Search Results

The dilemma between stability and plasticity is crucial in machine learning, especially when non-stationary input distributions are considered. This issue can be addressed by continual learning in order to alleviate catastrophic forgetting. This strategy ...

The problem of the human body localization in the video stream using the growing neural gas and feature description based on the Histograms of Oriented Gradients is solved. The original neuro-fuzzy model of growing neural gas for reinforcement learning (...

This paper presents a novel growing neural gas based background model (GNG-BM) for foreground detection in videos. We proposed a pixel-level background model, where the GNG algorithm is modified for clustering the input pixel data and a new algorithm ...

Activity recognition has recently gained a lot of interest and there already exist several methods to detect human activites based on wearable sensors. Most of the existing methods rely on a database of labelled activities that is used to train an ...

We propose the design of a real-time system to recognize and interprethand gestures. The acquisition devices are low cost 3D sensors. 3D hand pose will be segmented, characterized and track using growing neural gas (GNG) structure.The capacity of the ...

We present a new approach to supervised vector quantization inspired on growing neural gas network. An advantage of the new method is that it reduces the need for prior knowledge about the problem under study because it is able to determine at runtime ...

Our previous work has demonstrated that clustering-based outlier detection approach offers numerous advantages for detecting attacks in Wireless Sensor Networks, above all adaptability and the possibility to detect unknown attacks. In this work we ...

The paper gives a brief consideration of a new approach to clustering of large amounts of data. Developed by the authors in the course of research into clustering of geographic and graphical data, the approach involves two-stage clustering. In the first ...

Growing neural gas (GNG) has been successfully applied to unsupervised learning problems. However, GNG-inspired approaches can also be applied to classification problems, provided they are extended with an appropriate labelling function. Most approaches ...

The use of alert correlation methods in Distributed Intrusion Detection Systems (DIDS) has become an important process to address some of the current problems in this area. However, the efficiency obtained is far from optimal results. This paper ...

This paper aims to address the ability of self-organizing neural network models to manage video and image processing in real-time. The Growing Neural Gas networks (GNG) with its attributes of growth, flexibility, rapid adaptation, and excellent quality ...

This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce a Graphics Processing Unit (GPU) implementation with Compute Unified Device Architecture (CUDA) of the Growing ...

One of the more important issues in intelligent video surveillance systems is the ability to handle events from the motion of objects. Thus, the classification of the trajectory of an object of interest in a scene can give important information to ...

We propose a data structure that decreases complexity of unsupervised competitive learning algorithms which are based on the growing cells structures approach. The idea is based on a novel way of ordering the cells in a tree like data structure in a way ...

The goal of the work presented in this paper is to develop a novel scheme for the measurement and representation of deformable objects without a priori knowledge on their shape or material. The proposed solution advantageously combines a neural gas ...

The multi-objective optimization neural estimation of distribution algorithm (MONEDA) was devised with the purpose of dealing with the model-building issues of MOEDAs and, therefore address their scalability.

In this paper we put forward a comprehensive ...

Support Vector Machines (SVMs) represent a well known technique for data classification. However, the complexity of the training process makes the SVMs unsuitable for classifying large datasets. Examples of existing approaches to this problem are ...

In this paper we present different error measurements with the aim to evaluate the quality of the approximations generated by the GNG3D model for mesh simplification. The first phase of this method consists on the execution of the GNG3D algorithm, ...

In this paper we present different error measurements with the aim to evaluate the quality of the approximations generated by the GNG3D method for mesh simplification. The first phase of this method consists on the execution of the GNG3D algorithm, ...

A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D ...