Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

Sistema de localização indoor com base no protocolo ZIGBEE

Actualmente, os sistemas de localização são uma área em forte expansão sendo que para espaços exteriores existe uma grande variedade de sistemas de localização enquanto que para espaços interiores as soluções são mais escassas. Este trabalho apresenta o estudo e implementação de um sistema de localização indoor baseado no protocolo ZigBee, utilizando a informação da intensidade de sinal recebido (RSSI - Received Signal Strength Indication). Para a realização deste projecto foi necessário iniciar uma pesquisa mais pormenorizada do protocolo ZigBee. O dispositivo móvel a ser localizado é o módulo XBee Serie 2 que se baseia no mesmo protocolo. Posto isto, foi necessário efectuar um estudo sobre sistemas de localização existentes e analisar as técnicas de localização utilizadas para ambientes interiores. Desta forma utiliza-se neste projecto uma técnica que consiste na análise de fingerprinting, onde é criado um mapa com os valores RSSI para diferentes coordenadas do espaço físico. As intensidades de sinal recebido são relativas a dispositivos XBee instalados em pontos fixos de referência. Para calcular a localização do dispositivo móvel é utilizado o algoritmo K-NN (K- Nearest Neighbors) que permite estimar a posição aproximada do dispositivo móvel. Por último é descrito todo o desenvolvimento do projecto assim como a apresentação e discussão de resultados.

Automated image tagging through tag propagation

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial Para obtenção do grau de Mestre em Engenharia Informática

Improvements on the KNN classifier

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Análise comparada da classificação “pixel a pixel” e orientada por objecto de uma imagem WorldView 2 de Maputo, Moçambique

O desenvolvimento das tecnologias associadas à Detecção Remota e aos Sistemas de Informação Geográfica encontram-se cada vez mais na ordem do dia. E, graças a este desenvolvimento de métodos para acelerar a produção de informação geográfica, assiste-se a um crescente aumento da resolução geométrica, espectral e radiométrica das imagens, e simultaneamente, ao aparecimento de novas aplicações com o intuito de facilitar o processamento e a análise de imagens através da melhoria de algoritmos para extracção de informação. Resultado disso são as imagens de alta resolução, provenientes do satélite WorldView 2 e o mais recente software Envi 5.0, utilizados neste estudo. O presente trabalho tem como principal objectivo desenvolver um projecto de cartografia de uso do solo para a cidade de Maputo, com recurso ao tratamento e à exploração de uma imagem de alta resolução, comparando as potencialidades e limitações dos resultados extraídos através da classificação “pixel a pixel”, através do algoritmo Máxima Verossimilhança, face às potencialidades e eventuais limitações da classificação orientada por objecto, através dos algoritmos K Nearest Neighbor (KNN) e Support Vector Machine (SVM), na extracção do mesmo número e tipo de classes de ocupação/uso do solo. Na classificação “pixel a pixel”, com a aplicação do algoritmo classificação Máxima Verosimilhança, foram ensaiados dois tipos de amostra: uma primeira constituída por 20 classes de ocupação/uso do solo, e uma segunda por 18 classes. Após a fase de experimentação, os resultados obtidos com a primeira amostra ficaram aquém das espectativas, pois observavam-se muitos erros de classificação. A segunda amostra formulada com base nestes erros de classificação e com o objectivo de os minimizar, permitiu obter um resultado próximo das espectativas idealizadas inicialmente, onde as classes de interesse coincidem com a realidade geográfica da cidade de Maputo. Na classificação orientada por objecto foram 4 as etapas metodológicas utilizadas: a atribuição do valor 5 para a segmentação e 90 para a fusão de segmentos; a selecção de 15 exemplos sobre os segmentos gerados para cada classe de interesse; bandas diferentemente distribuídas para o cálculo dos atributos espectrais e de textura; os atributos de forma Elongation e Form Factor e a aplicação dos algoritmos KNN e SVM. Confrontando as imagens resultantes das duas abordagens aplicadas, verificou-se que a qualidade do mapa produzido pela classificação “pixel a pixel” apresenta um nível de detalhe superior aos mapas resultantes da classificação orientada por objecto. Esta diferença de nível de detalhe é justificada pela unidade mínima do processamento de cada classificador: enquanto que na primeira abordagem a unidade mínima é o pixel, traduzinho uma maior detalhe, a segunda abordagem utiliza um conjunto de pixels, objecto, como unidade mínima despoletando situações de generalização. De um modo geral, a extracção da forma dos elementos e a distribuição das classes de interesse correspondem à realidade geográfica em si e, os resultados são bons face ao que é frequente em processamento semiautomático.

