Now showing items 1-20 of 31

Analysis of the integration of drift detection methods in learning algorithms for electrical consumption forecasting in smart buildings

Mariano-Hernández, Deyslen; Hernández Callejo, Luis; Solís, Martín; Zorita Lamadrid, Angel Luis; Duque-Perez, Oscar; Gonzalez Morales, Luis Gerardo; Santos Garcia, Felix; Jaramillo Duque, Álvaro; Ospino C., Adalberto; Alonso Gómez, Víctor; Bello, Hugo J. (MDPI AGSwitzerland, 2022-05-12)

Buildings are currently among the largest consumers of electrical energy with considerable increases in CO2 emissions in recent years. Although there have been notable advances in energy efficiency, buildings still have ...
Aplicación de técnicas de machine Learning para la detección de fugas en una tubería horizontal que transporta una mezcla de agua y glicerol

Gámez De León, Adalberto (Corporación Universidad de la CostaIngeniería Electrónica, 2021)

During the last decades, the problem of detecting leaks in pipes with the help of software has been much discussed. Timely leak detection prevents water loss and helps prevent economic and environmental catastrophes. It ...
Classification, identification, and analysis of events on twitter through data mining

Silva, Jesús; Higa, Yuki; Cera Visbal, Juan Manuel; Cabrera, Danelys; Senior Naveda, Alexa; Flores, Yasmin; Pineda Lezama, Omar Bonerge (Corporación Universidad de la Costa, 2021)

Due to its popularity, Twitter is currently one of the major players in the global network, which has established a new form of communication: the microblogging. Twitter has become an essential media network for the ...
Comparison of bioinspired algorithms applied to cancer database

Silva, Jesús; Villareal-González, Reynaldo; Varela, Noel; Maco, José; Villón, Martín; Marín–González, Freddy; Pineda Lezama, Omar Bonerge (Corporación Universidad de la Costa, 2021)

Cancer is not just a disease; it is a set of diseases. Breast cancer is the second most common cancer worldwide after lung cancer, and it represents the most frequent cause of cancer death in women (Thurtle et al. in: PLoS ...
Compilation of a social network lexicon for determining the profile of authors

Viloria, Amelec; Parra Negrete, Kevin; Conde, Marcial; Pineda Lezama, Omar Bonerge (Corporación Universidad de la Costa, 2020-11-05)

The use of social networks is steadily increasing worldwide. Hundreds of users daily register in the different existing platforms, therefore, the content extracted from the social networks is fundamental for tasks such as ...
Conceptualización del diagnóstico del Dengue desde una perspectiva de la ingeniería y las nuevas tecnologías

ARRUBLA HOYOS, WILSON DE JESÚS (Corporación Universidad de la CostaBarranquilla, 2022)

Introducción— El dengue es una enfermedad tropical transmitida por mosquito que según reportes de la Organización Mundial de la Salud-OMS deja unos 390 millones de personas infectadas cada año, es una de las enfermedades ...
Critical rare earth metal adsorption onto expanded vermiculite: accurate modeling through response surface methodology and machine learning techniques

de Vargas Brião, Giani; Pfingsten Franco, Dison Stracke; Vasconcelos da Silva, Flávio; Carlos da Silva, Meuris Gurgel; Gurgel Adeodato Vieira, Melissa (Elsevier BVNetherlands, 2023)

The circular economy of rare earth metals (REM), such as dysprosium, is essential for a sustainable future in clean energy and high-tech fields. Adsorption has gained attention to recover and reintegrate REM into the ...
Design of a network with VANET sporadic cloud computing applied to traffic accident prevention

amelec, viloria; Pineda, Omar; Varela Izquierdo, Noel; Diaz Martínez, Jorge Luis (Corporación Universidad de la CostaRetracted, 2020-07-19)

The study analyzes the bandwidth available in a segment of route in the VANET network, since this value directly affects sporadic cloud computing. For this purpose, the bandwidth was tested on a highly complex urban scenario, ...
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition

