Search results for "machine learning."

Using proximity and spatial homogeneity in neighbourhood-based classifiers

1997

In this paper, a set of neighbourhood-based classifiers are jointly used in order to select a more reliable neighbourhood of a given sample and take an appropriate decision about its class membership. The approaches introduced here make use of two concepts: proximity and symmetric placement of the samples.

Resolving ambiguities in a grounded human-robot interaction

2009

In this paper we propose a trainable system that learns grounded language models from examples with a minimum of user intervention and without feedback. We have focused on the acquisition of grounded meanings of spatial and adjective/noun terms. The system has been used to understand and subsequently to generate appropriate natural language descriptions of real objects and to engage in verbal interactions with a human partner. We have also addressed the problem of resolving eventual ambiguities arising during verbal interaction through an information theoretic approach.

Network attack detection and classification by the F-transform

2015

We solve the problem of network attack detection and classification. We discuss the way of generation and simulation of an artificial network traffic data. We propose an efficient algorithm for data classification that is based on the F-transform technique. The algorithm successfully passed all tests and moreover, it showed ability to perform classification in an on-line regime.

Protein data condensation for effective quaternary structure classification

2007

Many proteins are composed of two or more subunits, each associated with different polypeptide chains. The number and the arrangement of subunits forming a protein are referred to as quaternary structure. The quaternary structure of a protein is important, since it characterizes the biological function of the protein when it is involved in specific biological processes. Unfortunately, quaternary structures are not trivially deducible from protein amino acid sequences. In this work, we propose a protein quaternary structure classification method exploiting the functional domain composition of proteins. It is based on a nearest neighbor condensation technique in order to reduce both the porti…

Convolutional Neural Networks for the Identification of Regions of Interest in PET Scans: A Study of Representation Learning for Diagnosing Alzheimer…

2017

When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.

Local Feature Selection with Dynamic Integration of Classifiers

2000

Multidimensional data is often feature space heterogeneous so that individual features have unequal importance in different sub areas of the feature space. This motivates to search for a technique that provides a strategic splitting of the instance space being able to identify the best subset of features for each instance to be classified. Our technique applies the wrapper approach where a classification algorithm is used as an evaluation function to differentiate between different feature subsets. In order to make the feature selection local, we apply the recent technique for dynamic integration of classifiers. This allows to determine which classifier and which feature subset should be us…

Reduction of the number of spectral bands in Landsat images: a comparison of linear and nonlinear methods

2006

We describe some applications of linear and nonlinear pro- jection methods in order to reduce the number of spectral bands in Land- sat multispectral images. The nonlinear method is curvilinear component analysis CCA, and we propose an adapted optimization of it for image processing, based on the use of principal-component analysis PCA, a linear method. The principle of CCA consists in reproducing the topol- ogy of the original space projection points in a reduced subspace, keep- ing the maximum of information. Our conclusions are: CCA is an im- provement for dimension reduction of multispectral images; CCA is really a nonlinear extension of PCA; CCA optimization through PCA called CCAinitP…

Comparing ELM Against MLP for Electrical Power Prediction in Buildings

2015

The study of energy efficiency in buildings is an active field of research. Modelling and predicting energy related magnitudes leads to analyse electric power consumption and can achieve economical benefits. In this study, two machine learning techniques are applied to predict active power in buildings. The real data acquired corresponds to time, environmental and electrical data of 30 buildings belonging to the University of Leon (Spain). Firstly, we segmented buildings in terms of their energy consumption using principal component analysis. Afterwards we applied ELM and MLP methods to compare their performance. Models were studied for different variable selections. Our analysis shows that…

Machine Learning Approaches for Environmental Mixtures Studies with Time-to-Event Outcomes and their Application to the Strong Heart Study

2021

CrowdVAS-Net: A Deep-CNN Based Framework to Detect Abnormal Crowd-Motion Behavior in Videos for Predicting Crowd Disaster

2019

With the increased occurrences of crowd disasters like human stampedes, crowd management and their safety during mass gathering events like concerts, congregation or political rally, etc., are vital tasks for the security personnel. In this paper, we propose a framework named as CrowdVAS-Net for crowd-motion analysis that considers velocity, acceleration and saliency features in the video frames of a moving crowd. CrowdVAS-Net relies on a deep convolutional neural network (DCNN) for extracting motion and appearance feature representations from the video frames that help us in classifying the crowd-motion behavior as abnormal or normal from a short video clip. These feature representations a…