Search

Spatial missions such as the Kepler mission, and the Transiting Exoplanet Survey Satellite (TESS) mission, have encouraged data scientists to analyze light curve datasets. The purpose of analyzing these data is to look for planet transits, with the aim of discovering and validating exoplanets, which are planets found outside our Solar System. Furthermore, transiting exoplanets can be better characterized when light curves and radial velocity curves are available. The manual examination of these datasets is a task that requires big quantities of time and effort, and therefore is prone to errors. As a result, the application of machine learning methods has become more common on exoplanet discovery and categorization research. This survey presents an analysis on different exoplanet transit discovery algorithms based on machine learning, some of which even found new exoplanets. The analysis of these algorithms is divided into four steps, namely light curve preprocessing, possible exoplanet signal detection, and identification of the detected signal to decide whether it belongs to an exoplanet or not. We propose a model to create synthetic datasets of light curves, and we compare the performance of several machine learning models used to identify transit exoplanets, with inputs preprocessed with and without using the Discrete Wavelet Transform (DWT). Our experimental results allow us to conclude that multiresolution analysis in the time-frequency domain can improve exoplanet signal identification, because of the characteristics of light curves and transiting exoplanet signals.

In this paper, we present a novel neural network able to classify epileptic seizures using electroencephalogram (EEG) signals, called “Multidimensional Radial Wavelons Feed-Forward Wavelet Neural Network” (MRW-FFWNN). The network is part of a classification system, which distinguishes among three brain states related to epilepsy namely ictal, interictal and healthy. Efficient methods for pre-processing EEG’s, extracting features and getting the final class decisions were selected using a statistical three-fold cross-validation method, which assures the robustness of the system and its generalization ability. The following methods were systematically analyzed to find the most appropriate for this problem: 1) Infinite Impulse Response (IIR) and Finite Impulse Response (FIR) filters for noise reduction; 2) discrete Wavelet Transform (DWT) and Maximal Overlap Discrete Wavelet Transform (MODWT) for frequency decomposition of the EEG signals; 3) average correlation and maximum voting correlation for selecting a suitable mother wavelet for frequency decomposition; 4) Binary-tree and one-vs-one (OVO) decomposition strategies for primary binary classification; 5) voting and weighted-voting strategy aggregation strategies for the final classification. The integrated system was assessed using a three-fold cross validation, applied to a benchmark provided by the University of Bonn, getting an average accuracy of 93.33% when tested using sets Z, S and F and 95.0% when sets Z, S, F and O were used. The proposed network got competitive accuracy, compared with other state-of-the art classifiers, training in almost a half of the time than the ones with similar accuracy.

This paper presents a novel approach on motor current signature analysis (MCSA) for broken bar fault detection of induction motors (IMs), using as input the current signal measured from one of the three motor phases. Independent component analysis (ICA) is used over the Fourier-domain spectral signals obtained from the input and its autocorrelation function. The standard deviation of spectral components within a region of interest (ROI) of an ICA signal output was found to exhibit substantial differences between damaged and healthy motors. Separation of the ROI in one, two, and three sectors leads to an improved extraction of feature vectors, which are further fed into a neural network for classification purposes. The assessment of the proposed method is carried out through several experiments using two damage levels (broken bar and half broken bar) and two load motor conditions (50% and 75%), with a classification accuracy ranging from 90% to 99%. The contribution of this paper lies in a new technique of signal processing for ICA-based feature extraction in a 3-D feature space for IM fault diagnosis.

Current video coding standards such as the H.264 or Advanced Video Coding (AVC) and the H.265 or High Efficiency Video Coding (HEVC) are based on the Integer Discrete Cosine Transform (IDCT). However, it has been shown that wavelet-based algorithms have better performance than IDCT-based algorithms for still images. Also, exploiting the human visual system characteristics in stationary point of view image and video transmissions like the fovea aliasing can improve the quality of the reconstructed image. In this paper, two wavelet-based video coding approaches called SPECK-based Codec (SP-Codec) and Adaptive Wavelet/Fovea-based Codec (AWFV-Codec) are proposed. The proposed SP-Codec approach applies the Set Partitioned Embedded Block Codec (SPECK) wavelet-based compression algorithm in order to increase the intra-frame coding quality. The second proposed approach AWFV-Codec uses the Adaptive Fovea Set Partitioned Embedded Block Codec (AFV-SPECK) fovea wavelet-based compression algorithm for intra-frame coding. Fovea based compression allows to increase the quality of the reconstructed frames over regions of interest (ROI). A comparison of the proposed algorithms against the HEVC based on IDCT approach shows how the proposed wavelet-based schemes achieve higher compression ratios and higher reconstruction quality. When fixation point of view is stationary, the proposed wavelet/fovea-based algorithm achieves better quality at lower compression ratios than the wavelet-based only proposed algorithm.

