Tópicos Sugeridos dentro de su búsqueda.
Tópicos Sugeridos dentro de su búsqueda.
Buscar alternativas:
data learning » meta learning (Expander búsqueda), deep learning (Expander búsqueda), a learning (Expander búsqueda)
data learning » meta learning (Expander búsqueda), deep learning (Expander búsqueda), a learning (Expander búsqueda)
1
artículo
Publicado 2018
Enlace
Enlace
Disruptive technologies and their impact on journalism and communication force us to assume challenges in learning new techniques for data and information processing. Interdisciplinary knowledge is evident in the teaching of new professional profiles. Data journalism is an example of this, so the immersion into a data culture must be preceded by awareness in the learning of news applications, algorithms or the treatment of Big Data, elements that configure new paradigms among journalists of the media on the Internet. With the revision of texts, direct observation of selected applications and case study, some conclusions are established that contain a growing demand in the knowledge of new techniques. The results show the use of technological resources and the proposal of changes in the curricula of the communication faculties.
2
artículo
Publicado 2018
Enlace
Enlace
Disruptive technologies and their impact on journalism and communication force us to assume challenges in learning new techniques for data and information processing. Interdisciplinary knowledge is evident in the teaching of new professional profiles. Data journalism is an example of this, so the immersion into a data culture must be preceded by awareness in the learning of news applications, algorithms or the treatment of Big Data, elements that configure new paradigms among journalists of the media on the Internet. With the revision of texts, direct observation of selected applications and case study, some conclusions are established that contain a growing demand in the knowledge of new techniques. The results show the use of technological resources and the proposal of changes in the curricula of the communication faculties.
3
capítulo de libro
Publicado 2019
Enlace
Enlace
This work proposes a semi-automated analysis and modeling package for Machine Learning related problems. The library goal is to reduce the steps involved in a traditional data science roadmap. To do so, Sparkmach takes advantage of Machine Learning techniques to build base models for both classification and regression problems. These models include exploratory data analysis, data preprocessing, feature engineering and modeling. The project has its basis in Pymach, a similar library that faces those steps for small and medium-sized datasets (about ten millions of rows and a few columns). Sparkmach central labor is to scale Pymach to overcome big datasets by using Apache Spark distributed computing, a distributed engine for large-scale data processing, that tackle several data science related problems in a cluster environment. Despite the software nature, Sparkmach can be of use for local ...
4
artículo
Publicado 2023
Enlace
Enlace
With the increase of the university population, the individual psychological care service by psychologists in universities has been affected. Which has caused discomfort among students to access the psychological consulting service. Therefore, this project aims to implement a data analysis system to control the psychological variables that affect university students, improving attention to them through the use of artificial intelligence (AI). We present a system that allows the visualization of data related to the mental health of the students who developed a psychological test, with which the psychologist will be able to diagnose the student's mental state and determine if he or she requires personalized attention. Finally, with this research, we achieved an improvement in the speed of attention and quality of service for the student.
5
artículo
Publicado 2023
Enlace
Enlace
Currently, type 2 diabetes mellitus is one of the world's most prevalent diseases and has claimed millions of people's lives. The present research aims to know the impact of the use of machine learning in the diagnostic process of type 2 diabetes mellitus and to offer a tool that facilitates the diagnosis of the dis-ease quickly and easily. Different machine learning models were designed and compared, being random forest was the algorithm that generated the model with the best performance (90.43% accuracy), which was integrated into a web platform, working with the PIMA dataset, which was validated by specialists from the Peruvian League for the Fight against Diabetes organization. The result was a decrease of (A) 88.28% in the information collection time, (B) 99.99% in the diagnosis time, (C) 44.42% in the diagnosis cost, and (D) 100% in the level of difficulty, concluding that the appl...
6
artículo
Publicado 2023
Enlace
Enlace
Currently, type 2 diabetes mellitus is one of the world's most prevalent diseases and has claimed millions of people's lives. The present research aims to know the impact of the use of machine learning in the diagnostic process of type 2 diabetes mellitus and to offer a tool that facilitates the diagnosis of the dis-ease quickly and easily. Different machine learning models were designed and compared, being random forest was the algorithm that generated the model with the best performance (90.43% accuracy), which was integrated into a web platform, working with the PIMA dataset, which was validated by specialists from the Peruvian League for the Fight against Diabetes organization. The result was a decrease of (A) 88.28% in the information collection time, (B) 99.99% in the diagnosis time, (C) 44.42% in the diagnosis cost, and (D) 100% in the level of difficulty, concluding that the appl...
