Tópicos Sugeridos dentro de su búsqueda.
Tópicos Sugeridos dentro de su búsqueda.
Buscar alternativas:
computing machine » computing machinery (Expander búsqueda), sorting machine (Expander búsqueda), boosting machine (Expander búsqueda)
computing machine » computing machinery (Expander búsqueda), sorting machine (Expander búsqueda), boosting machine (Expander búsqueda)
1
artículo
Attention deficit hyperactivity disorder (ADHD) represents a medical condition characterized by the presence of inattention, hyperactivity, and impulsivity, which affects the academic development of students globally. In Peru, it affects a proportion of the pediatric population ranging from 2% to 12%, with a prevalence of 12.1% in South Lima, particularly in public schools. This research presents an online application with machine learning to improve the detection of ADHD in elementary school children. Several machine learning algorithms were reviewed and Random Forest was selected as the best-performing model with an accuracy of 96.08%. The model uses 27 selected variables, optimizing data collection and training. The child answers the questionnaire within the app and psychologists can access the app to visualize the results, aiding in the early detection of ADHD. The experiment involve...
2
objeto de conferencia
Publicado 2018
Enlace
Enlace
Classification green coffee beans is one of the main tasks during the quality grading process. This evaluation is normally carried out by specialist doing a visual inspection or using traditional instruments which have some limitations. This work is focused on the implementation of a computer vision system combining a hardware prototype and a software module. The hardware was made to guarantee the controlled conditions to capture the images of green coffee beans, the software is based on computer vision algorithms in order to detect defects of the coffee beans. The novelty of our proposal is the combination of algorithms to enhance the accuracy and the high number of defects detected. We applied a White Patch algorithm as an image enhancement procedure, color histograms as feature extractor and Support Vector Machine (SVM) for the classification task. It was constituted an image beans da...
3
artículo
Publicado 2023
Enlace
Enlace
Identifying and classifying text extracted from social networks, following the traditional method, is very complex. In recent years, computer science has advanced exponentially, helping significantly to identify and classify text extracted from social networks, specifically Twitter. This work aims to identify, classify and analyze tweets related to real natural disasters through tweets with the hashtag #NaturalDisasters, using Machine learning (ML) algorithms, such as Bernoulli Naive Bayes (BNB), Multinomial Naive Bayes (MNB), Logistic Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF). First, tweets related to natural disasters were identified, creating a dataset of 122k geolocated tweets for training. Secondly, the data-cleaning process was carried out by applying stemming and lemmatization techniques. Third, exploratory data analysis (EDA) was performed...
4
artículo
Publicado 2024
Enlace
Enlace
The trade of horticultural products is a crucial sector in the local economy of Lima, Peru. Microenterprises dedicated to this activity face various challenges, including demand volatility. This volatility can decrease the likelihood of generating profits and impact the stability of the business, primarily due to the challenges associated with adjusting selling prices. To address this issue, our proposal is based on implementing the XGBoost algorithm, which has the capability to handle heterogeneous data and variables of different types. This algorithm leverages historical data to provide accurate and up-to-date price recommendations for horticultural products. This, in turn, enables micro-entrepreneurs to make informed decisions when setting prices, thereby achieving expected benefits and enhancing their competitiveness. The integration of our project with microenterprises in Lima has t...
5
artículo
Publicado 2024
Enlace
Enlace
The persistent issue of student dropout negatively impacts the educational sector and society at large. This study presents a machine learning model that leverages data from the National Household Survey to predict student dropout in Peru, integrating a wide range of socio-demographic variables. The research fills a gap in existing literature by providing a model that incorporates socio-demographic variables, an area not fully explored in previous studies. The predictive model aims to identify factors associated with student dropout, aiding educational stakeholders in implementing effective interventions. The findings underscore the model's potential to enhance educational outcomes by enabling early identification of at-risk students, thereby facilitating targeted support. This work contributes to refining predictive models of university dropout rates and sug- gests the use of ensemble m...
6
artículo
Publicado 2024
Enlace
Enlace
Dry forests are ecosystems of great importance worldwide, but in recent decades they have been affected by climate change and changes in land use. In this study, we evaluated land use and land cover changes (LULC) in dry forests in Peru between 2017 and 2021 using Sentinel-2 images, and cloud processing with Machine Learning (ML) models. The results reported a mapping with accuracies above 85% with an increase in bare soil, urban areas and open dry forest, and reduction in the area of crops and dense dry forest. Protected natural areas lost 2.47% of their conserved surface area and the areas with the greatest degree of land use impact are located in the center and north of the study area. The study provides information that can help in the management of dry forests in northern Peru.
