Orion Fausto Reyes-Galaviz

Evolutionary-Neural System to Classify Infant Cry Units for Pathologies Identification in Recently Born Babies

This work presents an infant cry automatic recognizer development, with the objective of classifying two kinds of infant cries, normal and pathological, from recently born babies. Extraction of acoustic features is used such as MFCC (Mel Frequency Cepstral Coefficients), obtained from Infant Cry Units sound waves, and a genetic feature selection system combined with a feed forward input delay neural network, trained by adaptive learning rate back-propagation. For the experiments, recordings from Cuban and Mexican babies are used, classifying normal and pathological cry in three different experiments; Cuban babies, Mexican Babies, and Cuban & Mexican babies. It is also shown a comparison between a simple traditional feed-forward neural network and another complemented with the proposed genetic feature selection system, to reduce the feature input vectors. In this paper the whole process is described; in which the acoustic features extraction is included, the hybrid system design, implementation, training and testing. The results from some experiments are also shown, in which the infant cry recognition rate obtained is of up to 100% using our genetic system.

Analysis of an infant cry recognizer for the early identification of pathologies

This work presents the development and analysis of an automatic recognizer of infant cry, with the objective of classifying three classes, normal, hypo acoustics and asphyxia. We use acoustic feature extraction techniques like MFCC, for the acoustic processing of the crys sound wave, and a Feed Forward Input Delay neural network with training based on Gradient Descent with Adaptive Back-Propagation for classification. We also use principal component analysis (PCA) in order to reduce vectors size and to improve training time. The complete infant cry database is represented by plain text vector files, which allows the files to be easily processed in any programming environment. The paper describes the design, implementation as well as experimentation processes, and the analysis of results of each type of experiment performed.

Classification of Infant Crying to Identify Pathologies in Recently Born Babies with ANFIS

In this work we present the design of an Automatic Infant Cry Recognizer hybrid system, that classifies different kinds of cries, with the objective of identifying some pathologies in recently born babies. These cries are recordings of normal, deaf and asphyxiating infants, of ages from 1 day up to one year old. For its acoustic processing we used a free software tool called Praat [1]. Additionally, we used Matlab to implement the system, based on ANFIS [2], to classify the infant’s crying. In the model here presented, we classify the input vectors in three corresponding classes, normal cry, hypo acoustic (deaf) and asphyxiating cries. We have obtained scores up to 96 % in precision on the classification.

A Fuzzy Relational Neural Network for Pattern Classification

In this paper we describe the implementation of a fuzzy relational neural network model. In the model, the input features are represented by fuzzy membership, the weights are described in terms of fuzzy relations. The output values are obtained with the max-min composition, and are given in terms of fuzzy class membership values. The learning algorithm is a modified version of back-propagation. The system is tested on an infant cry classification problem, in which the objective is to identify pathologies in recently born babies.

Granular fuzzy models: Analysis, design, and evaluation

Abstract The study is concerned with a design of granular fuzzy models. We exploit a concept of information granularity by developing a model coming as a network of intuitively structured collection of interval information granules described in the output space and a family of induced information granules (in the form of fuzzy sets) formed in the input space. In contrast to most fuzzy models encountered in the literature, the results produced by granular models are information granules rather than plain numeric entities. The design of the model concentrates on a construction of information granules that form a backbone of the overall construct. Interval information granules positioned in the output space are built by considering intervals of equal length, equal probability, and developing an optimized version of the intervals. The induced fuzzy information granules localized in the input space are realized by running a conditional Fuzzy C-Means (FCM). The performance of the model is assessed by considering criteria of coverage and information specificity (information granularity). Further optimization of the model is proposed along the line of an optimal re-distribution of input information granules induced by the individual interval information granules located in the output space. Experimental results involve some synthetic low-dimensional data and publicly available benchmark data sets.

Validation of the Cry Unit as Primary Element for Cry Analysis Using an Evolutionary-Neural Approach

The present paper proposes the use of a basic element for the infant cry analysis: the cry unit. In order to display the real possibility of the cry unit for the detection of pathological features (based on Hypoxia) in newborns, a novel combined treatment of the cry signal was implemented using an evolutionary-neural system. For that purpose the cry signal was segmented into cry units, the MFCC were computed as acoustic features, and a genetic feature selection system combined with a feed forward input delay neural network, trained by adaptive learning rate back-propagation were properly developed. The data for the experiments were obtained from a Mexican-Cuban infant cry database. It is also shown a comparison between a simple neural network and the proposed genetic feature selection system, to reduce the feature input vectors. The results are also shown from some experiments, in which the infant cry recognition is improved to 100% using our genetic system.

