Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Embedded DC motor control system for humanoid robot applications(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-12-05) Durán Hernández, Juan de Dios; FUENTES AGUILAR, RITA QUETZIQUEL; 2229297; Fuentes Aguilar, Rita Quetziquel; puemcuervo, emipsanchez; Campos Macías, Leobardo Emmanuel; Hernández Melgarejo, Gustavo; Navarro Gutiérrez, Manuel; School of Engineering and Sciences; Campus Monterrey; Carbajal Espinosa, Oscar ElenoHumanoid robots have been researched during the last few years because of the useful applications they can be implemented in the future. Some of these include medicine, education, military, industry, and support areas. A humanoid can be used to rescue people and animals from natural disasters, be a support in a production line, teach students, form part of military defense, and many other applications. Biped robots are known as the lower part of the humanoid robot and the principal characteristic is that it has 2 feet. To generate movements in a biped robot requires following specific trajectories in all actuators. A control algorithm is responsible to follow the specific references in the DC motors individually. Some basic motions for a biped robot are walking and squats because are the principal movements to travel and lift heavy things. Additionally, the analysis of the implementation of control algorithms to individual actuators for biped robot applications is not completely studied. This thesis proposes the development of an embedded system to apply controllers and the implementation of a second-order Super Twisting Sliding Mode control (STSMC) in the actuators for a constructed biped robot with 12 degrees of freedom actuated by 12 DC motors and an individual comparison with a PID (Proportional, Integrative, and Derivative control) controller. First, the DC motor model is identified using the least square method. Then, the model is validated to ensure representation in simulation. Next, the Sliding Mode control (SMC) is analyzed to evaluate the functional theory in simulation. Additionally, the STSMC is simulated and then implemented in one DC motor. Moreover, to generate walking and squatting patterns the model of the three-dimensional inverted pendulum is applied using the stability criterion. The inverse kinematics provides the joint angles to generate the trajectories. Finally, the mean squared error (MSE) is implemented to measure the effectiveness of the control algorithms. The results show that the PID and STSMC controls have an MSE average of 0.4704 and 0.0228 respectively when replicating the squat trajectory. Meaning an improvement of 1961%. The maximum error with the STSMC was was 0.5° when the joint reached the change of direction because of the inertial force. This error represents an error of 6.71mm at the end of the foot. This error is inside the allowed limits, the robot can reproduce the squat without falling. Finally, this research can be applied to manipulator robots that use DC motors to control the position.
- Automatic emergency braking system in autonomous vehicles based on the state of the traffic light and fuzzy logic decision making(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-12-01) Palma Zubia, Alejandro; BALLESTEROS ESCAMILLA, MARIANA FELISA; 882791; Fuentes Aguilar, Rita Quetziquel; puemcuervo, emipsanchez; Vazquez Topete, Carlos Renato; Ballesteros Escamilla, Mariana Felisa; School of Engineering and Sciences; Campus Monterrey; Carbajal Espinosa, Oscar ElenoThis work presents the thesis proposal for obtaining the degree of Master of Science in Engineering and tries to solve the problem of braking emergency system of an autonomous vehicle based on the detection and interpretation of traffic lights present on the road. Autonomous braking systems require a control system that can respond to incoming signals in real time corresponding to nearby objects, such as nearby pedestrians, traffic signs and traffic lights. Currently, existing emergency braking systems are designed to avoid vehicles or objects in front of or to the side of the car. On the other hand, the interpretation of the traffic light as an object in front of the vehicle and not as an acceleration or braking signal, reducing the consideration of these in the design of an emergency braking system. In this work the necessary basic knowledge about the concept of functional safety in the existing ISO 26262 an standard for vehicles and automobiles, the current considerations for the development and implementation of an autonomous braking system. As well as the robust control theories previously used for the development of these systems will be presented. The objective of this investigation is the development of a braking system utilizing robust control techniques for emergency braking actions.