7
tesis de grado
Publicado 2024
Enlace
Enlace
Machine learning is becoming increasingly important and pervasive in people's lives, yet when its conclusions reflect biases that support ingrained prejudices in society, many vulnerable groups' psychological wellbeing may be impacted. To investigate if gender biases exist in image search engine algorithms that use machine learning, the study focuses on occupations. To do this, searches for various professions were run on Google, DuckDuckGo, and Yandex. Using web scraping techniques, a sample of images was retrieved for each selected profession and search engine. The images were then manually classified by gender, and statistical indicators and analyses were computed to detect potential biases in the representation of each gender. This analysis included a comparison between search engines, the calculation of mean, standard deviation, and coefficient of variation, a confidence interval an...
8
tesis de grado
Publicado 2023
Enlace
Enlace
Market basket analysis provides an insight into customer consumption patterns and trends in the industry. These will be achieved by analyzing and studying the performance of the large datasets of transactions made by consumers held in retail stores. These commercial transactions will be analyzed using the Machine Learning technique called the A priori algorithm by establishing association rules and determining those groups of items in a market basket whose association could represent better economic benefits for companies. This study will analyze the historical sales data of the product groups, in order to identify relationships that al-low companies in the sector to generate patterns to propose the increase of their portfolio based on the products with the greatest purchasing trends. At the end of this investigation, commercial strategies will be proposed to improve sales, take advantag...
9
artículo
Publicado 2024
Enlace
Enlace
Making raw material purchase forecasts for companies is very difficult and, if inadequately controlled, can affect the company's decision making and profitability. Currently, there are optimized systems or mathematical models to try to predict the demands and solve this problem. In this study, a raw material purchase prediction model is proposed that uses the Elastic Net algorithm to analyze historical sales and inventory data. The model is used to improve prediction accuracy, allowing SMEs to optimize inventories, reduce costs and improve efficiency. Experimental results indicate that the proposed model obtains better results in the MAE, RMSE and R2 indicators.
10
artículo
Publicado 2024
Enlace
Enlace
In the context of IT incident management, the prioritization and automation of tickets can be a challenge for companies that lack advanced technologies. However, these difficulties can be overcome today by applying machine learning algorithms and techniques that use historical data to train predictive models, which allows for more efficient and effective IT incident management. The article proposes the implementation of a predictive model that uses machine learning to prioritize IT incidents in these companies. The goal of this proposal is to allow small and medium-sized enterprises to prioritize their incidents automatically, using a model that has been previously trained with a supervised multi-label classification algorithm technique to achieve high accuracy. Experimental results show that the Mean Absolute Error (MAE) is 2.79 and a Mean Squared Error (MSE) of 8.21, using the metrics ...
11
artículo
Publicado 2024
Enlace
Enlace
Smartphone addiction has emerged as a growing concern in society, particularly among teenagers, due to its potential negative impact on physical, emotional social well-being. The excessive use of smartphones has consistently shown associations with negative outcomes, highlighting a strong dependence on these devices, which often leads to detrimental effects on mental health, including heightened levels of anxiety, distress, stress depression. This psychological burden can further result in the neglect of daily activities as individuals become increasingly engrossed in seeking pleasure through their smartphones. The aim of this study is to develop a predictive model utilizing machine learning techniques to identify smartphone addiction based on the "Big Five Personality Traits (BFPT)". The model was developed by following five out of the six phases of the "Cross Industry Standard Process ...
12
objeto de conferencia
Publicado 2017
Enlace
Enlace
In this paper, we present the first attempts to develop a machine translation (MT) system between Spanish and Shipibo-konibo (es-shp).
13
objeto de conferencia
Publicado 2019
Enlace
Enlace
WordNet-like resources are lexical databases with highly relevance information and data which could be exploited in more complex computational linguistics research and applications. The building process requires manual and automatic tasks, that could be more arduous if the language is a minority one with fewer digital resources. This study focuses in the construction of an initial WordNetdatabase for a low-resourced and indigenous language in Peru: Shipibo-Konibo (shp). First, the stages of development from a scarce scenario (a bilingual dictionary shp-es) are described. Then, it is proposed a synset alignment method by comparing the definition glosses in the dictionary (written in Spanish) with the content of a Spanish WordNet. In this sense, word2vec similarity was the chosen metric for the proximity measure. Finally, an evaluation process is performed for the synsets, using a manually...
14
tesis de grado
Publicado 2025
Enlace
Enlace
El envejecimiento poblacional es un desafío permanente para la sociedad en las áreas económica, social y sanitaria. La expansión demográfica del grupo adulto mayor implicará un incremento progresivo en la demanda de servicios. Por otro lado, el deterioro progresivo de la salud asociado al envejecimiento, que se manifiesta en dolores y caídas frecuentes, constituye un problema de salud pública, pues ocasiona inmovilidad y afecta de manera significativa la calidad de vida. En este contexto, el presente trabajo expone el desarrollo de un sistema autónomo de detección basado en visión por computador y redes neuronales, orientado a identificar dolor y caídas en tiempo real por medio de la clasificación de la postura corporal. El monitoreo constante, la detección temprana y el aviso de una posible emergencia permitirá una pronta atención y mejorará la recuperación. La metodol...
