Detección de anomalías físicas en redes IoT empleando técnicas de machine learning
El propósito de este trabajo era generar un conjunto de datos que permitiera entrenar un modelo de machine learning basado en el algoritmo KNN para poder detectar anomalías físicas en una red IoT. El modelo generado permitió clasificar correctamente los paquetes con anomalías físicas con tiempos de...
- Autores:
-
Plata Ayala, Néstor Andrés
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2023
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/63992
- Acceso en línea:
- http://hdl.handle.net/1992/63992
- Palabra clave:
- IoT
Red de sensores
Anomalías físicas
KNN
Machine Learning
Ingeniería
- Rights
- openAccess
- License
- Attribution-NonCommercial-NoDerivatives 4.0 Internacional
| id |
UNIANDES2_a376ad0871a8ccafde65fbff4b9495fd |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/63992 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| title |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| spellingShingle |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning IoT Red de sensores Anomalías físicas KNN Machine Learning Ingeniería |
| title_short |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| title_full |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| title_fullStr |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| title_full_unstemmed |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| title_sort |
Detección de anomalías físicas en redes IoT empleando técnicas de machine learning |
| dc.creator.fl_str_mv |
Plata Ayala, Néstor Andrés |
| dc.contributor.advisor.none.fl_str_mv |
Montoya Orozco, Germán Adolfo Lozano Garzon, Carlos Andres |
| dc.contributor.author.none.fl_str_mv |
Plata Ayala, Néstor Andrés |
| dc.contributor.researchgroup.es_CO.fl_str_mv |
COMIT |
| dc.subject.keyword.none.fl_str_mv |
IoT Red de sensores Anomalías físicas KNN Machine Learning |
| topic |
IoT Red de sensores Anomalías físicas KNN Machine Learning Ingeniería |
| dc.subject.themes.es_CO.fl_str_mv |
Ingeniería |
| description |
El propósito de este trabajo era generar un conjunto de datos que permitiera entrenar un modelo de machine learning basado en el algoritmo KNN para poder detectar anomalías físicas en una red IoT. El modelo generado permitió clasificar correctamente los paquetes con anomalías físicas con tiempos de ejecución cortos. |
| publishDate |
2023 |
| dc.date.accessioned.none.fl_str_mv |
2023-01-19T14:28:02Z |
| dc.date.available.none.fl_str_mv |
2023-01-19T14:28:02Z |
| dc.date.issued.none.fl_str_mv |
2023-01-18 |
| dc.type.es_CO.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.content.es_CO.fl_str_mv |
Text |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
http://hdl.handle.net/1992/63992 |
| dc.identifier.instname.es_CO.fl_str_mv |
instname:Universidad de los Andes |
| dc.identifier.reponame.es_CO.fl_str_mv |
reponame:Repositorio Institucional Séneca |
| dc.identifier.repourl.es_CO.fl_str_mv |
repourl:https://repositorio.uniandes.edu.co/ |
| url |
http://hdl.handle.net/1992/63992 |
| identifier_str_mv |
instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/ |
| dc.language.iso.es_CO.fl_str_mv |
spa |
| language |
spa |
| dc.relation.references.es_CO.fl_str_mv |
