Search

Atrial fibrillation is the most common arrhythmia in the world affecting up to 2% of the world population. Atrial fibrillation and atrial flutter increase the risk of serious diseases such as, heart failure, renal disease and sudden death, in addition atrial fibrillation increases up to 5 times the probability of suffering a stroke which is the third cause of death in the world. The main challenge related to these diseases is the lack of diagnosis, since in early stage of these conditions events are random and self-terminated. Because of this, it is estimated that approximately 33% of the population are undiagnosed. In this work we propose the use of spatio-temporal filtering to perform a robust characterization of the atrial activity in ECG records. Spatio-temporal filter has been adapted using two configurations of this. In on of the configurations the filter is trained to detect the position of the P wave and then PQ distances are computed and their variability. This configuration is called spatio-temporal detection filter and allows to distinguish normal sinus rhythm signals from atrial fibrillation. The proposed method allowed for AF detection with the accuracy of 98:75% on the basis of both 8–channel and 2–channel signals of 12s length. When the signals length was decreased to 6s, the accuracy varied in the range of 95% to 97:5% depending on the number of channels and the dispersion measure applied. In the second configuration, spatio-temporal filter is used to enhance atrial waveform, this configuration is called spatio-temporal enhacing filter. The ability of spatio-temporal filter to enhance the atrial flutter waves is presented. The proposed algorithm allows simple but effective classification of the two types of atrial arrhythmias: Atrial flutter and atrial fibrillation. Tested on a database containing the cases of both atrial arrhythmias, the algorithm achieved 98% of accuracy.

Los dispositivos electrónicos se han convertido en un elemento indispensable para estar en contacto, sin embargo, vivir en una era tecnológica en donde las personas están sumidas en el constante uso de los artefactos móviles produce que esta incesante manipulación del teléfono celular lleve consigo problemas de postura y de visión que con el tiempo puede ocasionar enfermedades. El presente trabajo tuvo como propósito investigar las posturas comunes durante el uso de teléfonos móviles que pueden estar asociadas a síntomas de dolencias o problemas musculoesqueléticos y de la visión. Este trabajo utiliza modelos biomecánicos simplificados de la cabeza, cuello, espalda y antebrazos para estimar las fuerzas y los momentos netos en las articulaciones necesarias para mantener el equilibrio estático durante uso del teléfono móvil. Se realizó una encuesta para identificar las posturas comunes adoptadas por estudiantes universitarios al usar el teléfono móvil, y se seleccionaron dos de estas para realizar el análisis biomecánico. posterior a eso, se escogieron diez voluntarios entre hombres y mujeres para analizar los resultados que muestran los cálculos biomecánicos y así determinar una relación entre las posturas y los ángulos de visión. Los resultados muestran que las posturas que permiten ángulos de visión cómodos pueden causar momentos de carga más altos en las articulaciones, lo que puede producir molestias musculoesqueléticas.

El objetivo de este trabajo es diseñar y realizar el seguimiento de un instrumento quirúrgico para estimación de poses con alta precisión, usando como metodología la estimación de la pose tridimensional a partir marcadores planos, específicamente marcadores ArUco para mayor correspondencia de puntos, por otro lado fue necesaria una calibración de la posición de la punta del instrumento respecto a los marcadores, basada en optimización por mínimos cuadrados, lo anterior se implementó usando la librería OpenCV y el lenguaje de programación Python. Para diferentes experimentos de seguimiento y reconstrucción de un objeto se obtuvieron errores submilimétricos. Por lo tanto, el sistema puede usarse teniendo un ambiente controlado para procedimientos médicos.

Attention deficit hyperactivity disorder (ADHD) is a neurological condition that is diagnosed based on the evaluation of a number of symptoms of excessive and impairing levels of inattention, hyperactivity and impulsivity. Electroencephalography (EEG) tests are used to diagnose ADHD, but they serve as a supplement to the main clinical and psychological evaluation. This work presents a method for the classification of ADHD and control cases, with the use of EEG signals. The initial data set is formed from EEG records of 47 children including 22 diagnosed with ADHD and 25 in a control group. The system consists the following stages: signal acquisition, pre-processing and filtering, feature extraction and selection, and final classification. The 2-tone oddball paradigm was used to elicit auditory event-related potentials (ERP). The filtering stage includes wavelet filtering and synchronized averaging. For feature extraction, different measures were selected, including amplitude and latency of cognitive evoked potentials, frequency bands power, and entropy and chaos quantification. For the classification process, two previously selected subsets were passed through the same process of classification, where first was applied two different dimensionality reduction methods, and finally, multiple machine learning algorithms were applied. The best performance was obtained when using the Support Vector Machines algorithm, with a maximum accuracy value of 86.84$\%$ using a subset obtained though ridge regression, and both dimensionality reduction algorithms.

