Aprendizaje Profundo para la Detección de Caídas en Personas Vulnerables

Saa Beltrán, María Paula

Aprendizaje Profundo para la Detección de Caídas en Personas Vulnerables

dc.contributor.advisor	Cruz Capador, Gerson David
dc.contributor.advisor	Guarnizo Marín, José Guillermo
dc.contributor.author	Saa Beltrán, María Paula
dc.contributor.corporatename	Universidad Santo Tomás	spa
dc.contributor.cvlac	https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001334709	spa
dc.contributor.cvlac	https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000855847	spa
dc.contributor.cvlac	https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001767650	spa
dc.contributor.googlescholar	https://scholar.google.com/citations?hl=es&user=fVo6U9MAAAAJ	spa
dc.contributor.googlescholar	https://scholar.google.com/citations?hl=es&user=3JSJ0C4AAAAJ	spa
dc.contributor.orcid	https://orcid.org/0000-0002-3723-7509	spa
dc.contributor.orcid	https://orcid.org/0000-0002-8401-4949	spa
dc.contributor.orcid	https://orcid.org/0000-0001-8509-2378	spa
dc.coverage.campus	CRAI-USTA Bogotá	spa
dc.date.accessioned	2023-04-19T16:31:33Z
dc.date.available	2023-04-19T16:31:33Z
dc.date.issued	2023-04-17
dc.description	El proyecto de tesis, muestra el diseño, implementación y desarrollo de un algoritmo de aprendizaje profundo que permite realizar detección de caídas en especial en personal mayores que se encuentran viviendo solas, en espacios médicos o en centros de cuidados geriátricos. Se busca que este proyecto pueda realizar esta detección, sin la necesidad de emplear dispositivos corporales que pueden generar inconvenientes en los pacientes, razón por la cual se opta por emplear un algoritmo basado en redes neuronales recurrentes de tipo LSTM (Memoria prolongada de corto plazo), que tienen la capacidad de recordar información relevante en secuencias y preservarlo por varios instantes de tiempo. Se realizan las pruebas en ambientes controlados, junto con personas que emulen las caídas y que no cuenten con ningún inconveniente de salud, la evaluación del proyectó se realiza a través de distintas métricas y pruebas en tiempo real.	spa
dc.description.abstract	The undergraduate project shows the design, implementation and development of a deep learning algorithm that allows fall detection, especially in older people who are living alone, in medical centres or in geriatric care centres. It is sought that this project can carry out this detection, without the need to use body devices that can generate inconveniences in patients, that is why it is chosen to use an algorithm based on recurrent neural networks of the LSTM type (Long short-term memory), that have the ability to remember relevant information in sequences and preserve it for several instants of time. The tests are carried out in controlled environments, with people who emulate the falls and do not have any health issues, the evaluation of the project is carried out through different metrics and tests in real time.	spa
dc.description.degreelevel	Pregrado	spa
dc.description.degreename	Ingeniero Electronico	spa
dc.format.mimetype	application/pdf	spa
dc.identifier.citation	Saa Beltrán, M. P. (2023). Aprendizaje Profundo para la Detección de Caídas en Personas Vulnerables. [Trabajo de Grado, Universidad Santo Tomás]. Repositorio Institucional.	spa
dc.identifier.instname	instname:Universidad Santo Tomás	spa
dc.identifier.reponame	reponame:Repositorio Institucional Universidad Santo Tomás	spa
dc.identifier.repourl	repourl:https://repository.usta.edu.co	spa
dc.identifier.uri	http://hdl.handle.net/11634/50378
dc.language.iso	spa	spa
dc.publisher	Universidad Santo Tomás	spa
dc.publisher.faculty	Facultad de Ingeniería Electrónica	spa
dc.publisher.program	Pregrado Ingeniería Electrónica	spa
dc.relation.references	Ahmed Abobakr, Mohammed Hossny, Hala Abdelkader, and Saeid Nahavandi. Rgb-d fall detection via deep residual convolutional lstm networks. In 2018 Digital Image Computing: Techniques and Applications (DICTA), pages 1–7, 2018.	spa
dc.relation.references	Charu C Aggarwal et al. Neural networks and deep learning. Springer, 10:978–3, 2018.	spa
dc.relation.references	Xavier Basogain. Redes neuronales artificiales y sus aplicaciones. Dpto. Ingeniería de Sistemas y Automática, Escuela Superior de Ingeniería Bilbao, howpublished=http://ocw.ehu.es/ensenanzas-tecnicas/ redes-neuronales-artificiales-y-sus-aplicaciones/Course_ listing., year=2008.	spa
