Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera

La movilidad vial y el buen comportamiento del conductor en la carretera es de vital importancia para mantener una movilidad sin accidentes de tránsito y conductores prudentes en las vías. Los sistemas inteligentes de transporte (SIT) brindan la optimización de la estructura vial incrementando el co...

Full description

Autores:
Aguilar Camacho, Joaquin Fernando
Tipo de recurso:
Fecha de publicación:
2023
Institución:
Universidad Autónoma de Bucaramanga - UNAB
Repositorio:
Repositorio UNAB
Idioma:
spa
OAI Identifier:
oai:repository.unab.edu.co:20.500.12749/22585
Acceso en línea:
http://hdl.handle.net/20.500.12749/22585
Palabra clave:
Systems engineer
Software development
K-Means
Machine learning
Driving behaviors
On-board diagnostics
Artificial intelligence
Automatic control
Psychology observation
Desarrollo de Software
Ingeniería de sistemas
Inteligencia artificial
Aprendizaje automático
Control automático
Observación psicología
Comportamientos de conducción
Diagnóstico a bordo
GUI
PCA
Rights
License
http://creativecommons.org/licenses/by-nc-nd/2.5/co/
id UNAB2_0126871aa5cf47eadabd4aae4bf02e05
oai_identifier_str oai:repository.unab.edu.co:20.500.12749/22585
network_acronym_str UNAB2
network_name_str Repositorio UNAB
repository_id_str
dc.title.spa.fl_str_mv Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
dc.title.translated.spa.fl_str_mv Classification of driver behavior using machine learning techniques and onboard monitoring with OBD ll in real road conditions
title Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
spellingShingle Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
Systems engineer
Software development
K-Means
Machine learning
Driving behaviors
On-board diagnostics
Artificial intelligence
Automatic control
Psychology observation
Desarrollo de Software
Ingeniería de sistemas
Inteligencia artificial
Aprendizaje automático
Control automático
Observación psicología
Comportamientos de conducción
Diagnóstico a bordo
GUI
PCA
title_short Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
title_full Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
title_fullStr Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
title_full_unstemmed Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
title_sort Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carretera
dc.creator.fl_str_mv Aguilar Camacho, Joaquin Fernando
dc.contributor.advisor.none.fl_str_mv Maradey Lázaro, Jessica Gissella
Huertas, José Ignasio
dc.contributor.author.none.fl_str_mv Aguilar Camacho, Joaquin Fernando
dc.contributor.cvlac.spa.fl_str_mv Maradey Lázaro, Jessica Gissella [0000040553]
dc.contributor.orcid.spa.fl_str_mv Maradey Lázaro, Jessica Gissella [0000-0003-2319-1965]
dc.contributor.researchgroup.spa.fl_str_mv Grupo de Investigación Tecnologías de Información - GTI
Grupo de Investigaciones Clínicas
dc.contributor.apolounab.spa.fl_str_mv Maradey Lázaro, Jessica Gissella [jessica-gissella-maradey-lázaro]
dc.subject.keywords.spa.fl_str_mv Systems engineer
Software development
K-Means
Machine learning
Driving behaviors
On-board diagnostics
Artificial intelligence
Automatic control
Psychology observation
topic Systems engineer
Software development
K-Means
Machine learning
Driving behaviors
On-board diagnostics
Artificial intelligence
Automatic control
Psychology observation
Desarrollo de Software
Ingeniería de sistemas
Inteligencia artificial
Aprendizaje automático
Control automático
Observación psicología
Comportamientos de conducción
Diagnóstico a bordo
GUI
PCA
dc.subject.lemb.spa.fl_str_mv Desarrollo de Software
Ingeniería de sistemas
Inteligencia artificial
Aprendizaje automático
Control automático
Observación psicología
dc.subject.proposal.spa.fl_str_mv Comportamientos de conducción
Diagnóstico a bordo
GUI
PCA
description La movilidad vial y el buen comportamiento del conductor en la carretera es de vital importancia para mantener una movilidad sin accidentes de tránsito y conductores prudentes en las vías. Los sistemas inteligentes de transporte (SIT) brindan la optimización de la estructura vial incrementando el control, la eficiencia, efectividad, la educación de los conductores al momento de la conducción, con el objetivo de gestionar el crecimiento demanda de movilidad y el comportamiento de los conductores en las vías. Un aporte crucial para los sistemas inteligentes de transporte son las campañas de monitoreo en condiciones reales de carretera que permitan la recolección de datos y su vez identificar el tipo de comportamiento del conductor. En el proyecto desarrollado se implementó una campaña de monitoreo abordo con un dispositivo ODB ll instalado en una muestra de 5 vehículos, que por medio de la conexión a bluetooth y una App instalada en el Smartphone se realiza la captura de los datos pertinentes para identificar el comportamiento de conducción. Para la identificación de los comportamientos de conducción se desarrolló un modelo de Machine Learning por medio de la técnica K-Means donde se clasificaron a los conductores en 3 grandes grupos (clúster): conductor normal, agresivo y peligroso. Con la identificación de los comportamientos de conducción se logra evidenciar que el conductor peligroso al ir a velocidad altas, tiene un mayor consumo de combustible y el riesgo de ocasionar accidenten en la malla vial.
publishDate 2023
dc.date.accessioned.none.fl_str_mv 2023-11-03T17:51:52Z
dc.date.available.none.fl_str_mv 2023-11-03T17:51:52Z
dc.date.issued.none.fl_str_mv 2023-10-24
dc.type.driver.none.fl_str_mv info:eu-repo/semantics/masterThesis
dc.type.local.spa.fl_str_mv Tesis
dc.type.hasversion.none.fl_str_mv info:eu-repo/semantics/acceptedVersion
dc.type.redcol.none.fl_str_mv http://purl.org/redcol/resource_type/TM
status_str acceptedVersion
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/20.500.12749/22585
dc.identifier.instname.spa.fl_str_mv instname:Universidad Autónoma de Bucaramanga - UNAB
dc.identifier.reponame.spa.fl_str_mv reponame:Repositorio Institucional UNAB
dc.identifier.repourl.spa.fl_str_mv repourl:https://repository.unab.edu.co
url http://hdl.handle.net/20.500.12749/22585
identifier_str_mv instname:Universidad Autónoma de Bucaramanga - UNAB
reponame:Repositorio Institucional UNAB
repourl:https://repository.unab.edu.co
dc.language.iso.spa.fl_str_mv spa
language spa
dc.relation.references.spa.fl_str_mv Albornoz, M. (2014, October). Diseño de interfaz gráfica de usuario. In XVI Workshop de Investigadores en Ciencias de la Computación.