Background and objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia in the world. It is associated with significantly increased morbidity and mortality. Diagnosis of the disease can be based on the analysis of the electrical atrial activity, on quantification of the heart rate irregularity or on a mixture of the both approaches. Since the amplitude of the atrial waves is small, their analysis can lead to false results. On the other hand, the heart rate based analysis usually leads to many unnecessary warnings. Therefore, our goal is to develop a new method for effective AF detection based on the analysis of the electrical atrial waves. Methods: The proposed method employs the fact that there is a lack of repeatable P waves preceding QRS complexes during AF. We apply the operation of spatio-temporal filtering (STF) to magnify and detect the prominent spatio-temporal patterns (STP) within the P waves in multi-channel ECG recordings. Later we measure their distances (PQ) to the succeeding QRS complexes, and we estimate dispersion of the obtained PQ series. For signals with normal sinus rhythm, this dispersion is usually very low, and contrary, for AF it is much raised. This allows for effective discrimination of this cardiologic disorder. Results: Tested on an ECG database consisting of AF cases, normal rhythm cases and cases with normal rhythm restored by the use of cardioversion, the method proposed allowed for AF detection with the accuracy of 98.75% on the basis of both 8–channel and 2–channel signals of 12 s length. When the signals length was decreased to 6 s, the accuracy varied in the range of 95% − 97.5% depending on the number of channels and the dispersion measure applied. Conclusions: Our approach allows for high accuracy of atrial fibrillation detection using the analysis of electrical atrial activity. The method can be applied to an early detection of the desease and can advantageously be used to decrease the number of false warnings

We propose a three-dimensional (3D) multimodal medical imaging system that combines freehand ultrasound and structured light 3D reconstruction in a single coordinate system without requiring registration. To the best of our knowledge, these techniques have not been combined as a multimodal imaging technique. The system complements the internal 3D information acquired with ultrasound with the external surface measured with the structured light technique. Moreover, the ultrasound probe’s optical tracking for pose estimation was implemented based on a convolutional neural network. Experimental results show the system’s high accuracy and reproducibility, as well as its potential for preoperative and intraoperative applications. The experimental multimodal error, or the distance from two surfaces obtained with different modalities, was 0.12 mm

La prueba cutánea (SPT) se utiliza para diagnosticar múltiples alergias. Este método se basa en medir el tamaño de las pápulas que aparecen en la piel al exponerse a un alérgeno. No obstante, la medición manual es un proceso tedioso y es susceptible a errores inter e intraobservador. Por esta razón, se han planteado diferentes enfoques, con el fin de mejorar la reproducibilidad de la prueba. El objetivo de este trabajo es mejorar parte de la lectura automatizada de la prueba cutánea, mejorando la confiabilidad del proceso de detección de pápulas mediante el uso de redes neuronales convolucionales (CNN). El conjunto de datos está conformado por imágenes 3D de la superficie del brazo. Con estas, se entrena una CNN para detectar y segmentar las pápulas, y finalmente, se realiza un ajuste paramétrico para medir su diámetro mayor. Estos resultados son comparados con las mediciones realizadas por un médico en una interfaz, para así obtener indicadores de concordancia entre las medidas. Los resultados muestran que, a pesar de la poca cantidad de datos adquiridos, el método planteado permite realizar una detección confiable. Estos resultados podrían ser mejorados teniendo una mayor cantidad de datos para mejorar la generalización y exactitud de la segmentación de la CNN.

The low participation of women in STEM fields has been considered a critical issue in our society. It affects the rights of women to receive high quality education, to develop their skills and to improve their career prospects. Additionally, it has a negative impact on the outcomes of science and engineering projects. This paper describes the methodology and preliminary results of the application of an instrument to measure indicators for gender equality in STEM programs. The SAGA survey, developed by UNESCO, was applied in fifteen European and Latin American universities within the framework of the W-STEM project. This paper presents the results of nine Latin American universities related to gender equality in student population and teaching staff, as well as attraction, access, and graduation of female vs male students. The gender gap is evident in all the indicators, so it is necessary to define policies and strategies to face this issue from different levels

