Urban Detection From Hyperspectral Images Using Dimension-Reduction Model and Fusion of Multiple Segmentations Based on Stuctural and Textural Features

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales.

Trend detection in folksonomies

As the number of resources on the web exceeds by far the number of documents one can track, it becomes increasingly difficult to remain up to date on ones own areas of interest. The problem becomes more severe with the increasing fraction of multimedia data, from which it is difficult to extract some conceptual description of their contents. One way to overcome this problem are social bookmark tools, which are rapidly emerging on the web. In such systems, users are setting up lightweight conceptual structures called folksonomies, and overcome thus the knowledge acquisition bottleneck. As more and more people participate in the effort, the use of a common vocabulary becomes more and more stable. We present an approach for discovering topic-specific trends within folksonomies. It is based on a differential adaptation of the PageRank algorithm to the triadic hypergraph structure of a folksonomy. The approach allows for any kind of data, as it does not rely on the internal structure of the documents. In particular, this allows to consider different data types in the same analysis step. We run experiments on a large-scale real-world snapshot of a social bookmarking system.

A Trainable Object Detection System: Car Detection in Static Images

This paper describes a general, trainable architecture for object detection that has previously been applied to face and peoplesdetection with a new application to car detection in static images. Our technique is a learning based approach that uses a set of labeled training data from which an implicit model of an object class -- here, cars -- is learned. Instead of pixel representations that may be noisy and therefore not provide a compact representation for learning, our training images are transformed from pixel space to that of Haar wavelets that respond to local, oriented, multiscale intensity differences. These feature vectors are then used to train a support vector machine classifier. The detection of cars in images is an important step in applications such as traffic monitoring, driver assistance systems, and surveillance, among others. We show several examples of car detection on out-of-sample images and show an ROC curve that highlights the performance of our system.

Feature Selection for Face Detection

We present a new method to select features for a face detection system using Support Vector Machines (SVMs). In the first step we reduce the dimensionality of the input space by projecting the data into a subset of eigenvectors. The dimension of the subset is determined by a classification criterion based on minimizing a bound on the expected error probability of an SVM. In the second step we select features from the SVM feature space by removing those that have low contributions to the decision function of the SVM.

Serum proteomic abnormality predating screen detection of ovarian cancer

Ovarian cancer is characterized by vague, non-specific symptoms, advanced stage at diagnosis and poor overall survival. A nested case control study was undertaken on stored serial serum samples from women who developed ovarian cancer and healthy controls (matched for serum processing and storage conditions as well as attributes such as age) in a pilot randomized controlled trial of ovarian cancer screening. The unique feature of this study is that the women were screened for up to 7 years. The serum samples underwent prefractionation using a reversed-phase batch extraction protocol prior to MALDI-TOF MS data acquisition. Our exploratory analysis shows that combining a single MS peak with CA125 allows statistically significant discrimination at the 5% level between cases and controls up to 12 months in advance of the original diagnosis of ovarian cancer. Such combinations work much better than a single peak or CA125 alone. This paper demonstrates that mass spectra from the low molecular weight serum proteome carry information useful for early detection of ovarian cancer. The next step is to identify the specific biomarkers that make early detection possible.

Unsupervised genetic algorithm deployed for intrusion detection

This paper represents the first step in an on-going work for designing an unsupervised method based on genetic algorithm for intrusion detection. Its main role in a broader system is to notify of an unusual traffic and in that way provide the possibility of detecting unknown attacks. Most of the machine-learning techniques deployed for intrusion detection are supervised as these techniques are generally more accurate, but this implies the need of labeling the data for training and testing which is time-consuming and error-prone. Hence, our goal is to devise an anomaly detector which would be unsupervised, but at the same time robust and accurate. Genetic algorithms are robust and able to avoid getting stuck in local optima, unlike the rest of clustering techniques. The model is verified on KDD99 benchmark dataset, generating a solution competitive with the solutions of the state-of-the-art which demonstrates high possibilities of the proposed method.

