Efficient Optimization Algorithms for Nonlinear Data Analysis

Identification of low-dimensional structures and main sources of variation from multivariate data are fundamental tasks in data analysis. Many methods aimed at these tasks involve solution of an optimization problem. Thus, the objective of this thesis is to develop computationally efficient and theoretically justified methods for solving such problems. Most of the thesis is based on a statistical model, where ridges of the density estimated from the data are considered as relevant features. Finding ridges, that are generalized maxima, necessitates development of advanced optimization methods. An efficient and convergent trust region Newton method for projecting a point onto a ridge of the underlying density is developed for this purpose. The method is utilized in a differential equation-based approach for tracing ridges and computing projection coordinates along them. The density estimation is done nonparametrically by using Gaussian kernels. This allows application of ridge-based methods with only mild assumptions on the underlying structure of the data. The statistical model and the ridge finding methods are adapted to two different applications. The first one is extraction of curvilinear structures from noisy data mixed with background clutter. The second one is a novel nonlinear generalization of principal component analysis (PCA) and its extension to time series data. The methods have a wide range of potential applications, where most of the earlier approaches are inadequate. Examples include identification of faults from seismic data and identification of filaments from cosmological data. Applicability of the nonlinear PCA to climate analysis and reconstruction of periodic patterns from noisy time series data are also demonstrated. Other contributions of the thesis include development of an efficient semidefinite optimization method for embedding graphs into the Euclidean space. The method produces structure-preserving embeddings that maximize interpoint distances. It is primarily developed for dimensionality reduction, but has also potential applications in graph theory and various areas of physics, chemistry and engineering. Asymptotic behaviour of ridges and maxima of Gaussian kernel densities is also investigated when the kernel bandwidth approaches infinity. The results are applied to the nonlinear PCA and to finding significant maxima of such densities, which is a typical problem in visual object tracking.

Statistical analysis of survey-based event history data with application to modeling of unemployment duration

Longitudinal surveys are increasingly used to collect event history data on person-specific processes such as transitions between labour market states. Surveybased event history data pose a number of challenges for statistical analysis. These challenges include survey errors due to sampling, non-response, attrition and measurement. This study deals with non-response, attrition and measurement errors in event history data and the bias caused by them in event history analysis. The study also discusses some choices faced by a researcher using longitudinal survey data for event history analysis and demonstrates their effects. These choices include, whether a design-based or a model-based approach is taken, which subset of data to use and, if a design-based approach is taken, which weights to use. The study takes advantage of the possibility to use combined longitudinal survey register data. The Finnish subset of European Community Household Panel (FI ECHP) survey for waves 1–5 were linked at person-level with longitudinal register data. Unemployment spells were used as study variables of interest. Lastly, a simulation study was conducted in order to assess the statistical properties of the Inverse Probability of Censoring Weighting (IPCW) method in a survey data context. The study shows how combined longitudinal survey register data can be used to analyse and compare the non-response and attrition processes, test the missingness mechanism type and estimate the size of bias due to non-response and attrition. In our empirical analysis, initial non-response turned out to be a more important source of bias than attrition. Reported unemployment spells were subject to seam effects, omissions, and, to a lesser extent, overreporting. The use of proxy interviews tended to cause spell omissions. An often-ignored phenomenon classification error in reported spell outcomes, was also found in the data. Neither the Missing At Random (MAR) assumption about non-response and attrition mechanisms, nor the classical assumptions about measurement errors, turned out to be valid. Both measurement errors in spell durations and spell outcomes were found to cause bias in estimates from event history models. Low measurement accuracy affected the estimates of baseline hazard most. The design-based estimates based on data from respondents to all waves of interest and weighted by the last wave weights displayed the largest bias. Using all the available data, including the spells by attriters until the time of attrition, helped to reduce attrition bias. Lastly, the simulation study showed that the IPCW correction to design weights reduces bias due to dependent censoring in design-based Kaplan-Meier and Cox proportional hazard model estimators. The study discusses implications of the results for survey organisations collecting event history data, researchers using surveys for event history analysis, and researchers who develop methods to correct for non-sampling biases in event history data.

Spectral Analysis of Symmetric and Anti-Symmetric Pairwise Kernels

This work investigates theoretical properties of symmetric and anti-symmetric kernels. First chapters give an overview of the theory of kernels used in supervised machine learning. Central focus is on the regularized least squares algorithm, which is motivated as a problem of function reconstruction through an abstract inverse problem. Brief review of reproducing kernel Hilbert spaces shows how kernels define an implicit hypothesis space with multiple equivalent characterizations and how this space may be modified by incorporating prior knowledge. Mathematical results of the abstract inverse problem, in particular spectral properties, pseudoinverse and regularization are recollected and then specialized to kernels. Symmetric and anti-symmetric kernels are applied in relation learning problems which incorporate prior knowledge that the relation is symmetric or anti-symmetric, respectively. Theoretical properties of these kernels are proved in a draft this thesis is based on and comprehensively referenced here. These proofs show that these kernels can be guaranteed to learn only symmetric or anti-symmetric relations, and they can learn any relations relative to the original kernel modified to learn only symmetric or anti-symmetric parts. Further results prove spectral properties of these kernels, central result being a simple inequality for the the trace of the estimator, also called the effective dimension. This quantity is used in learning bounds to guarantee smaller variance.

