently been considered. The advantages of this approach include the avoidance of a parameter-to-state map and numerical improve- ments compared to the reduced setting. We want to find out about the eigenvalues of such operators formulated in an all-at-once fashion (i.e. putting the model and the observation equation in a joint model resulting in a block operator matrix). By means of an inverse source problem and the backward heat equation we perform the eigenvalue analysis both analytically and numerically. The operators of interest are transformed such that they are symmetric with respect to an L2-related inner product. It can be shown that the resulting operators lead to approximate eigenvalues, which can be computed in an analytic way. Finally, the problems are discretized and the analysis is done numerically.Vortragende(r)Anna Theresa SchlintlKontaktsenka haznadar (senka.haznadar@aau.at)

Veranstaltungsorthttps://classroom.aau.at/b/anw-ezd-k9gVeranstalter Institut für MathematikBeschreibungTitel:A novel Bayesian approach for variable selection in linear regression modelsKurzfassung:A novel Bayesian approach to the problem of variable selection in multiple linear regression models is proposed. In particular, a hierarchical setting which allows for direct specification of a priori beliefs about the number of nonzero regression coefficients as well as a specification of beliefs that given coefficients are nonzero is presented. This is done by introducing a new prior for a random set which holds the indices of the predictors with nonzero regression coefficients. To guarantee numerical stability, a g-prior with an additional ridge parameter is adopted for the unknown regression coefficients. In order to simulate from the joint posterior distribution an intelligent random walk Metropolis-Hastings algorithm which is able to switch between different models is proposed. For the model transitions a novel proposal, which prefers to add a priori or empirically important predictors to the model and further tries to remove less important ones, is used. Testing the algorithm on real and simulated data illustrates that it performs at least on par and often even better than other well-established methods. Finally, it is proven that under some nominal assumptions, the presented approach is consistent in terms of model selection.Vortragende(r)Konstantin PoschKontaktSenka Haznadar (senka.haznadar@aau.at)