Aljaafreh, A., Alshabatat, N. & Din, A. (2012). Driving style recognition using fuzzy logic. De International Conference on Vehicular Electronics and Safety.
Al Haddad, C. & Antoniou, C. (2022). A data–information–knowledge cycle for modeling driving behavior. Transportation Research Part F: Traffic Psychology and Behaviour, 85, 83–102. https://doi.org/10.1016/j.trf.2021.12.017
Ameen, H. A., Mahamad, A. K., Saon, S., Malik, R. Q., Kareem, Z. H., Bin Ahmadon, M. A., & Yamaguchi, S. (2021). Identification of driving safety profiles in vehicle to vehicle communication system based on vehicle obd information. Information (Switzerland), 12(5). https://doi.org/10.3390/info12050194
Barbé, J. & Boy, G. (2006). On-board system design to optimize energy management. In Proceedings of the European Annual Conference on Human Decision-Making and Manual Control, Valenciennes, 27–29.
Bejani, M. & Ghatee, M. (2019). Convolutional neural network with adaptive regularization to classify driving styles on smartphones. IEEE Transactions on Intelligent Transportation Systems, 21, 543–552.
Bussooa, A., & Mungur, A. (2019). Driving behaviour analysis using IoT. Advances in Intelligent Systems and Computing, 863, 233–243. https://doi.org/10.1007/978-981- 13-3338-5_22
Chen, S., Xue, Q., Zhao, X., Xing, Y., & Lu, J. (2021). Risky driving behavior recognition based on vehicle trajectory. International Journal of Environmental Research and Public Health, 18(23). https://doi.org/10.3390/ijerph182312373
Ciapponi, A. (2021). La declaración PRISMA 2020: una guía actualizada para reportar revisiones sistemáticas. Evidencia, actualizacion en la práctica ambulatoria, 24(3), e002139-e002139.
Constantinescu, Z., Marinoiu, C. y Vladoiu, M. (2010). Driving style analysis using data mining techniques. International Journal of Computers Communications & Control, 5, 654–663.
Comportamiento. (2022). Significado de Comportamiento. Https://Www.Significados.Com/Comportamiento/
Crisol, E., Herrera, L., & Montes, R. (2020). Virtual education for all: Systematic review. In Education in the Knowledge Society (Vol. 21). Ediciones Universidad de Salamanca. https://doi.org/10.14201/eks.20327
Deery, H. (1999). Hazard and risk perception among young novice drivers. 30, 225–236.
Del Campo, I., Asua, E., Martínez, V., Mata, O. y Echanobe, J. (2018). Driving style recognition based on ride comfort using a hybrid machine learning algorithm. 21st International Conference on Intelligent Transportation Systems (ITSC), 3251–3258
Derbel, O. & Landry, R. (2015). Driving style assessment based on the GPS data and fuzzy inference systems. De 12th International Multi-Conference on Systems, Signals & Devices
Deng, C., Wu, C., Lyu, N. & Huang, Z. (2017). Driving style recognition method using braking characteristics based on hidden Markov model. PLOS ONE, 12
Dong, C. H., Ma, R. G., Zhang, D., Zhang, W. T., & Wang, F. F. (2019). Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving. Mobile Information Systems, 2019. https://doi.org/10.1155/2019/9527890
El Naqa, I., & Murphy, M. J. (2015). What is machine learning? (pp. 3-11). Springer International Publishing.
Felstead, T., McDonald, M. & Fowkes, M. (2009). Driving style extremes and potential vehicle emission effects. In Proceedings of the Institution of Civil EngineersTransport, 162, 141–148.
Feng, Y., Pickering, S., Chappell, E., Iravani, P. & Brace, C. (2018). Driving Style Modelling with Adaptive Neuro-Fuzzy Inference System and Real Driving Data. In International Conference on Applied Human Factors and Ergonomics, 481–490.
Figueroa, J., Duarte, M., Jaramillo, S., Orjuela, A., & Díaz, Y. (2019). Applied Computer Sciences in Engineering (Vol. 1052). Springer International Publishing. https://doi.org/10.1007/978-3-030-31019-6
Fu, X., Meng, H., Wang, X., Yang, H. & Wang J (2022). A hybrid neural network for driving behavior risk prediction based on distracted driving behavior data. PLoS ONE 17(1): e0263030. https://doi.org/10.1371/journal.pone.0263030
GonzaleZ, F., Van Aken, E., & Keathley, H. (2020). Bibliometric Analysis of Research Design Characteristics in Continuous Improvement Projects in Hospitals.
Guo, J., Liu, Y., Zhang, L., & Wang, Y. (2018). Driving behaviour style study with a hybrid deep learning framework based on GPS data. Sustainability (Switzerland), 10(7). https://doi.org/10.3390/su10072351
Jiménez, F., Amarillo, J., Naranjo, J., Serradilla, F. & Díaz. A. (2015). Energy consumption estimation in electric vehicles considering driving style. De IEEE 18th International Conference on Intelligent Transportation Systems.
