Mostrar el registro sencillo del ítem

Desarrollo de un estudio para la implementación de cosecha selectiva de café arábica aplicando vibraciones de alta frecuencia

dc.contributor.advisorArizmendi Pereira, Carlos Julio
dc.contributor.authorYarce Herrera, Jeison Ivan
dc.coverage.spatialColombiaspa
dc.date.accessioned2023-03-07T19:12:15Z
dc.date.available2023-03-07T19:12:15Z
dc.date.issued2022
dc.identifier.urihttp://hdl.handle.net/20.500.12749/19201
dc.description.abstractEn el presente estudio se propone analizar un dispositivo que permita estimular los frutos maduros discriminando el movimiento de los frutos verdes en frecuencias muy específicas de movimiento. La tecnología del dispositivo se propone sobre la base de un dispositivo acústico, con una técnica que permita focalizar la energía mediante arreglos de ondas armónica que deben ser controladas para excitar solo frutos maduros. Por lo tanto, una oportunidad es ampliamente observada en el estudio de la subestructura fruto pedúnculo para determinar en los diferentes estados de maduración índices dinámicos que favorezcan el desprendimiento de frutos maduros.spa
dc.description.tableofcontents1 Introducción ............................................................................................................................1 1.1 Motivación ..........................................................................................................................1 1.2 Objetivos .............................................................................................................................3 2 Estado del arte.........................................................................................................................5 2.1 Introducción ........................................................................................................................5 2.2 Estado del arte en detección de objetos...............................................................................6 2.2.1 R-CNN ......................................................................................................................6 2.2.2 Fast R-CNN...............................................................................................................7 2.2.3 Faster R-CNN............................................................................................................9 2.2.4 YOLO......................................................................................................................10 2.3 Estado del arte en cosecha selectiva..................................................................................11 2.3.1 Vibraciones mecánicas............................................................................................11 2.3.2 Técnicas visuales.....................................................................................................12 2.3.3 Propiedades de la fruta del café...............................................................................13 2.3.4 Análisis armónico....................................................................................................15 2.4 Principales tecnologías utilizadas......................................................................................16 2.4.1 Python......................................................................................................................16 2.4.2 Pytorch ....................................................................................................................16 2.4.3 OpenCV...................................................................................................................17 2.4.4 Pandas......................................................................................................................18 2.4.5 Numpy.....................................................................................................................19 3 Redes neuronales artificiales.................................................................................................20 3.1 Introducción ......................................................................................................................20 3.2 La neurona biológica.........................................................................................................20 3.3 La neurona artificial ..........................................................................................................21 3.4 Estructura de las redes neuronales.....................................................................................23 3.4.1 Redes de tipo feed-forward .....................................................................................23 3.4.2 Redes de tipo recurrente ..........................................................................................25 3.4.3 Redes de tipo residual..............................................................................................26 