Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

A concurrent region growing algorithm guided by circumscribed contours

Image segmentation of natural scenes constitutes a major problem in machine vision. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. This approach begins by detecting the main contours of the scene which are later used to guide a concurrent set of growing processes. A previous analysis of the seed pixels permits adjustment of the homogeneity criterion to the region's characteristics during the growing process. Since the high variability of regions representing outdoor scenes makes the classical homogeneity criteria useless, a new homogeneity criterion based on clustering analysis and convex hull construction is proposed. Experimental results have proven the reliability of the proposed approach

Flavonoids affect host-microbiota crosstalk through TLR modulation

Interaction between host cells and microbes is known as crosstalk. Among other mechanisms, this takes place when certain molecules of the micro-organisms are recognized by the toll-like receptors (TLRs) in the body cells, mainly in the intestinal epithelial cells and in the immune cells. TLRs belong to the pattern-recognition receptors and represent the first line of defense against pathogens, playing a pivotal role in both innate and adaptive immunity. Dysregulation in the activity of such receptors can lead to the development of chronic and severe inflammation as well as immunological disorders. Among components present in the diet, flavonoids have been suggested as antioxidant dietary factors able to modulate TLR-mediated signaling pathways. This review focuses on the molecular targets involved in the modulatory action of flavonoids on TLR-mediated signaling pathways, providing an overview of the mechanisms involved in such action. Particular flavonoids have been able to modify the composition of the microbiota, to modulate TLR gene and protein expression, and to regulate the downstream signaling molecules involved in the TLR pathway. These synergistic mechanisms suggest the role of some flavonoids in the preventive effect on certain chronic diseases.

Flavonoids affect host-microbiota crosstalk through TLR modulation

Interaction between host cells and microbes is known as crosstalk. Among other mechanisms, this takes place when certain molecules of the micro-organisms are recognized by the toll-like receptors (TLRs) in the body cells, mainly in the intestinal epithelial cells and in the immune cells. TLRs belong to the pattern-recognition receptors and represent the first line of defense against pathogens, playing a pivotal role in both innate and adaptive immunity. Dysregulation in the activity of such receptors can lead to the development of chronic and severe inflammation as well as immunological disorders. Among components present in the diet, flavonoids have been suggested as antioxidant dietary factors able to modulate TLR-mediated signaling pathways. This review focuses on the molecular targets involved in the modulatory action of flavonoids on TLR-mediated signaling pathways, providing an overview of the mechanisms involved in such action. Particular flavonoids have been able to modify the composition of the microbiota, to modulate TLR gene and protein expression, and to regulate the downstream signaling molecules involved in the TLR pathway. These synergistic mechanisms suggest the role of some flavonoids in the preventive effect on certain chronic diseases.

Computational Techniques for Spectral Image Analysis

Multispectral images are becoming more common in the field of remote sensing, computer vision, and industrial applications. Due to the high accuracy of the multispectral information, it can be used as an important quality factor in the inspection of industrial products. Recently, the development on multispectral imaging systems and the computational analysis on the multispectral images have been the focus of a growing interest. In this thesis, three areas of multispectral image analysis are considered. First, a method for analyzing multispectral textured images was developed. The method is based on a spectral cooccurrence matrix, which contains information of the joint distribution of spectral classes in a spectral domain. Next, a procedure for estimating the illumination spectrum of the color images was developed. Proposed method can be used, for example, in color constancy, color correction, and in the content based search from color image databases. Finally, color filters for the optical pattern recognition were designed, and a prototype of a spectral vision system was constructed. The spectral vision system can be used to acquire a low dimensional component image set for the two dimensional spectral image reconstruction. The data obtained by the spectral vision system is small and therefore convenient for storing and transmitting a spectral image.

