Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Oliotietokannan muuttaminen relaatiotietokannaksi

Diplomityön tavoitteena oli parantaa oliotietokantaan perustuvan mökkivarausjärjestelmän pitkiä vasteaikoja ja epävakaata toimintaa sekä luoda tietokantaperusta uusille toiminnoille. Ratkaisua etsittiin korvaamalla oliotietokanta relaatiotietokannalla. Diplomityö on osa koko varausjärjestelmän uusintaa. Työn teoreettinen osuus käsittelee sekä olio- että relaatiotietokannan rakennetta ja oliomallin muuttamista relaatiomalliksi. Käytännön osassa esitellään relaatiotietokannan luominen vaiheittain ja kerrotaan tietojen siirron periaatteesta. Relaatiotietokannan havaittiin olevan vakaampi ja tehokkaampi vasteajoiltaan. Samoin sen vaatima levytilan ja muistin määrä oli pienempi kuin oliotietokannalla. Lisäksi siihen todettiin uusien järjestelmien liittämisen olevan yksinkertaisempaa.

Lossless Compression Methods for Multispectral Images: Development and Comparisons

Main purpose of this thesis is to introduce a new lossless compression algorithm for multispectral images. Proposed algorithm is based on reducing the band ordering problem to the problem of finding a minimum spanning tree in a weighted directed graph, where set of the graph vertices corresponds to multispectral image bands and the arcs’ weights have been computed using a newly invented adaptive linear prediction model. The adaptive prediction model is an extended unification of 2–and 4–neighbour pixel context linear prediction schemes. The algorithm provides individual prediction of each image band using the optimal prediction scheme, defined by the adaptive prediction model and the optimal predicting band suggested by minimum spanning tree. Its efficiency has been compared with respect to the best lossless compression algorithms for multispectral images. Three recently invented algorithms have been considered. Numerical results produced by these algorithms allow concluding that adaptive prediction based algorithm is the best one for lossless compression of multispectral images. Real multispectral data captured from an airplane have been used for the testing.

Tilastollinen tutkimus ohjelmiston laatuun vaikuttavista tekijöistä

Tämä työ on tehty osana MASTO-tutkimushanketta, jonka tarkoituksena on kehittää ohjelmistotestauksen adaptiivinen referenssimalli. Työ toteutettiin tilastollisena tutkimuksena käyttäen survey-menetelmää. Tutkimuksessa haastateltiin 31 organisaatioyksikköä eri puolelta suomea, jotka tekevät keskikriittisiä sovelluksia. Tutkimuksen hypoteeseina oli laadun riippuvuus ohjelmistokehitysmenetelmästä, asiakkaan osallistumisesta, standardin toteutumisesta, asiakassuhteesta, liiketoimintasuuntautuneisuudesta, kriittisyydestä, luottamuksesta ja testauksen tasosta. Hypoteeseista etsittiin korrelaatiota laadun kanssa tekemällä korrelaatio ja regressioanalyysi. Lisäksi tutkimuksessa kartoitettiin minkälaisia ohjelmistokehitykseen liittyviä käytäntöjä, menetelmiä ja työkaluja organisaatioyksiköissä käytettiin, ongelmia ja parannusehdotuksia liittyen ohjelmistotestaukseen, merkittävimpiä tapoja asiakkaan vaikuttamiseksi ohjelmiston laatuun sekä suurimpia hyötyjä ja haittoja ohjelmistokehityksen tai testauksen ulkoistamisessa. Tutkimuksessa havaittiin, että laatu korreloi positiivisesti ja tilastollisesti merkitsevästi testauksen tason, standardin toteutumisen, asiakasosallistumisen suunnitteluvaiheessa sekä asiakasosallistumisen ohjaukseen kanssa, luottamuksen ja yhden asiakassuhteeseen liittyvän osakysymyksen kanssa. Regressioanalyysin perusteella muodostettiin regressioyhtälö, jossa laadun todettiin positiivisesti riippuvan standardin toteutumisesta, asiakasosallistumisesta suunnitteluvaiheessa sekä luottamuksesta.

