REAL TIME EMBBEDED RGB-D SLAM USING CNNS FOR DEPTH ESTIMATION AND FEATURE EXTRACTION

Marcos Renato Rocha Hernández (2023, [Tesis de maestría])

"A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for intelligent mobile robots to work in unknown environments. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically de signed in most cases, and can be vulnerable in complex environments. Also, most of the most robust SLAM algorithms rely on special devices like a stereo camera or depth sensors, which can be expensive and give more complexity to the system, that is why monocular depth estimation is an essential task in the computer vision community. This work shows that feature extraction and depth estimation using a monocular camera with deep convolutional neural networks (CNNs) can be incorporated into a modern SLAM framework. The proposed SLAM system utilizes two CNNs, one to detect keypoints in each im age frame, and to give not only keypoint descriptors, but also a global descriptor of the whole image and the second one to make depth estimations from a single image frame, all using only a monocular camera."

SLAM Inteligencia Artificial CNN Sistemas embebidos Redes neuronales Cámara monocular INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES INTELIGENCIA ARTIFICIAL INTELIGENCIA ARTIFICIAL

Classification of Cucumber Leaves Based on Nitrogen Content Using the Hyperspectral Imaging Technique and Majority Voting.

Sajad Sabzi Razieh Pourdarbani Mohammad Hossein Rohban Alejandro Fuentes_Penna José Luis Hernández-Hernández Mario Hernández Hernández (2021, [Artículo])

Improper usage of nitrogen in cucumber cultivation causes nitrate accumulation in the fruit and results in food poisoning in humans; therefore, mandatory evaluation of food products becomes inevitable. Hyperspectral imaging has a very good ability to evaluate the quality of fruits and vegetables in a non-destructive manner. The goal of the present paper was to identify excess nitrogen in cucumber plants. To obtain a reliable result, the majority voting method was used, which takes into account the unanimity of five classifiers, namely, the hybrid artificial neural network¿imperialism competitive algorithm (ANN-ICA), the hybrid artificial neural network¿harmonic search (ANN-HS) algorithm, linear discrimination analysis (LDA), the radial basis function network (RBF), and the Knearest- neighborhood (KNN). The wavelengths of 723, 781, and 901 nm were determined as optimal wavelengths using the hybrid artificial neural network¿biogeography-based optimization (ANNBBO) algorithm, and the performance of classifiers was investigated using the optimal spectrum. The results of a t-test showed that there was no significant difference in the precision of the algorithm when using the optimal wavelengths and wavelengths of the whole range. The correct classification rate of the classifiers ANN-ICA, ANN-HS, LDA, RBF, and KNN were 96.14%, 96.11%, 95.73%, 64.03%, and 95.24%, respectively. The correct classification rate of majority voting (MV) was 95.55% for test data in 200 iterations, which indicates the system was successful in distinguishing nitrogen-rich leaves from leaves with a standard content of nitrogen.

artificial neural network cucumber hyperspectral imaging majority voting nitrogen INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ALIMENTOS

Interfaces hápticas para identificar marcadores digitales del Trastorno del Espectro Autista

Haptic interfaces to identify digital markers of Autism Spectrum Disorder

GLORIA IVONNE MONARCA PINTLE (2023, [Tesis de doctorado])

El uso de herramientas de cribado durante la infancia es de suma importancia para identificar a niños que pueden Trastorno del Espectro Autista (TEA); sin embargo, las pruebas que existen en la actualidad se basan en cuestionarios y observaciones contestadas por los padres por lo que el resultado puede ser subjetivo. Además, la mayoría de las pruebas de cribado se enfocan en el área social y de comunicación, dejando a un lado las características sensoriales, un área donde los padres notan las primeras señales de un desarrollo atípico. En los últimos años, ha crecido el interés por identificar marcadores digitales del TEA que puedan apoyar el cribado de dicho trastorno, usando tecnología que pueda ser usada en cualquier lugar y momento para agilizar el proceso de cribado. Hasta el momento, la investigación en torno a marcadores digitales del TEA relacionados con el procesamiento táctil, ha sido poco explorada debido a que la investigación se ha centrado en explorar otros comportamientos, como la atención visual, movimientos motores, y voz. El crecimiento de las interfaces hápticas abre la posibilidad de explorar el procesamiento táctil e identificar marcadores digitales del TEA. En esta tesis exploramos si las interfaces hápticas pueden ser usadas para promover y recolectar interacciones táctiles que revelen marcadores digitales del TEA. Para tener un mejor entendimiento de las interfaces hápticas, en este trabajo de tesis exploramos dos interfaces hápticas. Una interfaz háptica pasiva llamada BendableSound, la cual cuenta con una retroalimentación por textura y espacio; y una interfaz háptica activa llamada Feel and Touch, la cual es un juego móvil que utiliza patrones vibrotactiles para retroalimentar las interacciones de los niños. Los resultados muestran que las interfaces hápticas tienen la capacidad recolectar interacciones táctiles y revelar marcadores digitales que pueden estar asociados al TEA. En el caso pasivo, participaron 37 niños neurotípicos (NT) y 22 niños con TEA quienes interactuar con BendableSound; los resultados muestran que existen diferencias entre los niños NT y TEA en cuanto al ancho de las interacciones táctiles, la fuerza que aplican y el tiempo que utilizan para realizar interacciones táctiles. En el caso activo, participaron 36 niños NT y 19 niños con TEA quienes interactuaron con Feel and Touch; los resultados muestran que existen diferencias entre los niños NT y TEA en cuanto a la ...