Discrimination of Brazilian propolis according to the seasoning using chemometrics and machine learning based on UV-Vis scanning data

Propolis is a chemically complex biomass produced by honeybees (Apis mellifera) from plant resins added of salivary enzymes, beeswax, and pollen. The biological activities described for propolis were also identified for donor plants resin, but a big challenge for the standardization of the chemical composition and biological effects of propolis remains on a better understanding of the influence of seasonality on the chemical constituents of that raw material. Since propolis quality depends, among other variables, on the local flora which is strongly influenced by (a)biotic factors over the seasons, to unravel the harvest season effect on the propolis chemical profile is an issue of recognized importance. For that, fast, cheap, and robust analytical techniques seem to be the best choice for large scale quality control processes in the most demanding markets, e.g., human health applications. For that, UV-Visible (UV-Vis) scanning spectrophotometry of hydroalcoholic extracts (HE) of seventy-three propolis samples, collected over the seasons in 2014 (summer, spring, autumn, and winter) and 2015 (summer and autumn) in Southern Brazil was adopted. Further machine learning and chemometrics techniques were applied to the UV-Vis dataset aiming to gain insights as to the seasonality effect on the claimed chemical heterogeneity of propolis samples determined by changes in the flora of the geographic region under study. Descriptive and classification models were built following a chemometric approach, i.e. principal component analysis (PCA) and hierarchical clustering analysis (HCA) supported by scripts written in the R language. The UV-Vis profiles associated with chemometric analysis allowed identifying a typical pattern in propolis samples collected in the summer. Importantly, the discrimination based on PCA could be improved by using the dataset of the fingerprint region of phenolic compounds ( = 280-400m), suggesting that besides the biological activities of those secondary metabolites, they also play a relevant role for the discrimination and classification of that complex matrix through bioinformatics tools. Finally, a series of machine learning approaches, e.g., partial least square-discriminant analysis (PLS-DA), k-Nearest Neighbors (kNN), and Decision Trees showed to be complementary to PCA and HCA, allowing to obtain relevant information as to the sample discrimination.

Efficient knowledge retrieval to calibrate input variables in forest fire prediction

Forest fires are a serious threat to humans and nature from an ecological, social and economic point of view. Predicting their behaviour by simulation still delivers unreliable results and remains a challenging task. Latest approaches try to calibrate input variables, often tainted with imprecision, using optimisation techniques like Genetic Algorithms. To converge faster towards fitter solutions, the GA is guided with knowledge obtained from historical or synthetical fires. We developed a robust and efficient knowledge storage and retrieval method. Nearest neighbour search is applied to find the fire configuration from knowledge base most similar to the current configuration. Therefore, a distance measure was elaborated and implemented in several ways. Experiments show the performance of the different implementations regarding occupied storage and retrieval time with overly satisfactory results.

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Aplicació de visió per dispositius mòbils

En aquest projecte es presenta l’aplicació per a dispositius mòbils Doppelganger. La seva funció és, a partir d’una fotografia, detectar la cara i mostrar la persona famosa de la nostra base de dades que més s’assembla a la persona en la fotografia. Per la implementació s’han utilitzat algoritmes de visió per computador i d’aprenentatge automàtic com per exemple el PCA i el K-Nearest Neighbor, tot utilitzant llibreries gratuïtes com són les OpenCV.

Detection of millimetric deformation using a terrestrial laser scanner: experiment and application to a rockfall event

Abstract. Terrestrial laser scanning (TLS) is one of the most promising surveying techniques for rockslope characteriza- tion and monitoring. Landslide and rockfall movements can be detected by means of comparison of sequential scans. One of the most pressing challenges of natural hazards is com- bined temporal and spatial prediction of rockfall. An outdoor experiment was performed to ascertain whether the TLS in- strumental error is small enough to enable detection of pre- cursory displacements of millimetric magnitude. This con- sists of a known displacement of three objects relative to a stable surface. Results show that millimetric changes cannot be detected by the analysis of the unprocessed datasets. Dis- placement measurement are improved considerably by ap- plying Nearest Neighbour (NN) averaging, which reduces the error (1σ ) up to a factor of 6. This technique was ap- plied to displacements prior to the April 2007 rockfall event at Castellfollit de la Roca, Spain. The maximum precursory displacement measured was 45 mm, approximately 2.5 times the standard deviation of the model comparison, hampering the distinction between actual displacement and instrumen- tal error using conventional methodologies. Encouragingly, the precursory displacement was clearly detected by apply- ing the NN averaging method. These results show that mil- limetric displacements prior to failure can be detected using TLS.