Kalra, N., Goyal, R. K., Parashar, A., Singh, J., & Singla, G. (2021). Driving Style Recognition System Using Smartphone Sensors Based on Fuzzy Logic. Computers, Materials and Continua, 69(2), 1967–1978. https://doi.org/10.32604/cmc.2021.018732
Kang, H. B. (2013). Various approaches for driver and driving behavior monitoring: A review. Proceedings of the IEEE International Conference on Computer Vision, 616– 623. https://doi.org/10.1109/ICCVW.2013.85
Karaduman, M. & Eren, H. (2017). Deep learning based traffic direction sign detection and determining driving style. 2017 International Conference on Computer Science and Engineering, 1046–1050.
Karginova, N., Byttner, S. & Svensson, M. (2012). Data-driven methods for classification of driving styles in buses. SAE Technical Paper.
Kleisen, L. (2011). The relationship between thinking and driving styles and their contribution to young driver road safety. University of Canberra.
Koskinen, O. (2008). Improving vehicle fuel economy and reducing emissions by driving technique, Pattern Recognition Model of Intelligent Driving Behavior Based on Prototype Matching Fig. 3 Structure of Virtual Scene Simulation System.
Kumtepe, O., Akar, G. B., & Yuncu, E. (2016). Driver aggressiveness detection via multisensory data fusion. Eurasip Journal on Image and Video Processing, 2016(1), 1–16. https://doi.org/10.1186/s13640-016-0106-9
Laapotti, S., Keskinen, E. & Rajalin, S. (2002). Comparison of young male and female drivers’ attitude and self-reported traffic behaviour in Finland in 1978 and 2001. 34(5), 579–587.
Lashkov, I. B. (2021). Determination of dangerous driving behavior based on the use of information from wearable electronic devices. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 21(4), 515–524. https://doi.org/10.17586/2226-1494-2021-21-4-515-524
Ledoux, K., Visser, P. W., Hulin, J. D., & Nguyen, H. (2015). Starting large synchronous motors in weak power systems. IEEE Transactions on Industry Applications, 51(3), 2676–2682. https://doi.org/10.1109/TIA.2014.2373820
Li, Y., Wei, Y., Li, W., & Bao, L. (2017). Research on Evaluation Method of Driving Behavior Safety for Taxi Driver Based on Space-Time Trajectory Feature
Liu, H., Taniguchi, T., Takenaka, K., & Bando, T. (2018). Defect-repairable latent feature extraction of driving behavior via a deep sparse autoencoder. Sensors (Switzerland), 18(2). https://doi.org/10.3390/s18020608
Lobo, M. (2000). Rendimiento de los sistemas de recuperación de información en la web: evaluación de servicios de búsqueda (search engines). Revista española de documentación científica, 23(3), 302-316.
Ma, Y., Zhang, Z., Chen, S., Yu, Y., & Tang, K. (2019). A Comparative Study of Aggressive Driving Behavior Recognition Algorithms Based on Vehicle Motion Data. IEEE Access, 7, 8028–8038. https://doi.org/10.1109/ACCESS.2018.2889751
Mantouka, E., Barmpounakis, E., Vlahogianni, E., & Golias, J. (2021). Smartphone sensing for understanding driving behavior: Current practice and challenges. In International Journal of Transportation Science and Technology (Vol. 10, Issue 3, pp. 266–282). Elsevier B.V. https://doi.org/10.1016/j.ijtst.2020.07.001
Martínez, C., Heucke, M., Wang, F., Gao, B. & Cao, D. (2017). Driving Style Recognition for Intelligent Vehicle Control and Advanced Driver Assistance: A Survey. 19, 666– 676.
McTish, P., & Park, S. (2016). Exploring Aggressive Driving Behavior in Pennsylvania’s Delaware Valley Region. Procedia Engineering, 145, 836–843. https://doi.org/10.1016/j.proeng.2016.04.109
MinTransporte. (2022, February 25). MinTransporte. Https://Www.Mintransporte.Gov.Co/Publicaciones/10673/Colombia-Avanza-EnIniciativas-Para-La-Movilidad-Sostenible
Molina, J. y Acuña, B. (2022), “Clasificación de Estilos de Conducción en el Área Metropolitana de Bucaramanga con Monitoreo a Bordo (OBD ll) en Condiciones Reales de Carretera”
National Science Foundation (U.S.), & Institute of Electrical and Electronics Engineers. (2019) IEEE International Conference on Healthcare Informatics (ICHI): 10-13 June 2019, Xi’an, China.
Navarro, S y García, R. (2021), Desarrollo de un ciclo de conducción bajo condiciones reales de carretera en el área metropolitana de Bucaramanga, Bucaramanga.
Pereira, J. M., & Rivera, J. F. (2008). Digital surveillance tools for contact tracking of infected persons by SARS-CoV-2. https://www.researchgate.net/publication/342421313
Piñeiro Gómez, J. (2022). Entornos de desarrollo. Ediciones Paraninfo, SA.
Portafolio. (2019, August 9). Los 7 tipos de personalidades al volante. Https://Www.Portafolio.Co/Economia/Los-7-Tipos-de-Personalidades-al-Volante531962.
Priyadharshini, G. & Femilda, J. (2020). A comprehensive review of various data collection approaches, features, and algorithms used for the classification of driving style,». De Materials Science and Engineering.
Rafael, M., Sanchez, M., Mucino, V., Cervantes, J., & Lozano, A. (2006). Impact of driving styles on exhaust emissions and fuel economy from a heavy-duty truck: Laboratory tests,» International Journal of Heavy Vehicle System. 13, 56–73
Reimer, B., Donmez,B., Lavallière, M., Mehler, B., Coughlin, J. & Teasdale, N. (2013). Impact of age and cognitive demand on lane choice and changing under actual highway condition. Accident Analysis & Prevention, 52, 125–132.
Saad, F. (2004). Behavioural adaptions to new driver support systems: Some critical issues (pp. 288–293).
Sagberg, F., Bianchi, G. & Engström, J. (2015). A Review of Research on Driving Styles and Road Safety,». 7, 1248–1275.
Shi, Y., Cui, N. & Du, Y. (2020). Energy Management Strategy based on Driving Style Recognition for Plug-in Hybrid Electric Bus. De 2020 39th Chinese Control Conference, 5511–5516.
