Bayesian classification of forest ecological type from satellite data

The main objective of this study was todo a statistical analysis of ecological type from optical satellite data, using Tipping's sparse Bayesian algorithm. This thesis uses "the Relevence Vector Machine" algorithm in ecological classification betweenforestland and wetland. Further this bi-classification technique was used to do classification of many other different species of trees and produces hierarchical classification of entire subclasses given as a target class. Also, we carried out an attempt to use airborne image of same forest area. Combining it with image analysis, using different image processing operation, we tried to extract good features and later used them to perform classification of forestland and wetland.

Puhdastilojen suunnitteluprosessi ja teknisten järjestelmien validointi

Puhdastilojen suunnittelussa pyritään saamaan hallittu ja valvottu ilmanpuhtaus luokiteltuun tilaan.Luokittelu tapahtuu puhdastilastandardeilla, lisäksi lääkevalmisteita valmistettavassa tilassa GMP -säädösten mukaisin luokituksin. Puhdastilastandardi ISO 14644 käsittää seitsemän osaa, jossa on käsitelty puhdastilaa koskevia määräyksiä suunnittelusta käyttöön ja testaukseen. GMP-säädökset sisältävät yhdeksän kappaletta, joista kappale 3: 'Tilat ja laitteet' on keskeinen osa lääkeainevalmistuksen puhdastilasuunnittelua. Puhtaan ilman aikaansaamiseksi puhdastilaan merkittävimmät roolit ovat ilmanvaihdolla, puhdastilarakenteilla ja rakennusautomaatiolla. Ilma voidaan tuoda tilaan kolmella eri periaatteella. Ilmaa tuodaan tilaan yhdensuuntaisesti, turbulenttisesti tai sekavirtauksena HEPA -suodattimien kautta, joilla varmistetaan epäpuhtauksien korkea suodatusaste. Ilmapoistetaan rei'itettyjen, korotettujen lattioiden kautta tai tilan alaosassa olevien poistoilmasäleikköjen kautta, josta se johdetaan noin 75-90%:sti kierrätettynä takaisin tilaan. Lääketeollisuudessa rei'itettyjä, korotettuja lattioita eivoida käyttää kontaminaatiovaaran, vuoksi. Tilaan suunniteltuja olosuhteita ylläpidetään rakennusautomaation avulla ja monitorointijärjestelmällä valvotaan tilassa olevan ilman laatua. Kaikki GMP-luokituksen mukaiset puhdastilat tulee validoida. Validointiin kuuluu teknisten järjestelmien kvalifiointi ja koko prosessin validointi. Teknisten järjestel-mien kvalifiointi käsittää suunnitelmien tarkastuksen (DQ), asennus - ja käyttöönotto tarkastukset (IQ), toiminnan testauksen (OQ) ja suorituksen testauksen (PQ). Kvali-fiointi kuuluu yhtenä osa-alueena validointiin. Prosessin validointi on osa yrityksen laadunvarmistusta. Validoinnilla hankitaan dokumentoidut todisteet siitä, että tila tai prosessi todella täyttää annetut vaatimukset. Tässä työssä laadittiin esimerkinomainen kvalifiointisuunnitelma puhdastilan tekni-sille järjestelmille. Suunnitelma sisältää asennus- ja käyttöönoton mukaiset tarkastukset (IQ)ja toiminnan aikaiset testaukset (OQ).

Cluster-based active learning for compact image classification

In this paper, we consider active sampling to label pixels grouped with hierarchical clustering. The objective of the method is to match the data relationships discovered by the clustering algorithm with the user's desired class semantics. The first is represented as a complete tree to be pruned and the second is iteratively provided by the user. The active learning algorithm proposed searches the pruning of the tree that best matches the labels of the sampled points. By choosing the part of the tree to sample from according to current pruning's uncertainty, sampling is focused on most uncertain clusters. This way, large clusters for which the class membership is already fixed are no longer queried and sampling is focused on division of clusters showing mixed labels. The model is tested on a VHR image in a multiclass classification setting. The method clearly outperforms random sampling in a transductive setting, but cannot generalize to unseen data, since it aims at optimizing the classification of a given cluster structure.

