Hae LUTPubista
Aineistot 31-40 / 41
Unsupervised anomaly detection from wooden boards using autoencoders
(2019)
For wood processing in the sawmill industry, quality of the raw material in every step affects the production efficiency. Defects in the sawn timber, such as wane, knots, cracks, watermarks, fungal damage, insect defects, ...
Ni-Mn-Ga magnetic shape memory alloy for precise high-speed actuation in micro-magneto-mechanical-systems
(Lappeenranta University of Technology, 2019-01-17)
Single crystalline Ni-Mn-Ga alloys are known for their large reversible magnetic-field-induced strain (MFIS) of several percent. This effect was discovered and named magnetic shape memory (MSM) by K. Ullakko in 1996. Since ...
Visualising deep grading of diabetic retinopathy
(2019)
Diabetic retinopathy is a medical condition that occurs when fluctuating levels of blood sugar damage the blood vessels of the retina. Presence of vascular abnormalities in the retinal images indicate the presence of ...
Forest stand parameter estimation by using neural networks
(2019)
Wood is a vital material used everywhere. And it is very important to monitor the state of forests. One of the most common ways to estimate different forest parameters is to make the model based on the data obtained by ...
Regularization of inverse problems by the Landweber iteration
(2019)
Landweber's method is a well-known iterative technique for regularizing linear and non-linear ill-posed equations. This thesis constructs in the Hilbert space setting a Landweber iteration to solve linear ill-posed inverse ...
Elliptic boundary values problems with Gaussian white noise
(2019)
This work focuses on the study of elliptic boundary value problems with Gaussian white noise on the form LX = W, where L = - Δ + v², with v > 0. First, the definitions and some properties of some important tools for this ...
Hamiltonian Monte Carlo and non-Gaussian random field priors for x-ray tomography
(2019)
Solving a statistical inverse problem requires selecting an appropriate prior distribution to model the phenomenon in question and using numerical algorithms, like MCMC methods, to calculate the estimates in practise. ...
Usean kohteen paikannus Kalman-suodatusta ja RBMCDA -algoritmeja hyödyntäen
(2019)
Työn tarkoituksena on demonstroida ja avata yksinkertaisin esimerkein Aalto-yliopiston verkkosivuilla julkaistuja "Extended Kalman Filter / Unscented Kalman Filter" ja "Rao-Blackwellized Monte Carlo Data Association" ...
Heuristic similarity- and distance-based supervised feature selection methods
(Lappeenranta-Lahti University of Technology LUT, 2019-12-16)
In the field of machine learning, the available data often contain many features to describe phenomena. This can pose a problem since only those features that are relevant to characterize the target concept are needed, ...
Henkilökohtaisten pisteiden skaalaaminen kyykässä
(2019)
Työssä etsittiin erilaisia tapoja asettaa joukkuepelinä pelattavassa kyykässä pelaajia paremmuusjärjestykseen henkilökohtaisten saavutusten perusteella. Työssä tutustuttiin yleisesti tunnettuihin pelaajien pisteytysmalleihin ...