Stoichkov, R. (2013). Android smartphone application for driving style recognition.
Vanguardia. (2022, August 2). Vanguardia. Https://Www.Vanguardia.Com/AreaMetropolitana/Bucaramanga/147-Aumento-En-Bucaramanga-y-Su-Area-ElParque-AutomotorCX4088712#:~:Text=Actualmente%20hay%20m%C3%A1s%20de%20760,Veh%C 3%ADculos%20durante%20la%20%C3%BAltima%20d%C3%A9cada.
Waard, D., Dijksterhuis, C. & Brookhuis, K. (2009). Merging into heavy motorway traffic by young and elderly drivers. Accident Analysis & Prevention, 41, 588–597.
Wang, X., Lou, X. Y., Hu, S. Y., & He, S. C. (2020). Evaluation of safe driving behavior of transport vehicles based on k-svm-xgboost. Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020, 84–92. https://doi.org/10.1109/AEMCSE50948.2020.00026
Wu, M., Zhang, S., & Dong, Y. (2016). A novel model-based driving behavior recognition system using motion sensors. Sensors (Switzerland), 16(10). https://doi.org/10.3390/s16101746
Xiao, D., Jin, X., Xu, X., Ma, C., & Yuan, Q. (2021). Exploring traffic safety climate with driving condition and driving behaviour: A random parameter structural equation model approach. Transportation Safety and Environment, 3(3). https://doi.org/10.1093/tse/tdab015
Xin, G., Li, G., & Gang, D. (2011). Research on intelligent driving behavior based on cognitive science and scene simulation. Proceedings - 2011 International Conference on Intelligence Science and Information Engineering, ISIE 2011, 226– 229. https://doi.org/10.1109/ISIE.2011.15
Xu, W., Wang, J., Fu, T., Gong, H., & Sobhani, A. (2022). Aggressive driving behavior prediction considering driver’s intention based on multivariate-temporal feature data. Accident Analysis and Prevention, 164. https://doi.org/10.1016/j.aap.2021.106477
Yuan, G., Wang, Y., Peng, J., & Fu, X. (2021). A Novel Driving Behavior Learning and Visualization Method with Natural Gaze Prediction. IEEE Access, 9, 18560–18568. https://doi.org/10.1109/ACCESS.2021.3054951
Zaragoza Galiana, A. (2021). Clustering y Analítica de clientes de SEMIC mediante Machine Learning.
Zhang, H., Nan, Z., Yang, T., Liu, Y., & Zheng, N. (2020). A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN. IEEE Intelligent Vehicles Symposium, Proceedings, 284–289. https://doi.org/10.1109/IV47402.2020.9304772
Zhang, J., Wu, Z., Li, F., Luo, J., Ren, T., Hu, S., Li, W., & Li, W. (2019). Attention-Based Convolutional and Recurrent Neural Networks for Driving Behavior Recognition Using Smartphone Sensor Data. IEEE Access, 7, 148031–148046. https://doi.org/10.1109/ACCESS.2019.2932434
dc.relation.uriapolo.spa.fl_str_mv https://apolo.unab.edu.co/en/persons/jessica-gissella-maradey-l%C3%A1zaro
dc.rights.coar.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.uri.*.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/2.5/co/
dc.rights.local.spa.fl_str_mv Abierto (Texto Completo)
dc.rights.creativecommons.*.fl_str_mv Atribución-NoComercial-SinDerivadas 2.5 Colombia
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/2.5/co/
Abierto (Texto Completo)
Atribución-NoComercial-SinDerivadas 2.5 Colombia
http://purl.org/coar/access_right/c_abf2
dc.format.mimetype.spa.fl_str_mv application/pdf
dc.coverage.spatial.spa.fl_str_mv Bucaramanga (Santander, Colombia)
dc.coverage.temporal.spa.fl_str_mv Marzo- Junio del 2023
dc.coverage.campus.spa.fl_str_mv UNAB Campus Bucaramanga
dc.publisher.grantor.spa.fl_str_mv Universidad Autónoma de Bucaramanga UNAB
dc.publisher.faculty.spa.fl_str_mv Facultad Ingeniería
dc.publisher.program.spa.fl_str_mv Maestría en Gestión, Aplicación y Desarrollo de Software
institution Universidad Autónoma de Bucaramanga - UNAB
bitstream.url.fl_str_mv https://repository.unab.edu.co/bitstream/20.500.12749/22585/1/Tesis.pdf
https://repository.unab.edu.co/bitstream/20.500.12749/22585/5/Licencia.pdf
https://repository.unab.edu.co/bitstream/20.500.12749/22585/4/license.txt
https://repository.unab.edu.co/bitstream/20.500.12749/22585/6/Tesis.pdf.jpg
https://repository.unab.edu.co/bitstream/20.500.12749/22585/7/Licencia.pdf.jpg
bitstream.checksum.fl_str_mv 24d2f205790a4e4c22f5a4499e62bf91
6fa4ac05ae563c1973fe67ca10dab9df
3755c0cfdb77e29f2b9125d7a45dd316
c610ebe1ae059a399fe067194882f8f9
e88d27f804e307e3526fd2f5956661dd
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional | Universidad Autónoma de Bucaramanga - UNAB
repository.mail.fl_str_mv repositorio@unab.edu.co
_version_ 1814278261662810112
spelling Maradey Lázaro, Jessica Gissellad6570851-23e5-44e4-8c29-fd312d351b94Huertas, José Ignasio4d2ba583-5a85-4920-934c-63b3fbeed92fAguilar Camacho, Joaquin Fernando2718b0c0-5d4b-4b24-80e9-47c7e3847f1cMaradey Lázaro, Jessica Gissella [0000040553]Maradey Lázaro, Jessica Gissella [0000-0003-2319-1965]Grupo de Investigación Tecnologías de Información - GTIGrupo de Investigaciones ClínicasMaradey Lázaro, Jessica Gissella [jessica-gissella-maradey-lázaro]Bucaramanga (Santander, Colombia)Marzo- Junio del 2023UNAB Campus Bucaramanga2023-11-03T17:51:52Z2023-11-03T17:51:52Z2023-10-24http://hdl.handle.net/20.500.12749/22585instname:Universidad Autónoma de Bucaramanga - UNABreponame:Repositorio Institucional UNABrepourl:https://repository.unab.edu.coLa movilidad vial y el buen comportamiento del conductor en la carretera es de vital importancia para mantener una movilidad sin accidentes de tránsito y conductores prudentes en las vías. Los sistemas inteligentes de transporte (SIT) brindan la optimización de la estructura vial incrementando el control, la eficiencia, efectividad, la educación de los conductores al momento de la conducción, con el objetivo de gestionar el crecimiento demanda de movilidad y el comportamiento de los conductores en las vías. Un aporte crucial para los