Jiménez-Gómez, Geovanna; Navarro-Escorcia, Daniela; Neira Rodado, Dionicio; Cleland, Ian (Springer International Publishing, 2021-09-17)

The impact that neurodegenerative diseases have in our society, have made human activity recognition (HAR) arise as a relevant field of study. The quality of life of people with such conditions, can be significantly improved ...
Development of machine learning methods in hybrid energy storage systems in electric vehicles

Tzu-Chia, Chen; Alazzawi, Fouad Jameel Ibrahim; Grimaldo Guerrero, John William; Chetthamrongchai, Paitoon; Dorofeev, Aleksei; Aras masood, Ismael; Ahmed, Dr. Alim Al Ayub; Akhmadeev, Ravil; Latipah, Asslia Johar; Abu Al-Rejal, Hussein (Hindawi Publishing CorporationUnited States, 2022)

The hybrid energy storage systems are a practical tool to solve the issues in single energy storage systems in terms of specific power supply and high specific energy. These systems are especially applicable in electric ...
Diabetes diagnostic prediction using vector support machines

amelec, viloria; Herazo-Beltrán, Yaneth; Cabrera, Danelys; Bonerge Pineda, Omar (Procedia Computer Science, 2020)

The most important factors for the diagnosis of diabetes mellitus (DM) are age, body mass index (BMI) and blood glucose concentration. Diagnosis of DM by a doctor is complicated, because several factors are involved in the ...
Electrical consumption patterns through machine learning

amelec, viloria; Senior Naveda, Alexa; Hernández Palma, Hugo; Niebles Núñez, William; Niebles Nuñez, Leonardo David (Journal of Physics: Conference Series, 2020)

Electricity distribution companies have been incorporating new technologies that allow them to obtain complete information in real time about their customers´ consumption. Thus, a new concept called "Smart Metering" has ...
Engineering of novel fe-based bulk metallic glasses using a machine learning-based approach

Tzu-Chia, Chen; Rajiman, Rajiman; Elveny, Marischa; Grimaldo Guerrero, John William; Lawal, Adedoyin Isola; Acwin Dwijendra, Ngakan Ketut; aravindhan, surendar; Danshina, Svetlana; ZHU, Yu (Arabian Journal for Science and Engineering, 2021-07-07)

A broad range of potential chemical compositions makes difficult design of novel bulk metallic glasses (BMGs) without performing expensive experimentations. To overcome this problem, it is very important to establish ...
Herramientas BIM para el análisis de requisitos de la norma de rendimiento para edificaciones en Brasil

Lima da Silva, Juliano; Quadrado Mussi, Andréa; Zardo, Paola; Silva , Luisa (Corporación Universidad de la Costa, 2020-10-01)

En esta conferencia la profesora Andrea Mussi (PhD) junto con algunos integrantes del grupo de Núcleo de Innovación y Tecnología en Arquitectura y Urbanismo, NITAU del IMED, nos expondrán los resultados de su investigación ...
Identificación de aminoácidos de cadena ramificada en proteína de quinua mediante modelo de regresión lineal con aprendizaje de máquinas

Caicedo, Nicolas; Caicedo, Juan M.; Oñate-Garzón, José (Corporación Universidad de la CostaColombia, 2022-07-07)

La quinua, se clasifica como pseudocereal y contiene componentes bioactivos, tales como proteínas con un alto valor nutricional. El consumo de proteína y especialmente aminoácidos esenciales de cadena ramificada juegan un ...
Intellectual property in colombian museums: an application of machine learning

Lis-Gutiérrez, Jenny-Paola; Zerda Sarmiento, Alvaro; amelec, viloria (Universidad de la Costa, 2019)

The purpose of this research is to answer the following guiding question: how can the behavior of museum networks in Colombia be predicted with respect to the protection of intellectual property (copyright, confidential ...
Machine learning applied to the h index of colombian authors with publications in scopus

amelec, viloria; Lis-Gutiérrez, Jenny-Paola; Gaitán-Angulo, Mercedes; Vásquez Stanescu, Carmen Luisa; Crissien Borrero, Tito José (Universidad de la Costa, 2019)