Asbestin tunnistaminen keinonenällä

Asbesti on yleisnimike kuitumaisille silikaattimineraaleille. Sillä on monia hyviä ominaisuuksia. Siksi sitä on käytetty useisiin eri käyttötarkoituksiin jo yli 4 000 vuoden ajan. Sisäänhengitettynä asbesti aiheuttaa kuitenkin vakavia terveyshaittoja, mm. asbestoosia, keuhkosyöpää ja mesotelioomaa. Vuosina 1918-1988 Suomessa käytettiin asbestia 300 000 tonnia. Yleisintä käyttö oli 1960-70-lukujen vaihteessa. Sairauksien viive altistumisesta on 10-40 vuotta. Sairauksien esiintyminen onkin nyt suurimmillaan. Suurin osa sairauksista on hyvänlaatuisia keuhkopussin paksuuntumia eli plakkeja. Vuosittain asbestin aiheuttamiin sairauksiin, etupäässä syöpiin, kuolee Suomessa noin 100 ihmistä. Yhteensä altistuneita arvellaan olevan 250 000. Heistä elossa on noin 50 000. Vaarallisuutensa vuoksi asbestin käyttö on useissa maissa kielletty, mutta maailmalla sitä käytetään edelleen suuria määriä. Suomessa asbestin käyttöä rajoitettiin jo 1970-luvulla. Pieniä poikkeuksia lukuun ottamatta täyskielto tuli voimaan 1.1.1994. Suomessa asbestia esiintyy edelleen vanhoissa rakennuksissa. Asbestipurkutyö on luvanvaraista. Asbestitöissä on huolehdittava siitä, että kukaan ei altistu asbestille. Asbestipitoisen materiaalin tunnistaminen silmämääräisesti on vaikeaa. Materiaali luokitellaan asbestipitoiseksi, jos siinä on asbestia yli 1 painoprosenttia tai jos sitä voidaan pölyävyytensä takia pitää vaarallisena. Asbestipitoisen materiaalin kartoituksessa voidaan käyttää rakennussuunnitelmia, vanhoja asiakirjoja kuten urakoitsijan laskuja sekä tuntemusta rakennusajan yleisistä rakennustavoista. Varmuus saadaan kuitenkin vain tutkimalla materiaali esimerkiksi laboratoriokokeissa. Tässä diplomityössä on pyritty selvittämään, voidaanko asbesti tunnistaa ChemPro 100 -keinonenällä. Laite perustuu ioniliikkuvuusspektrometriaan eli eri yhdisteiden erilaiseen liikkuvuuteen kaasumaisessa väliaineessa. Menetelmä on nopea ja yksinkertainen. Tutkimusta varten hankittiin asbestipitoisia materiaaleja, joista saatuja tuloksia vertailtiin toisiinsa. Nykyiset asbestintunnistusmenetelmät ovat monimutkaisia ja hitaita. Jos keinonenä pystyttäisiin kouluttamaan tunnistamaan asbestimateriaali, helpottaisi se asbestikartoituksen tekemistä.

Oliopohjainen konenäkösovelluskehys

Monet teollisuuden konenäkö- ja hahmontunnistusongelmat ovat hyvin samantapaisia, jolloin prototyyppisovelluksia suunniteltaessa voitaisiin hyödyntää pitkälti samoja komponentteja. Oliopohjaiset sovelluskehykset tarjoavat erinomaisen tavan nopeuttaa ohjelmistokehitystä uudelleenkäytettävyyttä parantamalla. Näin voidaan sekä mahdollistaa konenäkösovellusten laajempi käyttö että säästää kustannuksissa. Tässä työssä esitellään konenäkösovelluskehys, joka on perusarkkitehtuuriltaan liukuhihnamainen. Ylätason rakenne koostuu sensorista, datankäsittelyoperaatioista, piirreirrottimesta sekä luokittimesta. Itse sovelluskehyksen lisäksi on toteutettu joukko kuvankäsittely- ja hahmontunnistusoperaatioita. Sovelluskehys nopeuttaa selvästi ohjelmointityötä ja helpottaa uusien kuvankäsittelyoperaatioiden lisää mistä.

CFD Modelling of Direct Contact Condensation in Suppression Pools by Applying Condensation Models of Separated Flow