The discovery of planets outside our Solar System, called exoplanets, allows us to study the feasibility of life outside Earth. Different techniques such as the transit method have been employed to detect and identify exoplanets. The amount of time and effort required to perform such a task, hinder the manual examination of the existing data. Several machine learning approaches have been proposed to deal with this matter, though they are not yet unerring. Therefore, new models continue to be proposed. In this work, we present experimental results using the K-Nearest Neighbors, Random Forests, Convolutional Neural Network and the Ridge classifier models to identify simulated transit signals. Furthermore, we propose a methodology based on the Empirical Mode Decomposition and Ensemble Empirical Mode Decomposition techniques for light curve preprocessing. Following this methodology we prove that multiresolution analysis can be used to improve the robustness of the presented models.

During 2016, breast cancer was the second cause of death among women within ages of 24–30. This makes mandatory to find reliable strategies that support physicians and medical services for early diagnosis of such disease. Currently, mammography is considered the gold instrument for assessing the risk of having breast cancer, but other methods are being analyzed, looking for systems that may be cheaper and easier to apply, including the use of thermographic images. In this paper, we present an analysis of the performance of a system based on a “Feed-Forward Neural Network” (FFNN), for the identification of two and three levels of risk cancer. Indeed, a system based on a “Regions-Convolutional Neural network” (R-CNN) for automatic segmentation of the breast is proposed. Both systems were tested in a private database developed by the “Center for Studies and Cancer Prevention, A.C.” located in Oaxaca, Mexico, which presents important challenges as class unbalances, a slack recording with respect to application of the protocol and noise. The systems were evaluated using three subsets of the database, built using images with different levels of challenges. Our results showed that a FNNN classifier performed well only with data strictly following the protocol, while the levels of performance with noisy data are not yet acceptable for real applications. In the other hand, the results obtained by the automatic segmentation based on R-CNN were competitive, encouraging for more research in this area.

It is well-known that there has been a considerable progress in multimedia technologies during the last decades, namely TV, photography, sound and video recording, communication systems, etc., which came into the world during at least half of the previous century and were developed as analog systems, and nowadays have been almost completely replaced by digital systems. The aforementioned motivates a deep study of multimedia compression and intensive research in this area. Data compression is concerned with minimization of the number of information carrying units used to represent a given data set. Such smaller representation can be achieved by applying coding algorithms. Coding algorithms can be either lossless algorithms that reconstruct the original data set perfectly or lossy algorithms that reconstruct a close representation of the original data set. Both methods can be used together to achieve higher compression ratios. Lossless compression methods can either exploit statistical structure of the data or compress the data by building a dictionary that uses fewer symbols for each string that appears on the data set. Lossy compression, on the other hand, uses a mathematical transform that projects the current data set onto the frequency domain. The coefficients obtained from the transform are quantized and stored. The quantized coefficients require less space to be stored. This chapter is focused on the recently published advances in image and video compression to date considering the use of the integer discrete cosine transform (IDCT), wavelet transforms, and fovea centralis.

This paper presents an educational platform developed to explore some concepts related to the relatively new signal acquisition paradigm known as Compressed Sensing (CS). CS aims to acquire a signal with sparse or compressible representation in a suitable domain, using a number of samples under the limit established by the Nyquist–Shannon sampling theorem. The application consists of a graphical user interface in MATLAB, and a low-cost FPGA Xilinx Spartan 6, which in that way form a powerful and low-cost design station adequate to perform a number of CS experiments. Reconstruction of signals is carried out using a Greedy algorithm which solves the underdetermined system in real time with a novel Chebyshev-type matrix inversion. Effects related to the number of samples defined in the measurement matrix, and the use of different spaces, such as Discrete Cosine Transform, or Discrete Wavelet Transform, can be easily studied with the described tool. Results derived from its use in graduate courses are discussed. © 2015 Wiley Periodicals, Inc. Comput Appl Eng Educ 23:921–930, 2015; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21664