- Emotion recognition based on physiological signals for Virtual Reality applications(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-06-13) Oceguera Cuevas, Daniela; FUENTES AGUILAR, RITA QUETZIQUEL; 229297; Fuentes Aguilar, Rita Quetziquel; puemcuervo; Antelis Ortíz, Javier Mauricio; Fernández Cervantes, Victor; School of Engineering and Sciences; Campus Monterrey; Hernández Melgarejo, GustavoVirtual Reality (VR) Systems have been used in the last years with an increasing frequency because they can be implemented for multiple applications in various fields. Some of these include aerospace, military, psychology, education, and entertainment. A way to increase the sense of presence is to induce emotions through the VE, and since one of the main purposes of VR Systems is to evoke the same emotions as a real experience would, the induction of emotions and emotion recognition could be used to enhance the experience. The emotion of a user can be recognized through the analysis and processing of physiological signals such as Electrocardiogram (ECG) and Electrodermal Activity (EDA) signals. However, very few systems that present online feedback regarding the subject’s emotional state and the possibility of adapting the VE during user experience have been developed. This thesis proposes the development of a Virtual Reality video game that can be dynamically modified according to the physiological signals of a user to regulate his emotional state. The first experiment served for the creation of a database. Previous studies have shown that specific features from these signals, can be used to develop algorithms capable of classifying the emotional states of the subjects into multiple classes or the two emotional dimensions: valence and arousal. Thus, this experiment helped to develop an appropriate Virtual Reality video game for stress induction, a signal acquisition, and conditioning system, a signal processing model and to extract time-domain signal features offline. A statistical analysis was performed to find significant differences between game stages and machine learning algorithms were trained and tested to perform classification offline. A second experiment was performed for the Proof of Concept Validation. For this, a model was created to extract features online and the classification algorithms were re-fitted with the online extracted features. Additionally, to facilitate a completely online process, the signal processing and feature extraction models were embedded on an STM32F446 Nucleo board, a strategy was implemented to dynamically modify the VE of the Virtual Reality video game according to the detected class, and the complete system was tested.
- EfficientDet and fuzzy logic for an emergency brake driver assistant system based on traffic lights using a Jetson TX2 and a ZED stereo camera(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-04) García Escalante, Andrés Ricardo; FUENTES AGUILAR, RITA QUETZIQUEL; 229297; Fuentes Aguilar, Rita Quetziquel; puelquio, emipsanchez; Terashima Marín, Hugo; Falcón Morales, Luis Eduardo; Álvarez González, Rodolfo Rubén; Escuela de Ingeniería y Ciencias; Campus Monterrey; Carbajal, Oscar Eleno EspinosaA study developed by the University of West Virginia analyzed the vehicle collisions, these occur due to the slow reaction time (RT) of humans. The study involved human RT under specific conditions, they found out that fully aware drivers have an estimated RT between 0.70 to 0.075 seconds, unexpected but normal situations like a lead car brake’s lights, is 1.25 seconds, and for surprising events is estimated to be around 1.50 seconds. Therefore, the presented work provides a solution to implement an Advanced Driver Assistant System (ADAS) level 1 called Emergency Brake Driver Assistant System based on Traffic Lights (EBDASTL) using a Jetson TX2 and a ZED Stereo camera to detect Traffic Light States (TLSs), estimate the distance to a Traffic Light (TL), and perform a brake decision based on the TLS and TLD that can have a better response time than human RT in surprising events. The main contribution of this research project is the implementation of a single ADAS that has three stages. The Traffic Light State Detection Model (TLSDM) stage using EfficientDet D0. The Traffic Light Distance (TLD) stage using a ZED Stereo camera, and the Traffic Light Decision-Making (TLDM) stage using Fuzzy Logic. Up to date there is not a related work that have the three stages. The second main contribution is the on Road test performed in Queretaro Mexico, where all the components of the EBDASTL have been mounted in a car and tested in a real-world scenario. The experiment consisted of detecting red and green TLSs at six different positions (5, 7, 9, 11, 13, and 15 meters from the TL). The TLSDM achieved a mean Average Precision of 96% for distances lower than 13 meters, and 89.50% for 15 meters. The TLD achieved an overall Root Mean Squared Error (RMSE) of 0.84 for all distances. The TLDM provided a smooth brake profile. Finally, the EBDASTL provided a response time of 0.23 seconds.
- Comparison of methodologies to detect and evaluate Sharp Wave Ripples: assessed in the hippocampus of rats treated with a chronic dose of alcohol(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022) Ruelas Hernández, Marina; Fuentes Aguilar, Rita Quetziquel; dnbsmr; Mendoza Montoya, Omar; López Cuevas, Armando; School of Engineering and Sciences; Campus Monterrey; Medina Ceja, Laura GuadalupeEvidence from several rodent models has revealed that ethanol causes cognitive impairments in hippocampal-dependent activities and that the severity of the damage varies depending on the stage of development at which the rodent was exposed to ethanol and the dose. To the authors’ knowledge, there is a biomarker for cognitive processes in the hippocampus that has not been evaluated in association with memory impairment by alcohol administration. This biomarker is called Sharp Wave Ripples which are synchronous oscillatory events that are well known to be involved in memory consolidation. Examining the effect of alcohol consumption in Sharp Wave Ripples as a biomarker for memory consolidation could provide an opportunity for new treatments to restore and improve cognitive impairment in alcoholism. This thesis focused on analyzing the effect of chronic exposure to alcohol on the occurrence, latency, and peak frequency of Sharp Wave Ripples generated in the hippocampus through Intracranial Electroencephalography signal analysis. In this work, registers from 28 rats were evaluated by implementing and integrating four reported methodologies for ripples identification. A significant difference (p = 0.009) was found in the occurrence of the group that received the alcohol treatment when compared to the before and after state of an evaluation set.