Our research aims to establish how to predict the H index of Colombian authors with publications in Scopus until 2016. The selection of the date was because, as mentioned earlier, the number of documents indexed per year ...
Machine learning approach applied to human activity recognition – an application to the VanKasteren dataset

Ariza Colpas, Paola Patricia; Oñate-Bowen, Alvaro Agustín; Suarez-Brieva, Eydy del Carmen; Oviedo Carrascal, Ana Isabel; Urina Triana, Miguel; Piñeres Melo, Marlon Alberto; Butt Shariq, Aziz; COLLAZOS MORALES, CARLOS ANDRES; Ramayo González, Ramón Enrique (Corporación Universidad de la Costa, 2021)

Reminders are a core component of many assistive technology systems and are aimed specifically at helping people with dementia function more independently by compensating for cognitive deficits. These technologies are often ...
A machine learning solution for bed occupancy issue for smart healthcare sector

Gochhait, Dr Saikat; De-La-Hoz-Franco, Emiro; Shaheen, Qaisar; Diaz Martinez, Jorge Luis; Piñeres Espitia, Gabriel Dario; MERCADO POLO, DARWIN (Pleiades PublishingUnited States, 2021)

The health care domain is a culmination and emergence of many other economic sectors that give different services from patient treatment to healing, protective, rehabilitation, and palliative care. The GDP consumes to ...
Management system for optimizing public transport networks: GPS record

Silva, Jesús; GUERRA ALEMAN, ERICK; Varela Izquierdo, Noel; Pineda, Omar (Corporación Universidad de la CostaRetracted, 2020-07-19)

As cities continue to grow in size and population, the design of public transport networks becomes complicated, given the wide diversity in the origins and destinations of users [1], as well as the saturation of vehicle ...

Envíos recientes

Analysis of the integration of drift detection methods in learning algorithms for electrical consumption forecasting in smart buildings
...
Mariano-Hernández, Deyslen | 2022-05-12

Buildings are currently among the largest consumers of electrical energy with considerable increases in CO2 emissions in recent years. Although there have been notable advances in energy efficiency, buildings still have great untapped savings potential. Within demand-side management, some tools have helped improve electricity consumption, such as energy forecast models. However, because most forecasting models are not focused on updating based on the changing nature of buildings, they do not help exploit the savings potential of buildings. Considering the aforementioned, the objective of this article is to analyze the integration of methods that can help forecasting models to better adapt to the changes that occur in the behavior of buildings, ensuring that these can be used as tools to enhance savings in buildings. For this study, active and passive change detection methods were considered to be integrators in the decision tree and deep learning models. The results show that constant retraining for the decision tree models, integrating change detection methods, helped them to better adapt to changes in the whole building’s electrical consumption. However, for deep learning models, this was not the case, as constant retraining with small volumes of data only worsened their performance. These results may lead to the option of using tree decision models in buildings where electricity consumption is constantly changing.

LEER
Aplicación de técnicas de machine Learning para la detección de fugas en una tubería horizontal que transporta una mezcla de agua y glicerol
...
Gámez De León, Adalberto | 2021

During the last decades, the problem of detecting leaks in pipes with the help of software has been much discussed. Timely leak detection prevents water loss and helps prevent economic and environmental catastrophes. It is evident that companies choose to have good leak control policies, detection systems in Control Centers and teams of operators who locate leaks directly on the ground. However, these strategies do not allow for real-time leak detection. This project implements techniques based on machine learning that, through the introduction of process data from the studied pipes, systematically determine the presence of leaks. With this project, it is hoped to improve the speed and accuracy of leak detection, using only process data, system knowledge and intelligent software.

LEER
Classification, identification, and analysis of events on twitter through data mining
...
Silva, Jesús | 2021

Due to its popularity, Twitter is currently one of the major players in the global network, which has established a new form of communication: the microblogging. Twitter has become an essential media network for the follow-up, diffusion and coordination of events of diverse nature and importance (Gonzalez-Agirre et al. in Multilingual central repository version 3.0. Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12). Istanbul, Turkey, 2012, [1]), such as a presidential campaign, a disaster situation, a war or the repercussion of information. In such scenario, it is considered a relevant source of information to know the opinions that are emitted about different issues or people. This research proposes the evaluation of several supervised classification algorithms to address the problem of opinion mining on Twitter.