A novel approach for automatic segmentation and recognition of CAPTCHAs with variable orientation and random collapse of overlapped characters is presented in this paper. Additionally, the extension of the proposed approach to break reCAPTCHA of version of 2012 is also discussed. The original proposal consists in straightening characters and word in CAPTCHA exploiting then a three-color bar code for their segmentation. The recognition of straightened characters and whole word is provided by the proposed original SVM-based learning classifier. The main goal of this research is to reduce vulnerability of CAPTCHA from spam and frauds as well as to provide an approach for recognizing either handwritten or degraded and damaged texts in ancient manuscripts by OCR systems. The designed framework for breaking CAPTCHAs by the proposed approach has been tested achieving average segmentation success rate up to 82% for reCAPTCHA of version 2011 and achieving 95.5% by extended approach for reCAPTCHA of version 2012 with response time less than 0.5s per two-word reCAPTCHA. The implemented SVM classifier shows a competitive precision about 94%. The obtained very satisfactory results confirm that the proposed approach may be used for development of new security mechanisms to protect users against cyber-criminal activities and Internet threats. Automatic segmentation and recognition of CAPTCHAs in Web sites is proposed.Anti-recognition techniques use collapsed characters with variable orientation.Aligned word and straightened characters are segmented by three-color bar code.Original SVM-based learning classifier provides real-time CAPTCHA recognition.Extended approach for beating reCAPTCHA of version 2012 shows better performance.

Currently, a particular focus of human centered technology is in expanding traditional contextual sensing and smart processing capabilities of ubiquitous systems exploiting user's affective and emotional states to develop more natural communication between computing artefacts and users. This paper presents a smart environment of Web services that has been developed to integrate and manage different existing and new emotion sensing applications, which working together provide tracking and recognition of human affective state in real time. In addition, two emotion interpreters based on the proposed 6-FACS and Distance models have been developed. Both models operate with encoded facial deformations described either in terms of Ekman's Action Units or Facial Animation Parameters of MPEG-4 standards. Fuzzy inference system based on reasoning model implemented in a knowledge base has been used for quantitative measurement and recognition of three-level intensity of basic and non-prototypical facial expressions. Designed frameworks integrated to smart environment have been tested in order to evaluate capability of the proposed models to extract and classify facial expressions providing precision of interpretation of basic emotions in range of 65--96% and non-prototypical emotions in range of 55--65%. The conducted tests confirm that such basic as non-prototypical expressions may be composed by other basic emotions establishing in this way the concordance between existing psychological models of emotions and Ekman's model traditionally used by affective computing applications.

Analytic models allow the performance evaluation of proposed system changes without requiring complex and expensive detailed simulations. In this paper, Real-Time Calculus (RTC), a high-level analysis technique previously proposed for stream-processing hard real-time systems and frequently used to evaluate trade-offs in packet stream processing architectures, has been applied to analyse the behaviour of network interfaces. Moreover, the simulation of HDL (Hardware Description Language) models has been used to build the RTC descriptions required to analyse the behaviour of these relatively complex systems. As a case study of this proposed combination of Real-Time Calculus and HDL simulation, the prediction of buffer-size requirements and bottlenecks on the Network Interface Card (NIC) of a node receiving Ethernet packets, is also provided. This work intends to increase the efficiency of the performance evaluation of systems by providing real-time guarantees on delays and backlogs that are valid up to a certain level of confidence, as opposed to the hard guarantees commonly derived by formal methods.

Results of lossy image compression using wavelet transforms and several thresholding techniques are presented here. The analyzed image was divided into little sub-images and each one was decomposed in a vector following a Hilbert fractal curve. The wavelet transform was applied to each vector and some of the high frequency components were suppressed based on some threshold criteria. Different levels of wavelet decomposition and wavelet mother functions were assessed. The Huffman coding algorithm was then applied in order to reduce image weight. Simulation results have revealed that high compression ratios were obtained with the mean and the standard deviation thresholding algorithms at different levels of wavelet decomposition.