Emotions are affective states related to physiological responses. This study proposes a model for recognition of three emotions: amusement, sadness, and neutral from physiological signals with the purpose of developing a reliable methodology for emotion recognition using wearable devices. Target emotions were elicited in 37 volunteers using video clips while two biosignals were recorded: photoplethysmography, which provides information about heart rate, and galvanic skin response. These signals were analyzed in frequency and time domains to obtain a set of features. Several feature selection techniques and classifiers were evaluated. The best model was obtained with random forest recursive feature elimination, for feature selection, and a support vector machine for classification. The results show that it is possible to detect amusement, sadness, and neutral emotions using only galvanic skin response features. The system was able to recognize the three target emotions with accuracy up to 100% when evaluated on the test data set. © 2019 Elsevier Ltd

The growing need to perform surgical procedures, monitoring, and intervention of greater precision have led to the development of multimodal medical imaging systems. Multimodal images are a strategy to overcome the limitations of medical imaging technologies by combining the strengths of individual modalities or technologies. In this work, we propose a low-cost multimodal system that combines 3D freehand ultrasound with fringe projection profilometry to obtain information from the external and the internal structure of an object of interest. Both modalities are referred to a single coordinate system defined in the calibration to avoid post-processing and registration of the acquired images. The freehand ultrasound calibration results are similar to those previously reported in the literature using more expensive infrared tracking systems. The calibration reproducibility at the center point of the ultrasound image was 0.6202 mm for 8 independent calibrations. We tested our system on a breast phantom with tumors. Encouraging results show the potential of the system for applications in intraoperative settings.

Pneumonia is an infection of the lungs caused by virus, bacteria or fungi. It affects mainly children under five and can be life-threatening. Diagnosis of pneumonia is usually performed using imaging techniques such as chest radiography, ultrasound, and CT. Several studies have shown that ultrasound is an effective, safe and cost-efficient technique for pneumonia detection. However, due to the low signal-to-noise ratio of the images, this technique is highly dependent on the experience of the practitioner. This paper proposes an approach for pneumonia detection from image texture features. We used empirical mode decomposition for feature extraction, principal component analysis for dimensionality reduction and supervised learning methods for classification. Results show that features of the first mode present large differences between healthy and pneumonia patients according to the Cohen’s d index. Pneumonia detection was possible with a rotation forest model with a mean accuracy of 83.33%.

Attention deficit and hyperactivity disorder (ADHD) is a medical condition that affects approximately 7% of children worldwide. The diagnosis of ADHD can be done using psychological tests and electroencephalography (EEG). However, the variability and complexity of EEG signals affects its diagnostic utility. The purpose of this work is to identify relevant features of EEG signals from children diagnosed with ADHD and control cases for their classification. A total of 47 children were included in the study (22 with ADHD and 25 in the control group). EEG of cognitive evoked potentials were preprocessed using wavelet filtering and synchronized averaging. Then, fourteen features were calculated in signals from four channels (F3, AF3, F4 and AF4), including evoked potentials, power spectrum, entropy, chaos, bicoherence measures, and prominent peaks. For feature selection, the algorithms PCA, hybrid stepwise regression, ridge regression, and correlation values were evaluated. It was evidenced that evoked potentials have a relative high level of importance, as well as the prominent peaks. On the other hand, the values of chaos and bicoherence measures, along with the gender, are the least representative features. These results are consistent among the four feature selection algorithms. In conclusion, 9 of the 14 features are representative of the data set and were used for the classification stage of this work.

The need to make timely and accurate diagnoses of brain diseases has posed challenges to computer-aided diagnosis systems. In this field, advances in deep learning techniques play an important role, as they carry out processes to extract relevant anatomical and functional characteristics of the tissues to classify them. In this paper, the study of various architectures of convolutional neural networks (CNN) is presented, with the aim of classifying three types of brain tumors in high-contrast magnetic resonance (MR) images. The architectures of the present study were VGG16, ResNet50, Xception, whose implementations are defined in the Keras framework. The evaluation of these architectures were preceded by data augmentation techniques and transfer learning, which improved the effectiveness of the training process, thanks to the use of pre-trained models with the ImageNet dataset. The VGG16 architecture was the one with the best performance, with an accuracy of 98.04%, followed by ResNet50 with 94.89%, and finally, Xception with 92.18%.

The use of mobile phones for long periods of time has been associated with musculoskeletal and vision symptoms. This work uses simplified biomechanical models of the head, neck, back, and forearms to estimate the forces and net moments at the joints required to maintain static equilibrium during mobile phone use. We conducted a survey to identify the most common postures adopted by university students when using the mobile phone and selected two of them to perform the biomechanical analysis. The results show that postures that allow comfortable viewing angles may cause higher loading moments at the joints, which can produce musculoskeletal discomfort.

