Tópicos Sugeridos dentro de su búsqueda.
Tópicos Sugeridos dentro de su búsqueda.
Buscar alternativas:
machine transformation » machine translation (Expander búsqueda), imaging transformation (Expander búsqueda), planning transformation (Expander búsqueda)
machine transformation » machine translation (Expander búsqueda), imaging transformation (Expander búsqueda), planning transformation (Expander búsqueda)
1
artículo
Publicado 2021
Enlace
Enlace
This study aimed to identify the causes of significant problems existing in the metallurgical sector, and a solution is proposed for the setup process. We detail the theoretical background of the processes in the lean manufacturing methodology, which will be applied to a rolling machine. Further, we provide a brief description of the company and the sector’s problems. We describe success stories of companies that implemented various lean manufacturing tools. We also present some of the results achieved across sectors to gain an in-depth understanding of the technique and a practical support of the implemented model. Our proposal is based on the lean manufacturing methodology; tools such as Single Minute Exchanges of Dies, Kaizen, 5S, and value stream mapping (VSM) will be used to reduce setup times and to impact machine layout and productivity positively. We also show the implementatio...
2
artículo
The need to develop a BCI brain- computer interface system for the control of a robotic arm in Peru arises from the possibility of interconnecting the human nervous system with a robotic or mechatronic system, and using this concept to recover some motor function. Brain Computer Interface (BCI) is a communication system based on the recording of brain signals (EEG). The electroencephalogram is the basis and support of the BCI technology. It is a novel technology that allows human-machine interaction in a virtual or physical environment, through a communication channel between the central nervous system and a robotic device. In recent years, the aforementioned systems have caused the interest of important research centers worldwide.
3
tesis de grado
Publicado 2022
Enlace
Enlace
In the present investigation of the design of a processing machine for hybrid compounds based on coconut and maguey fibers, using the non-experimental quantitative method, under the German VDI 2221 and 2225 methodology, using mathematical models of machine elements and mechanical design and selection. of electronic components, where the main objective was the design of the hybrid compound processing machine, which consists of four processes: material transport, crushing process, mixing and compacting process, to obtain boards agglomerated, with the purpose of reusing usable solid waste and transforming it into fibers, in order to avoid the use of wood and to reduce the logging that occurs in the central jungle of Peru, for which it is essential to know the mechanical characteristics of coconut and maguey fiber, coconut fiber has a tensile strength of 220 Mpa and fiber Maguey has a tensil...
4
artículo
Publicado 2021
Enlace
Enlace
For social robots, knowledge regarding human emotional states is an essential part of adapting their behavior or associating emotions to other entities. Robots gather the information from which emotion detection is processed via different media, such as text, speech, images, or videos. The multimedia content is then properly processed to recognize emotions/sentiments, for example, by analyzing faces and postures in images/videos based on machine learning techniques or by converting speech into text to perform emotion detection with natural language processing (NLP) techniques. Keeping this information in semantic repositories offers a wide range of possibilities for implementing smart applications. We propose a framework to allow social robots to detect emotions and to store this information in a semantic repository, based on EMONTO (an EMotion ONTOlogy), and in the first figure or table...
5
artículo
Publicado 2022
Enlace
Enlace
Transformer models have evolved natural language processing tasks in machine learning and set a new standard for the state of the art. Thanks to the self-attention component, these models have achieved significant improvements in text generation tasks (such as extractive and abstractive text summarization). However, research works involving text summarization and the legal domain are still in their infancy, and as such, benchmarks and a comparative analysis of these state of the art models is important for the future of text summarization of this highly specialized task. In order to contribute to these research works, the researchers propose a comparative analysis of different, fine-tuned Transformer models and datasets in order to provide a better understanding of the task at hand and the challenges ahead. The results show that Transformer models have improved upon the text summarizatio...
6
artículo
This paper reviews the most recent literature on experiments with different Machine Learning, Deep Learning and Natural Language Processing techniques applied to predict judicial and administrative decisions. Among the most outstanding findings, we have that the most used data mining techniques are Support Vector Machine (SVM), K Nearest Neighbours (K-NN) and Random Forest (RF), and in terms of the most used deep learning techniques, we found Long-Term Memory (LSTM) and transformers such as BERT. An important finding in the papers reviewed was that the use of machine learning techniques has prevailed over those of deep learning. Regarding the place of origin of the research carried out, we found that 64% of the works belong to studies carried out in English-speaking countries, 8% in Portuguese and 28% in other languages (such as German, Chinese, Turkish, Spanish, etc.). Very few works of...
7
tesis de grado
Publicado 2025
Enlace
Enlace
Abstract — Automated composting has proven to be a vital solution for the transformation of organic waste into high - quality compost, soil enrichment, and improved agricultural production. This innovation responds to the need to manage urban waste efficiently and mitigate emissions of polluting gases. The implementation of the VDI 2222 Methodology ensures a structured design in key stages, from preparation to compost collection, maximizing its efficiency and quality. The use of black box simulation modeling, backed by probability distributions and precise technology, is an advanced approach to improving the process. The combination of PID controllers and IoT technologies in the control system enables real - time monitoring and adjustment of temperature and humidity, optimizing the process and reducing the environmental footprint. In addition to improving soil quality and food producti...