The use of screening tools during infancy is crucial to identify children who are likely to have Autism Spectrum Disorder (ASD); however, the current screening tests are based on questionnaires and observations that parents answer bases on their observations; however, the results might be subjective. In addition, most screening tests focus on the assessment of social and communication skills, disregard sensory skills, an area where parents often notice the first signals of ASD. In recent years, there has been growing interest in identifying digital markers of ASD that can support screening, particularly those that that can be used at any time and any place to speed up the screening process. So far, research on digital markers of ASD related to tactile processing has been little explored due to the lack of tools to assess it. The growth of haptic interfaces opens the possibility to explore tactile processing and identify digital markers of ASD. In this thesis, we propose to investigate the use of haptic interfaces to promote and collect tactile interactions that can reveal digital markers of ASD. To have a better understanding of haptic interfaces, in this thesis work we explore two types of haptic interface. A passive haptic interface called BendableSound, which features texture and spatial feedback; and an active haptic interface called Feel and Touch, which is a mobile game that uses vibrotactile patterns to provide feedback on children’s interactions. The results show that haptic interfaces have the potential to collect touch interactions and reveal digital markers that may be associated with ASD. In the first case, 37 neurotypical (NT) children and 22 children with ASD participated and interacted with BendableSound; the results show that there are differences between NT and ASD children in the width of tactile interactions, the force they apply, and the time they use to perform tactile interactions. In the second case, 36 NT children and 19 children with ASD participated and interacted with Feel and Touch; the results show that there are differences between NT and ASD children in terms of the tilt they produce on the mobile when performing tactile interactions, the total acceleration they produce, and the closeness to the center of the screen of their tactile interactions. The results of this thesis indicate that haptic interfaces have the ability to gather touch interactions and uncover digital markers associated with ASD. The findings of this ...

autismo, cribado, marcadores digitales, interfaces hápticas, aprendizaje automático autism, screnning, digital markers, haptic interfaces, machine learning INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES ORDENADORES DIGITALES ORDENADORES DIGITALES

EVALUACIÓN DE LA INTERACCIÓN ENTRE LAS ACTIVIDADES PRIORITARIAS DE PESCA Y CONSERVACIÓN EN EL SISTEMA SOCIOAMBIENTAL DEL GOLFO DE ULLOA. ESTUDIO DE CASO: Caretta caretta y Chelonia mydas (Linnaeus, 1758)

JEHIEL ZACIL RETANA ARELLANO (2023, [Tesis de maestría])