Ultrasound has been considered a safe and accurate alternative to radiography and computerized tomography to diagnose lung diseases such as pneumonia. However, speckle noise, artifacts or certain conditions can difficult image interpretation. For example, in some cases, the pleura line cannot be observed. This work proposes an approach for discriminating between lung and muscular tissues in ultrasound images. We evaluated the symlet and daubechies wavelets for feature extraction, principal component analysis and recursive backward elimination for feature selection, and supervised learning methods for classification. Statistical moments and the energy of the second horizontal coefficient and peak-to-peak root mean squared ratio were the features more outstanding over the rest. The best model was obtained with recursive backward elimination for feature selection and knearest neighbor for classification. Tissue classification was possible with a mean accuracy of 97.5% and area under the curve of 99%. These results offer great insights on the recognition of lung and muscular tissues, which could improve the effectiveness of automatic segmentation and analysis algorithms.

esis contributesto the strengthening of FPP systems in the clinical setting and the problems that arisealong the 3D imaging pipeline. We have dealt with and proposed a solution to theproblems arising in FPP acquisition, especially when measuring human skin. We have dealt with and proposed a solution to theproblems arising in FPP acquisition, especially when measuring human skin. Also,we have explored the main shortcomings of Fourier Transform Profilometry (FTP) forphase retrieval and proposed a modified FTP method to overcome these limitations.Furthermore, we have introduced a Simultaneous Phase Unwrapping and Denoisingalgorithm for phase imaging in challenging conditions. Finally, we have described aframework for the robust automated measurement of 3D skin features from the SkinPrick Test. Through experimental results, we have shown that the proposed methodsprovide accurate and reliable measurements of human skin features

Fringe Projection Profilometry (FPP) is becoming an essential tool in the measurementof 3D human skin features due to its non-contact nature and high precision. Skinfeatures are necessary for monitoring and characterize lesions of the skin. However, theconventional methods for assessing skin lesions are cumbersome and prone to interandintra-observer variations. Recently, FPP 3D scanning technology promises the bestresults in terms of accuracy, fast acquisition, and processing. This thesis contributesto the strengthening of FPP systems in the clinical setting and the problems that arisealong the 3D imaging pipeline. We have dealt with and proposed a solution to theproblems arising in FPP acquisition, especially when measuring human skin. Also,we have explored the main shortcomings of Fourier Transform Profilometry (FTP) forphase retrieval and proposed a modified FTP method to overcome these limitations.Furthermore, we have introduced a Simultaneous Phase Unwrapping and Denoisingalgorithm for phase imaging in challenging conditions. Finally, we have described aframework for the robust automated measurement of 3D skin features from the SkinPrick Test. Through experimental results, we have shown that the proposed methodsprovide accurate and reliable measurements of human skin features.

Los estilos de conducción se puede dividir en dos categorías principales: "tranquilo"(no agresivo) y agresivo. El reconocimiento de los mismos puede ayudar a lossistemas de seguridad de los vehículos y, potencialmente, reducir las muertes detráfico en las carreteras. Estos estilos son afectados fuertemente por las emociones.Este trabajo presenta el análisis de impacto de los estados emocionales obtenidos apartir de señales fisiológicas en la atuonomía de vehículos eléctricos. Este enfoque serealizó desde el dominio fisiológico y del rendimiento del vehículo. La metodologíapropuesta no solo es capaz de reconocer el comportamiento de conducción de lasseñales biológicas y el rendimiento del vehiculo, sino también de estimar su impactoen el rango de vehículos eléctricos.

This paper presents a new database consisting of concurrent articulatory and acoustic speech data. The articulatory data correspond to ultrasound videos of the vocal tract dynamics, which allow the visualization of the tongue upper contour during the speech production process. Acoustic data is composed of 30 short sentences that were acquired by a directional cardioid microphone. This database includes data from 17 young subjects (8 male and 9 female) from the Santander region in Colombia, who reported not having any speech pathology. © 2019 IEEE.

In this paper, we propose to apply spatio-temporal filtering to atrial activity enhancement, prior to the detection of possible atrial arrhythmias. During normal sinus rhythm, the atrial activity is well synchronized with the ventricular one. The distances between ventricular QRS complexes and the preceding atrial P waves are approximately constant. However, during atrial arrhythmias such a synchronization does not exist. Although both atrial fibrillation (AF) and atrial flutter (AFL) are also characterized by irregularity of RR intervals, nevertheless it is this lack of atrioventricular synchronization and the associated irregularity of atrial activity (AA) that is the most straightforward symptom of atrial arrhythmias. In AFL episodes, the atrial activity tends to be more regular, whereas in AF it is almost completely unpredictable. Our objective is to enhance this activity to facilitate discrimination between the two arrhythmias. Spatio-temporal filtering (STF) was developed for detection of fetal QRS complexes in an ECG signal recorded from the abdomen of a pregnant woman. The filter can easily be applied to enhance the P waves in regular ECG signals. In this paper, however, we modify the learning phase of STF, to make it useful also for enhancement of abnormal atrial activity. The STF ability to enhance the atrial flutter waves is presented. An algorithm is proposed that allows for simple but effective discrimination between the two types of atrial irregular activity: AFL and AF. Tested on a database containing the cases of both atrial arrhythmias, the algorithm allows for their almost faultless recognition. © 2019 Association for Computing Machinery.