A new algorithm for OFDM joint data detection and phase noise cancellation

This paper proposes a new iterative algorithm for OFDM joint data detection and phase noise (PHN) cancellation based on minimum mean square prediction error. We particularly highlight the problem of "overfitting" such that the iterative approach may converge to a trivial solution. Although it is essential for this joint approach, the overfitting problem was relatively less studied in existing algorithms. In this paper, specifically, we apply a hard decision procedure at every iterative step to overcome the overfitting. Moreover, compared with existing algorithms, a more accurate Pade approximation is used to represent the phase noise, and finally a more robust and compact fast process based on Givens rotation is proposed to reduce the complexity to a practical level. Numerical simulations are also given to verify the proposed algorithm.

OFDM joint data detection and phase noise cancellation based on minimum mean square prediction error

This paper proposes a new iterative algorithm for orthogonal frequency division multiplexing (OFDM) joint data detection and phase noise (PHN) cancellation based on minimum mean square prediction error. We particularly highlight the relatively less studied problem of "overfitting" such that the iterative approach may converge to a trivial solution. Specifically, we apply a hard-decision procedure at every iterative step to overcome the overfitting. Moreover, compared with existing algorithms, a more accurate Pade approximation is used to represent the PHN, and finally a more robust and compact fast process based on Givens rotation is proposed to reduce the complexity to a practical level. Numerical Simulations are also given to verify the proposed algorithm. (C) 2008 Elsevier B.V. All rights reserved.

An improved lesion detection approach based on similarity measurement between fuzzy intensity segmentation and spatial probability maps

The application of automatic segmentation methods in lesion detection is desirable. However, such methods are restricted by intensity similarities between lesioned and healthy brain tissue. Using multi-spectral magnetic resonance imaging (MRI) modalities may overcome this problem but it is not always practicable. In this article, a lesion detection approach requiring a single MRI modality is presented, which is an improved method based on a recent publication. This new method assumes that a low similarity should be found in the regions of lesions when the likeness between an intensity based fuzzy segmentation and a location based tissue probabilities is measured. The usage of a normalized similarity measurement enables the current method to fine-tune the threshold for lesion detection, thus maximizing the possibility of reaching high detection accuracy. Importantly, an extra cleaning step is included in the current approach which removes enlarged ventricles from detected lesions. The performance investigation using simulated lesions demonstrated that not only the majority of lesions were well detected but also normal tissues were identified effectively. Tests on images acquired in stroke patients further confirmed the strength of the method in lesion detection. When compared with the previous version, the current approach showed a higher sensitivity in detecting small lesions and had less false positives around the ventricle and the edge of the brain

One-step reverse transcriptase polymerase chain reaction for the diagnosis of respiratory syncytial virus in children

Human respiratory syncytial virus (HRSV) is the main cause of acute lower respiratory tract infections in infants and children. Rapid diagnosis is required to permit appropriate care and treatment and to avoid unnecessary antibiotic use. Reverse transcriptase (RT-PCR) and indirect immunofluorescence assay (IFA) methods have been considered important tools for virus detection due to their high sensitivity and specificity. In order to maximize use-simplicity and minimize the risk of sample cross-contamination inherent in two-step techniques, a RT-PCR method using only a single tube to detect HRSV in clinical samples was developed. Nasopharyngeal aspirates from 226 patients with acute respiratory illness, ranging from infants to 5 years old, were collected at the University Hospital of the University of Sao Paulo (HU-USP), and tested using IFA, one-step RT-PCR, and semi-nested RT-PCR. One hundred and two (45.1%) samples were positive by at least one of the three methods, and 75 (33.2%) were positive by all methods: 92 (40.7%) were positive by one-step RT-PCR, 84 (37.2%) by IFA, and 96 (42.5%) by the semi-nested RT-PCR technique. One-step RT-PCR was shown to be fast, sensitive, and specific for RSV diagnosis, without the added inconvenience and risk of false positive results associated with semi-nested PCR. The combined use of these two methods enhances HRSV detection. (C) 2007 Elsevier B.V. All rights reserved.