[1] D. ElMenshawx, y W. Helmy, "(PDF) Detection techniques of data anomalies in loT: literature survey", http://www.laeme.com/IJCIET/index.asp 794 editor@iaeme.com International Journal of Civil Engineering and Technology (ICIET), vol. 9, no 12, pp. 794-807, dic. 2018, Accedido: ago. 27, 2022. [En línea]. Available: https://www.researchgate.net/publication/330192913_Detection_techniques_of_data_anomal les_in_loT_A_literature_survey [2] A. Gaddam, T. Wilkin, M. Angelova, and J. Gaddam, "Detecting Sensor Faults, Anomalies and Outliers inthe Internet of Things: A Survey on theChallenees and Solutions," Electronics (Basel), vol. 9, no. 511, pp. 2-15, Jan. 2020, dol; 10.3390/electronics9030511. [3] N. Yousefnezhad, A. Malhi, and K. Främline, "Security in product lifecycle of loT devices: A survey," Journal of Network and Computer Applications, vol. 171, pp. 102-779, Dec. 2020, dpi: 10.101/1.JNCA.2020.102779. [4] K. A. Omar, A. D. Malik, A. Jamil, and H. M. Gheni, "Faulty sensor detection using multi- variate sensors in internet of things (loTs)," Indonesian Journal of Electrical Engineering and Computer Science, vol. 18, no. 3, pp. 1391-1399, Jun. 2020, dei: 10.11591/WEECS.V18.13.PP1391-1399. M. Lot, S. Belekar, and P. Redekar, "Sensor Fault Detection in loT System Using Machine Learning," International Research Journal of Engineering and Technology, vol. 09, no. 07, pp. 2576-2579, Aug. 2022, Accessed: Aug. 28, 2022. [Online]. Available: http://www.irjet.net/ [5] A. Makhshari and A. Mesbah, "IoT Bugs and Development Challenges," 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, pp. 460-472, doi: 10.1109/ICSE43902.2021.00051. [6] Oracle.com. 2022. What is the Internet of Things (IoT)?. [online] Available at: <https://www.oracle.com/internet-of-things/what-is-iot/> [Accessed 26 September 2022]. [7] Till Johnson, J., 2022. 6 IoT Architecture Layers and Components Explained. [online] IoT Agenda. Available at: <https://www.techtarget.com/iotagenda/tip/A-comprehensive-view-of-the-4-IoT-architecture-layers> [Accessed 26 September 2022]. [8] Education, I., 2022. What is Machine Learning?. [online] Ibm.com. Available at: <https://www.ibm.com/cloud/learn/machine-learning> [Accessed 26 September 2022]. [9] Tesca Global Blog. 2022. What Is Wireless Sensor Network, And Types Of WSN?. [online] Available at: <https://www.tescaglobal.com/blog/what-is-wireless-sensor-network-and-types-of-wsn/> [Accessed 26 September 2022]. [10] Enjoyalgorithms.com. 2022. Publisher-Subscriber (Pub-Sub) Design Pattern. [online] Available at: <https://www.enjoyalgorithms.com/blog/publisher-subscriber-pattern> [Accessed 26 September 2022]. [11] Ibm.com. 2022. What is the k-nearest neighbors algorithm? | IBM. [online] Available at: <https://www.ibm.com/topics/knn> [Accessed 26 September 2022]. [12] 2022. [online] Available at: <https://www.datacamp.com/tutorial/k-nearest-neighbor-classification-scikit-learn> [Accessed 26 September 2022]. [13] Bajaj, A., 2022. Performance Metrics in Machine Learning [Complete Guide] - neptune.ai. [online] neptune.ai. Available at: <https://neptune.ai/blog/performance-metrics-in-machine-learning-complete-guide> [Accessed 26 September 2022]. [14]Yick, J., Mukherjee, B. and Ghosal, D., 2008. Wireless sensor network survey. [online] Available at: <https://www.sciencedirect.com/science/article/pii/S1389128608001254> [Accessed 12 September 2022]. [15]Ying, X. (2019) "An overview of overfitting and its solutions," Journal of Physics: Conference Series, 1168, p. 022022. Available at: https://doi.org/10.1088/1742-6596/1168/2/022022. 