Ultrasound imaging is a safe and cost-effective diagnostic tool, but the quality of the images is affected by speckle noise and artifacts. Anisotropic diffusion filters can be used to reduce noise and preserve the edges in the image. However, this technique is very sensitive to the number of iterations selected. This paper proposes a stopping criterion for effective noise removal without blurring the edges, based on the relative variance between the estimated denoised image and the original one. Different quality metrics were evaluated in 25 test images. The results suggest that the proposed stopping criterion can be implemented efficiently and aids in the process of automation of the filter. © 2019 IEEE.

The recognition of aggressive driving patterns could aid to improve driving safety and potentially reduce traffic fatalities on the roads. Driving behavior is strongly shaped by emotions and can be divided into two main categories: calmed (non-aggressive) and aggressive. In this paper, we present a methodology to recognize driving behavior using driving performance features and biosignals. We used biosensors to measure heart rate and galvanic skin response of fifteen volunteers while driving in a simulated scenario. They were asked to drive in two different situations to elicit calmed and aggressive driving behaviors. The purpose of this study was to determine if driving behavior can be assessed from biosignals and acceleration/braking events. From two-tailed student t-tests, the results suggest that it is possible to differentiate between aggressive and calmed driving behavior from biosignals and also from longitudinal vehicle’s data. © 2019, Springer Nature Switzerland AG.

Pneumonia is a condition that can be life-threatening and affects a high number of children around the world. Lung ultrasound can be used for the diagnosis of pneumonia, but requires high experience. This paper presents an approach for pneumonia detection based on texture analysis of ultrasound images. Several measures were taken in healthy tissues and pneumonia lesions, and the most significant features were identified by statistical analysis. The results of the analysis of variance and exploratory analysis suggest that detection of pneumonia is possible based on image texture features. © 2019 IEEE.

Attention-deficit/hyperactivity disorder (ADHD) is a neurological condition that affects the quality of life of the patients. It can be diagnosed using a combination of psychological tests. In addition to that, the brain activity of the patients can be analyzed using electroencephalography (EEG). The application of EEG tests requires the cooperation of the patients, which can be challenging in patients with ADHD. This paper describes the development of a system for stimuli generation, and acquisition and analysis of cognitive evoked potentials using the commercial system Emotiv EPOC+ headset. The results show that the system allows precise and reliable measurements of the P300 waves in children, and may provide a more comfortable experience for the patients compared to medical-grade systems. © 2019 IEEE.

Actualmente, el desarrollo de dispositivos de bajo costo que puedan medir la oxigenación en la sangre y el ritmo cardíaco de forma correcta es un tema prioritario en estudios médicos, permitiendo tanto a familiares como médicos tener conocimiento del estado del individuo y así poder realizar un seguimiento que pueda prevenir trastornos a futuro. Esto es de vital importancia si se considera que muchos pacientes con problemas pulmonares y cardíacos tienen que llevar un control en el nivel de oxígeno en su sangre, como sucede con los neonatos prematuros, pues sus pulmones son de los últimos órganos en desarrollarse. Es por esta razón que los pediatras recomiendan el uso de un oxímetro de pulso en casa para que, en caso de una emergencia, la familia logre percatarse a tiempo y contactar al médico para recibir atención oportuna de la enfermedad o de algún otro padecimiento. Por esta razón se propone el diseño de un dispositivo inalámbrico de bajo costo para el uso cotidiano con el cual se obtendrán datos referentes a la saturación de oxígeno y ritmo cardíaco del individuo. El prototipo fue diseñado con la ayuda de un módulo de intercomunicación inalámbrica, un módulo infrarrojo para la detección de pulsos cardíacos y oxígeno en la sangre y una batería portable, para el uso diario junto con el desarrollo de una página web para poder monitorear los datos en tiempo real.

