Hae LUTPubista
Aineistot 21-30 / 104
Open-set plankton recognition
(2021)
Research on the plankton community is often dealt with acquiring species-level information of individual micro-organisms. The efficiency is limited when manually analyzing a massive collection of plankton image data generated ...
Plankton recognition using similarity learning
(2021)
Several automated classification methods for plankton images have been developed. These methods typically require an explicit description of features, data augmentation, and are not suitable for classes with a few example ...
Improving the accuracy of time-of-flight camera -based floor height estimation in mixed reality head-mounted displays
(2021)
In recent years, the use of mixed reality headsets has gained a lot of popularity in several applications ranging from creative design work to implementation of complex training procedures. To ensure a pleasant user ...
Statistical fault characterization in industrial processes
(2021)
Fault detection is used to identify anomalous behavior in a process or machine. This study aims to characterize faults in an industrial process based on vibration signal. The studied data is unlabeled process data containing ...
Image clustering for unsupervised analysis of plankton data
(2020)
Advancements in automated imaging has made it possible to enhance the data both in terms of quantity and quality. This has prompted the development of plankton imaging systems for acquiring the species level information ...
Bayesian optimal design in X-ray tomography
(2020)
This thesis focuses on Bayesian optimal design and its applications to X-ray tomography. X-ray tomography is a well-known setting where X-rays are projected at an object. X-ray intensity data is recorded on the other side ...
Unsupervised profiling of electricity consumers for load forecasting applications
(2020)
Electric power suppliers are typically interested in profiling their customers. Different
consumer categories or load profiles can give insight into behavior which affects the power grid and facilitate load forecasting ...
Analysis of survey data by numerical modelling
(2020)
Analysing survey data poses a challenge of often being based on human feelings, which cannot be measured by objective numerical values. The Finnish Institute of Occupational Health has formulated a survey to measure the ...
Matemaattisen mallin rakentaminen kysynnän ennustettavuuteen palvelualan yrityksessä
(2021)
Työn tavoitteena oli luoda palvelualan yritykselle, Yritys X:lle, tilausmäärien tuntikohtainen ennustemalli, joka menneen datan pohjalta osaisi ennustaa riittävällä tarkkuudella seuraavan viikon päivä- ja tuntikohtaiset ...
Predicting lead times of purchase orders using gradient boosting machine
(2020)
A company can make more accurate predictions of its internal processes and sales lead
times when it has accurate predictions of the lead times of purchase orders. It results in more
efficient processes as well as improved ...