sistemas inteligentes de transporte son las campañas de monitoreo en condiciones reales de carretera que permitan la recolección de datos y su vez identificar el tipo de comportamiento del conductor. En el proyecto desarrollado se implementó una campaña de monitoreo abordo con un dispositivo ODB ll instalado en una muestra de 5 vehículos, que por medio de la conexión a bluetooth y una App instalada en el Smartphone se realiza la captura de los datos pertinentes para identificar el comportamiento de conducción. Para la identificación de los comportamientos de conducción se desarrolló un modelo de Machine Learning por medio de la técnica K-Means donde se clasificaron a los conductores en 3 grandes grupos (clúster): conductor normal, agresivo y peligroso. Con la identificación de los comportamientos de conducción se logra evidenciar que el conductor peligroso al ir a velocidad altas, tiene un mayor consumo de combustible y el riesgo de ocasionar accidenten en la malla vial.INTRODUCCIÓN...............................................................................................13 1.MARCO TEÓRICO O ESTADO DEL ARTE.................................................16 1.1 MARCO TEÓRICO......................................................................................16 1.1.1 Comportamiento de conducción..............................................................16 1.1.2 Estilos de conducción...............................................................................22 1.2 ESTADO DEL ARTE ...................................................................................25 1.2.1 Análisis Bibliométrico ...............................................................................25 1.2.2 Tipos de comportamiento del conductor.................................................29 1.2.3 Instrumentación para la recolección de datos ........................................30 1.2.4 Técnicas de clasificación para el comportamiento del conductor .........31 2.METODOLOGÍA.............................................................................................33 3.MONITOREO DE VARIABLES DE OPERACIÓN Y ACTUALIZACIÓN DE LA BASE DE DATOS...............................................................................34 3.1 CAMPAÑA DE MONITOREO.....................................................................34 3.1.1 Ruta Seleccionada ...................................................................................35 3.1.2 Datos técnicos de los vehículos monitoreados.......................................36 3.1.3 Datos sociodemográficos de los conductores ........................................37 3.1.4 Variables monitoreadas ...........................................................................38 3.1.5 Sistema de monitoreo ejecutado.............................................................39 3.1.6 Sistema de captura de los datos .............................................................40 3.1.7 Canal de Conectividad para él envió de la información.........................42 3.2. SISTEMA CAPTURAR DE DATOS...........................................................44 3.2.1 Almacenamiento de datos .......................................................................48 3.2.2 Captura de los datos ................................................................................50 3.2.3 Eliminación de Datos Atípicos .................................................................50 3.2.4 Registro de datos en la nube...................................................................54 3.3 BASE DE DATOS PROYECTO ACTUAL 2023 ........................................54 3.4 BASE DE DATOS CONCATENADA..........................................................56 4.TÉCNICA DE MACHINE LEARNING PARA LA CLASIFICACIÓN DE LOS COMPORTAMIENTOS DE CONDUCCIÓN ........................................58 7 4.1 METODOLOGÍA APLICADA PARA LA CLASIFICACIÓN DE LOS COMPORTAMIENTOS DE CONDUCCIÓN. ...................................................58 4.2 ELECCIÓN Y CONFIGURACIÓN DEL ENTORNO DE DESARROLLO .62 4.2.1 Entorno de desarrollo integrado IDE.......................................................62 4.2.2 Listado de IDE en el lenguaje de programación Python........................63 4.2.3 Cuadro comparativo de los IDE...............................................................64 4.3 CONSTRUCCIÓN DEL MODELO DE MACHINE LEARNING.................65 4.3.1 Paso a paso para la construcción del modelo de Machine Learning:...67 4.4 ANÁLISIS DE LOS DATOS ........................................................................70 4.5 MODELO DE MACHINE LEARNING.........................................................76 4.6 PREDICCIONES SEGÚN EL MODELO DE MACHINE LEARNING .......89 4.6.1 Pasos para realizar la predicción con el modelo de Machine Learning 90 4.7 RESULTADOS OBTENIDOS DE LAS PREDICCIONES DE LOS CONDUCTORES...............................................................................................98 4.8 ANÁLISIS DE LOS DIAGRAMAS SAFD..................................................102 5.VALIDACIÓN DE RESULTADOS POR MEDIO DE GUI (INTERFAZ GRÁFICA DE USUARIO) ............................................................................104 5.1 VALIDACIÓN DEL ALGORITMO .............................................................104 5.2 INTERFAZ GRÁFICA................................................................................109 5.2.1 Librerías implementadas en Python para la creación de la interfaz gráfica…...........................................................................................................110 5.2.2 Proceso de construcción de la GUI.......................................................112 