An Assessment ofFatigue Strength of Load Carrying Welded Joints with Lack of Penetration

On yleisesti tiedossa, että väsyttävän kuormituksen alaisena olevat hitsatut rakenteet rikkoutuvat juuri hitsausliitoksista. Täyden tunkeuman hitsausliitoksia sisältävien rakenteiden asiantunteva suunnittelu janykyaikaiset valmistusmenetelmät ovat lähes eliminoineet väsymisvauriot hitsatuissa rakenteissa. Väsymislujuuden parantaminen tiukalla täyden tunkeuman vaatimuksella on kuitenkin epätaloudellinen ratkaisu. Täyden tunkeuman hitsausliitoksille asetettavien laatuvaatimuksien on määriteltävä selkeät tarkastusohjeet ja hylkäämisperusteet. Tämän diplomityön tarkoituksena oli tutkia geometristen muuttujien vaikutusta kuormaa kantavien hitsausliitosten väsymislujuuteen. Huomio kiinnitettiin pääasiassa suunnittelumuuttujiin, joilla on vaikutusta väsymisvaurioiden syntymiseen hitsauksen juuren puolella. Nykyiset määräykset ja standardit, jotka perustuvat kokeellisiin tuloksiin; antavat melko yleisiä ohjeita hitsausliitosten väsymismitoituksesta. Tämän vuoksi muodostettiin kokonaan uudet parametriset yhtälöt sallitun nimellisen jännityksen kynnysarvon vaihteluvälin, ¿¿th, laskemiseksi, jotta vältettäisiin hitsausliitosten juuren puoleiset väsymisvauriot. Lisäksi, jokaiselle liitostyypille laskettiin hitsin juuren puolen väsymisluokat (FAT), joita verrattiin olemassa olevilla mitoitusohjeilla saavutettuihin tuloksiin. Täydentäviksi referensseiksi suoritettiin useita kolmiulotteisia (3D) analyysejä. Julkaistuja kokeellisiin tuloksiin perustuvia tietoja käytettiin apuna hitsausliitosten väsymiskäyttäytymisen ymmärtämiseksi ja materiaalivakioiden määrittämiseksi. Kuormaa kantavien vajaatunkeumaisten hitsausliitosten väsymislujuus määritettiin käyttämällä elementtimenetelmää. Suurimman pääjännityksen kriteeriä hyödynnettiin murtumiskäyttäytymisen ennakoimiseksi. Valitulle hitsatulle materiaalille ja koeolosuhteille murtumiskäyttäytymistä mallinnettiin särön kasvunopeudella da/dN ja jännitysintensiteettikertoimen vaihteluvälillä, 'K. Paris:n yhtälön numeerinen integrointi suoritettiin FRANC2D/L tietokoneohjelmalla. Saatujen tulosten perusteella voidaan laskea FAT tutkittavassa tapauksessa. ¿¿th laskettiin alkusärön jännitysintensiteettikertoimen vaihteluvälin ja kynnysjännitysintensiteettikertoimen, 'Kth, perusteella. ¿Kth arvoa pienemmällä vaihteluvälillä särö ei kasva. Analyyseissäoletuksena oli hitsattu jälkikäsittelemätön liitos, jossa oli valmis alkusärö hitsin juuressa. Analyysien tulokset ovat hyödyllisiä suunnittelijoille, jotka tekevät päätöksiä koskien geometrisiä parametreja, joilla on vaikutusta hitsausliitosten väsymislujuuteen.

Aircraft tracking and classification with vhf passive bistatic radar

Since the times preceding the Second World War the subject of aircraft tracking has been a core interest to both military and non-military aviation. During subsequent years both technology and configuration of the radars allowed the users to deploy it in numerous fields, such as over-the-horizon radar, ballistic missile early warning systems or forward scatter fences. The latter one was arranged in a bistatic configuration. The bistatic radar has continuously re-emerged over the last eighty years for its intriguing capabilities and challenging configuration and formulation. The bistatic radar arrangement is used as the basis of all the analyzes presented in this work. The aircraft tracking method of VHF Doppler-only information, developed in the first part of this study, is solely based on Doppler frequency readings in relation to time instances of their appearance. The corresponding inverse problem is solved by utilising a multistatic radar scenario with two receivers and one transmitter and using their frequency readings as a base for aircraft trajectory estimation. The quality of the resulting trajectory is then compared with ground-truth information based on ADS-B data. The second part of the study deals with the developement of a method for instantaneous Doppler curve extraction from within a VHF time-frequency representation of the transmitted signal, with a three receivers and one transmitter configuration, based on a priori knowledge of the probability density function of the first order derivative of the Doppler shift, and on a system of blocks for identifying, classifying and predicting the Doppler signal. The extraction capabilities of this set-up are tested with a recorded TV signal and simulated synthetic spectrograms. Further analyzes are devoted to more comprehensive testing of the capabilities of the extraction method. Besides testing the method, the classification of aircraft is performed on the extracted Bistatic Radar Cross Section profiles and the correlation between them for different types of aircraft. In order to properly estimate the profiles, the ADS-B aircraft location information is adjusted based on extracted Doppler frequency and then used for Bistatic Radar Cross Section estimation. The classification is based on seven types of aircraft grouped by their size into three classes.