Jesús B. Alonso-Hernández

Robust and complex approach of pathological speech signal analysis

This paper presents a study of the approaches in the state-of-the-art in the field of pathological speech signal analysis with a special focus on parametrization techniques. It provides a description of 92 speech features where some of them are already widely used in this field of science and some of them have not been tried yet (they come from different areas of speech signal processing like speech recognition or coding). As an original contribution, this work introduces 36 completely new pathological voice measures based on modulation spectra, inferior colliculus coefficients, bicepstrum, sample and approximate entropy and empirical mode decomposition. The significance of these features was tested on 3 (English, Spanish and Czech) pathological voice databases with respect to classification accuracy, sensitivity and specificity. To our best knowledge the introduced approach based on complex feature extraction and robust testing outperformed all works that have been published already in this field. The results (accuracy, sensitivity and specificity equal to 100.0 ? 0.0 % ) are discussable in the case of Massachusetts Eye and Ear Infirmary (MEEI) database because of its limitation related to a length of sustained vowels, however in the case of Principe de Asturias (PdA) Hospital in Alcala de Henares of Madrid database we made improvements in classification accuracy ( 82.1 ? 3.3 % ) and specificity ( 83.8 ? 5.1 % ) when considering a single-classifier approach. Hopefully, large improvements may be achieved in the case of Czech Parkinsonian Speech Database (PARCZ), which are discussed in this work as well. All the features introduced in this work were identified by Mann-Whitney U test as significant ( p < 0.05 ) when processing at least one of the mentioned databases. The largest discriminative power from these proposed features has a cepstral peak prominence extracted from the first intrinsic mode function ( p = 6.9443 i? 10 - 32 ) which means, that among all newly designed features those that quantify especially hoarseness or breathiness are good candidates for pathological speech identification. The paper also mentions some ideas for the future work in the field of pathological speech signal analysis that can be valuable especially under the clinical point of view.

Assessing progress of Parkinson's disease using acoustic analysis of phonation

This paper deals with a complex acoustic analysis of phonation in patients with Parkinsons disease (PD) with a special focus on estimation of disease progress that is described by 7 different clinical scales (e. g. Unified Parkinsons disease rating scale or Beck depression inventory). The analysis is based on parametrization of 5 Czech vowels pronounced by 84 PD patients. Using classification and regression trees we estimated all clinical scores with maximal error lower or equal to 13 %. Best estimation was observed in the case of Mini-mental state examination (MAE = 0.77, estimation error 5.50 %). Finally, we proposed a binary classification based on random forests that is able to identify Parkinsons disease with sensitivity SEN = 92.86% (SPE = 85.71 %). The parametrization process was based on extraction of 107 speech features quantifying different clinical signs of hypokinetic dysarthria present in PD.

A low consumption real time environmental monitoring system for smart cities based on ZigBee wireless sensor network

Nowadays, there is an increasing interest in wireless sensor networks (WSN) for environmental monitoring systems because it can be used to improve the quality of life and living conditions are becoming a major concern to people. This paper describes the design and development of a real time monitoring system based on ZigBee WSN characterized by a lower energy consumption, low cost, reduced dimensions and fast adaptation to the network tree topology. The developed system encompasses an optimized sensing process about environmental parameters, low rate transmission from sensor nodes to the gateway, packet parsing and data storing in a remote database and real time visualization through a web server. A monitoring system integrating the outlined system has been deployed and tested for monitoring the level of dust particles in the air, acoustic levels in different places of a city, ambient temperature and relative humidity. A calibration process of a low cost audio sensor was performed to measure the acoustic level from different noise sources, hence, it is not necessary to use an expensive sound level meter at each node. Furthermore, experimental results show autonomy nodes can be about three months.

Feature selection for automatic analysis of emotional response based on nonlinear speech modeling suitable for diagnosis of Alzheimer׳s disease

Abstract Alzheimer׳s disease (AD) is the most common type of dementia among the elderly. This work is part of a larger study that aims to identify novel technologies and biomarkers or features for the early detection of AD and its degree of severity. The diagnosis is made by analyzing several biomarkers and conducting a variety of tests (although only a post-mortem examination of the patients’ brain tissue is considered to provide definitive confirmation). Non-invasive intelligent diagnosis techniques would be a very valuable diagnostic aid. This paper concerns the Automatic Analysis of Emotional Response (AAER) in spontaneous speech based on classical and new emotional speech features: Emotional Temperature (ET) and fractal dimension (FD). This is a pre-clinical study aiming to validate tests and biomarkers for future diagnostic use. The method has the great advantage of being non-invasive, low cost, and without any side effects. The AAER shows very promising results for the definition of features useful in the early diagnosis of AD.