6.CONCLUSIONES.........................................................................................118 7.RECOMENDACIONES Y TRABAJOS FUTUROS ....................................119 REFERENCIAS Y BIBLIOGRAFIA.................................................................120 LISTA DE ANEXOS.........................................................................................126 ANEXOS..........................................................................................................127MaestríaRoad mobility and good driver behavior on the road is of vital importance to maintain mobility without traffic accidents and prudent drivers on the roads. Intelligent transportation systems (ITS) provide optimization of the road structure by increasing control, efficiency, effectiveness, and driver education at the time of driving, with the aim of managing the growing demand for mobility and the behavior of drivers. drivers on the roads. A crucial contribution to intelligent transportation systems are monitoring campaigns in real road conditions that allow data collection and in turn identify the type of driver behavior. In the developed project, an on-board monitoring campaign was implemented with an ODB II device installed in a sample of 5 vehicles, which through a Bluetooth connection and an App installed on the Smartphone captures the relevant data to identify the driving behavior. To identify driving behaviors, a Machine Learning model was developed using the K-Means technique where drivers were classified into 3 large groups (cluster): normal, aggressive and dangerous driver. With the identification of driving behaviors, it is possible to show that the dangerous driver, when traveling at high speed, has greater fuel consumption and the risk of causing accidents on the road network.Modalidad Virtualapplication/pdfspahttp://creativecommons.org/licenses/by-nc-nd/2.5/co/Abierto (Texto Completo)Atribución-NoComercial-SinDerivadas 2.5 Colombiahttp://purl.org/coar/access_right/c_abf2Clasificación del comportamiento del conductor mediante técnicas de aprendizaje automático y monitoreo a bordo con OBD ll en condiciones reales de carreteraClassification of driver behavior using machine learning techniques and onboard monitoring with OBD ll in real road conditionsMagíster en Gestión, Aplicación y Desarrollo de SoftwareUniversidad Autónoma de Bucaramanga UNABFacultad IngenieríaMaestría en Gestión, Aplicación y Desarrollo de Softwareinfo:eu-repo/semantics/masterThesisTesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/redcol/resource_type/TMSystems engineerSoftware developmentK-MeansMachine learningDriving behaviorsOn-board diagnosticsArtificial intelligenceAutomatic controlPsychology observationDesarrollo de SoftwareIngeniería de sistemasInteligencia artificialAprendizaje automáticoControl automáticoObservación psicologíaComportamientos de conducciónDiagnóstico a bordoGUIPCAAlbornoz, M. (2014, October). Diseño de interfaz gráfica de usuario. In XVI Workshop de Investigadores en Ciencias de la Computación.Aljaafreh, A., Alshabatat, N. & Din, A. (2012). Driving style recognition using fuzzy logic. De International Conference on Vehicular Electronics and Safety.Al Haddad, C. & Antoniou, C. (2022). A data–information–knowledge cycle for modeling driving behavior. Transportation Research Part F: Traffic Psychology and Behaviour, 85, 83–102. https://doi.org/10.1016/j.trf.2021.12.017Ameen, H. A., Mahamad, A. K., Saon, S., Malik, R. Q., Kareem, Z. H., Bin Ahmadon, M. A., & Yamaguchi, S. (2021). Identification of driving safety profiles in vehicle to vehicle communication system based on vehicle obd information. Information (Switzerland), 12(5). https://doi.org/10.3390/info12050194Barbé, J. & Boy, G. (2006). On-board system design to optimize energy management. In Proceedings of the European Annual Conference on Human Decision-Making and Manual Control, Valenciennes, 27–29.Bejani, M. & Ghatee, M. (2019). Convolutional neural network with adaptive regularization to classify driving styles on smartphones. IEEE Transactions on Intelligent Transportation Systems, 21, 543–552.Bussooa, A., & Mungur, A. (2019). Driving behaviour analysis using IoT. Advances in Intelligent Systems and Computing, 863, 233–243. https://doi.org/10.1007/978-981- 13-3338-5_22Chen, S., Xue, Q., Zhao, X., Xing, Y., & Lu, J. (2021). Risky driving behavior recognition based on vehicle trajectory. International Journal of Environmental Research and Public Health, 18(23). https://doi.org/10.3390/ijerph182312373Ciapponi, A. (2021). La declaración PRISMA 2020: una guía actualizada para reportar revisiones sistemáticas. Evidencia, actualizacion en la práctica ambulatoria, 24(3), e002139-e002139.Constantinescu, Z., Marinoiu, C. y Vladoiu, M. (2010). Driving style analysis using data mining techniques. International Journal of Computers Communications & Control, 5, 654–663.Comportamiento. (2022). Significado de Comportamiento. Https://Www.Significados.Com/Comportamiento/Crisol, E., Herrera, L., & Montes, R. (2020). Virtual education for all: Systematic review. In Education in the Knowledge Society (Vol. 21). Ediciones Universidad de Salamanca. https://doi.org/10.14201/eks.20327Deery, H. (1999). Hazard and risk perception among young novice drivers. 30, 225–236.Del Campo, I., Asua, E., Martínez, V., Mata, O. y Echanobe, J. (2018). Driving style recognition based on ride comfort using a hybrid machine learning algorithm. 