LEER
Comparison of bioinspired algorithms applied to cancer database
...
Silva, Jesús | 2021

Cancer is not just a disease; it is a set of diseases. Breast cancer is the second most common cancer worldwide after lung cancer, and it represents the most frequent cause of cancer death in women (Thurtle et al. in: PLoS Med 16(3):e1002758, 2019, 1]). If it is diagnosed at an early age, the chances of survival are greater. The objective of this research is to compare the performance of method predictions: (i) Logistic Regression, (ii) K-Nearest Neighbor, (iii) K-means, (iv) Random Forest, (v) Support Vector Machine, (vi) Linear Discriminant Analysis, (vii) Gaussian Naive Bayes, and (viii) Multilayer Perceptron within a cancer database.

LEER
Compilation of a social network lexicon for determining the profile of authors
...
Viloria, Amelec | 2020-11-05

The use of social networks is steadily increasing worldwide. Hundreds of users daily register in the different existing platforms, therefore, the content extracted from the social networks is fundamental for tasks such as sentiment analysis, detection of author profiles, identification of authors, opinions mining, plagiarism detection, calculation of similarity between texts and to develop robust systems that help to make decisions in related areas such as politics, education, economy, among others. This paper provides a lexical aid for the pre-processing of texts posted in social networks evolved for the subsequent languages: English, Spanish, Dutch and Italian.

LEER
Conceptualización del diagnóstico del Dengue desde una perspectiva de la ingeniería y las nuevas tecnologías
...
ARRUBLA HOYOS, WILSON DE JESÚS | 2022

Introducción— El dengue es una enfermedad tropical transmitida por mosquito que según reportes de la Organización Mundial de la Salud-OMS deja unos 390 millones de personas infectadas cada año, es una de las enfermedades que más afecta la salud de la población y la economía a nivel mundial. En consecuencia, Se han realizado esfuerzos desde diferentes áreas del saber donde se incluyen las Tecnologías de la Información y Comunicación-TIC para hacer frente a esta enfermedad. Objetivos— El objetivo de este artículo es presentar una conceptualización de la enfermedad del dengue desde una perspectiva de la ingeniería, caracterizando su comportamiento en las personas y como las principales tecnologías están realizando investigaciones para la predicción temprana. Métodología— Para su desarrollo se consultaron bases de datos especializadas como SCOPUS, WOS, IEEE, PUBMED utilizando cadenas de búsquedas que relacionan palabras claves de la enfermedad y las tecnologías de la información. Resultado: Como resultado se obtuvo que las principales tecnologías son el Machine Learning, el Big Data y la Inteligencia artificial con el desarrollo de modelos capaces de predecir la enfermedad de manera temprana. Existen muchas técnicas específicas que se utilizan, sin embargo, no se abordan en este artículo, solo se presenta la conceptualización de las tecnologías principales. Conclusiones— Se logra concluir que existen esfuerzos desde el área de la ingeniería en realizar investigaciones asociadas a la predicción temprana del dengue para hacer frente al impacto que está generando la enfermedad. Por un lado, existen modelos predictivos que apoyan las decisiones médicas en el diagnóstico temprano del dengue, aquí juega un papel importante la inteligencia artificial y el machine learning, y, por otro lado, se están generando grandes volúmenes de información en la práctica médica que posibilitan hacer nuevas investigaciones orientadas al diagnóstico y control del dengue.