This paper presents a project on the development of a cursor control emulating the typical operations of a computer-mouse, using gyroscope and eye-blinking electromyographic signals which are obtained through a commercial 16-electrode wireless headset, recently released by Emotiv. The cursor position is controlled using information from a gyroscope included in the headset. The clicks are generated through the user’s blinking with an adequate detection procedure based on the spectral-like technique called Empirical Mode Decomposition (EMD). EMD is proposed as a simple and quick computational tool, yet effective, aimed to artifact reduction from head movements as well as a method to detect blinking signals for mouse control. Kalman filter is used as state estimator for mouse position control and jitter removal. The detection rate obtained in average was 94.9%. Experimental setup and some obtained results are presented.

Quick Response QR barcode detection in nonarbitrary environment is still a challenging task despite many existing applications for finding 2D symbols. The main disadvantage of recent applications for QR code detection is a low performance for rotated and distorted single or multiple symbols in images with variable illumination and presence of noise. In this paper, a particular solution for QR code detection in uncontrolled environments is presented. The proposal consists in recognizing geometrical features of QR code using a binary large object- (BLOB-) based algorithm with subsequent iterative filtering QR symbol position detection patterns that do not require complex processing and training of classifiers frequently used for these purposes. The high precision and speed are achieved by adaptive threshold binarization of integral images. In contrast to well-known scanners, which fail to detect QR code with medium to strong blurring, significant nonuniform illumination, considerable symbol deformations, and noising, the proposed technique provides high recognition rate of 80%–100% with a speed compatible to real-time applications. In particular, speed varies from 200 ms to 800 ms per single or multiple QR code detected simultaneously in images with resolution from 640 × 480 to 4080 × 2720, respectively.

Face detection, tracking and recognition is still actual field of human centered technologies used for developing more natural communication between computing artefacts and users. Analyzing modern trends and advances in this field, two approaches for face sensing and recognition have been proposed. The first color/shape-based approach uses sets of fuzzy saturated color regions providing face detection by Fourier descriptors and recognition by SVM. The second approach provides fast face detection by adaptive boosting algorithm, and recognition based on SIFT key point extraction into eye-nose-mouth regions has been improved using Bayesian approach. Designed systems have been tested in order to evaluate capability of the proposed approaches to detect, trace and interpret faces of known individuals registered into facial standard databases providing correct recognition rate in range of 94.5-99.0% with recall up to 46%. The conducted tests ensure that both approaches have satisfactory performance achieving less than 3 seconds for human face detection and recognition in live video streams.

In steel production the finishing process on hot rolling mill includes a set of essential operations managed by complex control mechanical, electrical and hydraulic equipment. However, accuracy of mill automating mechanisms and sensors is still low due to hot hostile environment with strong vibration and shock. The proposed solution is a computer vision application that exploits morphological filtering and discontinuity masks for detection and separation of rods on rolling mill and provides fast recognition and tracking rod front ends during their deceleration on cooler. The proposed algorithm has been implemented and evaluated in real time conditions achieving precision of rod front end recognition in range of 90–98% on artificial and daylight illumination, respectively.

In the past years, efforts have been made to improve the efficiency of long-term time series forecasting. However, when the involved series is highly oscillatory and nonlinear, this is still an open problem. Given the fact that signals may be approximated as linear combinations of sine functions, the study of the behavior of an adaptive dynamical model able to reproduce a sine function may be relevant for long-term prediction. In this chapter, we present an analysis of the modeling and prediction abilities of the “Long Short-Term Memory” (LSTM) recurrent neural network, when the input signal has a discrete sine function shape. Previous works have shown that LSTM is able to learn relevant events among long-term lags, however, its oscillatory abilities have not been analyzed enough. In our experiments, we found that some configurations of LSTM were able to model the signal, accurately predicting up to 400 steps forward. However, we also found that similar architectures did not perform properly when experiments were repeated, probably due to the fact that the LSTM architectures got over trained and the learning algorithm got trapped in a local minimum.