16]Docs.sunfounder.com. 2022. Lessons : SunFounder SunFounder_SensorKit_for_RPi2 documentation. [online] Available at: <https://docs.sunfounder.com/projects/sensorkit-v2-pi/en/latest/lessons.html> [Accessed 12 September 2022]. [17]D. Soni A. Makwana, "A SURVEY ON MQTT: A PROTOCOL OF INTERNET OF THINGS(IOT)", 04 2017. [18] ¿Qué es el coeficiente de correlación de pearson? QuestionPro, 09-Nov-2020. [Online]. Available: https://www.questionpro.com/blog/es/coeficiente-de-correlacion-de-pearson/. [Accessed: 26-Oct-2022]. [19] Nyuytiymbiy, K. (2020) Parameters, hyperparameters, machine learning | towards data science, Towards Data Science. Available at: https://towardsdatascience.com/parameters-and-hyperparameters-aa609601a9ac [Accessed: October 31, 2022]. [20] Terra, J. (2022) What is a ROC curve, and how do you use it in performance modeling?: Simplilearn, Simplilearn.com. Simplilearn. Available at: https://www.simplilearn.com/what-is-a-roc-curve-and-how-to-use-it-in-performance-modeling-article (Accessed: November 23, 2022). |
| dc.rights.license.spa.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| dc.rights.uri.*.fl_str_mv |
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.es_CO.fl_str_mv |
41 paginas |
| dc.format.mimetype.es_CO.fl_str_mv |
application/pdf |
| dc.publisher.es_CO.fl_str_mv |
Universidad de los Andes |
| dc.publisher.program.es_CO.fl_str_mv |
Ingeniería de Sistemas y Computación |
| dc.publisher.faculty.es_CO.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.department.es_CO.fl_str_mv |
Departamento de Ingeniería Sistemas y Computación |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/331f301f-1d62-43c9-95c4-7319a84dabac/download https://repositorio.uniandes.edu.co/bitstreams/ca5ac9cc-1f74-480d-9bb8-3e6408c123ba/download https://repositorio.uniandes.edu.co/bitstreams/26b86388-5c13-46ca-ac67-a4ebbc29f78b/download https://repositorio.uniandes.edu.co/bitstreams/97f0f1b2-8880-442a-84c2-f949ad1c9af1/download https://repositorio.uniandes.edu.co/bitstreams/6e06d4c2-4d34-4184-9a7e-1000148aaf46/download https://repositorio.uniandes.edu.co/bitstreams/b7f4adb4-ed6b-467e-b3e7-1ae42e556cdb/download https://repositorio.uniandes.edu.co/bitstreams/35e3d6cb-dfd4-45a5-b1f8-dca06980fa05/download |
| bitstream.checksum.fl_str_mv |
a8f3fa94f609e390e5ff735703dad598 e691d0fe020c0930cca79d6b1e4c2ea1 4dc2721714b8ecc62a24368ab1ce782d 9de3aae51868bbf15271f1680ec44a36 5aa5c691a1ffe97abd12c2966efcb8d6 29ca4d43cc42b1db8031d04156d39274 902a7f15f615de2d4a887791d1925201 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1812133814044983296 |
| spelling |
Attribution-NonCommercial-NoDerivatives 4.0 Internacionalhttps://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Montoya Orozco, Germán Adolfo6215ccc6-8a26-4e94-8ce5-66f0c0dac3a2600Lozano Garzon, Carlos Andresvirtual::1396-1Plata Ayala, Néstor Andrés3110203a-5541-4aac-aefd-3b4ab1259967600COMIT2023-01-19T14:28:02Z2023-01-19T14:28:02Z2023-01-18http://hdl.handle.net/1992/63992instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/El propósito de este trabajo era generar un conjunto de datos que permitiera entrenar un modelo de machine learning basado en el algoritmo KNN para poder detectar anomalías físicas en una red IoT. El modelo generado permitió clasificar correctamente los paquetes con anomalías físicas con tiempos de ejecución cortos.En los últimos años ha cobrado popularidad el uso de redes IoT en diferentes contextos de la cotidianidad. Los sensores que recopilan información, como base de este tipo de redes hacen que estas sean vulnerables a posibles fallas a nivel físico que afectan la veracidad de los datos capturados. En este trabajo se realiza el despliegue de una red de sensores para la posterior captura de información de tráfico normal y tráfico con anomalías. La información capturada fue usada para entrenar y probar un modelo de machine learning con el algoritmo KNN que permite identificar anomalías físicas en una red. El modelo presentó un desempeño positivo, clasificando correctamente