LEER
Critical rare earth metal adsorption onto expanded vermiculite: accurate modeling through response surface methodology and machine learning techniques
...
de Vargas Brião, Giani | 2023

The circular economy of rare earth metals (REM), such as dysprosium, is essential for a sustainable future in clean energy and high-tech fields. Adsorption has gained attention to recover and reintegrate REM into the productive chain; however, accurate modeling of adsorptive processes still needs to be addressed, which delays further scale-up studies. Thus, this paper studied the adsorption of Dy on expanded vermiculite and applied novel empirical methods, such as artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS), and the classical response surface methodology (RSM) for modeling of dysprosium recovery as a function of adsorbent size, mass, and pH of the solution, variables often ignored in the mathematical modeling of adsorption. In our work, the effect of each operational parameter on Dy removal efficiency was examined by the RSM approach, in which only the adsorbent dosage and pH were the significant factors. So, ANFIS with two input membership functions (Gaussian type) was the most accurate procedure to predict and model the dysprosium removal efficiency (R2 = 0.99681). Also, vermiculite removed dysprosium with high efficiency (99.2%) under the best experimental conditions, at pH around 3.5 and adsorbent mass of 0.64 g, indicating an effective process optimization. The loaded vermiculite, after the adsorption, was characterized by textural and thermal properties that confirmed the stability of the material. Thus, according to basic operational parameters, accurate modeling of the Dy adsorption on expanded vermiculite (a low-cost, available, and non-toxic material) can improve adsorption technology's maturity to reconcentrate and recover rare earth metals.

LEER
Design of a network with VANET sporadic cloud computing applied to traffic accident prevention
...
amelec, viloria | 2020-07-19

The study analyzes the bandwidth available in a segment of route in the VANET network, since this value directly affects sporadic cloud computing. For this purpose, the bandwidth was tested on a highly complex urban scenario, where a number of mobile nodes were used with random conditions both in mobility and in resources of transmission. The results of the tests show that the stability of the bandwidth available in each region is proportional to the number of real mobile nodes in the region. However, a considerable bandwidth is also reached with a smaller number of mobile nodes, but there is no stability in the region, thus causing the network to collapse. The VANET network simulation tool was NS-3, since it is currently one of the most commonly used free software that allows configure the simulation parameters in a vehicular environment. The urban simulation scenario is the historic center of the City of Bogotá, Colombia, which was created with SUMO for obtaining the mobility traces

LEER
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition
...
Jiménez-Gómez, Geovanna | 2021-09-17

The impact that neurodegenerative diseases have in our society, have made human activity recognition (HAR) arise as a relevant field of study. The quality of life of people with such conditions, can be significantly improved with the outcomes of the projects within this area. The application of machine learning techniques on data from low level sensors such as accelerometers is the base of HAR. To improve the performance of these classifiers, it is necessary to carry out an adequate training process. To improve the training process, an analysis of the different features used in literature to tackle these problems was performed on datasets constructed with students performing 18 different activities of daily living. The outcome of the process shows that an adequate selection of features improves the performance of Random Forest from 94.6% to 97.2%. It was also found that 78 features explain 80% of the variability.

LEER
Development of machine learning methods in hybrid energy storage systems in electric vehicles
...
Tzu-Chia, Chen | 2022

The hybrid energy storage systems are a practical tool to solve the issues in single energy storage systems in terms of specific power supply and high specific energy. These systems are especially applicable in electric and hybrid vehicles. Applying a dynamic and coherent strategy plays a key role in managing a hybrid energy storage system. The data obtained while driving and information collected from energy storage systems can be used to analyze the performance of the provided energy management method. Most existing energy management models follow predetermined rules that are unsuitable for vehicles moving in different modes and conditions. Therefore, it is so advantageous to provide an energy management system that can learn from the environment and the driving cycle and send the needed data to a control system for optimal management. In this research, the machine learning method and its application in increasing the efficiency of a hybrid energy storage management system are applied. In this regard, the energy management system is designed based on machine learning methods so that the system can learn to take the necessary actions in different situations directly and without the use of predicted select and run the predefined rules. The advantage of this method is accurate and effective control with high efficiency through direct interaction with the environment around the system. The numerical results show that the proposed machine learning method can achieve the least mean square error in all strategies.