Los estilos de conducción se puede dividir en dos categorías principales: "tranquilo"(no agresivo) y agresivo. El reconocimiento de los mismos puede ayudar a lossistemas de seguridad de los vehículos y, potencialmente, reducir las muertes detráfico en las carreteras. Estos estilos son afectados fuertemente por las emociones.Este trabajo presenta el análisis de impacto de los estados emocionales obtenidos apartir de señales fisiológicas en la atuonomía de vehículos eléctricos. Este enfoque serealizó desde el dominio fisiológico y del rendimiento del vehículo. La metodologíapropuesta no solo es capaz de reconocer el comportamiento de conducción de lasseñales biológicas y el rendimiento del vehiculo, sino también de estimar su impactoen el rango de vehículos eléctricos.

no tiene

En este proyecto se propone el diseño del prototipo de un dispositivo para la inspección de busques y embarcaciones sumergidos empleando sensores de ultrasonido. Se evaluaron diferentes tipos de sensores, configuraciones y materiales para la construcción del sistema.

Es una práctica común en la oftalmología el hacer el estudio del estado de la córnea en los pacientes mediante la microscopía especular. El objetivo de dicho estudio es, principalmente, conocer la densidad celular (CD, por sus siglas en inglés), de manera que el profesional encargado pueda dar un diagnóstico de la salud de la córnea del paciente en cuestión. Realizar esta tarea manualmente resulta tedioso y consume mucho tiempo, razón por la cual en muchas clínicas se ha optado por usar softwares capaces de medir la densidad celular de manera automática o semi-automática (guiada por el operador). Sin embargo, distintas enfermedades pueden afectar a la córnea y dificultar la evaluación automática mediante software. En este trabajo tratamos específicamente las imágenes de pacientes con córnea guttata. Para esto desarrollamos un software que permite corregir la segmentación de células en imágenes de microscopía especular. Este ha demostrado ser robusto y flexible a las distintas necesidades del especialista en estos casos.

Novel technological aids have been developed to evaluate sport performance. Among these tools there are wearable sensors that monitor physical and physiological variables during the execution of exercises. This paper describes the design and construction of an instrumented insole for acquisition and transmission of plantar pressure. The system was designed to support heavy weights, such as in weightlifting. It uses five high-range force sensors located in relevant anatomical points. It can be worn comfortably by the athlete and plantar pressure can be transmitted wirelessly to be registered and visualized in real-time. © Springer Nature Switzerland AG 2018.

Brain activity during perception and recognition of faces have been studied by researchers with the purpose to develop brain-computer interfaces and to study neurological disorders. In this paper, we analyzed evoked potentials as neurophysiological indicators and developed a model based on signal processing and machine learning techniques to find descriptive patterns that allow the differentiation of familiar and unfamiliar faces. We considered wave components such as P1, N170, N250, P300, and N400 to describe the events. Morphological analysis and wavelet transform were used for the feature extraction stage, and support vector machines and binomial logistic regression were evaluated for the classification stage. The best classification results were obtained with the morphological characteristics, where the highest classification accuracy was 80% on average. © 2018 IEEE.

La fatiga muscular no solo conlleva a la disminuci´on del rendimiento f´ısico de un individuo, sino tambi´en al aumento del riesgo de sufrir lesiones a nivel muscular, es por ello que el prop´osito de la presente investigaci´on consiste en predecir dichos estados de fatiga (Ausencia/Presencia) al realizar actividades f´ısicas repetitivas. Para ello la se˜nal Electromiogr´afica (EMG) fue sometida a un proceso de extracci´on de caracter´ısticas mediante el uso de la Transformada Discreta de Wavelet (DWT) con el ´animo de obtener las variables independientes (Coeficientes de energ´ıa y Voltaje RMS) requeridas por el algoritmo clasificador de regresi´on log´ıstica binaria. Con esta estrategia se obtuvieron resultados por encima del 85 % de probabilidad para pronosticar la ocurrencia de fatiga muscular, lo que la convierte en una buena herramienta de clasificación de dichos estados.

La percepción y el reconocimiento de caras se ha estudiado con el fin de analizar la actividad cerebral en respuesta a este tipo de estímulos. Esta información es importante para el desarrollo de las interfaces cerebro-computadora y el estudio de los trastornos neurológicos. En este trabajo, se analizaron potenciales evocados como indicadores neurofisiológicos y desarrollamos un modelo basado en técnicas de procesamiento de señales y aprendizaje automático para encontrar patrones descriptivos que permitan la diferenciación de rostros familiares y no familiares. Consideramos componentes de onda como P1, N170, N250, P300 y N400 para describir los eventos. El análisis morfológico y la transformada wavelet se utilizaron para la etapa de extracción de características, y las máquinas de vectores de soporte y la regresión logística binomial se evaluaron para la etapa de clasificación. Los mejores resultados de clasificación se obtuvieron con las características morfológicas, donde la mayor precisión de clasificación fue del 80% en promedio.