Detection of adulterations in processed coffee with cereals and coffee husks using capillary zone electrophoresis

The proposed method for the identification of adulteration was based on the controlled acid hydrolysis of xylan and starch present in some vegetable adulterants, followed by the analysis of the resulting xylose and glucose, which are the monosaccharides that compose, respectively, the two polysaccharides. The acid hydrolysis with HCl increases the ionic strength of the sample, which impairs the electrophoretic separation. Thus, a neutralization step based on anion exchange resin was necessary. The best separations were obtained in NaOH 80 mmol/L, CTAB 0.5 mmol/L, and methanol 30% v/v. Because of the high value of pH, monosaccharides are separated as anionic species in such running electrolyte. The LOQ for both monosaccharides was 0.2 g for 100 g of dry matter, which conforms to the tolerable limits.

Simultaneous voltammetric detection of ascorbic acid, dopamine and uric acid using a pyrolytic graphite electrode modified into dopamine solution

Pyrolytic graphite electrodes (PGE) were modified into dopamine solutions using phosphate buffer solutions, pH 10 and 6.5, as supporting electrolyte. The modification process involved a previous anodization of the working electrode at +1. 5 V into 0. 1 mol-L-1 NaOH followed by other anodization step, in the same experimental conditions, into dopamine (DA) solutions. pH of the supporting electrolyte performed an important role in the production of a superficial melanin polymeric film, which permitted the simultaneous detection of ascorbic acid (AA), (DA) and uric acid (UA), Delta EAA-DA = 222 mV-, Delta EAA-UA = 360 mV and Delta EDA-UA=138mV, avoiding the superficial poisoning effects. The calculated detection limits were: 1.4 x 10(-6) mol L-1 for uric acid, 1.3x10-(5) molL(-1) for ascorbic acid and 1.1 X 10(-7) mol L-1 for dopamine, with sensitivities of (7.7 +/- 0.5), (0.061 +/- 0.001) and (9.5 +/- 0.05)A mol(-1) cm(-2), respectively, with no mutual interference. Uric acid was determined in urine, blood and serum human samples after dilution in phosphate buffer and no additional sample pre-treatment was necessary. The concentration of uric acid in urine was higher than the values found in blood and serum and the recovery tests (92-102%) indicated that no matrix effects were observed. (C) 2008 Elsevier B.V. All rights reserved.

Rapid and direct determination of glyphosate and aminomethylphosphonic acid in water using anion-exchange chromatography with coulometric detection

A simple, rapid, and low-cost coulometric method for direct detection of glyphosate and aminomethylphosphonic acid (AMPA) in water samples using anion-exchange chromatography and coulometric detection with copper electrode is presented. Under optimized conditions, the limits of detection (LODs) (S/N = 3) were 0.038 mu g ml(-1) for glyphosate and 0.24 mu g ml(-1) for AMPA, without any preconcentration method. The calibration curves were linear and presented an excellent correlation coefficient. The method was successfully applied to the determination of glyphosate and AMPA in water samples without any kind of extraction, clean-up, or preconcentration step. No interferent was found in the water, like this, the recovery was, practically, 100%. (c) 2008 Elsevier B.V. All rights reserved.

Sensitivity evaluation of a single-step PCR assay using Ehrlichia canis p28 gene as a target and its application in diagnosis of canine ehrlichiosis

O objetivo deste estudo foi aperfeiçoar um ensaio de PCR que amplificasse um fragmento de 843 pares de bases do gene p28 da Ehrlichia canis e compará-lo com outros dois métodos de PCR utilizados para amplificar partes do gene 16S rRNA e dsb do gênero Ehrlichia. Amostras sanguíneas foram colhidas de cães com diagnóstico clínico de erliquiose. A amplificação do gene p28 pela PCR produziu um fragmento de 843pb e esse ensaio permitiu a detecção do DNA de um parasita dentre 1 bilhão de células. Todas as amostras positivas detectadas pela PCR baseada no gene p28 foram também positivas pela nested PCR para detecção do gene 16S rRNA e também pela PCR dsb. Dentre as amostras negativas para a PCR p28, 55,3% foram co-negativas, mas 27,6% foram positivas pela PCR baseada nos genes 16S rRNA e dsb. A PCR p28 parece ser um teste útil para detecção molecular de E. canis, entretanto otimizações na sensibilidade nesta PCR são necessárias, para que esta técnica se torne uma importante alternativa no diagnóstico da erliquiose canina.