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
- Deep learning for clothing classification, case study:thermal comfort(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-11-23) Medina Rosales, Adán; Ponce Cruz, Pedro; puemcuervo; López Caudana, Edgar Omar; Rojas Hernández, Mario; Soriano Avendaño, Luis Arturo; School of Engineering and Sciences; Campus Ciudad de México; Molina Gutiérrez, ArturoImage classification algorithm has being in quick development over the last 10 years with a new algorithm appearing every year, this new algorithms aim to be faster and more accurate than its predecessors, so real time implementations for object classifiers are more frequent. However the solutions for problems are going to more complex problems leaving things such as clothing ensemble classification on the side. There are some proposed solutions on the recognition of clothing garments but all aim to a specific solution in the fashion industry for customer categorization or shopping proposals, however a more general approach which recognizes multiple clothing garments is missing, and a real time clothing ensemble detection could be implemented in several problems. One of such problems is the case study for this project were a CNN implementation is used in video testing to propose the solution for clothing insulation determination using the real time clothing ensemble detector and therefore have a more accurate thermal comfort value. The results proved that the implementation of the chosen CNN architecture could be used as a clothing ensemble detector in a real time implementation, however since a minimized version of the needed dataset was used to verify the viability of this proposal a more complete dataset needs to be created in order to improve the models performance. In general this proposal shows the comparison between come CNN architectures and the datasets available for the propose objectives, as well as the creation of a new dataset that can be successfully used to train the chosen CNN model and produce a real time clothing ensemble detector.
- Detection of suspicious attitudes on video using neuroevolved shallow and deep neural networks models(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-11) Flores Munguía, Carlos; Terashima Marín, Hugo; puemcuervo/tolmquevedo; Oliva, Diego; Ortiz Bayliss, Jose Carlos; School of Engineering and Sciences; Campus MonterreyThe analysis of surveillance cameras is a critical task usually limited by the people involved in the video supervision devoted to such a task, their knowledge, and their judgment. Security guards protect other people from different events that can compromise their security, like robbery, extortion, fraud, vehicle theft, and more, converting them to an essential part of this type of protection system. If they are not paying attention, crimes may be overlooked. Nonetheless, different approaches have arisen to automate this task. The methods are mainly based on machine learning and benefit from developing neural networks that extract underlying information from input videos. However, despite how competent those networks have proved to be, developers must face the challenging task of defining the architecture and hyperparameters that allow the network to work adequately and optimize the use of computational resources. Furthermore, selecting the architecture and hyperparameters may significantly impact the neural networks’ performance if it is not carried out adequately. No matter the type of neural network used, shallow, dense, convolutional, 3D convolutional, or recurrent; hyperparameter selection must be performed using empirical knowledge thanks to the expertise of the designer, or even with the help of automated approaches like Random Search or Bayesian Optimization. However, such methods suffer from problems like not covering the solution space well, especially if the space is made up of large dimensions. Alternatively, the requirement to evaluate the models many times to get more information about the evaluation of the objective function, employing a diverse set of hyperparameters. This work proposes a model that generates, through a genetic algorithm, neural networks for behavior classification within videos. The application of genetic algorithms allows the exploration in the hyperparameters solution space in different directions simultaneously. Two types of neural networks are evolved as part of the thesis work: shallow and deep networks, the latter based on dense layers and 3D convolutions. Each sort of network takes distinct input data types: the evolution of people’s pose and videos’ sequences, respectively. Shallow neural networks are generated by NeuroEvolution of Augmented Topologies (NEAT), while CoDeepNEAT generates deep networks. NEAT uses a direct encoding, meaning that each node and connection in the network is directly represented in the chromosome. In contrast, CoDeepNEAT uses indirect encoding, making use of cooperative coevolution of blueprints and modules. This work trains networks and tests them using the Kranok-NV dataset, which exhibited better results than their competitors on various standard metrics.
- Development and implementation of a categorization model for the exoskeletons based on their design characteristics and practical projects(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020) de la Tejera de la Peña, Javier Alberto; BUSTAMANTE BELLO, MARTIN ROGELIO; 58810; IZQUIERDO REYES, JAVIER; 710170; Bustamante Bello, Martín Rogelio; emipsanchez; Izquierdo Reyes, Javier; School of Engineering and Sciences; Campus Ciudad de México; Ramírez Mendoza,Ricardo AmbrocioThe exoskeletons are the future of the humankind. The humankind is in a constant pursuit of improvement for themselves, both physically and mentally. The human body has physical constraints in which no physical training can surpass, but our ingenious and imagination are making this possible. Several decades ago the first developments started, and nowadays, these developments, plus the improvements, are imperative for the humans in the following decades. The exoskeletons can assist or rehabilitate a person, leading this personalized technology to depend on the needs and abilities that each user has. The exoskeletons have a wide spectrum of opportunities in their design, due to the variety of situations in which a person needs an augmentation of their physical performance, thus the diversity of projects. An exoskeleton for sarcopenia was made for assisting the elderly who require help to perform their daily activities, and tested with electromyography (EMG) to analyze its functionality. On the other hand, an exoskeleton made for rehabilitation, machining the exoskeleton gives us a testing platform for other kinds of projects. Through the development of different exoskeletons and projects related to them, an opportunity area was found to formalize the exoskeletons’ topic, creating a model for the categorization of all the exoskeletons using their design characteristics and a further analysis for recommendations in their design. Besides, in this work are proposed tools, based on the design characteristics of exoskeletons, for the optimization of the exoskeleton design process.