Human Computer Interactions in Next-Generation of Aircraft Smart Navigation Management Systems: Task Analysis and Architecture under an Agent-Oriented Methodological Approach

The limited efficiency of current air traffic systems will require a next-generation of Smart Air Traffic System (SATS) that relies on current technological advances. This challenge means a transition toward a new navigation and air-traffic procedures paradigm, where pilots and air traffic controllers perform and coordinate their activities according to new roles and technological supports. The design of new Human-Computer Interactions (HCI) for performing these activities is a key element of SATS. However efforts for developing such tools need to be inspired on a parallel characterization of hypothetical air traffic scenarios compatible with current ones. This paper is focused on airborne HCI into SATS where cockpit inputs came from aircraft navigation systems, surrounding traffic situation, controllers’ indications, etc. So the HCI is intended to enhance situation awareness and decision-making through pilot cockpit. This work approach considers SATS as a system distributed on a large-scale with uncertainty in a dynamic environment. Therefore, a multi-agent systems based approach is well suited for modeling such an environment. We demonstrate that current methodologies for designing multi-agent systems are a useful tool to characterize HCI. We specifically illustrate how the selected methodological approach provides enough guidelines to obtain a cockpit HCI design that complies with future SATS specifications.

Palm Vein Recognition using Local Tetra Patterns

Palm Vein Recognition is an emerging touch-less and spoof-resistant means of biometric authentication. However, matching algorithms tend to lack accuracy, due to the complexity of vascular patterns and irregularities in subsequent samples of the same person. This paper proposes a method that describes the spatial structure of local texture using direction of central gray pixel, formulating a discrete set of features which generates a unique template that improves the accuracy of identification. The features from various samples pertaining to the same person are strategically combined. This creates a robust feature vector which is able to handle the irregularities encountered while acquiring images for the database, and improves the efficiency manifolds as compared to present techniques. Matching and score calculation was done using cosine similarity measure. The method was tested on the PUT Vein Database which contained 1200 samples. The results showed an Equal Error Rate of 0%.

A novel approach to detect glaucoma in retinal fundus images using cup-disk and rim-disk ratio

Glaucoma is a chronic disease which if not detected in early stages can lead to permanent blindness. The medical techniques used by ophthalmologists like HRT and OCT is costly and time consuming. Hence there is a need to develop automatic computer aided system which can detect glaucoma efficiently and in less time. Optic disk and optic cup are prime features which help in diagnosing glaucoma. Thus proper segmentation of optic disk and optic cup plays an important role in detecting the disorder. In this paper an adaptive threshold based method which is independent of image quality and invariant to noise is used to segment optic disk, optic cup, Neuroretinal rim and cup to disk ratio is calculated to screen glaucoma. Another ocular parameter, rim to disk ratio is also considered which in combination with CDR gives more reliability in determining glaucoma and makes the system more robust. Further an SVM classifier has been used to categorize the images as glaucomatic or non glaucomatic. The experimental results obtained are compared with those of ophthalmologist and are found to have high accuracy of 90%. Also in addition, the proposed method is faster having low computational cost.

Finger vein recognition using Integrated Responses of Texture features

The finger vein recognition system is a secure and a reliable system with the advantage of robustness against malicious attacks. It is more convenient to operate this biometric feature than other biometric features such as facial and iris recognition system. The paper proposes a unique technique to find the local and the global features using Integrated Responses of Texture (IRT) features from finger veins which improves the overall accuracy of the system and is invariant to rotations. The segmentation of region of interest at different resolution levels makes the system highly efficient. The lower resolution data gives the overall global features and the higher resolution data gives the distinct local features. The complete feature set is descriptive in nature and reduces the Equal Error Rate to 0.523%. The Multi-Support Vector Machine (Multi-SVM) is used to classify and match the obtained results. The experimental results indicate that the system is highly accurate with an accuracy of 94%.

Evaluation of local descriptors and CNNs for non-adult detection in visual content

Abstract The recent evolution of storage devices, digital embedded cameras and the Internet have collaterally allowed sexual predators to take advantage of these technological breakthroughs to gather illegal media, which is exhibited uncensored through Peer-to-Peer file sharing networks. In this paper, we are particularly concerned about the increasing availability of Child Abuse Material. Therefore, we have explored alternatives to detect non-adults in visual content. Initially, different age estimations and underage detection techniques are reviewed by analyzing existing datasets. Finally, several local descriptors and Convolutional Neural Networks for underage detection are evaluated. The experimental results obtained for a large dataset that combines collections such as FG-Net, Adience, GenderChildren, The Image of Groups and Boys2Men evidence the complementary information contained in both local descriptors and neural networks, as their fusion boosts the accuracy of non-adult detection to over 93%.

Symmetry Extraction in High Sensitivity Melanoma Diagnosis

Melanoma diagnosis depends on the experience of doctors. Symmetry is one of the most important factors to measure, since asymmetry shows an uncontrolled growth of cells, leading to melanoma cancer. A system for melanoma detection in diagnosing melanocytic diseases with high sensitivity is proposed here. Two different sets of features are extracted based on the importance of the ABCD rule and symmetry evaluation to develop a new architecture. Support Vector Machines are used to classify the extracted sets by using both an alternative labeling method and a structure divided into two different classifiers which prioritize sensitivity. Although feature extraction is based on former works, the novelty lies in the importance given to symmetry and the proposed architecture, which combines two different feature sets to obtain a high sensitivity, prioritizing the medical aspect of diagnosis. In particular, a database provided by Hospital Universitario de Gran Canaria Doctor Negrin was tested, obtaining a sensitivity of 100% and a specificity of 66.66% using a leave-one-out validation method. These results show that 66.66% of biopsies would be avoided if this system is applied to lesions which are difficult to classify by doctors.