Granular fuzzy modeling with evolving hyperboxes in multi-dimensional space of numerical data

Clustering has been applied to numerous areas, including signal and image processing. Many approaches have been developed over the years to efficiently construct granular models on a basis of numerical experimental data. In this study, we propose a novel approach to construct a granular model that is fundamentally designed around information granules regarded as hyperboxes. Several studies have been focused on building a set of hyperboxes around data; one of them being a Min-Max Neural Network (NN) algorithm. Here we develop two different methods to construct these information granules, nevertheless some essential similarities to previous studies can be found. In particular, hyperboxes are constructed by using some reference data, and they are endowed with some parametric flexibility to facilitate controlling their size, whereas the construction of the hyperboxes involve elimination or reduction of possible overlaps between them. In the proposed approach, given a set of input and output data pairs, we construct interval-based information granules to partition the output space (viz. the space of the output variable). On a basis of these intervals, we carry out a so-called context-based Fuzzy C-Means algorithm to construct cluster centers (prototypes) in the multivariable input space. These prototypes serve as hyperbox cores. To construct the information granules, two methods are studied: one develops a family of hyperboxes by realizing some constrictions, while the other one engages Differential Evolution (DE) to realize further optimization. To reduce overlap, two methods are tested: one being previously proposed for the min-max NN and a new one, which engages DE to optimize the overlap reduction. Experimental studies involve synthetic data and publicly available real-world data. The results are compared with the outcomes produced by the algorithm proposed by Simpson. The performance of the method is quantified and it is demonstrated that the obtained results are substantially better when dealing with multi-dimensional data.

Applying Intelligent Systems for Modeling Students’ Learning Styles Used for Mobile and Web-Based Systems

The identification of the best learning style in an Intelligent Tutoring System must be considered essential as part of the success in the teaching process. This research work presents a set of three different approaches applying intelligent systems for automatic identification of learning styles in order to provide an adapted learning scheme under different software platforms. The first approach uses a neuro-fuzzy network (NFN) to select the best learning style. The second approach combines a NFN to classify learning styles with a genetic algorithm for weight optimization. The learning styles are based on Gardner’s Pedagogical Model of Multiple Intelligences. The last approach implements a self-organising feature map (SOM) for identifying learning styles under the Felder-Silverman Model. The three approaches are used by an author tool for building Intelligent Tutoring Systems running under a Web 2.0 collaborative learning platform. The tutoring systems together with the neural networks can also be exported to mobile devices. We present results of three different tutoring systems produced by three implemented authoring tools.

Feature Selection for a Fast Speaker Detection System with Neural Networks and Genetic Algorithms

Today, there is a great necessity for security systems in banks, laboratories, etc.; specially those that have restricted areas or expensive equipment. Most of the time people use magnetic cards or similar technologies. However, these kinds of devices can be vulnerable, because these might be used by intruders in case of a misplaced device. More advanced technologies use iris or voice detection, potentially increasing the security level against intruders. This work is focused on the latter group. This paper proposes a hybrid method, for the speech processing area, to select and extract the best features that represent a speech sample. The proposed method makes use of a genetic algorithm along with feed forward neural networks in order to either deny or accept personal access in real time. Finally, to test the proposed method, a series of experiments were conducted, by using fifteen different speakers; obtaining an efficiency rate of up to 97% on intruder detection

Enhancement of the classification and reconstruction performance of fuzzy C-means with refinements of prototypes

Abstract Owning to their abilities to reveal structural relationships in data, fuzzy clustering plays a pivotal role in fuzzy modeling, pattern recognition, and data analysis. As supporting an unsupervised mode of learning, fuzzy clustering, brings about unique opportunities to build a structural backbone of numerous constructs in the areas identified above. A follow-up phase is required when the structural findings developed in the form of fuzzy clusters need some refinements, usually when the clustering results are used afterwards in the model being developed in a supervised mode. Following this general line of thought, in this study we propose a novel approach to optimize the clustering and classification performance of the Fuzzy C-Means (FCM) algorithm. Proceeding with a collection of clusters (information granules) produced by the FCM, we carry out the refinements of the results (in order to improve the representation or classification capabilities of fuzzy clusters) by adjusting a location of the prototypes so that a certain performance index becomes optimized. At this phase, the optimization is carried out in a supervised mode with the aid of Differential Evolution (DE). We propose five different strategies to adjust a location of the prototypes. Experimental studies completed on synthetic data and publicly available real-world data quantify the improvement of the representation and classification abilities of the clustering method.