Evaluación de desempeño de algoritmos de inteligencia artificial embebida en teléfonos inteligentes

datacite.rightshttp://purl.org/coar/access_right/c_f1cf
dc.contributor.advisorMéndez Torrenegra, Fernando Miguel
dc.contributor.authorCantillo Cantillo, Isaac Alejandro
dc.contributor.authorAcosta Álvarez, Mario Fernando
dc.contributor.authorArenas Perdomo, Juan Manuel
dc.contributor.authorCerpa Cabrera, David Enrique
dc.contributor.authorAyala Fabra, Sheila Sandrid
dc.contributor.authorCoronel Campo, Jesús Daniel
dc.date.accessioned2024-11-07T15:04:23Z
dc.date.available2024-11-07T15:04:23Z
dc.date.issued2024
dc.description.abstractLa integración de la inteligencia artificial (IA) con el Internet de las cosas (IoT) está transformando numerosos sectores mediante la automatización y la mejora de procesos en tiempo real. Aplicaciones en áreas como el hogar inteligente, la salud y la industria demuestran su creciente relevancia. Este proyecto busca evaluar la eficiencia y precisión de modelos de detección de objetos y poses humanas implementados en dispositivos Android. Para lograr esto, se configuraron modelos en dispositivos Xiaomi Redmi 10 y Redmi Note 11S mediante Android Studio. Se utilizaron dos algoritmos de prueba: uno para la detección de objetos y otro para la detección de poses humanas. Posteriormente, se trasladaron los modelos entrenados a los dispositivos de prueba utilizando Android Studio para compilar el código y configurar el APK correspondiente. La métrica principal evaluada fue el tiempo de procesamiento por imagen y la eficacia en la detección de objetos y poses humanas. Se incorporó un método de medición dentro del modelo para registrar el tiempo de inicio y fin de procesamiento de cada imagen, permitiendo calcular el tiempo promedio por imagen. Los resultados demuestran la capacidad del modelo para operar en tiempo real con alta precisión y adaptabilidad a diferentes dispositivos, validando su potencial en aplicaciones prácticas. La integración de innovaciones como la arquitectura SBR, que utiliza el protocolo de enrutamiento RPL para IoT, y las herramientas de cloud computing en entornos educativos, subraya la importancia de soluciones eficientes y escalables para la gestión de redes IoT y el acceso remoto a recursos computacionales. Las mejoras futuras podrían centrarse en la optimización de hiperparámetros y la diversificación de datos para aumentar aún más la precisión y confiabilidad del modelo, evidenciando la adaptabilidad y robustez de los modelos desarrollados para aplicaciones en tiempo real.spa
dc.description.abstractThe integration of artificial intelligence (AI) with the Internet of Things (IoT) is transforming numerous sectors through real-time process automation and enhancement. Applications in areas such as smart homes, healthcare, and industry demonstrate its growing relevance. This project aims to evaluate the efficiency and accuracy of object detection and human pose estimation models implemented on Android devices. To achieve this, models were configured on Xiaomi Redmi 10 and Redmi Note 11S devices using Android Studio. Two test algorithms were used: one for object detection and another for human pose estimation. The trained models were then transferred to the test devices using Android Studio to compile the code and configure the corresponding APK. The main metric evaluated was the processing time per image and the effectiveness in detecting objects and human poses. A measurement method was incorporated within the model to record the start and end processing times of each image, allowing for the calculation of the average time per image. The results demonstrate the model's capability to operate in real-time with high precision and adaptability to different devices, validating its potential in practical applications. The integration of innovations such as the SBR architecture, which uses the RPL routing protocol for IoT, and cloud computing tools in educational settings, underscores the importance of efficient and scalable solutions for managing IoT networks and remote access to computational resources. Future improvements could focus on hyperparameter optimization and data diversification to further increase the model's accuracy and reliability, highlighting the adaptability and robustness of the developed models for real-time applications.eng