15
tesis de grado
Publicado 2025
Enlace
Enlace
Every year, 750,000 tonnes of waste coffee brushwood are dumped in the jungle of the Junín region of Peru. The purpose of this study is to promote a circular economy and mitigate the environmental impact. This article focused on the design of a crushing machine adapted to the needs of local small farmers in the central jungle. The design process was based on the VDI 2221 (Guidelines of the German Association of Engineers 2221) methodology, focused on finding effective solutions to facilitate the generation of organic compost. Detailed calculations of the key elements of the machine were carried out, complemented with CAD (Computer Aided Design) simulations such as SolidWorks and Altair EDEM, to evaluate stress resistance and the pressure required to crush the coffee brush. In addition, field studies were conducted to gather data on the essential requirements that influenced the design. ...
16
objeto de conferencia
Publicado 2021
Enlace
Enlace
Cardiovascular diseases and Coronary Artery Disease (CAD) are the leading causes of mortality among people of different ages and conditions. The use of different and not so invasive biomarkers to detect these types of diseases joined with Machine Learning techniques seems promising for early detection of these illnesses. In the present work, we have used the Sani Z-Alizadeh dataset, which comprises a set of different medical features extracted with not invasive methods and used with different machine learning models. The comparisons performed showed that the best results were using a complete set and a subset of features as input for the Random Forest and XGBoost algorithms. Considering the results obtained, we believe that using a complete set of features gives insights that the features should also be analyzed by considering the medical advances and findings of how these markers influe...
17
artículo
El pensamiento computacional es un conjunto de conocimientos en las áreas STEM introducido en los programas educativos para preparar a los estudiantes en la comprensión y el uso de los medios y las herramientas digitales. Sin embargo, no se ha tomado en cuenta que los medios digitales influyen no solo en el desarrollo del conocimiento, sino también en la economía, la cultura, la comunicación y las rela-ciones sociales. El objetivo es revisar y superar algunas limitaciones del paradigma del pensamiento computacional para aprovechar todo su potencial. Queremos de-mostrar, mediante la literatura científica y el trabajo de campo, que el pensamiento computacional rescate las humanidades, las manualidades y las tradiciones cultura-les locales. Para esto se estudiarán: a) la crítica a los fundamentos neopositivistas del tecnocentrismo; b) la naturaleza del medio digital, con énfasis en...
18
tesis de grado
Publicado 2022
Enlace
Enlace
La clasificación de objetos es uno de los campos de estudios más importantes de los últimos años y está asociado a la similitud de características entre los objetos y al continuo crecimiento de los conjuntos de datos de entrenamiento. En base a ello, aumentar el número de muestras de entrenamiento mejora el rendimiento de los clasificadores. Sin embargo, no hay estudios que determinen un estimado de cuántas muestras de entrenamiento son necesarias para generar clasificadores robustos. En esta investigación se intenta responder esta pregunta, enfocando el problema en la clasificación por marca y modelo vehicular. Para ello, se creó un conjunto de datos compuesto por 32 modelos vehiculares diferentes y se utilizó la red VGG16 para la tarea de extracción de características. Asimismo, se utilizaron los algoritmos de clasificación Máquinas de Vector Soporte (SVM), Bosques Alea...
19
objeto de conferencia
Publicado 2019
Enlace
Enlace
Linguistic corpus annotation is one of the most important phases for solving Natural Language Processing (NLP) tasks, as these methods are deeply involved with corpus-based techniques. However, meta-data annotation is a highly laborious manual task. A supportive alternative requires the use of computational tools. They are likely to simplify some of these operations, while can be adjusted appropriately to the needs of particular language features at the same time. Therefore, this paper presents ChAnot, a web-based annotation tool developed for Peruvian indigenous and highly agglutinative languages, where Shipibo-Konibo was the case study. This new tool is able to support a diverse set of linguistic annotation tasks, such as word segmentation, POS-tag markup, among others. Also, it includes a suggestion engine based on historic and machine learning models, and a set of statistics about pr...
20
artículo
Publicado 2024
Enlace
Enlace
The application of computer technologies associated with sensors and artificial intelligence (AI) in the quantification and qualification of quality parameters of meat products of various domestic species is an area of research, development, and innovation of great relevance in the agri-food industry. This review covers the most recent advances in this area, highlighting the importance of computer vision, artificial intelligence, and ultrasonography in evaluating quality and efficiency in meat products’ production and monitoring processes. Various techniques and methodologies used to evaluate quality parameters such as colour, water holding capacity (WHC), pH, moisture, texture, and intramuscular fat, among others related to animal origin, breed and handling, are discussed. In addition, the benefits and practical applications of the technology in the meat industry are examined, such as...