Toimitusketjun mallinnuksen tarpeet ja rakenne LOCOMOTIVE projekstissa

Työn tavoitteena oli kuvata ja priorisoida toimitusketjun dynaamisen mallinnustyökalun vaatimukset, sekä muodostaa tämän pohjalta ohjelmistokehitystä tukeva oliomalli. Vaatimuksia selvitettiin teoreettisen tarkastelun, aiemmin toteutettujen kyselytutkimusten sekä viiden pilottitapauksen avulla. Toimitusketjun hallinta ei ole pelkästään materiaalivirtojen vaan myös näihin liittyvän informaation hallintaa. Holististen toimitusketjuongelmien mallintaminen edellyttää siis informaatiovirtojen ja niitä saatelevien ohjausmekanisemien mallintamista. Markkinoilla on selkeästi tilaa tukijärjestelmille, jotka mahdollistaisivat multidimensionaalisten - tuotto, aika, palvelu - toimitusketjuongelmien tarkastelun. Systeemidynamiikan teorian mukaisesti oliomallin lähtökohdaksi valittiin tärkeimpien takaisinkytkentäsilmukkojen mallinnus. Takaisinkytkentäsilmukoiden avulla kyetään mallintamaan kompleksisia systeemejä ajan suhteen. Mallinnetut toimitusketjujen takaisinkytkentäsilmukkat ovat operaatio-, ohjaus-, kysyntä- ja strategiasilmukka. Toimitusketjun ohjausmekanismien, sekä systeemidynamiikan perusteiden pohjalta mallinnustyökalun vaatimuksista muodostettiin oliomalli. Muodostettu oliomalli on Locomotiven - toimitusketjun mallinnustyökalun - perusta.

Suunnitelma ohjelmistotestauksen adaptiivisen referenssimallin arviointiin

The aim of this bachelor’s thesis is to make a plan for the assessment of the adaptive reference model of software testing, which is based on the ISO/IEC 29119 testing standard. The assessment is not carried out in the scope of this thesis, but later in the related MASTO project. The ISO/IEC 29119 testing standard and the ISO/IEC 15504 process assessment standard are explained and a literary review is done about problems in software testing practices. Based on this background information a plan for the assessment is made. The assessment plan assesses the reference model from two perspectives. First the capability of the testing process described by the reference model is assessed and then the practical usefulness of the model is assessed.

Artificially Intelligent and Adaptive Methods for Prediction and Analysis of Superheater Fireside Corrosion in Fluidized Bed Boilers

Superheater corrosion causes vast annual losses for the power companies. With a reliable corrosion prediction method, the plants can be designed accordingly, and knowledge of fuel selection and determination of process conditions may be utilized to minimize superheater corrosion. Growing interest to use recycled fuels creates additional demands for the prediction of corrosion potential. Models depending on corrosion theories will fail, if relations between the inputs and the output are poorly known. A prediction model based on fuzzy logic and an artificial neural network is able to improve its performance as the amount of data increases. The corrosion rate of a superheater material can most reliably be detected with a test done in a test combustor or in a commercial boiler. The steel samples can be located in a special, temperature-controlled probe, and exposed to the corrosive environment for a desired time. These tests give information about the average corrosion potential in that environment. Samples may also be cut from superheaters during shutdowns. The analysis ofsamples taken from probes or superheaters after exposure to corrosive environment is a demanding task: if the corrosive contaminants can be reliably analyzed, the corrosion chemistry can be determined, and an estimate of the material lifetime can be given. In cases where the reason for corrosion is not clear, the determination of the corrosion chemistry and the lifetime estimation is more demanding. In order to provide a laboratory tool for the analysis and prediction, a newapproach was chosen. During this study, the following tools were generated: · Amodel for the prediction of superheater fireside corrosion, based on fuzzy logic and an artificial neural network, build upon a corrosion database developed offuel and bed material analyses, and measured corrosion data. The developed model predicts superheater corrosion with high accuracy at the early stages of a project. · An adaptive corrosion analysis tool based on image analysis, constructedas an expert system. This system utilizes implementation of user-defined algorithms, which allows the development of an artificially intelligent system for thetask. According to the results of the analyses, several new rules were developed for the determination of the degree and type of corrosion. By combining these two tools, a user-friendly expert system for the prediction and analyses of superheater fireside corrosion was developed. This tool may also be used for the minimization of corrosion risks by the design of fluidized bed boilers.

Object-oriented development of client / server application: case study of service control software

Tässä työssä on esitetty sen ohjelmiston kehittämisen prosessi, joka on tarkoitettu annettavien palveluiden valvottavaksi käyttäen prototyyppimallia. Raportti sisältää vaatimusten, kohteisiin suunnatun analyysin ja suunnittelun, realisointiprosessien kuvauksen ja prototyypin testauksen. Ohjelmiston käyttöala – antavien palveluiden valvonta. Vaatimukset sovellukselle analysoitiin ohjelmistomarkkinoiden perusteella sekä ohjelmiston engineeringin periaatteiden mukaisesti. Ohjelmiston prototyyppi on realisoitu käyttäen asiakas-/palvelinhybridimallia sekä ralaatiokantaa. Kehitetty ohjelmisto on tarkoitettu venäläisille tietokonekerhoille, jotka erikoistuvat pelipalvelinten antamiseen.