"El Golfo de Ulloa (GU) es un ecosistema de gran importancia socioeconómica y ecológica por su abundancia de recursos; se encuentra localizado en la costa occidental de Baja California Sur (BCS) bajo la influencia de la Corriente de California (CC). Debido a las artes de pesca empleadas en la zona, existe la interacción incidental con especies que no son el objetivo de la pesca, tal es el caso de las tortugas marinas, todas ellas sujetas a protección especial en la legislación nacional e internacional, sin embargo, a la fecha se desconoce una medición puntual de estas interacciones en el área; al respecto, en el presente trabajo se caracterizaron y dimensionaron las interacciones entre la actividad pesquera realizada con chinchorros y dos especies de tortugas marinas en la zona; para ello se consideró la información obtenida durante el censo pesquero de 2015 así como también la base de datos con información de avistamientos e interacciones de tortugas marinas con las actividades extractivas de la pesca realizada de junio 2015 a julio de 2016. Sobre la base de la información analizada, se registraron 5,661 chinchorros, de los cuales, el 95 % cumple con las medidas autorizadas en los permisos de pesca correspondientes. Por su parte, se registraron 458 avistamientos de tortugas marinas, de los cuales, el 56 % correspondió a tortuga amarilla y el resto a tortuga verde. Las interacciones de las tortugas con los sitios activos de pesca se categorizaron como: (1) viva sin enredo; (2) muerta sin enredo; (3) viva con enredo; y (4) muerta con enredo. Considerando ambas especies y estas categorías, para el periodo analizado, se observaron 85 registros, de los cuales, seis correspondieron a la categoría 1; cinco en la categoría 2; 42 en la categoría 3; y 32 en la categoría 4. Se determinó que la tortuga verde presentó mayor interacción (68.23 %) con respecto a la tortuga amarilla, con registros máximos en junio para ambas especies. Sobre estos registros, se creó un índice de interacción de artes de pesca y las tortugas marinas (IIAT), con el cual, se observó que el área de alto riesgo y daño dentro de la ZRP es muy reducida (<1 % del área total). Adicionalmente, a través de un análisis de probabilidad de Poisson se determinó que es considerablemente más probable (≈30 %) observar una tortuga viva y sin enredo que en cualesquiera de las otras tres categorías para las que se calculó una probabilidad máxima de observación de ≈12 % por cada cuadrante de 10 x 10 km..."

"The Gulf of Ulloa (GU) is an ecosystem of significant socioeconomic and ecological importance due to its abundance of resources. It is located on the western coast of Baja California Sur (BCS) and is influenced by the California Current (CC). Due to the fishing methods used in the area, there is bycatch with species that are not the target of fishing, such as sea turtles, all of which are subject to special protection under national and international legislation. However, there has been no specific measurement of these interactions in the area. In this study, the interactions between fishing activities using seine nets and two species of sea turtles in the area were characterized and quantified. The information obtained during the 2015 census and the database containing information on sea turtle sightings and interactions with fishing activities from June 2015 to July 2016 was considered. Based on the analyzed information, 5,661 seine nets were recorded, of which 95 % complied with the authorized measures in the corresponding fishing permits. Additionally, 458 sea turtle sightings were recorded, with 56 % corresponding to yellow turtles and the rest to green turtles. The interactions of turtles with active fishing sites were categorized as: (1) alive without entanglement; (2) dead without entanglement; (3) alive with entanglement; and (4) dead with entanglement. Considering both species and these categories, 85 records were observed during the analyzed period, of which six corresponded to category 1, five to category 2, 42 to category 3, and 32 to category 4. It was determined that the green turtle had a higher interaction rate (68.23 %) compared to the yellow turtle, with peak records in June for both species. Based on these records, an index of interaction between fishing gear and sea turtles (IIAT) was created. It was observed that the area of high risk and damage within the ZRP (Fishery Refuge Area) is very small (<1 % of the total area). Additionally, a Poisson probability analysis determined that it is considerably more likely (≈30 %) to observe an alive without entanglement turtle than in any of the other three categories, for which the maximum observation probability was ≈12 % for each 10 x 10 km quadrant..."

tortuga marina, captura incidental, pesca y conservación, refugio pesquero Sea turtle, bycatch, fishing and conservation, Fishery Refuge Area CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CIENCIAS AGRARIAS PECES Y FAUNA SILVESTRE PROTECCIÓN DE LOS PECES PROTECCIÓN DE LOS PECES

Comparison of Different Classifiers and the Majority Voting Rule for the Detection of Plum Fruits in Garden Conditions.

Razieh Pourdarbani Sajad Sabzi Mario Hernández Hernández José Luis Hernández-Hernández Ginés García_Mateos Davood Kalantari José Miguel Molina Martínez (2019, [Artículo])