dc.relation.references	Valentin Bazarevsky and Google Research Ivan Grishchenko, Research Engineers. On-device, real-time body pose tracking with mediapipe blazepose. https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html, aug 2020.	spa
dc.relation.references	Avijeet Biswal. Convolutional neural network tutorial. https://www.simplilearn.com/tutorials/deep-learning-tutorial/convolutional-neural-network, jul 2022.	spa
dc.relation.references	Avijeet Biswal. Recurrent neural network (rnn) tutorial: Types, examples, lstm and more. https://www.simplilearn.com/tutorials/deep-learning-tutorial/rnn, aug 2022.	spa
dc.relation.references	Sebastian Bittrich, Marika Kaden, Christoph Leberecht, Florian Kaiser, Thomas Villmann, and Dirk Labudde. Application of an interpretable classification model on early folding residues during protein folding. BioData mining, 12(1):1–16, 2019.	spa
dc.relation.references	Harsha Bommana. Introduction to neural networks — part 1. https://medium.com/deep-learning-demystified/introduction-to-neural-networks-part-1-e13f132c6d7e, may 2019.	spa
dc.relation.references	Kabalan Chaccour, Rony Darazi, Amir Hajjam El Hassani, and Emmanuel Andrès. From fall detection to fall prevention: A generic classification of fall-related systems. IEEE Sensors Journal, 17(3):812–822, 2017.	spa
dc.relation.references	Madhav Chamle, K. G. Gunale, and K. K. Warhade. Automated unusual event detection in video surveillance. In 2016 International Conference on Inventive Computation Technologies (ICICT), volume 2, pages 1–4, 2016.	spa
dc.relation.references	Pongsatorn Chutimawattanakul and Pranchalee Samanpiboon. Fall detection for the elderly using yolov4 and lstm. In 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pages 1–5,2022.	spa
dc.relation.references	Intel Corporation. Open source computer vision. https://docs.opencv.org/4.6.0/, jun 2022.	spa
dc.relation.references	DANE. Adulto mayor en colombia - características generales. https://www.dane.gov.co/files/investigaciones/genero/presentacion-caracteristicas-generales-adulto-mayor-en-colombia.pdf, jan 2021.	spa
dc.relation.references	Gobierno de Colombia. Misión de sabios - colombia - 2019. https://minciencias.gov.co/sites/default/files/libro_mision_de_sabios_digital_1_2_0.pdf, dec 2021.	spa
dc.relation.references	Congreso de la República. Medidas de protección al adulto mayor en colombia. http://www.secretariasenado.gov.co/senado/basedoc/ley_1850_2017.html, jul 2017.	spa
dc.relation.references	Congreso de la República. ConvenciÓn interamericana sobre la protección de los derechos humanos de las personas mayores. https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=141981, sep 2020.	spa
dc.relation.references	Sonia Patricia de Santillana Hernández, Luis Eduardo Alvarado Moctezuma, Gustavo Rodrigo Medina Beltrán, Gricelda Gómez Ortega, Rosa María Cortés Gonzálezzuela Espinoza, and Rosa María Cortés González. Caídas en el adulto mayor. factores intrínsecos y extrínsecos. Revista Médica del Instituto Mexicano del Seguro Social, 40(6):489–493, 2002.	spa
dc.relation.references	Riya Dichwalkar, Shreya Oak, Tania Rajabally, and Dhananjay Kalbande. Activity recognition and fall detection in elderly people. In 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pages 1–6, 2020.	spa
dc.relation.references	Tran Duc Tan and Nguyen Van Tinh. Reliable fall detection system using an 3-dof accelerometer and cascade posture recognitions. In Signal and Information Processing AssociationAnnual Summit and Conference (APSIPA), 2014 Asia-Pacific, pages 1–6, 2014.	spa
dc.relation.references	Nashwa El-Bendary, Qing Tan, Frédérique C Pivot, and Anthony Lam. Fall detection and prevention for the elderly: A review of trends and challenges. International Journal on Smart Sensing & Intelligent Systems, 6(3), 2013.	spa
dc.relation.references	National Geografic España. Sinapsis, el lenguaje de las neuronas en el cerebro. https://n9.cl/6vjro9, apr 2019.	spa
dc.relation.references	H Espínola. Caídas en el adulto mayor. Boletín de la pontificia Universidad Católica de Chile, 29:1–5, 2000.	spa
