Comparative Forecasting of Hospital Cardiovascular Emergency Demand in the Dominican Republic Using Time Series and Machine Learning Models Deyslen Mariano-Hernández Miguel Aybar-Mejia Navila Leon-Tejeda Edwin Sánchez-Camilo Armando J. Taveras-Cruz Iván Jiménez-Durán hospital demand forecasting cardiovascular emergencies emergency department demand time series forecasting machine learning forecasting model comparison Dominican Republic 2026 en info:eu-repo/semantics/bookPart book-chapter https://doi.org/10.1007/978-3-032-19019-2_8 Communications in computer and information science Communications in computer and information science urn:issn:1865-0929 urn:issn:1865-0937 Communications in computer and information science, 2026, p. 109-118 info:eu-repo/semantics/closedAccess closedAccess Q4 Good health and well-being Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal A dataset of coexisting Sargassum features and submesoescalar eddies near the south coast of the Dominican Republic in 2023 Deyslen Mariano-Hernández Iván Jiménez-Durán Elianna Castaño Abreu Edwin Sánchez-Camilo Carlos Sanlley Sargassum ocean eddies coastal ocean dynamics seaweed blooms coastal flooding inundation. 2026 en info:eu-repo/semantics/article journal-article https://doi.org/10.1016/j.dib.2026.113158 Data in Brief Data in Brief urn:issn:2352-3409 Data in Brief, 2026, vol. 68, p. 113158 info:eu-repo/semantics/openAccess openAccess cc-by-nc https://www.sciencedirect.com/science/article/pii/S2352340926007055/pdf Q1 doaj pubmed Life below water Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal A Machine Learning Approach to Forecasting Energy Consumption at Electric Vehicle Charging Stations Miguel Aybar-Mejia Deyslen Mariano-Hernandez David Aquino-Osorio Armando Jose Taveras Cruz Edwin Sanchez-Camilo Ali Bassam electric vehicle charging demand forecasting electric vehicle charging stations peak demand forecasting charging sessions XGBoost random forest LSTM ARIMA linear regression grid stability energy planning The growing adoption of electric vehicles (EVs) presents challenges for energy providers in managing demand and optimizing charging infrastructure. Accurate forecasting of EV charging demand is crucial to prevent grid overloads and efficiently allocate resources. This paper evaluated various models ARIMA, Linear Regression (LR), XGBoost, Random Forest (RF), and Long Short-Term Memory (LSTM) to predict EV charging demand at stations during working hours. The study utilized a dataset of 3,395 charging sessions from November 2014 to October 2015, involving 85 drivers and 105 stations across 25 sites. After data preprocessing, including anomaly correction and feature engineering, the models were assessed. LR and LSTM models proved more accurate for peak demand forecasting, while RF and XGBoost models performed better for overall forecasting, achieving mean absolute errors of 10.48 and 10.56, respectively. This methodology offers a valuable tool for energy providers, aiding in resource planning, optimization, and enhancing grid stability and efficiency. 2025 info:eu-repo/semantics/conferenceObject proceedings-article https://doi.org/10.1109/camsap66162.2025.11423966 2025 IEEE 10th International Workshop on Computational Advances in Multi Sensor Adaptive Processing Camsap 2025 Proceedings 2025 IEEE 10th International Workshop on Computational Advances in Multi Sensor Adaptive Processing Camsap 2025 Proceedings 2025 IEEE 10th International Workshop on Computational Advances in Multi Sensor Adaptive Processing Camsap 2025 Proceedings, 2025, p. 151-155 info:eu-repo/semantics/closedAccess closedAccess Industry, innovation and infrastructure Affordable and clean energy Climate action Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal Análisis de los modos de fallo del sistema de gestión de energía de un Cubesat Miguel Aybar Mejía Lía Hidalgo de los Santos Diorys Del Rosario Peñaló Edwin Sánchez Deyslen Mariano-Hernández failure modes energy management systems CubeSat nanosatellites solar panels batteries energy storage electricity generation system sizing satellite power systems Generadores de energía fotovoltaica Satélites artificiales Energía eléctrica Sistemas de energía eléctrica Un satélite es un dispositivo que se sitúa en órbita alrededor de la Tierra con fines científicos, militares, educacionales o de comunicaciones. Se pueden clasificar según su peso como: satélites grandes, que pesan más de 1,000 kilogramos (kg), satélites medianos, que pesan entre 500-1,000 kg, y satélites pequeños, que pesan menos de 500 kg. Dentro de los satélites pequeños se encuentran los nanosatélites, los cuales pesan entre 1-10 kg. La principal ventaja que poseen los nanosatélites es que son capaces de realizar misiones complejas a un menor costo. Dentro de las limitaciones que estos presentan es que tienen poca capacidad para captar y almacenar energía debido a su tamaño. Considerando la importancia del sistema de energía durante el funcionamiento de los satélites, este artículo analiza los modos de fallos que se presentan en el sistema y cómo estos afectan a los sistemas de generación y almacenamiento de energía. Para la simulación de estos sistemas se determinaron la cantidad mínima de paneles solares y baterías necesarios para su correcto funcionamiento. Los resultados obtenidos muestran que con este análisis se logra dimensionar correctamente el sistema de gestión de energía, reduciendo el tamaño de estos y a su vez el peso dentro del satélite. Instituto Tecnológico de Santo Domingo (INTEC) 2021 es info:eu-repo/semantics/article journal-article https://doi.org/10.22206/cyap.2021.v4i2.pp5-2 Ciencia, Ingenierías y Aplicaciones Ciencia, Ingenierías y Aplicaciones urn:issn:2636-2171 urn:issn:2636-218X Ciencia, Ingenierías y Aplicaciones, 2021, vol. 4, n. 2, p. 5-20 info:eu-repo/semantics/openAccess openAccess cc-by-nc-sa https://revistas.intec.edu.do/index.php/cite/article/download/2249/2747 Affordable and clean energy Industry, innovation and infrastructure Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal Cranfield Astrobiological Stratospheric Sampling Experiment (Cass.E): Overview of Flight Hardware Configuration, Implemented Planetary Protection and Contamination Control Procedures and Preliminary Post-Flight Results 2011 info:eu-repo/semantics/conferenceObject proceedings-article cris:cris-3ca8e197 2011 Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal Development and applications of remote sensors in Low Earth Orbit (LEO) to improve the decision making about climate and environmental resiliency in the Caribbean and the Hispaniola island – phase 1 2019 info:eu-repo/semantics/other conference-poster cris:cris-e5fcff76 27th Workshop on Space Technology for Socio-Economic Benefits: "Ensuring Inclusiveness through Space-based Applications and Space Exploration" 27th Workshop on Space Technology for Socio-Economic Benefits: "Ensuring Inclusiveness through Space-based Applications and Space Exploration" 27th Workshop on Space Technology for Socio-Economic Benefits: "Ensuring Inclusiveness through Space-based Applications and Space Exploration", 2019 Instituto Tecnológico de Santo Domingo https://www.intec.edu.do/portal