Search results for "Mach"
showing 10 items of 3360 documents
Active Learning for Monitoring Network Optimization
2012
Kernel-based active learning strategies were studied for the optimization of environmental monitoring networks. This chapter introduces the basic machine learning algorithms originated in the statistical learning theory of Vapnik (1998). Active learning is closer to an optimization done using sequential Gaussian simulations. The chapter presents the general ideas of statistical learning from data. It derives the basics of kernel-based support vector algorithms. The active learning framework is presented and machine learning extensions for active learning are described in the chapter. Kernel-based active learning strategies are tested on real case studies. The chapter explores the use of a c…
Remote sensing image segmentation by active queries
2012
Active learning deals with developing methods that select examples that may express data characteristics in a compact way. For remote sensing image segmentation, the selected samples are the most informative pixels in the image so that classifiers trained with reduced active datasets become faster and more robust. Strategies for intelligent sampling have been proposed with model-based heuristics aiming at the search of the most informative pixels to optimize model's performance. Unlike standard methods that concentrate on model optimization, here we propose a method inspired in the cluster assumption that holds in most of the remote sensing data. Starting from a complete hierarchical descri…
Discovering single classes in remote sensing images with active learning
2012
When dealing with supervised target detection, the acquisition of labeled samples is one of the most critical phases: the samples must be yet representative of the class of interest, but must also be found among a vast majority of non-target examples. Moreover, the efficiency of the search is also an issue, since the samples labeled as background are not used by target detectors such as the support vector data description (SVDD). In this work we propose a competitive and effective approach to identify the most relevant training samples for one-class classification based on the use of an active learning strategy. The SVDD classifier is first trained with insufficient target examples. It is t…
Improving active learning methods using spatial information
2011
Active learning process represents an interesting solution to the problem of training sample collection for the classification of remote sensing images. In this work, we propose a criterion based on the spatial information that can be used in combination with a spectral criterion in order to improve the selection of training samples. Experimental results obtained on a very high resolution image show the effectiveness of regularization in spatial domain and open challenging perspectives for terrain campaigns planning. © 2011 IEEE.
A context-aware approach for long-term behavioural change detection and abnormality prediction in ambient assisted living
2015
This research aims to describe pattern recognition models for detecting behavioural and health-related changes in a patient who is monitored continuously in an assisted living environment. The early anticipation of anomalies can improve the rate of disease prevention. Here we present different learning techniques for predicting abnormalities and behavioural trends in various user contexts. In this paper we described a Hidden Markov Model based approach for detecting abnormalities in daily activities, a process of identifying irregularity in routine behaviours from statistical histories and an exponential smoothing technique to predict future changes in various vital signs. The outcomes of t…
Recognition of Falls and Daily Living Activities Using Machine Learning
2018
A robust fall detection system is essential to support the independent living of elderlies. In this context, we develop a machine learning framework for fall detection and daily living activity recognition. Using acceleration data from public databases, we test the performance of two algorithms to classify seven different activities including falls and activities of daily living. We extract new features from the acceleration signal and demonstrate their effect on improving the accuracy and the precision of the classifier. Our analysis reveals that the quadratic support vector machine classifier achieves an overall accuracy of 93.2% and outperforms the artificial neural network algorithm. Re…
Combining Benford's Law and machine learning to detect money laundering. An actual Spanish court case.
2017
Abstract Objectives This paper is based on the analysis of the database of operations from a macro-case on money laundering orchestrated between a core company and a group of its suppliers, 26 of which had already been identified by the police as fraudulent companies. In the face of a well-founded suspicion that more companies have perpetrated criminal acts and in order to make better use of what are very limited police resources, we aim to construct a tool to detect money laundering criminals. Methods We combine Benford’s Law and machine learning algorithms (logistic regression, decision trees, neural networks, and random forests) to find patterns of money laundering criminals in the conte…
Gastric adenomas: relationship between clinicopathological findings, Helicobacter pylori infection, APC mutations and COX-2 expression.
2006
Gastric adenomas are rare neoplastic growths characterized by localized polypoid proliferations of dysplastic epithelium that tend to progress to infiltrating adenocarcinoma. Therefore, the identification of molecular markers that could reliably recognize adenomas at risk of progression is advocated in the clinical management. In this study we investigated, in a series of gastric adenoma specimens from an area at high risk of gastric cancer, the relationship between clinicopathological characteristics of adenoma and Helicobacter pylori infection, APC mutational status, and COX-2 and the down-stream enzyme mPGES1 expression. Helicobacter pylori infection, detected in 24%, and 33% by histolog…
Machine learning of reverse transcription signatures of variegated polymerases allows mapping and discrimination of methylated purines in limited tra…
2020
AbstractReverse transcription (RT) of RNA templates containing RNA modifications leads to synthesis of cDNA containing information on the modification in the form of misincorporation, arrest, or nucleotide skipping events. A compilation of such events from multiple cDNAs represents an RT-signature that is typical for a given modification, but, as we show here, depends also on the reverse transcriptase enzyme. A comparison of 13 different enzymes revealed a range of RT-signatures, with individual enzymes exhibiting average arrest rates between 20 and 75%, as well as average misincorporation rates between 30 and 75% in the read-through cDNA. Using RT-signatures from individual enzymes to trai…
The reverse transcription signature of N-1-methyladenosine in RNA-Seq is sequence dependent
2015
The combination of Reverse Transcription (RT) and high-throughput sequencing has emerged as a powerful combination to detect modified nucleotides in RNA via analysis of either abortive RT-products or of the incorporation of mismatched dNTPs into cDNA. Here we simultaneously analyze both parameters in detail with respect to the occurrence of N-1-methyladenosine (m1A) in the template RNA. This naturally occurring modification is associated with structural effects, but it is also known as a mediator of antibiotic resistance in ribosomal RNA. In structural probing experiments with dimethylsulfate, m1A is routinely detected by RT-arrest. A specifically developed RNA-Seq protocol was tailored to …