dc.relation.references	M.M. Fadoul. Python Machine Learning: Machine Learning and Deep Learning from Scratch Illustrated with Python, Scikit-Learn, Keras, Theano and Tensorflow. Independently Published, 2020.	spa
dc.relation.references	Yaxiang Fan, Martin D. Levine, Gongjian Wen, and Shaohua Qiu. A deep neural network for real-time detection of falling humans in naturally occurring scenes. Neurocomputing, 260:43–58, 2017.	spa
dc.relation.references	Aditya Rio Fansdana, Aulia Khamas Heikhmakhtiar, and Satria Mandala. Real-time falling detection system for elderly using cnn. In 2021 International Conference on Data Science and Its Applications (ICoDSA), pages 194–197, 2021.	spa
dc.relation.references	Shubham Garg, Aman Saxena, and Richa Gupta. Yoga pose classification: a cnn and mediapipe inspired deep learning approach for real-world application. Journal of Ambient Intelligence and Humanized Computing, pages 1–12, 2022.	spa
dc.relation.references	Sparsh Gupta. The 7 most common machine learning loss functions. https://builtin.com/machine-learning/common-loss-functions, apr 2022.	spa
dc.relation.references	Khadija Hanifi and M. Elif Karsligil. Elderly fall detection with vital signs monitoring using cw doppler radar. IEEE Sensors Journal, 21(15):16969–16978, 2021.	spa
dc.relation.references	Md Mahedi Hasan, Md Shamimul Islam, and Sohaib Abdullah. Robust pose-based human fall detection using recurrent neural network. In 2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), pages 48–51, 2019.	spa
dc.relation.references	Kyaw Kyaw Htike, Othman O. Khalifa, Huda Adibah Mohd Ramli, and Mohammad A. M. Abushariah. Human activity recognition for video surveillance using sequences of postures. In The Third International Conference on e-Technologies and Networks for Development (ICeND2014), pages 79–82, 2014.	spa
dc.relation.references	Madoka Inoue, Ryo Taguchi, and Taizo Umezaki. Bed-exit prediction applying neural network combining bed position detection and patient posture estimation. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 3208–3211, 2019.	spa
dc.relation.references	Shruti Jadon. What is an activation function? what are commonly used activation functions? https://medium.com/@shrutijadon/survey-on-activation-functions-for-deep-learning9689331ba092, mar 2018.	spa
dc.relation.references	Rose A Kenny, Cliodhna Ni Scanaill, and Michael McGrath. Falls prevention in the home: Challenges for new technologies. In Intelligent Technologies for Bridging the Grey Digital Divide, pages 46–64. IGI Global, 2011.	spa
dc.relation.references	Sangyeon Kim, Gawon Lee, and Jihie Kim. Lightweight real-time fall detection using bi- directional recurrent neural network. In 2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems (SCIS-ISIS), pages 1–5, 2020.	spa
dc.relation.references	Günter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. Selfnormalizing neural networks. Advances in neural information processing systems, 30, 2017.	spa
dc.relation.references	Xuan-Hien Le, Hung Viet Ho, Giha Lee, and Sungho Jung. Application of long short-term memory (lstm) neural network for flood forecasting. Water, 11(7):1387, 2019.	spa
dc.relation.references	Xiaogang Li, Tiantian Pang, Weixiang Liu, and Tianfu Wang. Fall detection for elderly person care using convolutional neural networks. In 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pages 1–6, 2017.	spa
dc.relation.references	Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Dollár. Microsoft coco: Common objects in context, 2014.	spa
dc.relation.references	Google LLC. Mediapipe pose. https://google.github.io/mediapipe/solutions/pose.html, jun 2020.	spa
dc.relation.references	Patricio Loncomilla. Deep learning: Redes convolucionales. Recuperado de https://ccc. inaoep. mx/ ̃ pgomez/deep/presentations, 2016.	spa
dc.relation.references	Steven T Moore, Valentina Dilda, Bandar Hakim, and Hamish G MacDougall. Validation of 24-hour ambulatory gait assessment in parkinson’s disease with simultaneous video observation. Biomedical engineering online, 10(1):1–9, 2011.	spa
dc.relation.references	Sarah Mroz, Natalie Baddour, Connor McGuirk, Pascale Juneau, Albert Tu, Kevin Cheung, and Edward Lemaire. Comparing the quality of human pose estimation with blazepose or openpose. pages 1–4, 12 2021.	spa
dc.relation.references	Abdulmajid Murad and Jae-Young Pyun. Deep recurrent neural networks for human activity recognition. Sensors, 17(11):2556, 2017.	spa