7
artículo
Publicado 2022
Enlace
Enlace
so, machine learning techniques are being developed to improve performance and maintenance prediction. Increasing our knowledge of the relationship between humans and algorithms, Because data is so valuable, improving strategies for intelligently having to manage the now-ubiquitous content infrastructures is a necessary part of the process toward completely autonomous agents. Numerous researchers recently developed numerous computer-aided diagnostic algorithms employing various supervised learning approaches. Early identification of sickness may help to reduce the number of people who die as a result of these illnesses. Using machine learning techniques, this research creates an efficient automated illness diagnostic algorithm. We chose three key disorders in this paper: coronavirus, cardiovascular diseases, and diabetes. The data are inputted into a mobile application in the suggested m...
8
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.
9
artículo
Publicado 2024
Enlace
Enlace
Este artículo presenta un análisis bibliométrico de la producción científica sobre aprendizaje profundo y big data a nivel mundial. Usando la R paquete y la biblioshiny asociada, el estudio analizó 456 artículos de investigación publicados en Scopus entre 2003 y 2023. El estudio análisis de rendimiento aplicado, análisis de palabras clave y análisis temático. China es el país con mayor producción (536 publicaciones) seguido de India (260 publicaciones), asimismo, la mayoría de estas colaboraciones se dan desde China hasta Estados Unidos, Hong Kong, Suecia, Australia, Pakistán, Arabia Saudita y otros países. El rápido crecimiento de las palabras clave Aprendizaje profundo, big data, sistemas de aprendizaje y datos analítica; Demostró el interés de investigadores, profesionales de la industria, gobiernos, inversores y todos los demás actores clave en la necesidad. par...
10
11
artículo
Publicado 2023
Enlace
Enlace
Machine learning is a branch of artificial intelligence that uses scientific computing, mathematics and statistics through automated techniques to solve problems based on classification, regression and clustering. Social demand refers to the need for service and product of the professional training process, expressed by interest groups, aimed at contributing to national development, as established by the quality assurance policy of university higher education and national licensing and accreditation models. In this context, this paper conducts research based on job positions of IT professionals posted n web portals, designs a machine learning process with an unsupervised approach, extracts occupational profiles, designs a multidimensional model, applies k-means clustering when determining clusters of job positions by similarity, and reports the results obtained.
12
artículo
The main purpose of the research was to create an educational approach to facilitate the learning of physics in a mechanics course at the university level, supported by the use of technological resources and active and participatory didactic approaches appropriate to meet the needs and requirements of the era. current. The study was carried out at the National University of Engineering, specifically at the UNI - North headquarters, located in Estelí, using a mixed approach with a qualitative predominance within the socio-critical paradigm. The sample included a total of 90 students, 5 professors, a coordinator and a director, who were selected using a non-probabilistic and convenience sampling method. To collect data, various techniques were used, such as document analysis, literature review, observation, interviews, matrix analysis, discussion groups and surveys. Based on the findings ...
13
tesis doctoral
Publicado 2024
Enlace
Enlace
This dissertation investigates the potential improvement of volcanic eruption understanding and forecasting methods by using advanced data processing techniques to analyze large datasets at three target volcanoes (Piton de la Fournaise (PdlF) (France), Sabancaya, and Ubinas (Peru)). The central objective of this study is to search for possible empirical relationships between the pre-eruptive behavior of the accelerated increase in seismic activity using the Failure Forecast Method (FFM) and velocity variations measured by Coda Wave Interferometry (CWI), since both observations are reported to be independently associated with medium damage. The FFM is a deterministic method used to forecast volcanic eruptions using an empirical relationship of increased and accelerated evolution of an observable (e.g., volcano-seismic event rates). The event rates used with FFM in this study were generate...
14
objeto de conferencia
Language identification is an elemental task in natural language processing, where corpus-based methods reign the state-of-the-art results in multi-lingual setups. However, there is a need to extend this application to other scenarios with scarce data and multiple classes to face, analyzing which of the most well-known methods is the best fit. In this way, Peru offers a great challenge as a multi-cultural and linguistic country. Therefore, this study focuses in three steps: (1) to build from scratch a digital annotated corpus for 49 Peruvian indigenous languages and dialects, (2) to fit both standard and deep learning approaches for language identification, and (3) to statistically compare the results obtained. The standard model outperforms the deep learning one as it was expected, with 95.9% in average precision, and both corpus and model will be advantageous inputs for more complex ta...