This article presents an educational platform developed to support the teaching of compensators design in a basic control theory course. The application consists of a graphical user interface in MATLAB®, and further connection to the plant under study through the data acquisition toolbox, and a data acquisition card. The developed system allows the students to experiment with parameter changes in the controllers under study, such as gain, overshoot, settling time, and peak time, and visualize results obtained from simulated or real signals. The methodology is based on the frequency response analysis. Typical Bode, root locus, and unit step response plots are easily obtained for a system before and after compensation, in a dynamical way. A modular design allows the students to easily upgrade the application in order to include further methodologies. Results derived from its use in undergraduate and graduate courses are presented. MATLAB is a registered trademark of The MathWorks, Inc.© 2012 Wiley Periodicals, Inc. Comput Appl Eng Educ 22:699–707, 2014; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21562

The accuracy of a model to forecast a time series diminishes as the prediction horizon increases, in particular when the prediction is carried out recursively. Such decay is faster when the model is built using data generated by highly dynamic or chaotic systems. This paper presents a topology and training scheme for a novel artificial neural network, named "Hybrid-connected Complex Neural Network" (HCNN), which is able to capture the dynamics embedded in chaotic time series and to predict long horizons of such series. HCNN is composed of small recurrent neural networks, inserted in a structure made of feed-forward and recurrent connections and trained in several stages using the algorithm back-propagation through time (BPTT). In experiments using a Mackey-Glass time series and an electrocardiogram (ECG) as training signals, HCNN was able to output stable chaotic signals, oscillating for periods as long as four times the size of the training signals. The largest local Lyapunov Exponent (LE) of predicted signals was positive (an evidence of chaos), and similar to the LE calculated over the training signals. The magnitudes of peaks in the ECG signal were not accurately predicted, but the predicted signal was similar to the ECG in the rest of its structure.

The authors have presented an overview and simulation of several path restoration schemes for MPLS networks. Each scheme has its own advantages and disadvantages that make them appropriate for different applications. These characteristics include recovery time in case of failure, packet loss, packet reordering, and recovery delay. The decision of implementing some of these schemes in a real network depends on how much resources are available and the requirements of the network user's. Furthermore, simulation results based on OMNET+ + show that the simple dynamic scheme has the lowest arrival time when compared to the other reported path restoration schemes. Future work will be focused on investigating further comparisons and enhancements of these schemes.

In this paper, an implementation of an educational platform for real-time linear and morphological image filtering using a FPGA NexysII, Xilinx®, Spartan 3E, is described. The system is connected to a USB port of a personal computer, which in that way form a powerful and low-cost design station for educational purposes. The FPGA-based system is accessed through a MATLAB graphical user interface, which handles the communication setup and data transfer. The system allows the students to perform comparisons between results obtained from MATLAB simulations and FPGA-based real-time processing. Concluding remarks derived from course evaluations and lab reports are presented. © 2010 Wiley Periodicals, Inc. Comput Appl Eng Educ 21: 193–201, 2013

In this paper, a multiresolution finite-impulse-response (FIR) neural-network-based learning algorithm using the maximal overlap discrete wavelet transform (MODWT) is proposed. The multiresolution learning algorithm employs the analysis framework of wavelet theory, which decomposes a signal into wavelet coefficients and scaling coefficients. The translation-invariant property of the MODWT allows alignment of events in a multiresolution analysis with respect to the original time series and, therefore, preserving the integrity of some transient events. A learning algorithm is also derived for adapting the gain of the activation functions at each level of resolution. The proposed multiresolution FIR neural-network-based learning algorithm is applied to network traffic prediction (real-world aggregate Ethernet traffic data) with comparable results. These results indicate that the generalization ability of the FIR neural network is improved by the proposed multiresolution learning algorithm.

This chapter presents analysis of emerging mHealth applications as well as the exploration of novel trends supporting healthcare intelligent environments assisted by mobile devices. The case of study is mHealth and remote vital sign monitoring. Particularly, we present a methodology for recollecting, processing and real-time monitoring heart activity with the main purpose to interpret electrocardiogram ECG signals, detect and manage situations of risk and provide the interaction between medical practitioner and patient into smart healthcare environment. The proposed architecture and approach provide continuous detection and interpretation of the patient’s QRS complex. The challenge is to adapt some approaches for data gathering, processing, compression, storage, analysis, and visualization to capabilities of mobile devices. The designed system for monitoring vital signals has been tested using standard MIT-BIH Arrhythmia Database achieving satisfactory ECG interpretation accuracy with relative error in range from 4 % to 10 % for signal sampling frequency of 360 and 128 samples per second respectively. It is important to note that the proposed prototype does not substitute diagnosis by physician. Our intention is to propose methodologies that serve as guide for development of complex health assistance tool expanding coverage of medical services.