Profiling of counterfeit medicines by vibrational spectroscopy

Counterfeit pharmaceutical products have become a widespread problem in the last decade. Various analytical techniques have been applied to discriminate between genuine and counterfeit products. Among these, Near-infrared (NIR) and Raman spectroscopy provided promising results.The present study offers a methodology allowing to provide more valuable information fororganisations engaged in the fight against counterfeiting of medicines.A database was established by analyzing counterfeits of a particular pharmaceutical product using Near-infrared (NIR) and Raman spectroscopy. Unsupervised chemometric techniques (i.e. principal component analysis - PCA and hierarchical cluster analysis - HCA) were implemented to identify the classes within the datasets. Gas Chromatography coupled to Mass Spectrometry (GC-MS) and Fourier Transform Infrared Spectroscopy (FT-IR) were used to determine the number of different chemical profiles within the counterfeits. A comparison with the classes established by NIR and Raman spectroscopy allowed to evaluate the discriminating power provided by these techniques. Supervised classifiers (i.e. k-Nearest Neighbors, Partial Least Squares Discriminant Analysis, Probabilistic Neural Networks and Counterpropagation Artificial Neural Networks) were applied on the acquired NIR and Raman spectra and the results were compared to the ones provided by the unsupervised classifiers.The retained strategy for routine applications, founded on the classes identified by NIR and Raman spectroscopy, uses a classification algorithm based on distance measures and Receiver Operating Characteristics (ROC) curves. The model is able to compare the spectrum of a new counterfeit with that of previously analyzed products and to determine if a new specimen belongs to one of the existing classes, consequently allowing to establish a link with other counterfeits of the database.

Batch effect confounding leads to strong bias in performance estimates obtained by cross-validation.

BACKGROUND: With the large amount of biological data that is currently publicly available, many investigators combine multiple data sets to increase the sample size and potentially also the power of their analyses. However, technical differences ("batch effects") as well as differences in sample composition between the data sets may significantly affect the ability to draw generalizable conclusions from such studies. FOCUS: The current study focuses on the construction of classifiers, and the use of cross-validation to estimate their performance. In particular, we investigate the impact of batch effects and differences in sample composition between batches on the accuracy of the classification performance estimate obtained via cross-validation. The focus on estimation bias is a main difference compared to previous studies, which have mostly focused on the predictive performance and how it relates to the presence of batch effects. DATA: We work on simulated data sets. To have realistic intensity distributions, we use real gene expression data as the basis for our simulation. Random samples from this expression matrix are selected and assigned to group 1 (e.g., 'control') or group 2 (e.g., 'treated'). We introduce batch effects and select some features to be differentially expressed between the two groups. We consider several scenarios for our study, most importantly different levels of confounding between groups and batch effects. METHODS: We focus on well-known classifiers: logistic regression, Support Vector Machines (SVM), k-nearest neighbors (kNN) and Random Forests (RF). Feature selection is performed with the Wilcoxon test or the lasso. Parameter tuning and feature selection, as well as the estimation of the prediction performance of each classifier, is performed within a nested cross-validation scheme. The estimated classification performance is then compared to what is obtained when applying the classifier to independent data.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Automatic Mapping and Classification of Spatial Environmental Data

The paper deals with the development and application of the generic methodology for automatic processing (mapping and classification) of environmental data. General Regression Neural Network (GRNN) is considered in detail and is proposed as an efficient tool to solve the problem of spatial data mapping (regression). The Probabilistic Neural Network (PNN) is considered as an automatic tool for spatial classifications. The automatic tuning of isotropic and anisotropic GRNN/PNN models using cross-validation procedure is presented. Results are compared with the k-Nearest-Neighbours (k-NN) interpolation algorithm using independent validation data set. Real case studies are based on decision-oriented mapping and classification of radioactively contaminated territories.

Pedotransfer functions to predict water retention for soils of the humid tropics: a review

Over the past three decades, pedotransfer functions (PTFs) have been widely used by soil scientists to estimate soils properties in temperate regions in response to the lack of soil data for these regions. Several authors indicated that little effort has been dedicated to the prediction of soil properties in the humid tropics, where the need for soil property information is of even greater priority. The aim of this paper is to provide an up-to-date repository of past and recently published articles as well as papers from proceedings of events dealing with water-retention PTFs for soils of the humid tropics. Of the 35 publications found in the literature on PTFs for prediction of water retention of soils of the humid tropics, 91 % of the PTFs are based on an empirical approach, and only 9 % are based on a semi-physical approach. Of the empirical PTFs, 97 % are continuous, and 3 % (one) is a class PTF; of the empirical PTFs, 97 % are based on multiple linear and polynomial regression of n th order techniques, and 3 % (one) is based on the k-Nearest Neighbor approach; 84 % of the continuous PTFs are point-based, and 16 % are parameter-based; 97 % of the continuous PTFs are equation-based PTFs, and 3 % (one) is based on pattern recognition. Additionally, it was found that 26 % of the tropical water-retention PTFs were developed for soils in Brazil, 26 % for soils in India, 11 % for soils in other countries in America, and 11 % for soils in other countries in Africa.