Color segmentation is one of the most thoroughly studied problems in agricultural applications of remote image capture systems, since it is the key step in several different tasks, such as crop harvesting, site specific spraying, and targeted disease control under natural light. This paper studies and compares five methods to segment plum fruit images under ambient conditions at 12 different light intensities, and an ensemble method combining them. In these methods, several color features in different color spaces are first extracted for each pixel, and then the most e

ective features are selected using a hybrid approach of artificial neural networks and the cultural algorithm (ANN-CA). The features selected among the 38 defined channels were the b* channel of L*a*b*, and the color purity index, C*, from L*C*h. Next, fruit/background segmentation is performed using five classifiers: artificial neural network-imperialist competitive algorithm (ANN-ICA); hybrid artificial neural network-harmony search (ANN-HS); support vector machines (SVM); k nearest neighbors (kNN); and linear discriminant analysis (LDA). In the ensemble method, the final class for each pixel is determined using the majority voting method. The experiments showed that the correct classification rate for the majority voting method excluding LDA was 98.59%, outperforming the results of the constituent methods.

remote sensing in agriculture artificial neural network hybridization environmental conditions majority voting plum segmentation INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ALIMENTOS

Usando la descomposición de un grafo Halin para el diseño de algoritmos autoestabilizantes

Using Halin graph decomposition for the design of self-stabilizing algorithm

Daniel Uriel Orozco Lomelí (2023, [Tesis de maestría])

Sea G = (V, E) un grafo no dirigido. El problema de encontrar un conjunto independiente fuerte en G, es identificar un conjunto S ⊆ V , tal que dados dos vértices arbitrarios de S, éstos estén separados entre sí por el menos tres aristas. Encontrar un conjunto S de tamaño máximo pertenece a la clase NP-Difícil. Por otro lado, el problema de encontrar un conjunto dominante total en G es identificar un conjunto D ⊆ V , tal que cualquier vértice en V tenga al menos un vecino que pertenezca a D. Encontrar un conjunto D de tamaño mínimo también pertenece a la clase NP-Difícil. En este trabajo de tesis se diseñaron dos algoritmos, uno que resuelve el problema de encontrar un conjunto independiente fuerte maximal y otro que resuelve el problema de encontrar un conjunto dominante total minimal. Estos dos problemas son menos restrictivos que las versiones de optimización descritas al principio de este texto y se sabe que pertenecen a la clase P. Los algoritmos diseñados corren en un sistema distribuido, son autoestabilizantes, son tolerantes a fallas transitorias y funcionan para grafos Halin. Los grafos Halin pertenecen a la clase de grafos 2-outerplanares y tienen la propiedad de que se pueden partir en dos subgrafos muy conocidos, un árbol y un ciclo. Los algoritmos propuestos aprovechan la propiedad anterior para disminuir la complejidad de los mismos. Hasta donde tenemos conocimiento, los algoritmos propuestos, que corren en tiempo lineal en el número de vértices, son los algoritmos más rápidos existentes para los problemas del conjunto independiente fuerte maximal y el conjunto dominante total minimal.

Let G = (V, E) be an undirected graph. The problem of finding a strong stable set in G, is to identify a set S ⊆ V , such that given two arbitrary vertices of S, they are separated from each other by at least three edges. Finding a set S of maximum size belongs to the class NP-Hard. On the other hand, the problem of finding a total dominanting set in G is to identify a set D ⊆ V , such that any vertex in V has at least one neighbor belonging to D. Finding a set D of minimum size also belongs to the class NP-Hard. In this thesis work, two algorithms were designed, one that solves the problem of finding a maximal strong stable set and one that solves the problem of finding a minimal total dominanting set. These two problems are less restrictive than the optimization versions described at the beginning of this text and are known to belong to the P class. The designed algorithms run on a distributed system, are self-stabilizing, are transient fault tolerant, and work for Halin graphs. Halin graphs belong to the 2-outerplanar class of graphs and have the property that they can be split into two well-known subgraphs, a tree and a cycle. The proposed algorithms take advantage of the above property to decrease the complexity of the algorithms. To the best of our knowledge, the proposed algorithms, which run in linear time in the number of vertices, are the fastest existing algorithms for the maximal strong stable set and minimal total dominating set problems.

Grafo Halin, Sistemas Distribuidos, Autoestabilización, Conjunto Independiente Fuerte, Conjunto Dominante Total Halin Graph, Distributed Systems, Self-stabilizing, Strong Stable Set, Total Dominating Set INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES LENGUAJES ALGORÍTMICOS LENGUAJES ALGORÍTMICOS

Microbiological Analysis of the Air in a Popular Fish Processing and Marketing Area

Angélica Sinaí Quintanilla Martínez Lizet Aguirre Güitrón Luis Daniel Espinosa Chaurand MAYRA DIAZ RAMIREZ ALEJANDRO DE JESUS CORTES SANCHEZ (2022, [Artículo])