8
objeto de conferencia
Today's business landscape is characterized by competition and dynamism, which has transformed human resource management into an essential strategic partner for organizations. Employee turnover poses risks that affect productivity and knowledge management. This study focuses on predicting employee turnover using machine learning (ML) models. For the training process, a dataset composed of 4410 records and 29 variables was used, in the process of training and evaluation of the ten models, the artificial intelligence (AI) method was followed. The findings showed that the XG Boost Classifier (XGBC) and Random Forest (RF) models achieved the best accuracy and performance rates, with 98.8% and 98.7%. Followed by Decision Tree Classifier (DT) with 97.6%, and the other models, such as Gradient Boosting Classifier (GBC), Ada boost Classifier (AC), Logistic Regression (LR), KN Classifier (K-NNC),...
9
tesis doctoral
Publicado 2022
Enlace
Enlace
Descargue el texto completo en el repositorio de tesis doctorales TDX: http://hdl.handle.net/10803/674150
10
objeto de conferencia
Publicado 2023
Enlace
Enlace
The recent growing needs in the global food industry have been demanding an agile and resilient response to continue manufacturing products with the expected quality and food safety. A key element for this is the agility of the quality management of the supply chain, which has been achieved from using a correct quality management data digitization as well as its processing through business analytics and whose results are presented in this business case. A prerequisite to be met was the global standardization of supplier performance evaluation criteria, whose efforts were achieved through the coordination of quality management professionals from France, Italy, the United States, Mexico, Brazil and Chile. With the standardized performance evaluation criteria, the calculation mechanisms were defined, which were later developed by the IT teams through Business Analytics solutions and represe...
11
tesis de maestría
Publicado 2025
Enlace
Enlace
En una era dominada por la innovación tecnológica, los avances en el Machine Learning (ML) y Natural Language Processing (NLP) han transformado diversas industrias, incluyendo el ámbito de las patentes. Las patentes protegen invenciones y requieren que estas sean novedosas, un aspecto que implica un análisis detallado de grandes volúmenes de texto en un tiempo limitado. Este proyecto de tesis se centra en desarrollar un prototipo de apoyo para el análisis de novedad en patentes mediante la fusión de técnicas de procesamiento de texto como Embeddings, Transformers y algoritmos clásicos de machine learning. La metodología incluye la adquisición y el preprocesamiento de datos, la extracción de características mediante técnicas como Word2Vec, FastText y Transformers, y la experimentación con diversos modelos de ML y DL. Se implementaron técnicas de visualización de datos par...
12
artículo
Publicado 2024
Enlace
Enlace
This study presents Datalyzer, a system designed for data extraction, visualization, and prediction in the mining sector using advanced NLP and machine learning, specifically GPT-3.S Turbo. The system enhances operational efficiency through rigorous data preprocessing and specialized fine-tuning, validated on a simulated mining dataset. Results show significant improvements: data extraction time reduced by 94 % and visualization time by 97.6%. These improvements indicate a transformation in efficiency, usability, and user satisfaction. Despite limitations in data variability and complexity, this pioneering approach highlights the potential of NLP and machine learning in modernizing the mining industry and supporting data-driven decision-making.
13
tesis de maestría
Publicado 2025
Enlace
Enlace
El presente estudio, buscó diseñar un Modelo de Transformación Digital, incorporando Machine Learning para mejorar la Satisfacción de Clientes del sector PYME, se trata de una investigación no experimental, que permite el diseño de un modelo de transformación digital basado en metodologías existentes y que ayuden a tener procesos más eficientes, y tener clientes más satisfechos. Para esta investigación se estudiaron metodologías y buenas prácticas de modelo de transformación digital como son: metodología Agile Digital Transformation (ADT), metodología ADKAR y la Digital Transformation Framework. El resultado obtenido fue el diseño de un modelo nuevo, el cual fue validado con la aplicación de un caso de estudio en una PYME. Posterior al análisis estadístico respectivo se obtuvo una mejora significativa del 32.13% en la satisfacción con la propuesta respectiva
14
tesis de grado
Publicado 2024
Enlace
Enlace
El presente trabajo de investigación se realizó en la Molinería El Agricultor SAC, ubicado en la ciudad de Jaén, departamento de Cajamarca. Donde se pudo analizar el proceso productivo de pilado de arroz, con el objetivo principal de aumentar la eficiencia; misma que se considera baja, por no alcanzar el porcentaje nacional mínimo establecido, el cual debe tener un valor de 69%. Para ello, se procedió a realizar un diagnóstico acerca de la situación actual de la empresa, para lograr identificar las principales causas del problema, haciendo uso de herramientas de ingeniería como los son los diagramas de análisis de procesos DAP, DOP, Ishikawa y Pareto Como resultado, se evidenció las actividades con más frecuencia que limitaban la eficiencia del proceso, mismas que están relacionadas a la escasa capacitación al personal; en segunda instancia existen problemas con el secado a...