3.5 Tipos de aprendizaje en las redes neuronales....................................................................27 3.5.1 Aprendizaje supervisado .........................................................................................28 3.5.2 Aprendizaje no supervisado ....................................................................................29 3.5.3 Aprendizaje semi-supervisado o hibrido.................................................................29 3.5.4 Aprendizaje por refuerzo.........................................................................................30 3.6 Métodos de aprendizaje.....................................................................................................30 3.6.1 Función de coste......................................................................................................31 3.6.2 Descenso del gradiente............................................................................................32 3.6.3 Descenso estocástico de gradiente ..........................................................................34 3.6.4 Propagación hacia atrás...........................................................................................35 3.7 Medidas de prevención de sobreajuste ..............................................................................36 3.8 Redes neuronales convolucionales....................................................................................38 3.8.1 Capa de convolución ...............................................................................................39 3.8.2 Capa de pooling.......................................................................................................41 3.8.3 Capa softmax...........................................................................................................42 4 Detector de estados de maduración.......................................................................................43 4.1 Introducción ......................................................................................................................43 4.1.1 Funcionamiento general del sistema .......................................................................43 4.2 Módulo de detección y clasificación .................................................................................44 5 Configuración sistema acústico ............................................................................................47 5.1 Introducción ......................................................................................................................47 5.2 Dispositivos.......................................................................................................................48 5.2.1 TURBOSOUND IQ15 CABINA ACTIVA 15" TURBOSOUND............................48 5.2.2 micrófono de medición Behringer ecm8000..............................................................48 5.2.3 Interfaz De Audio Usb Presonus Studio 24c .............................................................48 5.2.4 sensor piezo eléctrico.................................................................................................48 5.2.5 sonómetro uni-t ut353................................................................................................49 5.3 Etapa de calibración ..........................................................................................................49 5.4 Diseño de soporte ..............................................................................................................50 5.4.1 Diseño de soporte.......................................................................................................50 5.4.2 Manufactura soporte ..................................................................................................51 5.5 Montaje..............................................................................................................................51 5.6 Simulaciones.....................................................................................................................52 6 Resultados.............................................................................................................................55 6.1 Introducción ......................................................................................................................5spa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.titleDesarrollo de un estudio para la implementación de cosecha selectiva de café arábica aplicando vibraciones de alta frecuenciaspa
dc.title.translatedDevelopment of a study for the implementation of selective harvesting of arabica coffee by applying high frequency vibrationsspa
dc.degree.nameIngeniero Mecatrónicospa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.rights.localAbierto (Texto Completo)spa
dc.publisher.facultyFacultad Ingenieríaspa