el 99.53% de los paquetes analizados.Ingeniero de Sistemas y ComputaciónPregrado41 paginasapplication/pdfspaUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería Sistemas y ComputaciónDetección de anomalías físicas en redes IoT empleando técnicas de machine learningTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPIoTRed de sensoresAnomalías físicasKNNMachine LearningIngeniería[1] D. ElMenshawx, y W. Helmy, "(PDF) Detection techniques of data anomalies in loT: literature survey", http://www.laeme.com/IJCIET/index.asp 794 editor@iaeme.com International Journal of Civil Engineering and Technology (ICIET), vol. 9, no 12, pp. 794-807, dic. 2018, Accedido: ago. 27, 2022. [En línea]. Available: https://www.researchgate.net/publication/330192913_Detection_techniques_of_data_anomal les_in_loT_A_literature_survey[2] A. Gaddam, T. Wilkin, M. Angelova, and J. Gaddam, "Detecting Sensor Faults, Anomalies and Outliers inthe Internet of Things: A Survey on theChallenees and Solutions," Electronics (Basel), vol. 9, no. 511, pp. 2-15, Jan. 2020, dol; 10.3390/electronics9030511.[3] N. Yousefnezhad, A. Malhi, and K. Främline, "Security in product lifecycle of loT devices: A survey," Journal of Network and Computer Applications, vol. 171, pp. 102-779, Dec. 2020, dpi: 10.101/1.JNCA.2020.102779.[4] K. A. Omar, A. D. Malik, A. Jamil, and H. M. Gheni, "Faulty sensor detection using multi- variate sensors in internet of things (loTs)," Indonesian Journal of Electrical Engineering and Computer Science, vol. 18, no. 3, pp. 1391-1399, Jun. 2020, dei: 10.11591/WEECS.V18.13.PP1391-1399. M. Lot, S. Belekar, and P. Redekar, "Sensor Fault Detection in loT System Using Machine Learning," International Research Journal of Engineering and Technology, vol. 09, no. 07, pp. 2576-2579, Aug. 2022, Accessed: Aug. 28, 2022. [Online]. Available: http://www.irjet.net/[5] A. Makhshari and A. Mesbah, "IoT Bugs and Development Challenges," 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, pp. 460-472, doi: 10.1109/ICSE43902.2021.00051.[6] Oracle.com. 2022. What is the Internet of Things (IoT)?. [online] Available at: <https://www.oracle.com/internet-of-things/what-is-iot/> [Accessed 26 September 2022].[7] Till Johnson, J., 2022. 6 IoT Architecture Layers and Components Explained. [online] IoT Agenda. Available at: <https://www.techtarget.com/iotagenda/tip/A-comprehensive-view-of-the-4-IoT-architecture-layers> [Accessed 26 September 2022].[8] Education, I., 2022. What is Machine Learning?. [online] Ibm.com. Available at: <https://www.ibm.com/cloud/learn/machine-learning> [Accessed 26 September 2022].[9] Tesca Global Blog. 2022. What Is Wireless Sensor Network, And Types Of WSN?. [online] Available at: <https://www.tescaglobal.com/blog/what-is-wireless-sensor-network-and-types-of-wsn/> [Accessed 26 September 2022].[10] Enjoyalgorithms.com. 2022. Publisher-Subscriber (Pub-Sub) Design Pattern. [online] Available at: <https://www.enjoyalgorithms.com/blog/publisher-subscriber-pattern> [Accessed 26 September 2022].[11] Ibm.com. 2022. What is the k-nearest neighbors algorithm? | IBM. [online] Available at: <https://www.ibm.com/topics/knn> [Accessed 26 September 2022].[12] 2022. [online] Available at: <https://www.datacamp.com/tutorial/k-nearest-neighbor-classification-scikit-learn> [Accessed 26 September 2022].[13] Bajaj, A., 2022. Performance Metrics in Machine Learning [Complete Guide] - neptune.ai. [online] neptune.ai. Available at: <https://neptune.ai/blog/performance-metrics-in-machine-learning-complete-guide> [Accessed 26 September 2022].