15
tesis de grado
Publicado 2024
Enlace
Enlace
Each country's metalworking industry has much economic development, providing companies with jobs and new products. However, companies have different problems in improving various aspects such as production, quality, and delivery times, among others. Therefore, to solve these problems, this article proposes a model based on implementing the Lean philosophy using different tools such as 5S, TPM, SLP, and SMED to increase the overall equipment efficiency (OEE). In addition, work was done on the mindset of workers to sensitize them through the ADKAR Model. A pilot test was carried out to validate the improvements, which gave us good results in the qualification of the audits carried out. In addition, a simulation was carried out in which the Arena software was implemented, and the result was an improvement in the OEE index of 17.60%, a reduction of 44.59 meters in operator movements, and an...
16
objeto de conferencia
Publicado 2023
Enlace
Enlace
Each country's metalworking industry has much economic development, providing companies with jobs and new products. However, companies have different problems in improving various aspects such as production, quality, and delivery times, among others. Therefore, to solve these problems, this article proposes a model based on implementing the Lean philosophy using different tools such as 5S, TPM, SLP, and SMED to increase the overall equipment efficiency (OEE). In addition, work was done on the mindset of workers to sensitize them through the ADKAR Model. A pilot test was carried out to validate the improvements, which gave us good results in the qualification of the audits carried out. In addition, a simulation was carried out in which the Arena software was implemented, and the result was an improvement in the OEE index of 17.60%, a reduction of 44.59 meters in operator movements, and an...
17
artículo
Publicado 2025
Enlace
Enlace
The COVID-19 pandemic accelerated the adoption of virtual and hybrid teaching methods, leading to substantial changes in educational approaches. This study focused on evaluating the effect of mediating technologies on post-pandemic educational processes, emphasizing their essential role in enhancing interaction and cooperation between teachers and students. Although their relevance is evident, challenges persist in terms of access, quality, and evaluation of technological educational initiatives. To address these challenges, a comprehensive literature review was conducted, examining 26 international academic studies published in the last five years. The findings indicate that mediating technologies positively influence motivation, student retention, and self-directed learning, especially in higher education and language teaching. However, the effects vary depending on the context. It is ...
18
tesis de grado
Publicado 2024
Enlace
Enlace
A nivel mundial el phishing en los últimos años se ha incrementado y el Perú no fue una excepción. Debido a la pandemia del Covid-19 se registró un aumento considerable de este tipo de ciberataques llamado phishing; entre los motivos de su crecimiento se encuentra la cuarentena. Este tipo de ataques suele afectar de manera negativa a los usuarios de internet y mucho más a las empresas, siendo uno de los ataques más frecuentes el phishing. Por ejemplo, en las noticias como en redes sociales se puede observar cómo los bancos o plataformas de pago advierten a sus usuarios sobre estos ataques para que estén atentos, al igual que se puede observar el malestar de los usuarios cuando publican o comentan en las redes sociales que han sido víctima de dichos ataques. Por este motivo, este trabajo busca identificar de manera correcta las opiniones de las personas acerca de publicaciones h...
19
tesis de grado
Publicado 2023
Enlace
Enlace
Durante los últimos años, la tecnología, la inteligencia de negocios, la ciencia de datos y los lenguajes de procesamiento han adquirido un protagonismo creciente en las empresas. Asimismo, desde mucho antes, con la llegada de la transformación digital en las empresas, estas se han visto obligadas a procesar cantidades cada vez mayores de datos, lo que ha generado la necesidad de minar, procesar y transformar los datos de manera eficaz y eficiente. A través del data storytelling, las empresas pueden crear nuevas estrategias respaldadas por su propia información. Los desafíos a los que se enfrentan muchas empresas están relacionados con su capacidad para predecir las ventas. Buscan que esta predicción sea dinámica y con un margen de error aceptable, ya que ello puede desencadenar inversiones, niveles de empleo, estrategias de publicidad, mano de obra, comunicación con los clien...
20
tesis de grado
Publicado 2025
Enlace
Enlace
En el sector de telecomunicaciones, la retención de clientes es un desafío clave debido a la alta competencia y la portabilidad numérica, que permite a los usuarios cambiar de operador con facilidad. En esta empresa se telecomunicaciones, ofrecer promociones personalizadas es fundamental, pero la gestión dispersa y manual puede generar errores, afectando la efectividad de las estrategias de fidelización. Se implementó un algoritmo de Machine Learning (ML) en Python conectado vía una Interfaz de Programación de Aplicaciones (API) para predecir la efectividad de promociones, optimizando decisiones y reduciendo errores. El sistema se integra con Power BI mediante el Lenguaje de Expresiones de Análisis de Datos (DAX) y el Lenguaje M para el modelado, procesos de Extracción, Transformación y Carga (ETL), creación de Indicadores Clave de Desempeño (KPI) e informes dinámicos, comp...