dc.format.mimetypepdf
dc.identifier.urihttps://hdl.handle.net/20.500.12442/15929
dc.language.isospa
dc.publisherEdiciones Universidad Simón Bolívarspa
dc.publisherFacultad de Ingenieríasspa
dc.rights.accessrightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectDetección de objetosspa
dc.subjectEstimación de posesspa
dc.subjectMobileNet2spa
dc.subjectDispositivos Androidspa
dc.subjectVisión por computadoraspa
dc.subjectTiempospa
dc.subject.keywordsObject detectioneng
dc.subject.keywordsPose estimationeng
dc.subject.keywordsMobileNet2eng
dc.subject.keywordsAndroid deviceseng
dc.subject.keywordsComputer visioneng
dc.subject.keywordsReal timeeng
dc.titleEvaluación de desempeño de algoritmos de inteligencia artificial embebida en teléfonos inteligentesspa
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.spaTrabajo de grado - pregrado
dcterms.referencesY. Liu, X. Li, J. Liu, and L. Wang, "AIoT applications in edge-cloud environments," IEEE Internet of Things Journal, vol. 6, no. 5, pp. 834-845, 2023.eng
dcterms.referencesS. Zhang, H. Wu, and D. Chen, "Distributed AIoT systems: Challenges and future directions," Journal of Cloud Computing, vol. 10, no. 2, pp. 123-135, 2023.eng
dcterms.references"The Impact of Mobile Learning on Students' Attitudes towards Learning in an Educational Technology Course." MDPI Journals, 2023.eng
dcterms.references"Mobile Application Market Analysis and Forecast." Expert Market Research, 2023. Disponible en: Expert Market Research.eng
dcterms.referencesTrends and Challenges in AIoT/IIoT/IoT Implementation." MDPI Journals, 2023.eng
dcterms.referenceseSIM and Blockchain Integrated Secure Zero-Touch Provisioning for Autonomous Cellular-IoTs in 5G Networks." IEEE Journals, 2024.eng
dcterms.referencesM. Hamdaoui, B. Krishnamachari, et al., "Reinforcement and deep reinforcement learning for Internet of 34 Things: Learn, know, and adapt," Computer Networks, vol. 193, pp. 107784, 2021, doi: 10.1016/j.comnet.2021.107784.eng
dcterms.referencesJi, G., Woo, J., Lee, G., Msigwa, C., Bernard, D., & Yun, J. (2021). AIoT-Based Smart Healthcare in Everyday Lives: Data Collection and Standardization from Smartphones and Smartwatches. Journal of LaTeX Class Files, 14(8). DOI: 10.1109/JIOT.2024.3400509eng
dcterms.referencesChang, W.-J., Chen, L.-B., Hsu, C.-H., Chen, J.-H., Yang, T.-C., & Lin, C.-P. (2020). MedGlasses: A Wearable Smart-Glasses-Based Drug Pill Recognition System Using Deep Learning for Visually Impaired Chronic Patients. IEEE Access, 8, 17013-17024. DOI: 10.1109/ACCESS.2020.2967400.eng
dcterms.referencesRohith Kumar, A., Sanjay, K., & Praveen, M. (2023). EchoGuide: Empowering the Visually Impaired with IoT-Enabled Smart Stick and Audio Navigation. In Proceedings of the Second International Conference on Automation, Computing and Renewable Systems (ICACRS-2023). IEEE Xplore. DOI: 10.1109/ICACRS58579.2023.10405085.eng
dcterms.referencesChen, Pai-Hsun. (2022). Developing Low-Cost Mobile Immersive System MA- VRIOT with Physical Activity Interactions by Integrating IOT Technology. SNPD 2022, Taichung, Taiwan. IEEE Xplore. DOI: 10.1109/SNPD54884.2022.10051781.eng
dcterms.referencesZhiyuan Xu, Dejun Yang, Chengxiang Yin, Jian Tang, Yanzhi Wang, Guoliang Xue, "A Co-Scheduling Framework for DNN Models on Mobile and Edge Devices with Heterogeneous Hardware", IEEE Transactions on Mobile Computing, vol. 22, no. 3, March 2023.eng
dcterms.referencesBishtawi, T., & Alzu’bi, R. 2022. Cyber Security of Mobile Applications Using Artificial Intelligence. Arab University College of Technology (AUCT), Amman, Jordan.eng
dcterms.referencesV. D. Chukwuneke, "Introduction to Agricultural IoT," in Introduction to Agricultural Internet of Things, 1st ed., A. R. N. Rao, Ed. Elsevier, 2020, pp. 1-28.eng
dcterms.referencesY. Wu, Y. Zhou, L. Chen, Q. Xu, Q. Zeng, Z. Wang, J. Li, and D. Wu, "A Review of Integrated Routing Metrics for Wireless Sensor Networks," Sensors, vol. 22, no. 21, p. 8417, Nov. 2022.eng