Many car accidents that result in pedestrian deaths or serious injuries are due to their inattention when crossing the street. Pedestrians often get distracted using mobile phones or music players, what prevents them to perceive warning signs and sounds. In this work, we developed a method to estimate the speed of an approaching vehicle using features of the generated acoustic signals. This system can be used as a component of a warning system of potential road risks for pedestrians. We used a single microphone to record audio signals. They were processed to extract features in frequency and time domains that were used as inputs to a neural network. Speed estimation was done using a feed forward neural network. We used several architectures and training algorithms. Results show mean error percentages of 14.57% for speeds from 10 to 40 km/h when using a neural network with two hidden layers. © 2016 IEEE.

The use of technological aids in sports has increased in the last years. These tools allow to register the athletes’ movements to evaluate and track their performance over time. With that information, it is possible to design more effective training routines, prevent and treat injuries, and improve performance. This paper describes the design and construction of an electronic system to register joint angle and electromyography signals during the execution of weightlifting exercises. The system was designed to be unobtrusive, energy efficient, and low cost. It was evaluated during the execution of flexion/extension exercises of the arm with weights, and was effective to acquire the signals and transmit them wirelessly in real-time. Electromiography signals were visualized and analyzed with an adequate dynamic range, and angle measurements were performed with error percentages less than 0.8 %. © 2016, International Sports Engineering Association.

This paper describes a region growing segmentation algorithm for medical ultrasound images. The algorithm starts with anisotropic diffusion filtering to reduce speckle noise without blurring the edges. Then, region growing is performed starting from a seed point, using a merging criterion that compares intensity gradients to the noise level inside the region. Finally, the boundaries are smoothed using morphological closing. The algorithm was evaluated with two simulated images and eleven phantom images and converged in 10 of them with accurate region delimitation. Preliminary results show that the proposed method can be used for ultrasound image segmentation and does not require previous knowledge of the anatomy of the structures. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

This paper describes the development of courses in the field of digital design that use Arduino boards as their main platforms. Arduino offers an intuitive development environment and multiple hardware and software resources that allow rapid development of microcontroller-based projects. However, due to the vast amount of information available, students were losing the capability to design their own prototypes. We propose a methodology that introduces the study of microcontrollers using Arduino to develop different types of projects and proceeds to study the system architecture to gain control on the device. This methodology has been used in an undergraduate course in microcontrollers and a graduate course in advanced techniques in digital design. The students of the microcontrollers course showed improved design skills and motivation compared to the students from previous versions of the course. With respect to the advanced techniques in digital design course, the students were able to take advantage of Arduino platform to gain a deep understanding of hardware/software co-design of embedded systems. © 2013 IEEE.

This paper proposes an approach to facilitate the process of individualization of patients from their medical images, without compromising the inherent confidentiality of medical data. The identification of a patient from a medical image is not often the goal of security methods applied to image records. Usually, any identification data is removed from shared records, and security features are applied to determine ownership. We propose a method for embedding a QR-code containing information that can be used to individualize a patient. This is done so that the image to be shared does not differ significantly from the original image. The QR-code is distributed in the image by changing several pixels according to a threshold value based on the average value of adjacent pixels surrounding the point of interest. The results show that the code can be embedded and later fully recovered with minimal changes in the UIQI index - less than 0.1% of different. © 2017 SPIE.

The use of technological devices has widespread around the world. It is known that inappropriate or prolonged use of electronic devices can cause musculoskeletal discomfort or even illness. However, there are not many studies that evaluate the associated risks on the children’s health. This paper describes a pilot ergonomic study for the analysis of the postures of a five-year old girl while using a laptop computer, a tablet, and a smart phone. The analysis was done using the software Delmia to generate 3D models of the child body, that were created based on photographs. We considered five positions: desk sitting, sitting cross legged, lying supine, lying prone and standing. The results suggest that the safest positions are sitting on a desk and standing, and the greatest risk is in the area of necktrunk. However, further investigation is needed to validate the musculoskeletal risks associated to the use of electronic devices by children. © Springer Nature Singapore Pte Ltd. 2017.

Fetal ECG monitoring is a useful method to assess the fetus health and detect abnormal conditions. In this paper we propose an approach to extract fetal ECG from abdomen and chest signals using independent component analysis based on the joint approximate diagonalization of eigenmatrices approach. The JADE approach avoids redundancy, what reduces matrix dimension and computational costs. Signals were filtered with a high pass filter to eliminate low frequency noise. Several levels of decomposition were tested until the fetal ECG was recognized in one of the separated sources output. The proposed method shows fast and good performance. © 2017 SPIE.