Object-Oriented Modelling of Multilayer Networks

Tämä diplomityökuuluu tietoliikenneverkkojen suunnittelun tutkimukseen ja pohjimmiltaan kohdistuu verkon mallintamiseen. Tietoliikenneverkkojen suunnittelu on monimutkainen ja vaativa ongelma, joka sisältää mutkikkaita ja aikaa vieviä tehtäviä. Tämä diplomityö esittelee ”monikerroksisen verkkomallin”, jonka tarkoitus on auttaa verkon suunnittelijoita selviytymään ongelmien monimutkaisuudesta ja vähentää verkkojen suunnitteluun kuluvaa aikaa. Monikerroksinen verkkomalli perustuu yleisille objekteille, jotka ovat yhteisiä kaikille tietoliikenneverkoille. Tämä tekee mallista soveltuvan mielivaltaisille verkoille, välittämättä verkkokohtaisista ominaisuuksista tai verkon toteutuksessa käytetyistä teknologioista. Malli määrittelee tarkan terminologian ja käyttää kolmea käsitettä: verkon jakaminen tasoihin (plane separation), kerrosten muodostaminen (layering) ja osittaminen (partitioning). Nämä käsitteet kuvataan yksityiskohtaisesti tässä työssä. Monikerroksisen verkkomallin sisäinen rakenne ja toiminnallisuus ovat määritelty käyttäen Unified Modelling Language (UML) -notaatiota. Tämä työ esittelee mallin use case- , paketti- ja luokkakaaviot. Diplomityö esittelee myös tulokset, jotka on saatu vertailemalla monikerroksista verkkomallia muihin verkkomalleihin. Tulokset osoittavat, että monikerroksisella verkkomallilla on etuja muihin malleihin verrattuna.

Adaptive MCMC methods with applications in environmental and geophysical models

This work presents new, efficient Markov chain Monte Carlo (MCMC) simulation methods for statistical analysis in various modelling applications. When using MCMC methods, the model is simulated repeatedly to explore the probability distribution describing the uncertainties in model parameters and predictions. In adaptive MCMC methods based on the Metropolis-Hastings algorithm, the proposal distribution needed by the algorithm learns from the target distribution as the simulation proceeds. Adaptive MCMC methods have been subject of intensive research lately, as they open a way for essentially easier use of the methodology. The lack of user-friendly computer programs has been a main obstacle for wider acceptance of the methods. This work provides two new adaptive MCMC methods: DRAM and AARJ. The DRAM method has been built especially to work in high dimensional and non-linear problems. The AARJ method is an extension to DRAM for model selection problems, where the mathematical formulation of the model is uncertain and we want simultaneously to fit several different models to the same observations. The methods were developed while keeping in mind the needs of modelling applications typical in environmental sciences. The development work has been pursued while working with several application projects. The applications presented in this work are: a winter time oxygen concentration model for Lake Tuusulanjärvi and adaptive control of the aerator; a nutrition model for Lake Pyhäjärvi and lake management planning; validation of the algorithms of the GOMOS ozone remote sensing instrument on board the Envisat satellite of European Space Agency and the study of the effects of aerosol model selection on the GOMOS algorithm.

Adaptive optimization schemes for mobile VoIP applications Battery life and call quality aspects

In this thesis programmatic, application-layer means for better energy-efficiency in the VoIP application domain are studied. The work presented concentrates on optimizations which are suitable for VoIP-implementations utilizing SIP and IEEE 802.11 technologies. Energy-saving optimizations can have an impact on perceived call quality, and thus energy-saving means are studied together with those factors affecting perceived call quality. In this thesis a general view on a topic is given. Based on theory, adaptive optimization schemes for dynamic controlling of application's operation are proposed. A runtime quality model, capable of being integrated into optimization schemes, is developed for VoIP call quality estimation. Based on proposed optimization schemes, some power consumption measurements are done to find out achievable advantages. Measurement results show that a reduction in power consumption is possible to achieve with the help of adaptive optimization schemes.

Automated, adaptive methods for forest inventory

Forest inventories are used to estimate forest characteristics and the condition of forest for many different applications: operational tree logging for forest industry, forest health state estimation, carbon balance estimation, land-cover and land use analysis in order to avoid forest degradation etc. Recent inventory methods are strongly based on remote sensing data combined with field sample measurements, which are used to define estimates covering the whole area of interest. Remote sensing data from satellites, aerial photographs or aerial laser scannings are used, depending on the scale of inventory. To be applicable in operational use, forest inventory methods need to be easily adjusted to local conditions of the study area at hand. All the data handling and parameter tuning should be objective and automated as much as possible. The methods also need to be robust when applied to different forest types. Since there generally are no extensive direct physical models connecting the remote sensing data from different sources to the forest parameters that are estimated, mathematical estimation models are of "black-box" type, connecting the independent auxiliary data to dependent response data with linear or nonlinear arbitrary models. To avoid redundant complexity and over-fitting of the model, which is based on up to hundreds of possibly collinear variables extracted from the auxiliary data, variable selection is needed. To connect the auxiliary data to the inventory parameters that are estimated, field work must be performed. In larger study areas with dense forests, field work is expensive, and should therefore be minimized. To get cost-efficient inventories, field work could partly be replaced with information from formerly measured sites, databases. The work in this thesis is devoted to the development of automated, adaptive computation methods for aerial forest inventory. The mathematical model parameter definition steps are automated, and the cost-efficiency is improved by setting up a procedure that utilizes databases in the estimation of new area characteristics.