LEER
Diabetes diagnostic prediction using vector support machines
...
amelec, viloria | 2020

The most important factors for the diagnosis of diabetes mellitus (DM) are age, body mass index (BMI) and blood glucose concentration. Diagnosis of DM by a doctor is complicated, because several factors are involved in the disease, and the diagnosis is subject to human error. A blood test does not provide enough information to make a correct diagnosis of the disease. A vector support machine (SVM) was implemented to predict the diagnosis of DM based on the factors mentioned in patients. The classes of the output variable are three: without diabetes, with a predisposition to diabetes and with diabetes. An SVM was obtained with an accuracy of 99.2% with Colombian patients and an accuracy of 65.6% with a data set of patients of a different ethnic background.

LEER
Electrical consumption patterns through machine learning
...
amelec, viloria | 2020

Electricity distribution companies have been incorporating new technologies that allow them to obtain complete information in real time about their customers´ consumption. Thus, a new concept called "Smart Metering" has been adopted, giving way to new types of meters that interact in an interconnected system. This will allow to make data analysis, accurate forecasts and detecting consumption patterns that will be relevant for the decision-making process. This research focuses on discovering common patterns among customers from data collected by smart meters.

LEER
Engineering of novel fe-based bulk metallic glasses using a machine learning-based approach
...
Tzu-Chia, Chen | 2021-07-07

A broad range of potential chemical compositions makes difficult design of novel bulk metallic glasses (BMGs) without performing expensive experimentations. To overcome this problem, it is very important to establish predictive models based on artificial intelligence. In this work, a machine learning (ML) approach was proposed for predicting glass formation in numerous alloying compositions and designing novel glassy alloys. The results showed that our ML model accurately predicted the glass formation and critical thickness of MGs. As a case study, the ternary Fe–B–Co system was selected and effects of minor additions of Cr, Nb and Y with different atomic percentages were evaluated. It was found that the minor addition of Nb and Y leads to the significant improvement of glass-forming ability (GFA) in the Fe–B–Co system; however, a shift in the optimized alloying composition was occurred. The experimental results on selective alloying compositions also confirmed the capability of our ML model for designing novel Fe-based BMGs. © 2021, King Fahd University of Petroleum & Minerals.

LEER
Herramientas BIM para el análisis de requisitos de la norma de rendimiento para edificaciones en Brasil
...
Lima da Silva, Juliano | 2020-10-01

En esta conferencia la profesora Andrea Mussi (PhD) junto con algunos integrantes del grupo de Núcleo de Innovación y Tecnología en Arquitectura y Urbanismo, NITAU del IMED, nos expondrán los resultados de su investigación en el desarrollo de herramientas de programación para proyectos, mediante herramientas personalizables centradas en la integración de la información, así como la elaboraron de instrumentos destinados a verificación de los requisitos de desempeño en un software BIM.

LEER
Identificación de aminoácidos de cadena ramificada en proteína de quinua mediante modelo de regresión lineal con aprendizaje de máquinas
...
Caicedo, Nicolas | 2022-07-07

La quinua, se clasifica como pseudocereal y contiene componentes bioactivos, tales como proteínas con un alto valor nutricional. El consumo de proteína y especialmente aminoácidos esenciales de cadena ramificada juegan un papel fundamental en la dieta, ya que favorece al mantenimiento de estructuras corporales

LEER
Intellectual property in colombian museums: an application of machine learning
...
Lis-Gutiérrez, Jenny-Paola | 2019

The purpose of this research is to answer the following guiding question: how can the behavior of museum networks in Colombia be predicted with respect to the protection of intellectual property (copyright, confidential information and use of patents, domain names, industrial designs, use of trademarks) and the interaction of different types of proximity (geographical, organizational, relational, cognitive, cultural and institutional), based on the use of supervised learning algorithms? Among the main findings are that the best learning algorithms to predict the behavior of networks, considering different target variables are the AdaBoost, the naive Bayes and CN2 rule inducer

LEER
Machine learning applied to the h index of colombian authors with publications in scopus
...
amelec, viloria | 2019