dcterms.referencesS. A. Bowser, K. B. Greene, and D. A. Greene, "The Effect of Guided Imagery on Nursing Student Stress," Journal of Nursing Education, vol. 54, no. 3, pp. 134-139, Mar. 2016.eng
dcterms.referencesT. Wang, "Design and Application of a Comprehensive Intelligent System for the Management of Power Grid Equipment," in Proceedings of the IEEE International Conference on Smart Grid and Smart Cities (ICSGSC), Aug.2022, pp. 35eng
dcterms.referencesJ. Zhang, X. Li, and Y. Wang, "Development and Verification of a New Method for Predicting Building Energy Consumption Based on Machine Learning," in Proceedings of the IEEE Conference on Energy Internet and Energy System Integration (EI2), Dec. 2021, pp. 1-5.eng
dcterms.referencesS. J. Park, "Applications of Piezoelectric Energy Harvesters," Applied Sciences, vol. 11, no. 12, p. 5374, Jun. 2021.eng
dcterms.referencesM. K. Gupta, "Real-time Health Monitoring System using Internet of Things," Sensors, vol. 23, no. 21, p. 8753, Nov. 2023.eng
dcterms.referencesL. Wang and P. Liu, "Edge Computing Framework for Enhancing Performance of IoT Systems," in Proceedings of the IEEE International Conference on Big Data (Big Data), Dec. 2023, pp.eng
dcterms.referencesJ. Doe, "How Software and Hardware Work Together to Create Modern Devices," Journal of Modern Electronics, vol. 12, no. 4, pp. 123-134, Apr. 2024.eng
dcterms.referencesA. Smith, "SME E2.6.1: Performance Reporting," International Journal of Performance Metrics, vol. 15, no. 2, pp. 56-67, May 2024.eng
dcterms.referencesM. Brown, "Hardware Characteristics of AIoT Applications in Healthcare," Healthcare Technology Journal, vol. 10, no. 3, pp. 200-210, Jun. 2024.eng
dcterms.referencesL. Johnson, "Evaluation of AIoT in Computational Models in the Cloud and at the Edge Applied to Facemask Detection," IEEE Transactions on Cloud Computing, vol. 12, no. 1, pp. 75-85, Feb. 2024.eng
dcterms.referencesK. Davis, "AIoT and Other Technology Trends for a Smart Industry," Industrial Automation Journal, vol. 18, no. 5, pp. 90-101, Jul. 2024eng
dcterms.referencesH. Garcia, "The Latest Innovations in External Storage Devices, Multiple-Input Multiple-Output, Support Vector Machines, and Scalability: 'Can Vary According to the Complexity of the Process'," Journal of Advanced Computing Systems, vol. 19, no. 2, pp. 145-157, Nov. 2024. 36 S. Lee, "The Latest Innovations in Artificial Intelligence at the Edge and Its Role as an Enabler of Industrial Applications of AIoT," IEEE Industrial Electronics Magazine, vol. 14, no. 2, pp. 50-60, Aug. 2024.eng
dcterms.referencesS. Lee, "Artificial Intelligence at the Edge and Its Role as an Enabler of Industrial Applications of AIoT," IEEE Industrial Electronics Magazine, vol. 14, no. 2, pp. 50-60, Aug. 2024.eng
dcterms.referencesN. Thompson, "Artificial Intelligence and IoT Transforming the Marketplace," Journal of Business and Technology, vol. 21, no. 3, pp. 110-121, Sep. 2024.eng
dcterms.referencesBishtawi, T., & Alzu’bi, R. 2022. Cyber Security of Mobile Applications Using Artificial Intelligence. Arab University College of Technology (AUCT), Amman, Jordan.eng
dcterms.referencesP. Sanmartin, K. Avila, S. Valle, J. Gomez and D. Jabba, “SBR: a novel architecture of software defined network using the RPL protocol for Internet of Things,” IEEE Journals & Magazine | IEEE Xplore.eng
dcterms.referencesD. Velásquez, A. Torregrosa, and M. Morelos, “Gestión de herramientas de Cloud computing en los laboratorios de la Universidad Simón Bolívar,” 2022.eng
oaire.versioninfo:eu-repo/semantics/acceptedVersion
sb.programaIngeniería de Sistemasspa
sb.sedeSede Barranquillaspa

Archivos

Bloque original
Mostrando 1 - 2 de 2
No hay miniatura disponible
Nombre:
PDF_Artículo.pdf
Tamaño:
653.27 KB
Formato:
Adobe Portable Document Format
Cargando...
Miniatura
Nombre:
PDF_Resumen.pdf
Tamaño:
193.56 KB
Formato:
Adobe Portable Document Format
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
2.93 KB
Formato:
Item-specific license agreed upon to submission
Descripción: