Manuel De Jesús Matuz Cruz

Tecnologico Nacional de México · Sistemas y Computación

In the self-driving vehicles domain, steering control is a process that transforms information obtained from sensors into commands that steer the vehicle on the road and avoid obstacles. Although a greater number of sensors improves perception and increases control precision, it also increases the computational cost and the number of processes. To...

In this study, a high-performing scheme is introduced to delimit benign and malignant masses in breast ultrasound images. The proposal is built upon by the Nonlocal Means filter for image quality improvement, an Intuitionistic Fuzzy C-Means local clustering algorithm for superpixel generation with high adherence to the edges, and the DBSCAN algorit...

This article proposes a method to classify atrial fibrillation signals using time-frequency characteristics through a BiLSTM network. The experiment was performed with the ECG signals, which are part of the PhysioNet CinC 2017 database. In addition to the BiLSTM network, machine learning algorithms such as k Nearest Neighbors, Linear SVM, RBF SVM,...

This paper presents a type-2 fuzzy inference tree designed for a differential wheeled mobile robot that navigates in indoor environments. The proposal consists of a controller designed for obstacle avoidance, a controller for path recovery and goal reaching, and a third controller for the real-time selection of behaviors. The system takes as inputs...

En este articulo se implementaron arquitecturas basadas en aprendizaje profundo en tarjetas embebidas. La experimentación se realizó en una tarjeta embebida Nvidia Jetson Nano y se emplearon las señales ECG de la base de datos CinC Challenge 2017 de PhysioNet, de las cuales, se extrajeron características de Tiempo-Frecuencia para el entrenamiento d...

This article proposes a method to classify cardiac arrhythmias using feature extraction and dimensionality reduction techniques. The experiment was carried out with the QRS complexes of the electrocardiographic signals, which are part of the Physionet MIT-BIH arrhythmia database. The machine learning algorithms used to perform the classification we...

In this paper, to reduce impulsive noise in color images we propose an extension of the Median Redescending M-Estimator. For that purpose, a multitasking approach was developed such as a multi-core processing in order to reduce in parallel the noise on R, G and B color channels. With this paradigm, an acceleration up to three times can be guarantee...

The Spherical Densiometer is a method of measuring the luminosity present inside the forest ecosystem. This information is essential to know the probability of survival and growth of seedlings; it also allows the estimation of the establishment and development of plants in the understory. This indirect measurement method is considered to be of acce...

Resumen-A common factor in road accidents is due to inattention in the driving task (drowsiness, distraction, etc.). Therefore, areas such as intelligent transportation systems are in continuous development to provide greater security. An example are the assistance systems that focus on improving occupant safety by merging information from sensors...

This paper proposes an approach based on the use of time dimension within a Convolutional and Recurrent Hybrid Neural Network to carry out the driving of a simulated vehicle in real time. Convolutional layers are transformed into time-distributed layers that process a series of images in parallel and are related in time and space by recurrent layer...

A pair of fully automatic brain tissue and tumor segmentation frameworks are introduced in current paper, these consist of a parallel and cascade architectures of a specialized convolutional deep neural network designed to develop binary segmentation. The main contributions of this proposal imply their ability to segment Magnetic Resonance Imaging...

This paper presents the heterogeneous implementation and evaluation of five algorithms to improve the resolution in magnetic resonance images, these are Nearest-Neighbor, Bilinear, Bicubic, Catmull-Rom and Lanczos. The experiments were carried out using the database BraTS 2017 considering T1, T2, T1ce and Flair acquisition modes. To measure the eff...