Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM
The objective of this titration work was to develop an early warning system to detect farrowing patterns in sows and issue an early alert to the caretakers of the pig herd indicating that the sow is close to labor using artificial intelligence techniques. such as convolutional neural networks and LS...
Đã lưu trong:
| Tác giả chính: | |
|---|---|
| Tác giả khác: | |
| Định dạng: | bachelorThesis |
| Ngôn ngữ: | spa |
| Được phát hành: |
2024
|
| Những chủ đề: | |
| Truy cập trực tuyến: | http://repositorio.espam.edu.ec/handle/42000/2424 |
| Các nhãn: |
Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!
|
Thêm thẻ | _version_ | 1856532500859322368 |
|---|---|
| author | Álava Zambrano, Karen Barbarita |
| author2 | Basurto Vidal, Willians Eduardo |
| author2_role | author |
| author_facet | Álava Zambrano, Karen Barbarita Basurto Vidal, Willians Eduardo |
| author_role | author |
| collection | Repositorio Escuela Superior Politécnica Agropecuaria de Manabí |
| dc.contributor.none.fl_str_mv | Pinargote Bravo, Víctor Joel |
| dc.creator.none.fl_str_mv | Álava Zambrano, Karen Barbarita Basurto Vidal, Willians Eduardo |
| dc.date.none.fl_str_mv | 2024-07-10T19:29:00Z 2024-07-10T19:29:00Z 2024-07 |
| dc.format.none.fl_str_mv | 64 p. application/pdf |
| dc.identifier.none.fl_str_mv | http://repositorio.espam.edu.ec/handle/42000/2424 |
| dc.language.none.fl_str_mv | spa |
| dc.publisher.none.fl_str_mv | Calceta: ESPAM MFL |
| dc.rights.none.fl_str_mv | Atribución-NoComercial-SinDerivadas 3.0 Ecuador http://creativecommons.org/licenses/by-nc-nd/3.0/ec/ info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:Repositorio Escuela Superior Politécnica Agropecuaria de Manabí instname:Escuela Superior Politécnica Agropecuaria de Manabí instacron:ESPAM |
| dc.subject.none.fl_str_mv | Redes neuronales CRISP-DM Parto porcino Patrón de comportamiento Predicción de parto |
| dc.title.none.fl_str_mv | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| dc.type.none.fl_str_mv | info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/bachelorThesis |
| description | The objective of this titration work was to develop an early warning system to detect farrowing patterns in sows and issue an early alert to the caretakers of the pig herd indicating that the sow is close to labor using artificial intelligence techniques. such as convolutional neural networks and LSTM (Long Short Term Memory) models. For the development of this work, two CRISP-DM methodologies were used, focused on planning and monitoring, which has phases such as: Understanding the problem, understanding data, data preparation, modeling, model implementation; The SABOR IBM methodology was also used, focused purely on the code development of the project in question. Finally, once the model was trained, a telegram bot was created to issue the prediction alert. After performing the respective hot test, it was confirmed that the system issues effective alerts to caregivers when the probability of birth exceeds 70%. This ensures timely intervention by the team in charge. |
| eu_rights_str_mv | openAccess |
| format | bachelorThesis |
| id | ESPAM_56b2e7d6f6c8dac2b6a063df5c96d722 |
| instacron_str | ESPAM |
| institution | ESPAM |
| instname_str | Escuela Superior Politécnica Agropecuaria de Manabí |
| language | spa |
| network_acronym_str | ESPAM |
| network_name_str | Repositorio Escuela Superior Politécnica Agropecuaria de Manabí |
| oai_identifier_str | oai:null:42000/2424 |
| publishDate | 2024 |
| publisher.none.fl_str_mv | Calceta: ESPAM MFL |
| reponame_str | Repositorio Escuela Superior Politécnica Agropecuaria de Manabí |
| repository.mail.fl_str_mv | . |
| repository.name.fl_str_mv | Repositorio Escuela Superior Politécnica Agropecuaria de Manabí - Escuela Superior Politécnica Agropecuaria de Manabí |
| repository_id_str | 0 |
| rights_invalid_str_mv | Atribución-NoComercial-SinDerivadas 3.0 Ecuador http://creativecommons.org/licenses/by-nc-nd/3.0/ec/ |