Current Issues in the Diagnosis and Classification of Peripheral T-Cell Lymphomas

Mature T-cell and T/NK-cell neoplasms are both uncommon and heterogeneous, among the broad category of non-Hodgkin's lymphomas. Due to the lack of specific genetic alterations in the vast majority of cases, most currently defined entities show overlapping morphologic and immunophenotypic features and therefore pose a challenge to the diagnostic pathologist. The goal of the symposium is to address current criteria for the recognition of specific subtypes of T-cell lymphoma, and to highlight new data regarding emerging immunophenotypic or molecular markers. This activity has been designed to meet the needs of practicing pathologists, and residents and fellows enrolled in training programs in anatomic and clinical pathology. It should be a particular benefit to those with an interest in hematopathology. Upon completion of this activity, participants should be better able to: -To be able to state the basis for the classification of mature T-cell malignancies involving nodal and extranodal sites. -To recognize and accurately diagnose the various subtypes of nodal and extranodal peripheral T-cell lymphomas. -To utilize immunohistochemical and molecular tests to characterize atypical T-cell proliferations. -To recognize and accurately diagnose T-cell lymphoproliferative lesions involving the skin and gastrointestinal tract, and be able to provide guidance regarding their clinical aggressiveness and management -To be able to utilize flow cytometric data to identify diverse functional T-cell subsets.

Image-Based Coral Reef Classification and Thematic Mapping

This paper presents a novel image classification scheme for benthic coral reef images that can be applied to both single image and composite mosaic datasets. The proposed method can be configured to the characteristics (e.g., the size of the dataset, number of classes, resolution of the samples, color information availability, class types, etc.) of individual datasets. The proposed method uses completed local binary pattern (CLBP), grey level co-occurrence matrix (GLCM), Gabor filter response, and opponent angle and hue channel color histograms as feature descriptors. For classification, either k-nearest neighbor (KNN), neural network (NN), support vector machine (SVM) or probability density weighted mean distance (PDWMD) is used. The combination of features and classifiers that attains the best results is presented together with the guidelines for selection. The accuracy and efficiency of our proposed method are compared with other state-of-the-art techniques using three benthic and three texture datasets. The proposed method achieves the highest overall classification accuracy of any of the tested methods and has moderate execution time. Finally, the proposed classification scheme is applied to a large-scale image mosaic of the Red Sea to create a completely classified thematic map of the reef benthos

Supervised localimage feature detection

This thesis is about detection of local image features. The research topic belongs to the wider area of object detection, which is a machine vision and pattern recognition problem where an object must be detected (located) in an image. State-of-the-art object detection methods often divide the problem into separate interest point detection and local image description steps, but in this thesis a different technique is used, leading to higher quality image features which enable more precise localization. Instead of using interest point detection the landmark positions are marked manually. Therefore, the quality of the image features is not limited by the interest point detection phase and the learning of image features is simplified. The approach combines both interest point detection and local description into one phase for detection. Computational efficiency of the descriptor is therefore important, leaving out many of the commonly used descriptors as unsuitably heavy. Multiresolution Gabor features has been the main descriptor in this thesis and improving their efficiency is a significant part. Actual image features are formed from descriptors by using a classifierwhich can then recognize similar looking patches in new images. The main classifier is based on Gaussian mixture models. Classifiers are used in one-class classifier configuration where there are only positive training samples without explicit background class. The local image feature detection method has been tested with two freely available face detection databases and a proprietary license plate database. The localization performance was very good in these experiments. Other applications applying the same under-lying techniques are also presented, including object categorization and fault detection.

Similarity measure based classification

Luokittelujärjestelmää suunniteltaessa tarkoituksena on rakentaa systeemi, joka pystyy ratkaisemaan mahdollisimman tarkasti tutkittavan ongelma-alueen. Hahmontunnistuksessa tunnistusjärjestelmän ydin on luokitin. Luokittelun sovellusaluekenttä on varsin laaja. Luokitinta tarvitaan mm. hahmontunnistusjärjestelmissä, joista kuvankäsittely toimii hyvänä esimerkkinä. Myös lääketieteen parissa tarkkaa luokittelua tarvitaan paljon. Esimerkiksi potilaan oireiden diagnosointiin tarvitaan luokitin, joka pystyy mittaustuloksista päättelemään mahdollisimman tarkasti, onko potilaalla kyseinen oire vai ei. Väitöskirjassa on tehty similaarisuusmittoihin perustuva luokitin ja sen toimintaa on tarkasteltu mm. lääketieteen paristatulevilla data-aineistoilla, joissa luokittelutehtävänä on tunnistaa potilaan oireen laatu. Väitöskirjassa esitetyn luokittimen etuna on sen yksinkertainen rakenne, josta johtuen se on helppo tehdä sekä ymmärtää. Toinen etu on luokittimentarkkuus. Luokitin saadaan luokittelemaan useita eri ongelmia hyvin tarkasti. Tämä on tärkeää varsinkin lääketieteen parissa, missä jo pieni tarkkuuden parannus luokittelutuloksessa on erittäin tärkeää. Väitöskirjassa ontutkittu useita eri mittoja, joilla voidaan mitata samankaltaisuutta. Mitoille löytyy myös useita parametreja, joille voidaan etsiä juuri kyseiseen luokitteluongelmaan sopivat arvot. Tämä parametrien optimointi ongelma-alueeseen sopivaksi voidaan suorittaa mm. evoluutionääri- algoritmeja käyttäen. Kyseisessä työssä tähän on käytetty geneettistä algoritmia ja differentiaali-evoluutioalgoritmia. Luokittimen etuna on sen joustavuus. Ongelma-alueelle on helppo vaihtaa similaarisuusmitta, jos kyseinen mitta ei ole sopiva tutkittavaan ongelma-alueeseen. Myös eri mittojen parametrien optimointi voi parantaa tuloksia huomattavasti. Kun käytetään eri esikäsittelymenetelmiä ennen luokittelua, tuloksia pystytään parantamaan.