The condensation rate has to be high in the safety pressure suppression pool systems of Boiling Water Reactors (BWR) in order to fulfill their safety function. The phenomena due to such a high direct contact condensation (DCC) rate turn out to be very challenging to be analysed either with experiments or numerical simulations. In this thesis, the suppression pool experiments carried out in the POOLEX facility of Lappeenranta University of Technology were simulated. Two different condensation modes were modelled by using the 2-phase CFD codes NEPTUNE CFD and TransAT. The DCC models applied were the typical ones to be used for separated flows in channels, and their applicability to the rapidly condensing flow in the condensation pool context had not been tested earlier. A low Reynolds number case was the first to be simulated. The POOLEX experiment STB-31 was operated near the conditions between the ’quasi-steady oscillatory interface condensation’ mode and the ’condensation within the blowdown pipe’ mode. The condensation models of Lakehal et al. and Coste & Lavi´eville predicted the condensation rate quite accurately, while the other tested ones overestimated it. It was possible to get the direct phase change solution to settle near to the measured values, but a very high resolution of calculation grid was needed. Secondly, a high Reynolds number case corresponding to the ’chugging’ mode was simulated. The POOLEX experiment STB-28 was chosen, because various standard and highspeed video samples of bubbles were recorded during it. In order to extract numerical information from the video material, a pattern recognition procedure was programmed. The bubble size distributions and the frequencies of chugging were calculated with this procedure. With the statistical data of the bubble sizes and temporal data of the bubble/jet appearance, it was possible to compare the condensation rates between the experiment and the CFD simulations. In the chugging simulations, a spherically curvilinear calculation grid at the blowdown pipe exit improved the convergence and decreased the required cell count. The compressible flow solver with complete steam-tables was beneficial for the numerical success of the simulations. The Hughes-Duffey model and, to some extent, the Coste & Lavi´eville model produced realistic chugging behavior. The initial level of the steam/water interface was an important factor to determine the initiation of the chugging. If the interface was initialized with a water level high enough inside the blowdown pipe, the vigorous penetration of a water plug into the pool created a turbulent wake which invoked the chugging that was self-sustaining. A 3D simulation with a suitable DCC model produced qualitatively very realistic shapes of the chugging bubbles and jets. The comparative FFT analysis of the bubble size data and the pool bottom pressure data gave useful information to distinguish the eigenmodes of chugging, bubbling, and pool structure oscillations.

Expression of CD14 and toll-like receptors 2 and 4 by milk neutrophils in bovine mammary glands infected with Corynebacterium bovis

This study evaluated the expression of CD14, toll-like receptor (TLR) 2 and TLR4 on the surface of milk neutrophils in bovine mammary glands infected with Corynebacterium bovis. Here, we used 23 culture-negative control quarters with no abnormal secretion on the strip cup test and milk somatic cell count lower than 1x105 cells/mL, and 14 C. bovis infected quarters. The identification of neutrophils, as well as, the percentage of neutrophils that expressed CD14, TLR2 and TLR4 were analyzed by flow cytometry using monoclonal antibodies. The present study encountered no significant difference in the percentages of milk neutrophils that expressed TLR2 and TLR4 or in the expression of TLR4 by milk neutrophils. Conversely, a lower median fluorescence intensity of TLR2 in milk neutrophils was observed in C. bovis-infected quarters. The percentage of neutrophils that expressed CD14 and the median fluorescence intensity of CD14 in milk neutrophils was also lower in C. bovis-infected quarters.

Nasopharyngeal colonization by pathogenic bacteria: effect of polymorphisms in innate immune genes of young children

Nasopharyngeal bacteria can asymptomatically colonize the nasopharynx of infants and young children but are also associated with the development of respiratory infections and diseases. Such nasopharyngeal bacteria include Streptococcus pneumoniae, Moraxella catarrhalis, Haemophilus influenzae and Staphylococcus aureus. The host defense against invading pathogens is largely relies germline-encoded pattern recognition receptors (PRR), which are expressed on the cells of innate immunity, and different cytokines. These include toll-like receptors (TLR), mannose-binding lectin (MBL) and different cytokines such as IL-17A. Single nucleotide polymorphisms (SNP) in these receptors and cytokines have been reported. The aim of this study was to investigate genetic polymorphisms in the genes for TLR2, 3 and 4, MBL as well as for IL-17A and their associations with nasopharyngeal pathogenic bacterial colonization during a two-year follow-up. The study revealed that polymorphisms in TLRs, MBL2 and IL17A are associated with the nasopharyngeal bacterial colonization in young children. Healthy young (2.6 months of age) children with variant types of MBL2, TLR2 R753Q or TLR4 D299G had an increased risk to be colonized by S. pneumonia, S. aureus or M. catarrhalis, respectively. Moreover, variant types of MBL2 in healthy children with might facilitate human rhinovirus (HRV)-induced S. pneumoniae colonization at 2.6 months of age. The polymorphism of TLR4 D299G was shown to be associated with M. catarrhalis colonization throughout the whole two-year follow-up (2.6, 13 and 24 months of age) and also with the bacterial load of this pathogen. Also, the polymorphism of IL17A G152A was shown to be associated with increased risk to be colonized by S. pneumoniae at 13 and 24 months of age. Furthermore, the results suggest that IL17A G152A has an effect on production of serum IL-17A already at young age. In conclusion, the results of this study indicate that polymorphisms in the key PRRs and IL17A seem to play an important role to colonization of S. pneumoniae, M. catarrhalis, and S. aureus in healthy young Finnish children. The nasopharyngeal colonization by these pathogenic bacteria may further promote the development of respiratory infections and may be related to development of asthma and allergy in the later life of children. These findings offer a possible explanation why some children have more respiratory infections than other children and provide a rational basis for future studies in this field.

