Search results for "Feature Extraction"
showing 10 items of 275 documents
UBFC-Phys: A Multimodal Database For Psychophysiological Studies of Social Stress
2021
As humans, we experience social stress in countless everyday-life situations. Giving a speech in front of an audience, passing a job interview, and similar experiences all lead us to go through stress states that impact both our psychological and physiological states. Therefore, studying the link between stress and physiological responses had become a critical societal issue, and recently, research in this field has grown in popularity. However, publicly available datasets have limitations. In this article, we propose a new dataset, UBFC-Phys, collected with and without contact from participants living social stress situations. A wristband was used to measure contact blood volume pulse (BVP…
Automatic screening of cardiac disorders using wavelet analysis of heart sound
2017
Body auscultation is a dominant method for physical examination of human heart using conventional stethoscope. This clinical method is non invasive and efficient but it requires a medical expert to interpret the heart sound for assessment of cardiac disorders. This paper presents analysis of heart sounds in wavelet domain for automated screening of cardiac disorders. Heart sound signal is transformed in wavelet domain to find out discrimination between heart sounds recorded from healthy and anomalous patients. Discriminatory features extracted from wavelet coefficients of heart sound are subjected to machine learning for screening of cardiac disorders automatically. The proposed method for …
Microphones’ Directivity for the Localization of Sound Sources
2011
In a recent paper [P. Rizzo, G. Bordoni, A. Marzani, and J. Vipperman, "Localization of Sound Sources by Means of Unidirectional Microphones, Meas. Sci. Tech., 20, 055202 (12pp), 2009] the proof-of-concept of an approach for the localization of acoustic sources was presented. The method relies on the use of unidirectional microphones and amplitude-based signals' features to extract information about the direction of the incoming sound. By intersecting the directions identified by a pair of microphones, the position of the emitting source can be identified. In this paper we expand the work presented previously by assessing the effectiveness of the approach for the localization of an acoustic…
VIRES: A distributed open architecture for pictorial database
2006
In this paper we describe VIRES (Visual Information Retrieval Extendible System) an open distributed pictorial database for image retrieval. The retrieval methods, pictorial indexing and data are distributed over the network. VIRES has been designed as an open architecture. The system is based on the concept of distributed model via dictionary in order to reach a good versatility without changing the kernel of VIRES.
Speech Activity Detection under Adverse Noisy Conditions at Low SNRs
2021
Speech originating from the noisy environments degrades the speech quality and intelligibility, thus reducing the human perceived Quality of Experience (QoE). For example, surveillance using drone during natural catastrophe needs an efficient speech recognition device to recognise the speech of the frozen human in presence of drone noise to save their life. Therefore, it often requires to pre-process the noisy speech in order to reduce the noise artifacts and enhance the speech. This paper detects the speech activity using Voice Activity Detection (VAD). The VAD distinguishes speech activity (speech presence) and speech inactivity (silence/noise) by extracting the speech features and compar…
Motor learning and body size within an insect brain computational model
2014
Nowadays modeling insect brains is also an important source of inspiration to develop learning architectures and control algorithms for applications on autonomous walking robots. Within the insect brain two important neuropiles received a lot of attention: the mushroom bodies (MBs) and the central complex (CX). Recent research activities considered the MBs as a unique architecture where different behavioural functions can be found. MBs are well known in bees and flies for their role in performing associative learning and memory in odor conditioning experiments [4]. They are also involved in the processing of multiple sensory modalities including visual tasks [3], different forms of learning…
Visualization in comparative music research
2007
Computational analysis of large musical corpora provides an approach that overcomes some of the limitations of manual analysis related to small sample sizes and subjectivity. The present paper aims to provide an overview of the computational approach to music research. It discusses the issues of music representation, musical feature extraction, digital music collections, and data mining techniques. Moreover, it provides examples of visualization of large musical collections.
Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections.
2016
This paper deals with the automated detection of Diabetic Macular Edema (DME) on Optical Coherence Tomography (OCT) volumes. Our method considers a generic classification pipeline with preprocessing for noise removal and flattening of each B-Scan. Features such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are extracted and combined to create a set of different feature vectors which are fed to a linear-Support Vector Machines (SVM) Classifier. Experimental results show a promising sensitivity/specificity of 0.75/0.87 on a challenging dataset.
Definition and Performance Evaluation of a Robust SVM Based Fall Detection Solution
2012
We propose an automatic approach to detect falls in home environment. A Support Vector Machine based classifier is fed by a set of selected features extracted from human body silhouette tracking. The classifier is followed by filtering operations taking into account the temporal nature of a video. The features are based on height and width of human body bounding box, the user's trajectory with her/his orientation, Projection Histograms and moments of order 0, 1 and 2. We study several combinations of usual transformations of the features (Fourier Transform, Wavelet transform, first and second derivatives), and we show experimentally that it is possible to achieve high performance using a si…
Real-time flaw detection on complex part: Study of SVM and hyperrectangle based method
2002
We present in this paper the study of two classifications methods used in order to control in real-time some industrials parts. We present the practical frame in which is made the operations, natures of the anomaly to be detected as well as the features extractions method. We tested two techniques of classification, with different algorithm complexities and performances. We compare the results obtained on various features spaces. We end by a combinatorial perspective of results of classification.