In this paper we report a novel application-basedmodel as a suitable alternative for the classification and identification ofattacks on a computer network, and thus guarantee its safety from HTTP protocol-based malicious commands. The proposed model is built on a self-recurrentneural network based on wavelets architecture with multidimensional radialwavelons, and is therefore suited to work online by analyzing non-linearpatterns in real time to self-adjust to changes in its input environment. Sixdifferent neural network based systems have been modeled and simulated forcomparison purposes in terms of overall performance, namely, a feed forwardneural network, an Elman network, a fully connected recurrent neural network, arecurrent neural network based on wavelets, a self-recurrent wavelet networkand the proposed self-recurrent wavelet network with multidimensional radialwavelons. Within the models studied, this paper presents two recurrentarchitectures which use wavelet functions in their functionality in verydistinct ways. The results confirm that recurrent architectures using waveletsobtain superior performance than their peers, in terms not only of theidentification and classification of attacks, but also the speed ofconvergence. DOI: http://dx.doi.org/10.5755/j01.itc.43.4.4626

An electroencephalogram (EEG) is a record of the electric signal generated by the cooperative action of brain cells, that is, the time course of extracellular field potentials generated by their synchronous action. EEG is widely used in medicine for diagnostic and analysis of several conditions. In this paper, we present a system based on neural networks and wavelet analysis, able to identify epilepsy seizures using EEG as inputs. This work is part of a research looking for novel models able to obtain classification rates better that the state-of-the-art, for the identification of normal and epileptic patients using EEG. Here we present results using a Discrete Wavelet Transform (DWT) and the Maximal Overlap Discrete Wavelet Transform (MODWT) for feature extraction and Feed-Forward Artificial Neural Networks (FF-ANN) for classification. By using the benchmark database provided by the University of Bonn, our approach obtains an average accuracy of 99.26 % tested using threefold cross-validation, which is better than other works using similar strategies.

This paper presents the proposed architecture that provides platform for implementation of intelligent software agents (Multi-Agent System) used for information retrieval based on user-oriented model. The existing architectures based on multi-agents as usual lack the ability for adaption to user requirements. Thus, the principal goal is to develop standard reusable scalable infrastructure based on intelligent multi-agents that incorporates particular user model providing relevant information to user queries taking into account his profile, operational patterns and preferences. The evaluation of the proposed architecture has been done comparing it with existing approaches taking into account relevant criteria such as used communication standards for information exchange between agents, available scalable layered structure and ability of adapting information or services to user habits, personal data and requirements. This approach has sufficient merit to be used as a reference for development of applications for user-oriented and adaptive information retrieval systems.

In this paper we present a novel approach for automatic annotation of objects or regions in images based on their color and texture. According to the proposed generalized architecture for automatic generation of image content descriptions the detected regions are labeled by developed cascade SVM-based classifier mapping them to structure that reflects their hierarchical and spatial relation used by text generation engine. For testing the designed system for automatic image annotation around 2,000 images with outdoor-indoor scenes from standard IAPR-TC12 image dataset have been processed obtaining an average precision of classification about 75 % with 94 % of recall. The precision of classification based on color features has been improved up to 15 ± 5 % after extension of classifier with texture detector based on Gabor filter. The proposed approach has a good compromise between classification precision of regions in images and speed despite used considerable time processing taking up to 1 s per image. The approach may be used as a tool for efficient automatic image understanding and description.

Image and video compression exploits the redundancy of data to create a smaller representation. Lossy compression can be considered to be a type of transform coding where the raw data is transformed to a domain. Such a transform coding stores most of image energy into very few coefficients. In this paper we propose a compression algorithm based on Set Partitioning In Hierarchical Trees (SPIHT) that exploits the Human Visual System (HVS) and its fovea. In order to increase the image quality of the reconstructed image, regions of interest (ROI) are defined around a given point of gaze. The use of a fovea combined with ROI for image compression can help to improve the quality of the perception of the image and preserve different levels of detail around the ROI. In the proposed approach, the image is compressed using the Lifting Wavelet Transform and then quantized at multiple compression ratios around the point of fixation of an observer, taking advantage of the natural aliasing of the HVS around the fovea. Such a compression delivers better image or frame reconstruction when a fixation point of an observer is given. DOI: http://dx.doi.org/10.5755/j01.itc.42.4.3076

This paper develops an integrated system for forest fire fighting facility location. We propose a mathematical model to deploy available fire fighting resources in proper positions so that any forest fire can be attacked within a specified response time. The proposed model considers budget constraints. This location problem is a variant of the well-known Maximal Covering Location Problem (MCLP) which is known to be NP-hard. We propose a hybrid algorithm that combines GRASP and Tabu Search procedures. According to preliminary computational experiments the hybrid algorithm provides good quality solutions with a reasonable amount of computer effort. This solution can give support to the decision maker for determining the location of fire-fighting resources.