21st International Conference on Intelligent Transportation Systems (ITSC), 3251–3258Derbel, O. & Landry, R. (2015). Driving style assessment based on the GPS data and fuzzy inference systems. De 12th International Multi-Conference on Systems, Signals & DevicesDeng, C., Wu, C., Lyu, N. & Huang, Z. (2017). Driving style recognition method using braking characteristics based on hidden Markov model. PLOS ONE, 12Dong, C. H., Ma, R. G., Zhang, D., Zhang, W. T., & Wang, F. F. (2019). Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving. Mobile Information Systems, 2019. https://doi.org/10.1155/2019/9527890El Naqa, I., & Murphy, M. J. (2015). What is machine learning? (pp. 3-11). Springer International Publishing.Felstead, T., McDonald, M. & Fowkes, M. (2009). Driving style extremes and potential vehicle emission effects. In Proceedings of the Institution of Civil EngineersTransport, 162, 141–148.Feng, Y., Pickering, S., Chappell, E., Iravani, P. & Brace, C. (2018). Driving Style Modelling with Adaptive Neuro-Fuzzy Inference System and Real Driving Data. In International Conference on Applied Human Factors and Ergonomics, 481–490.Figueroa, J., Duarte, M., Jaramillo, S., Orjuela, A., & Díaz, Y. (2019). Applied Computer Sciences in Engineering (Vol. 1052). Springer International Publishing. https://doi.org/10.1007/978-3-030-31019-6Fu, X., Meng, H., Wang, X., Yang, H. & Wang J (2022). A hybrid neural network for driving behavior risk prediction based on distracted driving behavior data. PLoS ONE 17(1): e0263030. https://doi.org/10.1371/journal.pone.0263030GonzaleZ, F., Van Aken, E., & Keathley, H. (2020). Bibliometric Analysis of Research Design Characteristics in Continuous Improvement Projects in Hospitals.Guo, J., Liu, Y., Zhang, L., & Wang, Y. (2018). Driving behaviour style study with a hybrid deep learning framework based on GPS data. Sustainability (Switzerland), 10(7). https://doi.org/10.3390/su10072351Jiménez, F., Amarillo, J., Naranjo, J., Serradilla, F. & Díaz. A. (2015). Energy consumption estimation in electric vehicles considering driving style. De IEEE 18th International Conference on Intelligent Transportation Systems.Kalra, N., Goyal, R. K., Parashar, A., Singh, J., & Singla, G. (2021). Driving Style Recognition System Using Smartphone Sensors Based on Fuzzy Logic. Computers, Materials and Continua, 69(2), 1967–1978. https://doi.org/10.32604/cmc.2021.018732Kang, H. B. (2013). Various approaches for driver and driving behavior monitoring: A review. Proceedings of the IEEE International Conference on Computer Vision, 616– 623. https://doi.org/10.1109/ICCVW.2013.85Karaduman, M. & Eren, H. (2017). Deep learning based traffic direction sign detection and determining driving style. 2017 International Conference on Computer Science and Engineering, 1046–1050.Karginova, N., Byttner, S. & Svensson, M. (2012). Data-driven methods for classification of driving styles in buses. SAE Technical Paper.Kleisen, L. (2011). The relationship between thinking and driving styles and their contribution to young driver road safety. University of Canberra.Koskinen, O. (2008). Improving vehicle fuel economy and reducing emissions by driving technique, Pattern Recognition Model of Intelligent Driving Behavior Based on Prototype Matching Fig. 3 Structure of Virtual Scene Simulation System.Kumtepe, O., Akar, G. B., & Yuncu, E. (2016). Driver aggressiveness detection via multisensory data fusion. Eurasip Journal on Image and Video Processing, 2016(1), 1–16. https://doi.org/10.1186/s13640-016-0106-9Laapotti, S., Keskinen, E. & Rajalin, S. (2002). Comparison of young male and female drivers’ attitude and self-reported traffic behaviour in Finland in 1978 and 2001. 34(5), 579–587.Lashkov, I. B. (2021). Determination of dangerous driving behavior based on the use of information from wearable electronic devices. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 21(4), 515–524. https://doi.org/10.17586/2226-1494-2021-21-4-515-524Ledoux, K., Visser, P. W., Hulin, J. D., & Nguyen, H. (2015). Starting large synchronous motors in weak power systems. IEEE Transactions on Industry Applications, 51(3), 2676–2682. https://doi.org/10.1109/TIA.2014.2373820Li, Y., Wei, Y., Li, W., & Bao, L. (2017). Research on Evaluation Method of Driving Behavior Safety for Taxi Driver Based on Space-Time Trajectory FeatureLiu, H., Taniguchi, T., Takenaka, K., & Bando, T. (2018). Defect-repairable latent feature extraction of driving behavior via a deep sparse autoencoder. Sensors (Switzerland), 18(2). https://doi.org/10.3390/s18020608Lobo, M. (2000). Rendimiento de los sistemas de recuperación de información en la web: evaluación de servicios de búsqueda (search engines). Revista española de documentación científica, 23(3), 302-316.Ma, Y., Zhang, Z., Chen, S., Yu, Y., & Tang, K. (2019). A Comparative Study of Aggressive Driving Behavior Recognition Algorithms Based on Vehicle Motion Data. IEEE Access, 7, 8028–8038. https://doi.org/10.1109/ACCESS.2018.2889751Mantouka, E., Barmpounakis, E., Vlahogianni, E., & Golias, J. (2021). Smartphone sensing for understanding driving behavior: Current practice and challenges. In International Journal of Transportation Science and Technology (Vol. 10, Issue 3, pp. 266–282). Elsevier B.V. https://doi.org/10.1016/j.ijtst.2020.07.001Martínez, C., Heucke, M., Wang, F., Gao, B. & Cao, D. (2017). Driving Style Recognition for Intelligent Vehicle Control and Advanced Driver Assistance: A Survey. 