Classification of brain tumor extracts by high resolution ¹H MRS using partial least squares discriminant analysis

High resolution proton nuclear magnetic resonance spectroscopy (¹H MRS) can be used to detect biochemical changes in vitro caused by distinct pathologies. It can reveal distinct metabolic profiles of brain tumors although the accurate analysis and classification of different spectra remains a challenge. In this study, the pattern recognition method partial least squares discriminant analysis (PLS-DA) was used to classify 11.7 T ¹H MRS spectra of brain tissue extracts from patients with brain tumors into four classes (high-grade neuroglial, low-grade neuroglial, non-neuroglial, and metastasis) and a group of control brain tissue. PLS-DA revealed 9 metabolites as the most important in group differentiation: γ-aminobutyric acid, acetoacetate, alanine, creatine, glutamate/glutamine, glycine, myo-inositol, N-acetylaspartate, and choline compounds. Leave-one-out cross-validation showed that PLS-DA was efficient in group characterization. The metabolic patterns detected can be explained on the basis of previous multimodal studies of tumor metabolism and are consistent with neoplastic cell abnormalities possibly related to high turnover, resistance to apoptosis, osmotic stress and tumor tendency to use alternative energetic pathways such as glycolysis and ketogenesis.

Cognitive set, absorption, and achievement as moderators of the perceptual closure effect in picture priming /

The present study examined individual differences in Absorption and fantasy, as well as in Achiievement and achievement striving as possible moderators of the perceptual closure effect found by Snodgrass and Feenan (1990). The study also examined whether different instructions (experiential versus instrumental) interact with the personality variables to moderate the relationship between priming and subsequent performance on a picture completion task. 1 28 participants completed two sessions, one to fill out the MPQ and NEO personality inventories and the other to complete the experimental task. The experimental task consisted of a priming phase and a test phase, with pictures presented on a computer screen for both phases. Participants were shown 30 pictures in the priming phase, and then shovm the 30 primed pictures along with 30 new pictures for the test phase. Participants were randomly assigned to receive one of the two different instruction sets for the task. Two measures of performance were calculated, most fragmented measure and threshold. Results of the present study confirm that a five-second exposure time is long enough to produce the perceptual closure effect. The analysis of the two-way interaction effects indicated a significant quadratic interaction of Absorption with priming level on threshold performance. The results were in the opposite direction of predictions. Possible explanations for the Absorption results include lack of optimal conditions, lack of intrinsic motivation and measurement problems. Primary analyses also revealed two significant between-subject effects of fantasy and achievement striving on performance collapsed across priming levels. These results suggest that fantasy has a beneficial effect on performance at test for pictures primed at all levels, whereas achievement striving seems to have an adverse effect on performance at test for pictures primed at all levels. Results of the secondary analyses with a revised threshold performance measure indicated a significant quadratic interaction of Absorption, condition and priming level. In the experiential condition, test performance, based on Absorption scores for pictures primed at level 4, showed a positive slope and performance for pictures primed at levels 1 and 7 based on Absorption showed a negative slope. The reverse effect was found in the instrumental condition. The results suggest that Absorption, in combination with experiential involvement, may affect implicit memory. A second significant result of the secondary analyses was a linear three-way interaction of Achievement, condition and priming level on performance. Results suggest that as Achievement scores increased, test performance improved for less fragmented primed pictures in the instrumental condition and test performance improved for more highly fragmented primes in the experiential condition. Results from the secondary analyses suggest that the revised threshold measure may be more sensitive to individual differences. Results of the exploratory analyses with Openness to Experience, Conscientiousness and agentic positive emotionality (PEM-A) measures indicated no significant effects of any of these personality variables. Results suggest that facets of the scales may be more useful with regard to perceptual research, and that future research should examine narrowly focused personality traits as opposed to broader constructs.