- Flexible three-dimensional robotic system with tomographic magnetic actuation(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-12-03) Pérez San Lázaro, Rafael Alberto; Fuentes Aguilar, Rita Quetziquel; puemcuervo/tolmquevedo; Román Flores, Armando; Cárdenas Fuentes, Diego Ernesto; Salgado Ramos, Iván de Jesús; School of Engineering and Sciences; Campus Guadalajara; Chairez Oria, Jorge IsaacMagnetic strategies implemented within the framework of flexible robotics represent an alternative for procedures where it is necessary to have a safe interaction for the user, taking advantage of the untethered movement, such as in the so-called minimally invasive procedures, performed in clinical environments. This thesis proposes the development of a flexible robotic magnetic structure controlled by an array of electromagnetic actuators arranged in a configuration inspired by the movement generated in tomographs, based on a multi-layer approach with rotatory motion. A first prototype, based on a simple magnetic pendulum controlled by electromagnetic actuators, serves to analyze the interaction between the magnetic fields generated in the system, while the second one illustrates the proof-of-concept of the multi-layer system with tomographic motion. For both prototypes, the scope of the thesis considers the design of the robotic structure and its mathematical modeling; the construction of the system; and its control and evaluation. The mathematical model of the systems considers the description of the interaction of the generalized forces generated by the electromagnetic actuators over the magnetic structure, which is based on a novel methodology proposed within the scope of the thesis and that considers the utilization only of algebraic expressions to approximate the force between electromagnets and permanent magnets. Furthermore, due to the nature of the interaction of the magnetic fields, which requires the magnetic elements not to be at close contact so that they can be separated, the prototype considers the inclusion of boundaries established at first in the mechanical structure to limit the range of movement and further implemented in the control algorithm by means of a Barrier Lyapunov Function (BLF). The results show that the proposed functions of the interaction of magnetic forces yield approximated results that are useful for its application in models for robotic systems. Regarding the robotic systems, it is possible to show the capability of electromagnetic actuators to generate untethered motion over magnetic structures, particularly for the proposed flexible magnetic structure with tomographic magnetic actuation, representing an alternative for robotic systems with wireless movement.
- Pre-diagnosis of diabetic retinopathy implementing supervised learning algorithms using an ocular fundus Latin-American dataset for cross-data validation(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-02) De la Cruz Espinosa, Emanuel; FUENTES AGUILAR, RITA QUETZIQUEL; 229297; Fuentes Aguilar, Rita Quetziquel; emipsanchez; García González, Alejandro; Ochoa Ruiz, Gilberto; Abaunza González, Hernán; School of Engineering and Sciences; Campus MonterreyNowadays diabetes is a disease with worldwide presence and high mortality rate, causing a big social and economic impact. One of the major negative effects of diabetes is visual loss due to diabetic retinopathy (DR). To prevent this condition is necessary to identify referable patients by screening for DR, and complementing with an Optic Coherence Tomography (OCT), that is another study to perform an early detection of blindness doing several longitudinal scans at a series of lateral locations to generate a map of reflection sites in the sample and display it as a two-dimensional image achieving transmission images in turbid tissue. Regrettably the number of ophthalmologists and OCT devices is not enough to provide an adequate health care to the diabetic population. Although there exist AI systems capable of do DR screening, they do not aim the assessment specifically in macula area considering visible and proliferated anomalies, signs of high damage and late intervention. This work presents three surpevised machine learnig algorithms; a Random Forest (RF) classifier, a Convolutional Neural Network (CNN) model, and a transfer learning (TL) pretrained model able to sort fundus images in three classes as an fundus images exclusive database is labeled. Processing techniques such as channel splitting, color space transforms, histogram and spatial based filters and data augmentation are used in order to detect presence of diabetic retinopathy. The stages of this work are: Publicly available dataset debugging, macular segmentation and cropping, data pre-processing, features extraction, model training, test and validation performance evaluation with a exclusive Latin-American dataset considering accuracy, sensitivity and specificity as metrics. The best results achieved are a 61.22% of accuracy, 86.67% of sensitivity and 89.47% of specificity.