In this paper, an architecture based on adaptive neuro-fuzzy inference systems (ANFIS) assembled to recurrent neural networks, applied to the problem of mental tasks temporal classification, is proposed. The electroencephalographic signals (EEG) are pre-processed through band-pass filtering in order to separate the set of energy signals in alpha and beta bands. The energy in each band is represented by fuzzy sets obtained through an ANFIS system, and the temporal sequence corresponding to the combination to be detected, associated to the specific mental task, is entered into a recurrent neural networks. This experiment has been carried out in the context of brain-computer-interface (BCI) systems development. Experimentation using EEG signals corresponding to mental tasks exercises, obtained from a database available to the international community for research purposes, is reported. Two recurrent neural networks are used for comparison purposes: Elman network and a fully connected recurrent neural network (FCRNN) trained by RTRL-EKF (real time recurrent learning – extended Kalman filter). A classification rate of 88.12% in average was obtained through the FCRNN during the generalization stage.

Wavelet foveated compression can be used in real-time video processing frameworks for reducing the communication overhead while keeping high visual quality. Such algorithm leads into high rate compression results due to the fact that the information loss is isolated outside a region of interest (ROI). The fovea compression can also be applied to other classic transforms such as the commonly used the discrete cosine transform (DCT). In this paper, a fovea window for wavelet-based compression is proposed. The proposed window allows isolate a fovea region over an image. A comparative analysis has been performed showing different error and compression rates between the proposed fovea window for wavelet-based and the DCT-based compression algorithms. Simulation results show that with foveated compression high ratio of compression can be achieved while keeping high quality over the designed ROI.

A novel framework on cell phone for recollecting, processing and interpretation of patient’s electrocardiograms ECG as part of development of health care and assisted living environments is presented in this paper. The proposed architecture and algorithm provide continuous detection of the QRS complex during real time ECG monitoring and interaction between doctor and patient expanding coverage of medical services. The developed procedure for heart activity monitoring uses a set of filters for image noise reduction and computes ECG signal gradient for identification of the components with the greatest slope. To highlight the steepest parts of ECG, the absolute value of gradient is averaged over a moving window of 80 ms considered as the minimum duration of QRS complex. In the decision phase, a peak detector is applied. The height of detected peaks is compared to the threshold determined as the signal-to-noise ratio for final definition of heart rate. The designed prototype has been tested using standard MIT-BIH Arrhythmia Database and evaluated confirming that system has good compromise between high transmission and processing speed and satisfactory accuracy, which does not fall below the precision of commercial equipment for heart monitoring.

A brain computer interface (BCI) is a system that aims to control devices by analyzing brain signals patterns. In this work, a convenient time-frequency representation (TFR) for visualizing ERD/ERS phenomenon (Event related synchronization and desynchronization) based on Hilbert transform and spatial patterns is addressed, and a wavelet based feature extraction method for motor imagery tasks is presented. The feature vectors are constructed with four statistical and energy parameters obtained from wavelet decomposition, based on the sub-band coding algorithm. Experimentation with three classification methods for comparison purposes was carried out using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Support Vector Machine (SVM). In each case, ten-fold validation is used to obtain average misclassification rates.

The aim of this work is the design and implementation of a DWT architecture FPGA-based platform for up to three dimensional signal processing. First, filter banks are designed using a distributed arithmetic technique. Then, we design controllers, interfaces and protocols that handle, transmit and sequence all the data during the computing process. Data is sent via USB to the FPGA and the user interface is programmed in MATLAB. A graphical user interface manages the system operation and displays the results on a PC. Designed filters are compared with a fully parallel architecture in relation to the number of gates used, speed, and algorithm performance.