dc.relation.references	Brian Mwandau and Matunda Nyanchama. Investigating Keystroke Dynamics as a Two-Factor Biometric Security. PhD thesis, 06 2018.	spa
dc.relation.references	Cristobal Olah. Introducción a la memoria a largo corto plazo (lstm). https://colah.github.io/posts/2015-08-Understanding-LSTMs/, aug 2015.	spa
dc.relation.references	Artem Oppermann. Loss functionsin deep learning. jun 2021.	spa
dc.relation.references	Jesús Pérez Guerrero. Redes recurrentes. 2020.	spa
dc.relation.references	M Gestal Pose. Introducción a las redes de neuronas artificiales. Departamento de Tecnologías de la Información y las Comunicaciones. Universidad da Coruña, 2009.	spa
dc.relation.references	Patryk Radzki. Detection of human body landmarks - mediapipe and openpose comparison. https://www.hearai.pl/post/14-openpose/, apr 2022.	spa
dc.relation.references	Nicholas Renotte. Action detection for sign language. https://github.com/nicknochnack/ActionDetectionforSignLanguage, jun 2021.	spa
dc.relation.references	Laura María Álvarez Rodríguez. Síndrome de caídas en el adulto mayor. Revista Médica de Costa Rica y Centroamérica, 72(617):807–810, 2016.	spa
dc.relation.references	Ravi Kiran Selvam. Adagrad and adadelta optimizers - implementation and testing:-. https://www.sravikiran.com/GSOC18/page2/, jul 2018.	spa
dc.relation.references	N Senthilkumar, M Manimegalai, S Karpakam, S.R Ashokkumar, and M Premkumar. Human action recognition based on spatial–temporal relational model and lstm-cnn framework. Materials Today: Proceedings, 57:2087–2091, 2022. International Conference on Innovation and Application in Science and Technology.	spa
dc.relation.references	Sagar Sharma, Simone Sharma, and Anidhya Athaiya. Activation functions in neural networks. towards data science, 6(12):310–316, 2017.	spa
dc.relation.references	Alex Sherstinsky. Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D: Nonlinear Phenomena, 404:132306, 2020.	spa
dc.relation.references	simpl!learn. What is neural network: Overview, applications, and advantages. https://www.simplilearn.com/tutorials/deep-learning-tutorial/what-is-neural-network, jan 2022.	spa
dc.relation.references	Ruoyu Sun. Optimization for deep learning: theory and algorithms. arXiv preprint ar Xiv:1912.08957, 2019.	spa
dc.relation.references	M. Taylor. Make Your Own Neural Network: An In-Depth Visual Introduction for Beginners. Amazon Digital Services LLC - KDP Print US, 2017.	spa
dc.relation.references	tutorialspoint. Evaluating model performance. https://www.tutorialspoint.com/deep_learning_with_keras/deep_learning_with_keras_evaluating_model_performance.htm#, feb 2022.	spa
dc.relation.references	Pavan Vadapalli. Biological neural network: Importance, components & comparison. https://www.upgrad.com/blog/biological-neural-network/, feb 2021.	spa
dc.relation.references	S Yan. Understanding lstm networks. Online). Accessed on August, 11, 2015.	spa
dc.relation.references	Xiaokang Zhou, Wei Liang, Kevin I-Kai Wang, Hao Wang, Laurence T. Yang, and Qun Jin. Deep-learning-enhanced human activity recognition for internet of healthcare things. IEEE Internet of Things Journal, 7(7):6429–6438, 2020.	spa
dc.rights	Atribución-NoComercial-SinDerivadas 2.5 Colombia	*
dc.rights.accessrights	info:eu-repo/semantics/openAccess
dc.rights.coar	http://purl.org/coar/access_right/c_abf2	spa
dc.rights.local	Abierto (Texto Completo)	spa
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/2.5/co/	*
dc.subject.keyword	Neural Networks	spa
dc.subject.keyword	Falls	spa
dc.subject.keyword	Long-Short Term Memory	spa
dc.subject.keyword	Deep Learning	spa
dc.subject.lemb	Ingeniería Electrónica	spa
dc.subject.lemb	Personas Vulnerables	spa
dc.subject.lemb	Diseño-Algoritmos	spa
dc.subject.proposal	Redes Neuronales	spa
dc.subject.proposal	Caídas	spa
dc.subject.proposal	Long-Short Term Memory (LSTM)	spa
dc.subject.proposal	Aprendizaje Profundo	spa
dc.title	Aprendizaje Profundo para la Detección de Caídas en Personas Vulnerables	spa
dc.type	bachelor thesis
dc.type.coar	http://purl.org/coar/resource_type/c_7a1f
dc.type.coarversion	http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.drive	info:eu-repo/semantics/bachelorThesis
dc.type.local	Tesis de pregrado	spa
dc.type.version	info:eu-repo/semantics/acceptedVersion