Our research aims to establish how to predict the H index of Colombian authors with publications in Scopus until 2016. The selection of the date was because, as mentioned earlier, the number of documents indexed per year exceeded 10,000 and they obtained the highest number of documents cited. To accomplish this purpose, a quantitative, nonexperimental, cross-sectional, descriptive, explanatory, and predictive research was designed using supervised learning algorithms. These were applied to information from 8,840 Colombian authors. Among the findings we can highlight that: (i) Colombia is in the fifth position in the scope of countries of South America and the Caribbean, in terms of the number of products and citations; (ii) the largest number of Colombian authors with products in Scopus until 2016, belonged mainly to the area of natural sciences, followed by medical sciences and health; (iii) most of the Colombian authors were men (64.2%, or 5,442) and they have higher H index rates than women; (iv) using random cross validation for 10 iterations, the methods with the best predictive value using R2 and the minimization of mean absolute error (MAE) correspond to: AdaBoost (96.6% and 0.397, respectively); Random Forest (96.8% and 0.431, respectively); KNN (94.4% and 0.525, respectively); Tree (94.9% and 0.53, respectively); and Neural Network (93.3% and 0.7, respectively); and (v) the variables that help predict the H index in the case of the Colombian authors, in addition to the citations, correspond to: the quantity of products, number of products in Q1, and international collaboration

LEER
Machine learning approach applied to human activity recognition – an application to the VanKasteren dataset
...
Ariza Colpas, Paola Patricia | 2021

Reminders are a core component of many assistive technology systems and are aimed specifically at helping people with dementia function more independently by compensating for cognitive deficits. These technologies are often utilized for prospective reminding, reminiscence, or within coaching-based systems. Traditionally, reminders have taken the form of nontechnology based aids, such as diaries, notebooks, cue cards and white boards. This article is based on the use of machine learning algorithms for the detection of Alzheimer’s disease. In the experimentation, the LWL, SimpleLogistic, Logistic, MultiLayerPercepton and HiperPipes algorithms were used. The result showed that the LWL algorithm produced the following results: Accuracy 98.81%, Precission 100%, Recall 97.62% and F- measure 98.80%

LEER
A machine learning solution for bed occupancy issue for smart healthcare sector
...
Gochhait, Dr Saikat | 2021

The health care domain is a culmination and emergence of many other economic sectors that give different services from patient treatment to healing, protective, rehabilitation, and palliative care. The GDP consumes to facilitate health in terms of smart device development, clinical examinations, outsourcing, and tele-medication facilities. The Asian countries and less developed countries with a high population rate are facing health care services related issues. One of these countries is India. India has two types of health care services systems: (i) public service system and (ii) private system. The public health system, i.e., the government, provides facilities to patients as primary health centers (PHCs) through limited secondary and tertiary health institutions like hospitals in rural areas while the private service is owned by local practitioners and institutions. Both of these service providers are facing bed occupancy issues for patients due to a highly populated country. To overcome this issue, we propose a machine learning solution for patient admission scheduling autonomously. The proposed framework helps hospitals to enhance the decision process for bed occupancy for patients concerning their departments and their diseases. We have deployed our framework in real time environment and find that it facilitates the overall performance of bed allocation in the prescribed hospitals.

LEER
Management system for optimizing public transport networks: GPS record
...
Silva, Jesús | 2020-07-19

As cities continue to grow in size and population, the design of public transport networks becomes complicated, given the wide diversity in the origins and destinations of users [1], as well as the saturation of vehicle infrastructure in large cities despite their attempts to adapt it according to population distribution. This indicates that, in order to reduce users’ travel time, it is necessary to implement alternative road solutions to the use of cars, increasing investment in public transportation [2, 3] by conducting a comprehensive analysis of the state of transportation. This situation has made appear the solutions and development oriented to transportation based on Internet of Things (IoT) which allows, in a first stage, monitoring of public transport systems, in order to optimize the deployment of transport units and thus reduce the time of transfer of users through the cities [4]. These solution proposals are focused on information collected from user resources (data collected through smart phones) to create a common database [5]. The present study proposes the development of an intelligent monitoring and management system for public transportation networks using a hybrid communication architecture based on wireless node networks using IPv6 and cellular networks (LTE, LTE-M).

LEER