Comparison of classification ability of hyperball algorithms to neural network and k-nearest neighbour algorithms

The main focus of this thesis is to evaluate and compare Hyperbalilearning algorithm (HBL) to other learning algorithms. In this work HBL is compared to feed forward artificial neural networks using back propagation learning, K-nearest neighbor and 103 algorithms. In order to evaluate the similarity of these algorithms, we carried out three experiments using nine benchmark data sets from UCI machine learning repository. The first experiment compares HBL to other algorithms when sample size of dataset is changing. The second experiment compares HBL to other algorithms when dimensionality of data changes. The last experiment compares HBL to other algorithms according to the level of agreement to data target values. Our observations in general showed, considering classification accuracy as a measure, HBL is performing as good as most ANn variants. Additionally, we also deduced that HBL.:s classification accuracy outperforms 103's and K-nearest neighbour's for the selected data sets.

Hyperspectral Mineral Identification using SVM and SOM

Remote sensing techniques involving hyperspectral imagery have applications in a number of sciences that study some aspects of the surface of the planet. The analysis of hyperspectral images is complex because of the large amount of information involved and the noise within that data. Investigating images with regard to identify minerals, rocks, vegetation and other materials is an application of hyperspectral remote sensing in the earth sciences. This thesis evaluates the performance of two classification and clustering techniques on hyperspectral images for mineral identification. Support Vector Machines (SVM) and Self-Organizing Maps (SOM) are applied as classification and clustering techniques, respectively. Principal Component Analysis (PCA) is used to prepare the data to be analyzed. The purpose of using PCA is to reduce the amount of data that needs to be processed by identifying the most important components within the data. A well-studied dataset from Cuprite, Nevada and a dataset of more complex data from Baffin Island were used to assess the performance of these techniques. The main goal of this research study is to evaluate the advantage of training a classifier based on a small amount of data compared to an unsupervised method. Determining the effect of feature extraction on the accuracy of the clustering and classification method is another goal of this research. This thesis concludes that using PCA increases the learning accuracy, and especially so in classification. SVM classifies Cuprite data with a high precision and the SOM challenges SVM on datasets with high level of noise (like Baffin Island).

Étude de la réponse du détecteur ATLAS-MPX aux neutrons rapides

Les détecteurs ATLAS-MPX sont des détecteurs Medipix2-USB recouverts de convertisseurs de fluorure de lithium et de polyéthylène pour augmenter l’efficacité de détection des neutrons lents et des neutrons rapides respectivement. Un réseau de quinze détecteurs ATLAS-MPX a été mis en opération dans le détecteur ATLAS au LHC du CERN. Deux détecteurs ATLAS-MPX de référence ont été exposés à des sources de neutrons rapides 252 Cf et 241 AmBe ainsi qu’aux neutrons rapides produits par la réaction 7Li(p, xn) pour l’étude de la réponse du détecteur à ces neutrons. Les neutrons rapides sont principalement détectés à partir des protons de recul des collisions élastiques entre les neutrons et l’hydrogène dans le polyéthylène. Des réactions nucléaires entre les neutrons et le silicium produisent des particules-α. Une étude de l’efficacité de reconnaissance des traces des protons et des particules-α dans le détecteur Medipix2-USB a été faite en fonction de l’énergie cinétique incidente et de l’angle d’incidence. L’efficacité de détection des neutrons rapides a été évaluée à deux seuils d’énergie (8 keV et 230 keV) dans les détecteurs ATLAS-MPX. L’efficacité de détection des neutrons rapides dans la région du détecteur couverte avec le polyéthylène augmente en fonction de l’énergie des neutrons : (0.0346 ± 0.0004) %, (0.0862 ± 0.0018) % et (0.1044 ± 0.0026) % pour des neutrons rapides de 2.13 MeV, 4.08 MeV et 27 MeV respectivement. L’étude pour déterminer l’énergie des neutrons permet donc d’estimer le flux des neutrons quand le détecteur ATLAS-MPX est dans un champ de radiation inconnu comme c’est le cas dans le détecteur ATLAS au LHC.