| spelling | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTMÁlava Zambrano, Karen BarbaritaBasurto Vidal, Willians EduardoRedes neuronalesCRISP-DMParto porcinoPatrón de comportamientoPredicción de partoThe objective of this titration work was to develop an early warning system to detect farrowing patterns in sows and issue an early alert to the caretakers of the pig herd indicating that the sow is close to labor using artificial intelligence techniques. such as convolutional neural networks and LSTM (Long Short Term Memory) models. For the development of this work, two CRISP-DM methodologies were used, focused on planning and monitoring, which has phases such as: Understanding the problem, understanding data, data preparation, modeling, model implementation; The SABOR IBM methodology was also used, focused purely on the code development of the project in question. Finally, once the model was trained, a telegram bot was created to issue the prediction alert. After performing the respective hot test, it was confirmed that the system issues effective alerts to caregivers when the probability of birth exceeds 70%. This ensures timely intervention by the team in charge.El presente trabajo de titulación tuvo como objetivo desarrollar un sistema de alerta temprana para detectar patrones de parto en las cerdas y emitir una alertar de forma anticipada a los cuidadores del hato porcino indicando que la cerda esta próxima a labor de parto empleando técnicas de inteligencia artificial tales como redes neuronales convolucionales y modelos LSTM (Long Short Term Memory). Para el desarrollo de este trabajo se emplearon dos metodologías CRISP-DM enfocada a la planificación y seguimiento mismo que cuenta con faces tale como: Comprensión del problema, comprensión de datos, preparación de datos, modelado, implementación del modelo; también se empleó la metodología SABOR IBM enfocada netamente al desarrollo de código del proyecto en cuestión. Finalmente, entrenado el modelo se creó un bot de Telegram para emitir la alerta de predicción, después de realizar la respectiva prueba en caliente, se confirmó que el sistema emite alertas efectivas a los cuidadores cuando la probabilidad de parto supera el 70%. Esto asegura una intervención oportuna por parte del equipo a cargo.Calceta: ESPAM MFLPinargote Bravo, Víctor Joel2024-07-10T19:29:00Z2024-07-10T19:29:00Z2024-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesis64 p.application/pdfhttp://repositorio.espam.edu.ec/handle/42000/2424spaAtribución-NoComercial-SinDerivadas 3.0 Ecuadorhttp://creativecommons.org/licenses/by-nc-nd/3.0/ec/info:eu-repo/semantics/openAccessreponame:Repositorio Escuela Superior Politécnica Agropecuaria de Manabíinstname:Escuela Superior Politécnica Agropecuaria de Manabíinstacron:ESPAM2025-12-30T06:45:56Zoai:null:42000/2424Institucionalhttps://repositorio.espam.edu.ec/Universidad públicahttp://www.espam.edu.ec/https://repositorio.espam.edu.ec/oai.Ecuador...opendoar:02025-12-30T06:45:56Repositorio Escuela Superior Politécnica Agropecuaria de Manabí - Escuela Superior Politécnica Agropecuaria de Manabífalse |
| spellingShingle | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM Álava Zambrano, Karen Barbarita Redes neuronales CRISP-DM Parto porcino Patrón de comportamiento Predicción de parto |
| status_str | publishedVersion |
| title | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| title_full | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| title_fullStr | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| title_full_unstemmed | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| title_short | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| title_sort | Sistema de alerta temprana de labor de parto en el hato porcino empleando técnicas de redes neuronales convolucionales y LSTM |
| topic | Redes neuronales CRISP-DM Parto porcino Patrón de comportamiento Predicción de parto |
| url | http://repositorio.espam.edu.ec/handle/42000/2424 |