Literatura académica sobre el tema "KNN classification"

Dissertação para obtenção do Grau de Mestre em Engenharia Informática<br>The object classification is an important area within the artificial intelligence and its application extends to various areas, whether or not in the branch of science. Among the other classifiers, the K-nearest neighbor (KNN) is among the most simple and accurate especially in environments where the data distribution is unknown or apparently not parameterizable. This algorithm assigns the classifying element the major class in the K nearest neighbors. According to the original algorithm, this classification implies the calculation of the distances between the classifying instance and each one of the training objects. If on the one hand, having an extensive training set is an element of importance in order to obtain a high accuracy, on the other hand, it makes the classification of each object slower due to its lazy-learning algorithm nature. Indeed, this algorithm does not provide any means of storing information about the previous calculated classifications,making the calculation of the classification of two equal instances mandatory. In a way, it may be said that this classifier does not learn. This dissertation focuses on the lazy-learning fragility and intends to propose a solution that transforms the KNNinto an eager-learning classifier. In other words, it is intended that the algorithm learns effectively with the training set, thus avoiding redundant calculations. In the context of the proposed change in the algorithm, it is important to highlight the attributes that most characterize the objects according to their discriminating power. In this framework, there will be a study regarding the implementation of these transformations on data of different types: continuous and/or categorical.

Throughout the 1990s ADHD diagnosis and medication rates have increased rapidly, and this trend continues today. These sharp increases have been met with both public and clinical criticism, detractors stating over-diagnosis is a problem and healthy children are being unnecessarily medicated and labeled as disabled. However, others say that ADHD is being under-diagnosed in some populations. Critics often state that there are multiple factors that introduce subjectivity into the diagnosis process, meaning that a final diagnosis may be influenced by more than the desire to protect a patient's wellbeing. Some of these factors include standardized testing, legislation affecting special education funding, and the diagnostic process. In an effort to circumvent these extraneous factors, this work aims to further develop a potential method of using EEG signals to accurately discriminate between ADHD and non-ADHD children using features that capture spectral and perhaps temporal information from evoked EEG signals. KNN has been shown in prior research to be an effective tool in discriminating between ADHD and non-ADHD, therefore several different KNN models are created using features derived in a variety of fashions. One takes into account the heterogeneity of ADHD, and another one seeks to exploit differences in executive functioning of ADHD and non-ADHD subjects. The results of this classification method vary widely depending on the sample used to train and test the KNN model. With unfiltered Dataset 1 data over the entire ANT1 period, the most accurate EEG channel pair achieved an overall vector classification accuracy of 94%, and the 5th percentile of classification confidence was 80%. These metrics suggest that using KNN of EEG signals taken during the ANT task would be a useful diagnosis tool. However, the most accurate channel pair for unfiltered Dataset 2 data achieved an overall accuracy of 65% and a 5th percentile of classification confidence of 17%. The same method that worked so well for Dataset 1 did not work well for Dataset 2, and no conclusive reason for this difference was identified, although several methods to remove possible sources of noise were used. Using target time linked intervals did appear to marginally improve results in both Dataset 1 and Dataset 2. However, the changes in accuracy of intervals relative to target presentation vary between Dataset 1 and Dataset 2. Separating subjects into heterogeneity classes does appear to result in good (up to 83%) classification accuracy for some classes, but results are poor (about 50%) for other heterogeneity classes. A much larger data set is necessary to determine whether or not the very positive results found with Dataset 1 extend to a wide population.<br>Master of Science

La classification des images est aujourd'hui un défi d'une grande ampleur puisque ça concerne d'un côté les millions voir des milliards d'images qui se trouvent partout sur le web et d'autre part des images pour des applications temps réel critiques. Cette classification fait appel en général à des méthodes d'apprentissage et à des classifieurs qui doivent répondre à la fois à la précision ainsi qu'à la rapidité. Ces problèmes d'apprentissage touchent aujourd'hui un grand nombre de domaines d'applications: à savoir, le web (profiling, ciblage, réseaux sociaux, moteurs de recherche), les "Big Data" et bien évidemment la vision par ordinateur tel que la reconnaissance d'objets et la classification des images. La présente thèse se situe dans cette dernière catégorie et présente des algorithmes d'apprentissage supervisé basés sur la minimisation de fonctions de perte (erreur) dites "calibrées" pour deux types de classifieurs: k-Plus Proches voisins (kNN) et classifieurs linéaires. Ces méthodes d'apprentissage ont été testées sur de grandes bases d'images et appliquées par la suite à des images biomédicales. Ainsi, cette thèse reformule dans une première étape un algorithme de Boosting des kNN et présente ensuite une deuxième méthode d'apprentissage de ces classifieurs NN mais avec une approche de descente de Newton pour une convergence plus rapide. Dans une seconde partie, cette thèse introduit un nouvel algorithme d'apprentissage par descente stochastique de Newton pour les classifieurs linéaires connus pour leur simplicité et leur rapidité de calcul. Enfin, ces trois méthodes ont été utilisées dans une application médicale qui concerne la classification de cellules en biologie et en pathologie.

As of 2016, diagnosis of ADHD in the US is controversial. Diagnosis of ADHD is based on subjective observations, and treatment is usually done through stimulants, which can have negative side-effects in the long term. Evidence shows that the probability of diagnosing a child with ADHD not only depends on the observations of parents, teachers, and behavioral scientists, but also on state-level special education policies. In light of these facts, unbiased, quantitative methods are needed for the diagnosis of ADHD. This problem has been tackled since the 1990s, and has resulted in methods that have not made it past the research stage and methods for which claimed performance could not be reproduced. This work proposes a combination of machine learning algorithms and signal processing techniques applied to EEG data in order to classify subjects with and without ADHD with high accuracy and confidence. More specifically, the K-nearest Neighbor algorithm and Gaussian-Mixture-Model-based Universal Background Models (GMM-UBM), along with autoregressive (AR) model features, are investigated and evaluated for the classification problem at hand. In this effort, classical KNN and GMM-UBM were also modified in order to account for uncertainty in diagnoses. Some of the major findings reported in this work include classification performance as high, if not higher, than those of the highest performing algorithms found in the literature. One of the major findings reported here is that activities that require attention help the discrimination of ADHD and Non-ADHD subjects. Mixing in EEG data from periods of rest or during eyes closed leads to loss of classification performance, to the point of approximating guessing when only resting EEG data is used.<br>Master of Science

There is a significant need to identify approaches for classifying chemical sensor array data with high success rates that would enhance sensor detection capabilities. The present study attempts to fill this need by investigating six machine learning methods to classify a dataset collected using a chemical sensor array: K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Classification and Regression Trees (CART), Random Forest (RF), Naïve Bayes Classifier (NB), and Principal Component Regression (PCR). A total of 10 predictors that are associated with the response from 10 sensor channels are used to train and test the classifiers. A training dataset of 4 classes containing 136 samples is used to build the classifiers, and a dataset of 4 classes with 56 samples is used for testing. The results generated with the six different methods are compared and discussed. The RF, CART, and KNN are found to have success rates greater than 90%, and to outperform the other methods.

La définition d'une métrique entre des séries temporelles est un élément important pour de nombreuses tâches en analyse ou en fouille de données, tel que le clustering, la classification ou la prédiction. Les séries temporelles présentent naturellement différentes caractéristiques, que nous appelons modalités, sur lesquelles elles peuvent être comparées, comme leurs valeurs, leurs formes ou leurs contenus fréquentielles. Ces caractéristiques peuvent être exprimées avec des délais variables et à différentes granularités ou localisations temporelles - exprimées globalement ou localement. Combiner plusieurs modalités à plusieurs échelles pour apprendre une métrique adaptée est un challenge clé pour de nombreuses applications réelles impliquant des données temporelles. Cette thèse propose une approche pour l'Apprentissage d'une Métrique Multi-modal et Multi-scale (M2TML) en vue d'une classification robuste par plus proches voisins. La solution est basée sur la projection des paires de séries temporelles dans un espace de dissimilarités, dans lequel un processus d'optimisation à vaste marge est opéré pour apprendre la métrique. La solution M2TML est proposée à la fois dans le contexte linéaire et non-linéaire, et est étudiée pour différents types de régularisation. Une variante parcimonieuse et interprétable de la solution montre le potentiel de la métrique temporelle apprise à pouvoir localiser finement les modalités discriminantes, ainsi que leurs échelles temporelles en vue de la tâche d'analyse considérée. L'approche est testée sur un vaste nombre de 30 bases de données publiques et challenging, couvrant des images, traces, données ECG, qui sont linéairement ou non-linéairement séparables. Les expériences montrent l'efficacité et le potentiel de la méthode M2TML pour la classification de séries temporelles par plus proches voisins<br>The definition of a metric between time series is inherent to several data analysis and mining tasks, including clustering, classification or forecasting. Time series data present naturally several characteristics, called modalities, covering their amplitude, behavior or frequential spectrum, that may be expressed with varying delays and at different temporal granularity and localization - exhibited globally or locally. Combining several modalities at multiple temporal scales to learn a holistic metric is a key challenge for many real temporal data applications. This PhD proposes a Multi-modal and Multi-scale Temporal Metric Learning (M2TML) approach for robust time series nearest neighbors classification. The solution is based on the embedding of pairs of time series into a pairwise dissimilarity space, in which a large margin optimization process is performed to learn the metric. The M2TML solution is proposed for both linear and non linear contexts, and is studied for different regularizers. A sparse and interpretable variant of the solution shows the ability of the learned temporal metric to localize accurately discriminative modalities as well as their temporal scales.A wide range of 30 public and challenging datasets, encompassing images, traces and ECG data, that are linearly or non linearly separable, are used to show the efficiency and the potential of M2TML for time series nearest neighbors classification

En esta tesis doctoral seha desarrollado el cálculo de la fiabilidad de clasificación y de la fiabilidad de predicción utilizando el método de los k-vecinos más cercanos (k-nearest neighbours, kNN) y estrategias de remuestreo basadas en bootstrap. Se han desarrollado, además, dos nuevos métodos de clasificación:Probabilistic Bootstrapk-Nearest Neighbours (PBkNN) y Bagged k-Nearest Neighbours (BaggedkNN),yun nuevo método de predicción,el Direct OrthogonalizationkNN (DOkNN).En todos los casos, los resultados obtenidos con los nuevos métodos han sido comparables o mejores que los obtenidos utilizando métodos clásicos de clasificación y calibración multivariante.<br>En aquesta tesi doctoral s'ha desenvolupat el càlcul de la fiabilitat de classificació i de la fiabilitat de predicció utilitzant el mètode dels k-veïns més propers (k-nearest neighbours, kNN) i estratègies de remostreig basades en bootstrap. S'han desenvolupat, a més, dos nous mètodes de classificació: Probabilistic Bootstrap k-Nearest Neighbours (PBkNN) i Bagged k-Nearest Neighbours (Bagged kNN), i un nou mètode de predicció, el Direct OrthogonalizationkNN (DOkNN). En tots els casos, els resultats obtinguts amb els nous mètodes han estat comparables o millors que els obtinguts utilitzant mètodes clàssics de classificació i calibratge multivariant.

Among the various remote sensing methods that can be used to map forest areas, the K Nearest Neighbor (KNN) supervised classification method is becoming increasingly popular for creating forest inventories in some countries. In this study, the utility of the KNN algorithm is evaluated for forest/non-forest/water stratification. Antalya is selected as the study area. The data used are composed of Landsat TM and Landsat ETM satellite images, acquired in 1987 and 2002, respectively, SRTM 90 meters digital elevation model (DEM) and land use data from the year 2003. The accuracies of different modifications of the KNN algorithm are evaluated using Leave One Out, which is a special case of K-fold cross-validation, and traditional accuracy assessment using error matrices. The best parameters are found to be Euclidean distance metric, inverse distance weighting, and k equal to 14, while using bands 4, 3 and 2. With these parameters, the cross-validation error is 0.009174, and the overall accuracy is around 86%. The results are compared with those from the Maximum Likelihood algorithm. KNN results are found to be accurate enough for practical applicability of this method for mapping forest areas.