dc.publisher.programPregrado Ingeniería Mecatrónicaspa
dc.description.degreelevelPregradospa
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.localTrabajo de Gradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.subject.keywordsMechatronicspa
dc.subject.keywordsCoffee harvestspa
dc.subject.keywordsArabica coffeespa
dc.subject.keywordsRipe fruitsspa
dc.subject.keywordsDeep learningspa
dc.subject.keywordsArtificial intelligencespa
dc.subject.keywordsTechnological innovationsspa
dc.subject.keywordsAgricultural innovationsspa
dc.subject.keywordsProcess developmentspa
dc.subject.keywordsAlgorithmsspa
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga - UNABspa
dc.identifier.reponamereponame:Repositorio Institucional UNABspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.relation.references[1] L. Figueiredo, I. Jesus, J. A. T. Machado, J. R. Ferreira, and J. L. Martins de Carvalho, “Towards the development of intelligent transportation systems,” in ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585), 2001, pp. 1206– 1211.spa
dc.relation.references[2] F. Torres, G. Barros, and M. J. Barros, “Computer vision classifier and platform for automatic counting: More than cars,” 2017 IEEE 2nd Ecuador Tech. Chapters Meet. ETCM 2017, pp. 1–6, 2017.spa
dc.relation.references[3] E. Soroush, A. Mirzaei, and S. Kamkar, “Near Real-Time Vehicle Detection and Tracking in Highways,” no. March 2017, p. 11, 2016spa
dc.relation.references[4] A.-O. Fulop and L. Tamas, “Lessons learned from lightweight CNN based object recognition for mobile robots,” 2018.spa
dc.relation.references[5] P. Abrahamsson et al., “Affordable and energy-efficient cloud computing clusters: The Bolzano Raspberry Pi cloud cluster experiment,” Proc. Int. Conf. Cloud Comput. Technol. Sci. CloudCom, vol. 2, pp. 170–175, 2013spa
dc.relation.references[6] D. Pena, A. Forembski, X. Xu, and D. Moloney, “Benchmarking of CNNs for Low-Cost, Low-Power Robotics Applications,” 2017.spa
dc.relation.references[7] J. Huang et al., “Speed/accuracy trade-offs for modern convolutional object detectors,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 3296–3305, 2017.spa
dc.relation.references[8] Ministerio del Trabajo, “Incremento del Salario Básico Unificado 2019.,” 2018. [Online]. Available: http://www.trabajo.gob.ec/incremento-del-salario-basico-unificado-2019/. [Accessed: 10-Sep-2019]spa
dc.relation.references[9] Z. Chen, T. Ellis, and S. A. Velastin, “Vehicle detection, tracking and classification in urban traffic,” IEEE Conf. Intell. Transp. Syst. Proceedings, ITSC, pp. 951–956, 2012.spa
dc.relation.references[10] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real time object detection,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 779–788, 2016spa
dc.relation.references[11] J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” Proc. - 30th IEEE Conspa
dc.relation.references[12] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 2018spa
dc.relation.references[13] W. Liu et al., “SSD: Single shot multibox detector,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9905 LNCS, pp. 21–37, 2016.spa
dc.relation.references[14] R. Girshick, “Fast R-CNN,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2015 Inter, pp. 1440– 1448, 2015.spa
dc.relation.references[15] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, 2017.spa
dc.relation.references[16] M. J. Shaifee, B. Chywl, F. Li, and A. Wong, “Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video,” J. Comput. Vis. Imaging Syst., vol. 3, no. 1, 2017spa
dc.relation.references[17] L. Zhang, L. Lin, X. Liang, and K. He, “Is faster R-CNN doing well for pedestrian detection?,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9906 LNCS, pp. 443–457, 2016spa
dc.relation.references[18] Y. Jia et al., “Caffe: Convolutional architecture for fast feature embedding,” MM 2014 - Proc. 2014 ACM Conf. Multimed., vol. abs/1506.0, pp. 675–678, 2014spa
dc.relation.references[19] P. B. Martín Abadi et al., “TensorFlow: A system for large-scale machine learning,” Methods Enzymol., 2016.spa
dc.relation.references[20] Y. LeCun et al., “Backpropagation Applied to Handwritten Zip Code Recognition,” Neural Comput., vol. 1, no. 4, pp. 541–551, 1989.spa
dc.relation.references[21] Chuanqi305, “MobileNet-SSD,” 2019. [Online]. Available: https://github.com/chuanqi305/MobileNet-SSD. [Accessed: 10-Sep- 2019].spa
dc.relation.references[22] A. Rosebrock, “Real-time object detection on the Raspberry Pi with the Movidius NCS,” 2018. [Online]. Available: https://www.pyimagesearch.com/2018/02/19/real-time-object detection-on-the-raspberry-pi-with-the-movidius-ncs/. [Accessed: 10-Sep-2019spa
dc.relation.references[23] Taehoonlee, “High level network definitions with pre-trained weights in TensorFlow,” 2019. [Online]. Available: https://github.com/taehoonlee/tensornets. [Accessed: 10-Sep 2019].spa