An EEG-based classification method in the time domain is proposed to identify left and right hand motor imagery as part of a brain-computer interface (BCI) experiment. The feature vector is formed by sixth order autoregressive coefficients (AR) or sixth order adaptive autoregressive coefficients (AAR) representing EEG signals obtained from C3 and C4 channels, according to the EEG 10–20 standard. The signal is analyzed considering 1 second windows with a 50% overlapping. A feature selection process based on the Fisher Criterion (FC) removes irrelevant or noisy information. A Linear Discriminant Analysis (LDA) is applied to both cases: feature vectors formed with the total number of coefficients, and feature vectors formed with coefficients corresponding to larger Fisher Ratio. Classification results obtained using two AR methods, Burg and Levinson-Durbin, and one AAR LMS are presented.

In this paper we present a novel approach for automatic segmentation and recognition of reCAPTCHA in Web sites. It is based on CAPTCHA image preprocessing with character alignment, morphological segmentation with three-color bar character encoding and heuristic recognition. The original proposal consists in exploiting three-color bar code for characters in CAPTCHA for their robust segmentation with presence of random collapse overlapping letters and distortions by particular patterns of waving rotation. Additionally, a novel implementation of SVM-based learning classifier for recognition of combinations of characters in training corpus has been proposed that permits to increment more than twice the recognition success rate without time extension of system response. The main goal of this research is to reduce vulnerability of CAPTCHA from spam and frauds as well as to provide a novel approach for recognizing either handwritten or degraded and damaged texts in ancient manuscripts. Our designed framework implementing the proposed approach has been tested in real-time applications with sites used CAPTCHAS achieving segmentation success rate about of 82% and recognition success rate about of 94%.

In this paper we compare an analytical framework based on Real-Time Calculus with the existing analytical approaches commonly used for the performance evaluation of network interfaces such as probabilistic queuing models, parallel computation model, and protocol offload models (LAWS and EMO). In particular, we focus on the capabilities of these alternatives that can be employed for the performance evaluation of the NIC's buffer requirements in a network node.

An experiment on the detection of a P-300 rhythm for potential applications on brain computer interfaces (BCI) using an Adaptive Neuro Fuzzy algorithm (ANFIS) is presented. P300 evoked potential is an electroencephalographic (EEG) signal obtained at the central-parietal region of the brain in response to rare or unexpected events. The P300 evoked potential is obtained from visual stimuli followed by a motor response from the subject. The EEG signals are obtained with a 14 electrodes Emotiv EPOC headset. Preprocessing of the signals includes denoising and blind source separation using an Independent Component Analysis algorithm. The P300 rhythm is detected using the discrete wavelet transform (DWT) applied on the preprocessed signal as a feature extractor, and further entered to the ANFIS system. Experimental results are presented.

Region of interest (ROI) based compression can be applied to real-time video transmission in medical or surveillance applications where certain areas are needed to retain better quality than the rest of the image. The use of a fovea combined with ROI for image compression can help to improve the perception of quality and preserve different levels of detail around the ROI. In this paper, a fovea-ROI compression approach is proposed based on the Set Partitioning In Hierarchical Tree (SPIHT) algorithm. Simulation results show that the proposed approach presents better details in objects inside the defined ROI than the standard SPIHT algorithm.

This paper presents a novel approach for registration of 3D images based on optimal free-form rigid transformation. A proposal consists in semiautomatic image segmentation reconstructing 3D object surfaces in medical images. The proposed extraction technique employs gradients in sequences of 3D medical images to attract a deformable surface model by using imaging planes that correspond to multiple locations of feature points in space, instead of detecting contours on each imaging plane in isolation. Feature points are used as a reference before and after a deformation. An issue concerning this relation is difficult and deserves attention to develop a methodology to find the optimal number of points that gives the best estimates and does not sacrifice computational speed. After generating a representation for each of two 3D objects, we find the best similarity transformation that represents the object deformation between them. The proposed approach has been tested using different imaging modalities by morphing data from Histology sections to match MRI of carotid artery.

Wavelet foveated compression can be used in real-time video processing frameworks for reducing the communication overhead. However, each wavelet can yields into different results on compression ratio. Classic foveation filters also applies cutoff frequencies over the region of interest (ROI). A comparative analysis has then been performed showing the different error rate for different cutoff frequency windows that preserves the ROI coefficients intact against windows that apply cutoffs over the ROI. Simulation results show that with wavelet-based foveated compression high ratio of compression can be achieved while keeping high quality over the designed ROI.