This study evaluated the ability of segment-based classification paired with non-parametric methods (CART and kNN) to classify a chronosequence of Landsat TM/ETM+ imagery spanning from 1992 to 2002 within the state of Rondônia, Brazil. Pixel-based classification was also implemented for comparison. Interannual multitemporal composites were used in each classification in an attempt to increase the separation of primary forest, cleared, and re-vegetated classes within a given year. The kNN and CART classification methods, with the integration of multitemporal data, performed equally well with overall accuracies ranging from 77% to 91%. Pixel-based CART classification, although not different in terms of mean or median overall accuracy, did have significantly lower variability than all other techniques (3.2% vs. an average of 13.2%), and thus provided more consistent results. Segmentation did not improve classification success over pixel-based methods and was therefore an unnecessary processing step with the used dataset. Through the appropriate band selection methods of the respective non-parametric classifiers, multitemporal bands were chosen in 38 of the 44 total classifications, strongly suggesting the utility of interannual multitemporal data for the separation of cleared, re-vegetated, and primary forest classes. The separation of the primary forest class from the cleared and re-vegetated classes was particularly successful and may be a possible result of the incorporation of multitemporal data. The land cover maps from this study allow for an accurate annualized analysis of land cover and can be coupled with household data to gain a better understanding of landscape change in the region.<br>Master of Science

Este trabalho propõe uma alternativa para o problema de classificação de espécies de abelhas a partir da implementação de um algoritmo com base na Morfométria Geométrica e estudo das Formas dos marcos anatômicos das imagens obtidas pelas asas das abelhas. O algoritmo implementado para este propósito se baseia no algoritmo dos k-Vizinho mais Próximos (do inglês, kNN) e na Lógica Fuzzy kNN (Fuzzy k-Nearest Neighbor) aplicados a dados analisados e selecionados de pontos bidimensionais referentes as características geradas por marcos anatômicos. O estudo apresentado envolve métodos de seleção e ordenação de marcos anatômicos para a utilização no algoritmo por meio da implementação de um método matemático que utiliza o calculo dos marcos anatômicos mais significativos (que são representados por marcos matemáticos) e a formulação da Ordem de Significância onde cada elemento representa variáveis de entrada para a Fuzzy kNN. O conhecimento envolvido neste trabalho inclui uma perspectiva sobre a seleção de características não supervisionada como agrupamentos e mineração de dados, analise de pré-processamento dos dados, abordagens estatísticas para estimação e predição, estudo da Forma, Analise de Procrustes e Morfométria Geométrica sobre os dados e o tópico principal que envolve uma modificação do algoritmo dos k- Vizinhos mais Próximos e a aplicação da Fuzzy kNN para o problema. Os resultados mostram que a classificação entre amostras de abelhas no seu próprio grupo apresentam acuracia de 90%, dependendo da espécie. As classificações realizadas entre as espécies de abelhas alcançaram acuracia de 97%.<br>This work presents a proposal to solve the bees classification problem by implementing an algorithm based on Geometrics Morphometrics and the Shape analysis of landmarks generated from bees wings images. The algorithm is based on the K-Nearest Neighbor (K-Nearest Neighbor) algorithm and Fuzzy Logic KNN applied to the analysis and selection of two-dimensional data points relating to landmarks. This work is part of the Architecture Reference Model for Automatic identification and Taxonomic Classification System of Stingless Bee using the Wing Morphometry. The study includes selection and ordering methods for landmarks used in the algorithm by developing a mathematical model to represent the significance order, generating the most significant mathematical landmarks as input variables for Fuzzy Logic kNN. The main objective of this work is to develop a classification system for bee species. The knowledge involved in the development of this work include an overview of feature selection, unsupervised clustering and data mining, analysis of data pre-processing, statistical approaches for estimation and prediction, study of Shape, Procrustes Analysis on data that comes from Geometric Morphometry and the modification of the k-Nearest Neighbors algorithm and the Fuzzy Logic kNN. The results show that the classification in bee samples of the same species presents a accuracy above 90%, depending on the specie in analysis. The classification done between the bees species reach accuracies of 97%.