Advances in the field of biomedical engineering have allowed the development of biometric devices to evaluate sport performance. This article describes the design and construction of a wearable electrogoniometer to monitor joint angle in real time for sports applications. The electrogoniometer uses four accelerometers connected to a microcontroller. The joint angle is estimated and transmitted via Bluetooth Low Energy. This prototype is a low-cost, low-power, and comfortable to wear solution for joint angle measurement. © Springer Nature Singapore Pte Ltd. 2017.

The purpose of the present article is to characterize sEMG signals to determine muscular fatigue levels. To do this, the signal is decomposed using the discrete wavelet transform, which offers noise filtering features, simplicity and efficiency. sEMG signals on the forearm were acquired and analyzed during the execution of cyclic muscular contractions in the presence and absence of fatigue. When the muscle fatigues, the sEMG signal shows a more erratic behavior of the signal as more energy is required to maintain the effort levels. © 2017 SPIE.

El propósito de este trabajo es realizar la evaluación ergonómica de las diferentes posturas que adoptan los niños con la utilización de tabletas, computadores y teléfonos móviles. En la actualidad existen pocos estudios que analicen los aspectos ergonómicos en la utilización de estos dispositivos en niños, y los riesgos musculo esqueléticos que estos pueden generar. Este documento describe un estudio piloto ergonómico y biomecánico para el análisis de las posturas de una niña de cinco años mientras utilizaba cada uno de los dispositivos en distintas posiciones. Se generaron modelos en 3D del cuerpo de la niña de cinco años de edad en un software llamado Delmia V5 basados en las medidas antropométricas según la Norma Técnica Colombiana NTC 5649 y en soportes fotográficos. Se consideraron las posiciones sentado, sentado con las piernas cruzadas, acostado boca arriba, acostado boca abajo y de pie. Se llegó a la conclusión de que las posiciones más adecuadas son: sentado en el escritorio y de pie, debido que requieren menos esfuerzo y la posición con mayor riesgo es sentado con piernas cruzadas. Se necesita más investigación para validar los riesgos musculo esqueléticos asociados con dispositivos electrónicos en los niños.

El presente trabajo tiene como objetivo el desarrollo de un sistema para la estimación de las fuerzas aplicadas en las extremidades superiores del ser humano, específicamente, en los dedos. Se diseñó un instrumento cómodo para el usuario que permite la realización de las mediciones por medio de cuatro sensores de fuerza ubicados en un guante, uno en cada dedo (pulgar, índice, medio y anular). Se empleó una tarjeta Bluno Nano, la cual integra un módulo Bluetooth 4.0 junto a un módulo Arduino UNO. A su vez se diseñó una PCB con los componentes requeridos para el acondicionamiento de las señales de los sensores: resistencias, amplificadores operacionales y batería. La tarjeta Bluno Nano envía los valores de fuerza de manera inalámbrica a una computadora con un adaptador Bluetooth de baja energía USB que cuenta con un programa para visualizar y guardar en archivos de texto la información adquirida.

Este trabajo se ha realizado con la finalidad de analizar imágenes médicas que comúnmente se ven afectadas por ruido granular (speckle) a través de algoritmos de segmentacion basados en crecimiento de regiones. Las imágenes empleadas fueron el resultado de una simulación a traves de Matlab con el fin de representar formas elisoidales con diferentes contrastes. También se usaron imágenes reales de fantomas. Se implementó un algoritmo combinado con métodos existentes por medio del cual se logró obtener una imagen con mejor calidad a la cual se le aplicaron algoritmos de segmentación. Los resultados obtenidos de la aplicación del algoritmo son plasmados con evidencias de un antes y un después de la aplicación. Dentro de la combinación de los algoritmos se implementó una primera parte de filtrado de la misma seguido de la parte de crecimiento de regiones, con la cual se logró identificar los pixeles de la región de interés a partir de un pixel semilla proporcionado por el usuario

Retinal eye fundus images are used for diagnostic purposes, but despite controlled conditions in acquisition they often suffer from uneven illumination and blur. In this work, we propose the use of multi-channel blind deconvolution for the restoration of blurred retinal images. The estimation of an adequate point-spread function (PSF) is highly dependent on the registration of at least two images from the same retina, which undergo illumination compensation. We use the bi-dimensional empirical mode decomposition (BEMD) approach to model the illumination distribution as a sum of non-stationary signals. The BEMD approach enables an artifact-free compensation of the illumination in order to estimate an adequate PSF and carry out the best restoration possible. Encouraging experimental results show significant enhancement in the retinal images with increased contrast and visibility of subtle details like small blood vessels. © 2016 IEEE.