Search results for "feature extraction"

Effective feature descriptor-based new framework for off-line text-independent writer identification

2018

Feature engineering is a key factor of machine learning applications. It is a fundamental process in writer identification of handwriting, which is an active and challenging field of research for many years. We propose a conceptually computationally efficient, yet simple and fast local descriptor referred to as Block Wise Local Binary Count (BW-LBC) for offline text-independent writer identification of handwritten documents. Proposed BW-LBC operator, which characterizes the writing style of each writer, is applied to a set of connected components extracted and cropped from scanned handwriting samples (documents or set of words/text lines) where each labeled component is seen as a texture im…

Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification

2020

In the last years, deep convolutional neural networks have become a standard for the development of state-of-the-art audio classification systems, taking the lead over traditional approaches based on feature engineering. While they are capable of achieving human performance under certain scenarios, it has been shown that their accuracy is severely degraded when the systems are tested over noisy or weakly segmented events. Although better generalization could be obtained by increasing the size of the training dataset, e.g. by applying data augmentation techniques, this also leads to longer and more complex training procedures. In this article, we propose a new type of pooling layer aimed at …

Combining feature extraction and expansion to improve classification based similarity learning

2017

Abstract Metric learning has been shown to outperform standard classification based similarity learning in a number of different contexts. In this paper, we show that the performance of classification similarity learning strongly depends on the data format used to learn the model. We then present an Enriched Classification Similarity Learning method that follows a hybrid approach that combines both feature extraction and feature expansion. In particular, we propose a data transformation and the use of a set of standard distances to supplement the information provided by the feature vectors of the training samples. The method is compared to state-of-the-art feature extraction and metric lear…

A multi-layer method to study genome-scale positions of nucleosomes

2009

AbstractThe basic unit of eukaryotic chromatin is the nucleosome, consisting of about 150 bp of DNA wrapped around a protein core made of histone proteins. Nucleosomes position is modulated in vivo to regulate fundamental nuclear processes. To measure nucleosome positions on a genomic scale both theoretical and experimental approaches have been recently reported. We have developed a new method, Multi-Layer Model (MLM), for the analysis of nucleosome position data obtained with microarray-based approach. The MLM is a feature extraction method in which the input data is processed by a classifier to distinguish between several kinds of patterns. We applied our method to simulated-synthetic and…

A Machine Learning Approach for Fall Detection and Daily Living Activity Recognition

2019

The number of older people in western countries is constantly increasing. Most of them prefer to live independently and are susceptible to fall incidents. Falls often lead to serious or even fatal injuries which are the leading cause of death for elderlies. To address this problem, it is essential to develop robust fall detection systems. In this context, we develop a machine learning framework for fall detection and daily living activity recognition. We use acceleration and angular velocity data from two public databases to recognize seven different activities, including falls and activities of daily living. From the acceleration and angular velocity data, we extract time- and frequency-do…

On the use of Deep Reinforcement Learning for Visual Tracking: a Survey

2021

This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning. It is showing interesting results in the computer vision field and, recently, it has been applied to the visual tracking problem yielding to the rapid development of novel tracking strategies. After providing an introduction to reinforcement learning, this paper compares recent visual tracking approaches based on deep reinforcement learning. Analysis of the state-of-the-art suggests that reinforcement learning allows modeling varying parts of the tracki…

WiWeHAR: Multimodal Human Activity Recognition Using Wi-Fi and Wearable Sensing Modalities

2020

Robust and accurate human activity recognition (HAR) systems are essential to many human-centric services within active assisted living and healthcare facilities. Traditional HAR systems mostly leverage a single sensing modality (e.g., either wearable, vision, or radio frequency sensing) combined with machine learning techniques to recognize human activities. Such unimodal HAR systems do not cope well with real-time changes in the environment. To overcome this limitation, new HAR systems that incorporate multiple sensing modalities are needed. Multiple diverse sensors can provide more accurate and complete information resulting in better recognition of the performed activities. This article…

A Machine Learning Approach for Fall Detection Based on the Instantaneous Doppler Frequency

2019

Modern societies are facing an ageing problem that is accompanied by increasing healthcare costs. A major share of this ever-increasing cost is due to fall-related injuries, which urges the development of fall detection systems. In this context, this paper paves the way for the development of radio-frequency-based fall detection systems, which do not require the user to wear any device and can detect falls without compromising the user's privacy. For the design of such systems, we present an activity simulator that generates the complex path gain of indoor channels in the presence of one person performing three different activities: slow fall, fast fall, and walking. We have developed a mac…

2020

Recommender systems are information software that retrieves relevant items for users from massive sources of data. The variational autoencoder (VAE) has proven to be a promising approach for recommendation systems, as it can explore high-level user-item relations and extract contingencies from the input effectively. However, the previous variants of VAE have so far seen limited application to domain-specific recommendations that require additional side information. Hence, The Ensemble Variational Autoencoder framework for recommendations (EnsVAE) is proposed. This architecture specifies a procedure to transform sub-recommenders’ predicted utility matrix into interest probabilities that allo…

2021

This paper proposes a new method for blind mesh visual quality assessment (MVQA) based on a graph convolutional network. For that, we address the node classification problem to predict the perceived visual quality. First, two matrices representing the 3D mesh are considered: a graph adjacency matrix and a feature matrix. Both matrices are used as input to a shallow graph convolutional network. The network consists of two convolutional layers followed by a max-pooling layer to provide the final feature representation. With this structure, the Softmax classifier predicts the quality score category without the reference mesh’s availability. Experiments are conducted on four publicly available …