19, 666– 676.McTish, P., & Park, S. (2016). Exploring Aggressive Driving Behavior in Pennsylvania’s Delaware Valley Region. Procedia Engineering, 145, 836–843. https://doi.org/10.1016/j.proeng.2016.04.109MinTransporte. (2022, February 25). MinTransporte. Https://Www.Mintransporte.Gov.Co/Publicaciones/10673/Colombia-Avanza-EnIniciativas-Para-La-Movilidad-SostenibleMolina, J. y Acuña, B. (2022), “Clasificación de Estilos de Conducción en el Área Metropolitana de Bucaramanga con Monitoreo a Bordo (OBD ll) en Condiciones Reales de Carretera”National Science Foundation (U.S.), & Institute of Electrical and Electronics Engineers. (2019) IEEE International Conference on Healthcare Informatics (ICHI): 10-13 June 2019, Xi’an, China.Navarro, S y García, R. (2021), Desarrollo de un ciclo de conducción bajo condiciones reales de carretera en el área metropolitana de Bucaramanga, Bucaramanga.Pereira, J. M., & Rivera, J. F. (2008). Digital surveillance tools for contact tracking of infected persons by SARS-CoV-2. https://www.researchgate.net/publication/342421313Piñeiro Gómez, J. (2022). Entornos de desarrollo. Ediciones Paraninfo, SA.Portafolio. (2019, August 9). Los 7 tipos de personalidades al volante. Https://Www.Portafolio.Co/Economia/Los-7-Tipos-de-Personalidades-al-Volante531962.Priyadharshini, G. & Femilda, J. (2020). A comprehensive review of various data collection approaches, features, and algorithms used for the classification of driving style,». De Materials Science and Engineering.Rafael, M., Sanchez, M., Mucino, V., Cervantes, J., & Lozano, A. (2006). Impact of driving styles on exhaust emissions and fuel economy from a heavy-duty truck: Laboratory tests,» International Journal of Heavy Vehicle System. 13, 56–73Reimer, B., Donmez,B., Lavallière, M., Mehler, B., Coughlin, J. & Teasdale, N. (2013). Impact of age and cognitive demand on lane choice and changing under actual highway condition. Accident Analysis & Prevention, 52, 125–132.Saad, F. (2004). Behavioural adaptions to new driver support systems: Some critical issues (pp. 288–293).Sagberg, F., Bianchi, G. & Engström, J. (2015). A Review of Research on Driving Styles and Road Safety,». 7, 1248–1275.Shi, Y., Cui, N. & Du, Y. (2020). Energy Management Strategy based on Driving Style Recognition for Plug-in Hybrid Electric Bus. De 2020 39th Chinese Control Conference, 5511–5516.Stoichkov, R. (2013). Android smartphone application for driving style recognition.Vanguardia. (2022, August 2). Vanguardia. Https://Www.Vanguardia.Com/AreaMetropolitana/Bucaramanga/147-Aumento-En-Bucaramanga-y-Su-Area-ElParque-AutomotorCX4088712#:~:Text=Actualmente%20hay%20m%C3%A1s%20de%20760,Veh%C 3%ADculos%20durante%20la%20%C3%BAltima%20d%C3%A9cada.Waard, D., Dijksterhuis, C. & Brookhuis, K. (2009). Merging into heavy motorway traffic by young and elderly drivers. Accident Analysis & Prevention, 41, 588–597.Wang, X., Lou, X. Y., Hu, S. Y., & He, S. C. (2020). Evaluation of safe driving behavior of transport vehicles based on k-svm-xgboost. Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020, 84–92. https://doi.org/10.1109/AEMCSE50948.2020.00026Wu, M., Zhang, S., & Dong, Y. (2016). A novel model-based driving behavior recognition system using motion sensors. Sensors (Switzerland), 16(10). https://doi.org/10.3390/s16101746Xiao, D., Jin, X., Xu, X., Ma, C., & Yuan, Q. (2021). Exploring traffic safety climate with driving condition and driving behaviour: A random parameter structural equation model approach. Transportation Safety and Environment, 3(3). https://doi.org/10.1093/tse/tdab015Xin, G., Li, G., & Gang, D. (2011). Research on intelligent driving behavior based on cognitive science and scene simulation. Proceedings - 2011 International Conference on Intelligence Science and Information Engineering, ISIE 2011, 226– 229. https://doi.org/10.1109/ISIE.2011.15Xu, W., Wang, J., Fu, T., Gong, H., & Sobhani, A. (2022). Aggressive driving behavior prediction considering driver’s intention based on multivariate-temporal feature data. Accident Analysis and Prevention, 164. https://doi.org/10.1016/j.aap.2021.106477Yuan, G., Wang, Y., Peng, J., & Fu, X. (2021). A Novel Driving Behavior Learning and Visualization Method with Natural Gaze Prediction. IEEE Access, 9, 18560–18568. https://doi.org/10.1109/ACCESS.2021.3054951Zaragoza Galiana, A. (2021). Clustering y Analítica de clientes de SEMIC mediante Machine Learning.Zhang, H., Nan, Z., Yang, T., Liu, Y., & Zheng, N. (2020). A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN. IEEE Intelligent Vehicles Symposium, Proceedings, 284–289. https://doi.org/10.1109/IV47402.2020.9304772Zhang, J., Wu, Z., Li, F., Luo, J., Ren, T., Hu, S., Li, W., & Li, W. (2019). Attention-Based Convolutional and Recurrent Neural Networks for Driving Behavior Recognition Using Smartphone Sensor Data. IEEE Access, 7, 148031–148046. https://doi.org/10.1109/ACCESS.2019.2932434https://apolo.unab.edu.co/en/persons/jessica-gissella-maradey-l%C3%A1zaroORIGINALTesis.pdfTesis.pdfTesisapplication/pdf2016818https://repository.unab.edu.co/bitstream/20.500.12749/22585/1/Tesis.pdf24d2f205790a4e4c22f5a4499e62bf91MD51open accessLicencia.pdfLicencia.pdfLicenciaapplication/pdf288414https://repository.unab.edu.co/bitstream/20.500.12749/22585/5/Licencia.pdf6fa4ac05ae563c1973fe67ca10dab9dfMD55metadata only accessLICENSElicense.txtlicense.txttext/plain; charset=utf-8829https://repository.unab.edu.co/bitstream/20.500.12749/22585/4/license.txt3755c0cfdb77e29f2b9125d7a45dd316MD54open accessTHUMBNAILTesis.pdf.jpgTesis.pdf.jpgIM Thumbnailimage/jpeg5008https://repository.unab.edu.co/bitstream/20.500.12749/22585/6/Tesis.pdf.jpgc610ebe1ae059a399fe067194882f8f9MD56open accessLicencia.pdf.jpgLicencia.pdf.jpgIM Thumbnailimage/jpeg10321https://repository.unab.edu.co/bitstream/20.500.12749/22585/7/Licencia.pdf.jpge88d27f804e307e3526fd2f5956661ddMD57metadata only access20.500.12749/22585oai:repository.unab.edu.co:20.500.12749/225852024-01-18 10:33:04.786open accessRepositorio Institucional | Universidad Autónoma de Bucaramanga - UNABrepositorio@unab.edu.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

Publicaciones similares