15
artículo
Publicado 2020
Enlace
Enlace
Commonly the searching and identification of new particles, requires to reach highest efficiencies and purities as well. It demands to apply a chain of cuts that reject the background substantially. In most cases the processes to extract signal from the background is carried out by hand with some assistance of well designed and intelligent codes that save time and resources in high energy physics experiments. In this paper we present one application of the Mitchell’s criteria to extract efficiently beyond Standard Model signal events yielding an error of order of 1.22%. The usage of Machine Learning schemes appears to be advantageous when large volumes of data need to be scrutinized.
16
tesis doctoral
Publicado 2024
Enlace
Enlace
This dissertation investigates the potential improvement of volcanic eruption understanding and forecasting methods by using advanced data processing techniques to analyze large datasets at three target volcanoes (Piton de la Fournaise (PdlF) (France), Sabancaya, and Ubinas (Peru)). The central objective of this study is to search for possible empirical relationships between the pre-eruptive behavior of the accelerated increase in seismic activity using the Failure Forecast Method (FFM) and velocity variations measured by Coda Wave Interferometry (CWI), since both observations are reported to be independently associated with medium damage. The FFM is a deterministic method used to forecast volcanic eruptions using an empirical relationship of increased and accelerated evolution of an observable (e.g., volcano-seismic event rates). The event rates used with FFM in this study were generate...
17
artículo
Publicado 2011
Enlace
Enlace
Student academic performance at universities is crucial for education management systems. Many actions and decisions are made based on it, specifically the enrollment process. During enrollment, students have to decide which courses to sign up for. This research presents the rationale behind the design of a recommender system to support the enrollment process using the students’ academic performance record. To build this system, the CRISP-DM methodology was applied to data from students of the Computer Science Department at University of Lima, Perú. One of the main contributions of this work is the use of two synthetic attributes to improve the relevance of the recommendations made. The first attribute estimates the inherent difficulty of a given course. The second attribute, named potential, is a measure of the competence of a student for a given course based on the grades obtained i...
18
artículo
Publicado 2021
Enlace
Enlace
The article examines the problem of studying the individual model of psychological health of the students and employees of the Moscow International Academy (MIA). The goal is to explore the specific characteristics of personal psychological health in MIA students and employees. The implementation of the research program required the researcher to be ready and able to interact in the field of mental and psychological health of the individual, knowledge of age, individual psychological characteristics of the respondents to develop a research program, the ability to conduct psychodiagnostic work, the ability to analyze their own activities in order to optimize it, as well as to be creative. solving the assinged tasks. Authors used the methodology “Individual model of psychological health” by A.V. Kozlov. The method “Individual model of psychological health” was developed in 2014 in ...
19
artículo
Publicado 2021
Enlace
Enlace
The article examines the problem of studying the individual model of psychological health of the students and employees of the Moscow International Academy (MIA). The goal is to explore the specific characteristics of personal psychological health in MIA students and employees. The implementation of the research program required the researcher to be ready and able to interact in the field of mental and psychological health of the individual, knowledge of age, individual psychological characteristics of the respondents to develop a research program, the ability to conduct psychodiagnostic work, the ability to analyze their own activities in order to optimize it, as well as to be creative. solving the assinged tasks. Authors used the methodology “Individual model of psychological health” by A.V. Kozlov. The method “Individual model of psychological health” was developed in 2014 in ...
20
artículo
Pedagogical dialogic gatherings: giving a voice to the learning process of higher education students
Publicado 2021
Enlace
Enlace
El presente artículo analiza el impacto de las Tertulias Pedagógicas Dialógicas (TPD) como práctica educativa de éxito en un contexto universitario, favoreciendo así otras formas de aprender alejadas de las clases magistrales. Durante cuatro cursos académicos se ha analizado el desarrollo de las intervenciones de 87 estudiantes de tercer curso del grado de Educación Social. Por un lado, se diseñó un cuestionario, cuyos datos se analizaron de forma cuantitativa y, por otro lado, se llevó a cabo un análisis cualitativo de los relatos de los estudiantes en las sesiones de TPD y de entrevistas en profundidad, estableciéndose cuatro categorías de análisis. Los resultados muestran la contribución de esta práctica a la futura actividad profesional del alumnado, dotándole de instrumentos para implementarla en diferentes contextos sociales. También muestran su contribución en ...