"Fish are marketed as a food and consumed worldwide. During the production of food, contamination by microorganisms is possible through the air, soil, water, surfaces, food handlers, etc. The air does not have a natural microbial composition, but it is a vehicle for the transmission of microorganisms of economic and health interest because they are associated with food spoilage and human diseases. The objective of this study was the microbiological analysis of the air in an area popular for the processing and marketing of fish products in the city of Tepic Nayarit. Using the passive or sedimentation method to collect microorganisms present in the air, the proportion of aerobic mesophile bacteria, coliform bacteria, fungi and yeast was determined at different locations in the fish processing and marketing area for four weeks. The results indicated that the aerobic mesophiles had the highest counts among all the microbial groups analyzed at the twelve different sampling points during the four weeks of the study; their numbers ranged from 2.44 to 2.95 log CFU/m3/h, followed by molds with counts from 1.44 to 2.75 log CFU/m3/h, yeasts with counts from 0.7 to 2.01 log CFU/m3/h and coliforms with counts that ranged from 0.7 to 1.68 log CFU/m3/h. We determined the proportion of the viable microbiological population present in the air at the different sampling points of the study area; several of these sampling points presented values above those recommended by various agencies around the world. Knowledge of the biological hazards transported through the air is important to establish and reduce the risk to the health of occupants and the contamination pathways of processed and marketed fishery products that may be associated with spoilage and foodborne diseases."

food safety, food quality, air pollution, airborne biohazard, environmental monitoring INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ALIMENTOS HIGIENE DE LOS ALIMENTOS HIGIENE DE LOS ALIMENTOS

Tensile behavior of 3D printed polylactic acid (PLA) based composites reinforced with natural fiber

Eliana M Agaliotis BALTAZAR DAVID AKE CONCHA ALEJANDRO MAY PAT Juan Pablo Morales Arias Celina Bernal Alex Valadez González Pedro Jesús Herrera Franco Gwenaelle Proust JUAN FRANCISCO KOH DZUL José Gonzalo Carrillo Baeza Emmanuel Alejandro Flores Johnson (2022, [Artículo])

Natural fiber-reinforced composite (NFRC) filaments for 3D printing were fabricated using polylactic acid (PLA) reinforced with 1–5 wt% henequen flour comprising particles with sizes between 90–250 μm. The flour was obtained from natural henequen fibers. NFRCs and pristine PLA specimens were printed with a 0° raster angle for tension tests. The results showed that the NFRCs’ measured density, porosity, and degree of crystallinity increased with flour content. The tensile tests showed that the NFRC Young’s modulus was lower than that of the printed pristine PLA. For 1 wt% flour content, the NFRCs’ maximum stress and strain to failure were higher than those of the printed PLA, which was attributed to the henequen fibers acting as reinforcement and delaying crack growth. However, for 2 wt% and higher flour contents, the NFRCs’ maximum stress was lower than that of the printed PLA. Microscopic characterization after testing showed an increase in voids and defects, with the increase in flour content attributed to particle agglomeration. For 1 wt% flour content, the NFRCs were also printed with raster angles of ±45° and 90° for comparison; the highest tensile properties were obtained with a 0° raster angle. Finally, adding 3 wt% content of maleic anhydride to the NFRC with 1 wt% flour content slightly increased the maximum stress. The results presented herein warrant further research to fully understand the mechanical properties of printed NFRCs made of PLA reinforced with natural henequen fibers. © 2022 by the authors.

POLYLACTIC ACID (PLA) NATURAL FIBER HENEQUEN FIBER NATURAL FIBER REINFORCED COMPOSITE (NFRC) ADDITIVE MANUFACTURING 3D PRINTING MECHANICAL PROPERTY INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE MATERIALES PROPIEDADES DE LOS MATERIALES PROPIEDADES DE LOS MATERIALES

Elaboración y caracterización fisicoquímica de una película polimérica a partir de colágena marina y PLA

VANESSA CAROLINA PAT CETINA (2023, [Tesis de maestría])

INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE MATERIALES PROPIEDADES DE LOS MATERIALES PROPIEDADES DE LOS MATERIALES

Elaboración de andamios electrohilados a base de colágena marina y ácido hialurónico con potencial aplicación en la ingeniería tisular

JOSE LUIS QUIJANO MENDOZA (2023, [Tesis de maestría])

INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE MATERIALES PROPIEDADES DE LOS MATERIALES PROPIEDADES DE LOS MATERIALES