The genetics of behaviour and other adaptive traits in nine-spined sticklebacks (Pungitius pungitius)

One of the main goals in current evolutionary biology research is to identify genes behind adaptive phenotypic variations. The advances in genomic technologies have made it possible to identify genetic loci behind these variations, also concerning non-model species. This thesis investigates the genetics of the behaviour and other adaptive traits of the nine-spined stickleback (Pungitius pungitius) through the application of different genetic approaches. Fennoscandian nine-spined stickleback populations express large phenotypical differences especially in behaviour, life –history traits and morphology. However the underlying genetic bases for these phenotypical differences have not been studied in detail. The results of the project will lay the foundation for further genetics studies and provide valuable information for our understanding of the genetics of the adaptive divergence of the nine-spined stickleback. A candidate gene approach was used to develop microsatellite markers situating close to candidate genes for behaviour in the nine-spined stickleback. Altogether 13 markers were developed and these markers were used in the subsequent studies with the anonymous random markers and physiologically important gene markers which are already currently available for nine-spined sticklebacks. It was shown that heterozygosity correlated with behaviour in one of the marine nine-spined stickleback populations but with contrasting effects: correlations with behaviour were negative when using physiological gene markers and positive with random markers. No correlation was found between behavioural markers and behaviour. From the physiological gene markers, a strong correlation was found between osmoregulation-related gene markers and behaviour. These results indicate that both local (physiological) and general (random) effects are important in the shaping of behaviour and that heterozygosity– behaviour correlations are population dependent. In this thesis a second linkage map for nine-spined sticklebacks was constructed. Compared to the earlier nine-spined stickleback linkage map, genomic rearrangements were observed between autosomal (LG7) and sex-determing (LG12) linkage groups. This newly constructed map was used in QTL mapping studies in order to locate genomic regions associated with pelvic structures, behaviour and body size/growth. One major QTL was found for pelvic structures and Pitx1 gene was related to these traits as was predicted from three-spined stickleback studies, but this was in contrast to earlier nine-spined stickleback study. The QTL studies also revealed that behaviour and body size/growth were genetically more complex by having more QTL than pelvic traits. However, in many cases, pelvic structure, body size/growth and behaviour were linked to similar map locations indicating possible pleiotropic effects of genes locating in these QTL regions. Many of the gene related markers resided in the QTL area. In the future, studying these possible candidate genes in depth might reveal the underlying mechanism behind the measured traits.

A Model-Based Development and Verification Framework for Distributed System-on-Chip Architecture

The capabilities and thus, design complexity of VLSI-based embedded systems have increased tremendously in recent years, riding the wave of Moore’s law. The time-to-market requirements are also shrinking, imposing challenges to the designers, which in turn, seek to adopt new design methods to increase their productivity. As an answer to these new pressures, modern day systems have moved towards on-chip multiprocessing technologies. New architectures have emerged in on-chip multiprocessing in order to utilize the tremendous advances of fabrication technology. Platform-based design is a possible solution in addressing these challenges. The principle behind the approach is to separate the functionality of an application from the organization and communication architecture of hardware platform at several levels of abstraction. The existing design methodologies pertaining to platform-based design approach don’t provide full automation at every level of the design processes, and sometimes, the co-design of platform-based systems lead to sub-optimal systems. In addition, the design productivity gap in multiprocessor systems remain a key challenge due to existing design methodologies. This thesis addresses the aforementioned challenges and discusses the creation of a development framework for a platform-based system design, in the context of the SegBus platform - a distributed communication architecture. This research aims to provide automated procedures for platform design and application mapping. Structural verification support is also featured thus ensuring correct-by-design platforms. The solution is based on a model-based process. Both the platform and the application are modeled using the Unified Modeling Language. This thesis develops a Domain Specific Language to support platform modeling based on a corresponding UML profile. Object Constraint Language constraints are used to support structurally correct platform construction. An emulator is thus introduced to allow as much as possible accurate performance estimation of the solution, at high abstraction levels. VHDL code is automatically generated, in the form of “snippets” to be employed in the arbiter modules of the platform, as required by the application. The resulting framework is applied in building an actual design solution for an MP3 stereo audio decoder application.