[14]Yick, J., Mukherjee, B. and Ghosal, D., 2008. Wireless sensor network survey. [online] Available at: <https://www.sciencedirect.com/science/article/pii/S1389128608001254> [Accessed 12 September 2022].[15]Ying, X. (2019) "An overview of overfitting and its solutions," Journal of Physics: Conference Series, 1168, p. 022022. Available at: https://doi.org/10.1088/1742-6596/1168/2/022022.16]Docs.sunfounder.com. 2022. Lessons : SunFounder SunFounder_SensorKit_for_RPi2 documentation. [online] Available at: <https://docs.sunfounder.com/projects/sensorkit-v2-pi/en/latest/lessons.html> [Accessed 12 September 2022].[17]D. Soni A. Makwana, "A SURVEY ON MQTT: A PROTOCOL OF INTERNET OF THINGS(IOT)", 04 2017.[18] ¿Qué es el coeficiente de correlación de pearson? QuestionPro, 09-Nov-2020. [Online]. Available: https://www.questionpro.com/blog/es/coeficiente-de-correlacion-de-pearson/. [Accessed: 26-Oct-2022].[19] Nyuytiymbiy, K. (2020) Parameters, hyperparameters, machine learning | towards data science, Towards Data Science. Available at: https://towardsdatascience.com/parameters-and-hyperparameters-aa609601a9ac [Accessed: October 31, 2022].[20] Terra, J. (2022) What is a ROC curve, and how do you use it in performance modeling?: Simplilearn, Simplilearn.com. Simplilearn. Available at: https://www.simplilearn.com/what-is-a-roc-curve-and-how-to-use-it-in-performance-modeling-article (Accessed: November 23, 2022).201822937Publicationhttps://scholar.google.es/citations?user=WRJlR-UAAAAJvirtual::1396-10000-0003-2920-6320virtual::1396-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000219541virtual::1396-1144aa5a0-592f-47a4-995b-a440d00b1658virtual::1396-1144aa5a0-592f-47a4-995b-a440d00b1658virtual::1396-1ORIGINALDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdfDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdfTrabajo de gradoapplication/pdf1380595https://repositorio.uniandes.edu.co/bitstreams/331f301f-1d62-43c9-95c4-7319a84dabac/downloada8f3fa94f609e390e5ff735703dad598MD53Autorizacion Tesis Nestor PLata.pdfAutorizacion Tesis Nestor PLata.pdfHIDEapplication/pdf274367https://repositorio.uniandes.edu.co/bitstreams/ca5ac9cc-1f74-480d-9bb8-3e6408c123ba/downloade691d0fe020c0930cca79d6b1e4c2ea1MD52TEXTDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdf.txtDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdf.txtExtracted texttext/plain53241https://repositorio.uniandes.edu.co/bitstreams/26b86388-5c13-46ca-ac67-a4ebbc29f78b/download4dc2721714b8ecc62a24368ab1ce782dMD54Autorizacion Tesis Nestor PLata.pdf.txtAutorizacion Tesis Nestor PLata.pdf.txtExtracted texttext/plain1414https://repositorio.uniandes.edu.co/bitstreams/97f0f1b2-8880-442a-84c2-f949ad1c9af1/download9de3aae51868bbf15271f1680ec44a36MD56LICENSElicense.txtlicense.txttext/plain; charset=utf-81810https://repositorio.uniandes.edu.co/bitstreams/6e06d4c2-4d34-4184-9a7e-1000148aaf46/download5aa5c691a1ffe97abd12c2966efcb8d6MD51THUMBNAILDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdf.jpgDeteccio¿n de anomali¿as fi¿sicas en redes IoT empleando te¿cnicas de machine learning.pdf.jpgIM Thumbnailimage/jpeg10091https://repositorio.uniandes.edu.co/bitstreams/b7f4adb4-ed6b-467e-b3e7-1ae42e556cdb/download29ca4d43cc42b1db8031d04156d39274MD55Autorizacion Tesis Nestor PLata.pdf.jpgAutorizacion Tesis Nestor PLata.pdf.jpgIM Thumbnailimage/jpeg18674https://repositorio.uniandes.edu.co/bitstreams/35e3d6cb-dfd4-45a5-b1f8-dca06980fa05/download902a7f15f615de2d4a887791d1925201MD571992/63992oai:repositorio.uniandes.edu.co:1992/639922024-03-13 11:57:12.113https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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 |