Stratification of the severity of critically ill patients with classification trees

Background: Development of three classification trees (CT) based on the CART (Classification and Regression Trees), CHAID (Chi-Square Automatic Interaction Detection) and C4.5 methodologies for the calculation of probability of hospital mortality; the comparison of the results with the APACHE II, SAPS II and MPM II-24 scores, and with a model based on multiple logistic regression (LR). Methods: Retrospective study of 2864 patients. Random partition (70:30) into a Development Set (DS) n = 1808 and Validation Set (VS) n = 808. Their properties of discrimination are compared with the ROC curve (AUC CI 95%), Percent of correct classification (PCC CI 95%); and the calibration with the Calibration Curve and the Standardized Mortality Ratio (SMR CI 95%). Results: CTs are produced with a different selection of variables and decision rules: CART (5 variables and 8 decision rules), CHAID (7 variables and 15 rules) and C4.5 (6 variables and 10 rules). The common variables were: inotropic therapy, Glasgow, age, (A-a)O2 gradient and antecedent of chronic illness. In VS: all the models achieved acceptable discrimination with AUC above 0.7. CT: CART (0.75(0.71-0.81)), CHAID (0.76(0.72-0.79)) and C4.5 (0.76(0.73-0.80)). PCC: CART (72(69- 75)), CHAID (72(69-75)) and C4.5 (76(73-79)). Calibration (SMR) better in the CT: CART (1.04(0.95-1.31)), CHAID (1.06(0.97-1.15) and C4.5 (1.08(0.98-1.16)). Conclusion: With different methodologies of CTs, trees are generated with different selection of variables and decision rules. The CTs are easy to interpret, and they stratify the risk of hospital mortality. The CTs should be taken into account for the classification of the prognosis of critically ill patients.

Prediction of crude protein and classification of the growth stage of wheat plant samples from NIR spectra

Near-infrared spectroscopy (NIRS) was used to analyse the crude protein content of dried and milled samples of wheat and to discriminate samples according to their stage of growth. A calibration set of 72 samples from three growth stages of wheat (tillering, heading and harvest) and a validation set of 28 samples was collected for this purpose. Principal components analysis (PCA) of the calibration set discriminated groups of samples according to the growth stage of the wheat. Based on these differences, a classification procedure (SIMCA) showed a very accurate classification of the validation set samples : all of them were successfully classified in each group using this procedure when both the residual and the leverage were used in the classification criteria. Looking only at the residuals all the samples were also correctly classified except one of tillering stage that was assigned to both tillering and heading stages. Finally, the determination of the crude protein content of these samples was considered in two ways: building up a global model for all the growth stages, and building up local models for each stage, separately. The best prediction results for crude protein were obtained using a global model for samples in the two first growth stages (tillering and heading), and using a local model for the harvest stage samples.

Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c1,...cm modelling some concept C results as an output, such that every cluster ci is labelled as positive or negative. Given a new, unlabelled instance enew, the above classification is used to determine to which particular cluster ci this new instance belongs. In such a setting clusters can overlap, and a new unlabelled instance can be assigned to more than one cluster with conflicting labels. In the literature, such a case is usually solved non-deterministically by making a random choice. This paper presents a novel, hybrid approach to solve this situation by combining a neural network for classification along with a defeasible argumentation framework which models preference criteria for performing clustering.