dc.relation.references[24] K. Hyodo, “YoloV3,” 2019. [Online]. Available: https://github.com/PINTO0309. [Accessed: 10-Sep-2019].spa
dc.relation.references[25] J. Redmon and A. Farhadi, “Tiny YOLOv3,” 2018. [Online]. Available: https://pjreddie.com/darknet/yolo/. [Accessed: 10-Sep- 2019].spa
dc.relation.references[26] J. Hui, “SSD object detection: Single Shot MultiBox Detector for real-time processing,” 2018. [Online]. Available: https://medium.com/@jonathan_hui/ssd-object-detection single-shot-multibox-detector-for-real-time-processing- 9bd8deac0e06. [Accessed: 10-Sep 2019].spa
dc.relation.references[27] CyberAILab, “A Closer Look at YOLOv3,” 2018. [Online]. Available: https://www.cyberailab.com/home/a-closer-look-at-yolov3. [Accessed: 10-Sep-2019].spa
dc.relation.references[28] T. Y. Lin et al., “Microsoft COCO: Common objects in context,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8693 LNCS, no. PART 5, pp. 740–755, 2014spa
dc.relation.references[29] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (VOC) challenge,” Int. J. Comput. Vis., vol. 88, no. 2, pp. 303–338, 2010spa
dc.relation.references[30] M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes Challenge 2012 (VOC2012),” 2012. [Online]. Available: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/. [Accessed: 10-Sep-2019].spa
dc.relation.references[31] A. Rosebrock, “Simple object tracking with OpenCV,” 2018. [Online]. Available: https://www.pyimagesearch.com/2018/07/23/simple object-tracking-with-opencv/. [Accessed: 10-Sep-2019].spa
dc.relation.references[32] M. Danelljan, G. Häger, F. S. Khan, and M. Felsberg, “Accurate scale estimation for robust visual tracking,” BMVC 2014 - Proc. Br. Mach. Vis. Conf. 2014, 2014spa
dc.relation.references[34] Intel, “Deep Learning For Computer Vision,” 2019. [Online]. Available: https://software.intel.com/en-us/openvino-toolkit/deep-spa
dc.relation.references[34] Intel, “Deep Learning For Computer Vision,” 2019. [Online]. Available: https://software.intel.com/en-us/openvino-toolkit/deep- 88 learning-cv. [Accessed: 10-Oct-2019].spa
dc.relation.references[35] Intel, “Intel® Neural Compute Stick 2,” 2019. [Online]. Available: https://software.intel.com/en-us/neural-compute-stick. [Accessed: 10-Oct-2019].spa
dc.relation.references[36] Raspberry Pi, “Raspberry Pi 3 Model B+,” 2018. [Online]. Available: https://www.raspberrypi.org/products/raspberry-pi-3-model-b- plus/. [Accessed: 10-Oct 2019].spa
dc.relation.references[37] Python, “About Python,” 2019. [Online]. Available: https://www.python.org/about/. [Accessed: 10-Oct-2019].spa
dc.relation.references[38] A. Rosebrock, “Faster video file FPS with cv2.VideoCapture and OpenCV,” 2017. [Online]. Available: https://www.pyimagesearch.com/2017/02/06/faster-video-file-fps-with-cv2- videocapture-and-opencv/. [Accessed: 10-Oct-2019].spa
dc.contributor.cvlacArizmendi Pereira, Carlos Julio [0001381550]spa
dc.contributor.googlescholarArizmendi Pereira, Carlos Julio [JgT_je0AAAAJ]spa
dc.contributor.orcidArizmendi Pereira, Carlos Juliospa
dc.contributor.scopusArizmendi Pereira, Carlos Julio [16174088500]spa
dc.contributor.researchgateArizmendi Pereira, Carlos Julio [Carlos_Arizmendi2]spa
dc.subject.lembMecatrónicaspa
dc.subject.lembInteligencia artificialspa
dc.subject.lembInnovaciones tecnológicasspa
dc.subject.lembInnovaciones agrícolasspa
dc.subject.lembDesarrollo de procesosspa
dc.subject.lembAlgoritmosspa
dc.identifier.repourlrepourl:https://repository.unab.edu.cospa
dc.description.abstractenglishIn the present study it is proposed to analyze a device that allows the stimulation of ripe fruits by discriminating the movement of green fruits in very specific frequencies of movement. The device technology is proposed on the basis of an acoustic device, with a technique that allows energy to be focused through harmonic wave arrangements that must be controlled to excite only ripe fruits. Therefore, an opportunity is widely observed in the study of the fruit peduncle substructure to determine in the different stages of maturation dynamic indices that favor the detachment of ripe fruits.spa
dc.subject.proposalCosecha de caféspa
dc.subject.proposalCafé arábicaspa
dc.subject.proposalFrutos madurosspa
dc.subject.proposalAprendizaje profundospa
dc.type.redcolhttp://purl.org/redcol/resource_type/TP
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.contributor.apolounabArizmendi Pereira, Carlos Julio [carlos-julio-arizmendi-pereira]spa
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.description.learningmodalityModalidad Presencialspa


Ficheros en el ítem

Thumbnail
Nombre:
2022_Tesis_Jeison_Yarce.pdf
Tamaño:
3.426Mb
Formato:
PDF
Descripción:
Tesis
Ver/
Thumbnail
Nombre:
2022_Licencia_Jeison_Yarce.pdf
Tamaño:
620.3Kb
Formato:
PDF
Descripción:
Licencia
Ver/

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución-NoComercial-SinDerivadas 2.5 Colombia
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 2.5 Colombia