Zurisaddai Severiche

Prof. Zurisaddai Severiche

Ingeniería Electrónica, University of Sucre, Sincelejo, Sucre, Colombia
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 August 2024 in Designs
Verified
Journal Article
Open access
PDF file
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
WHWilson de Jesus Arrubla Hoyos
Wilson de Jesus Arrubla Hoyos
Raul Ramirez-VelardeRaul Ramirez-Velarde
Raul Ramirez-Velarde
DPDora Cama Pinto
Dora Cama Pinto
Juan A. Holgado-TerrizaJuan A. Holgado-Terriza
Juan A. Holgado-Terriza
ACAlejandro Cama-Pinto
Alejandro Cama-Pinto
This study aims to develop and evaluate an LSTM neural network for predicting household energy consumption. To conduct the experiment, a testbed was created consisting of five common appliances, namely, a TV, air conditioner, fan, computer, and lamp, each connected to individual smart meters within a Home Energy Management System (HEMS). Additionally, a meter was installed on the distribution board to measure total consumption. Real-time data were collected at 15-min intervals for 30 days in a residence that represented urban energy consumption in Sincelejo, Sucre, inhabited by four people. This setup enabled the capture of detailed and specific energy consumption data, facilitating data analysis and validating the system before large-scale implementation. Using the detailed power consumption information of these devices, an LSTM model was trained to identify temporal connections in power usage. Proper data preparation, including normalisation and feature selection, was essential for the success of the model. The results showed that the LSTM model was effective in predicting energy consumption, achieving a mean squared error (MSE) of 0.0169. This study emphasises the importance of continued research on preferred predictive models and identifies areas for future research, such as the integration of additional contextual data and the development of practical applications for residential energy management. Additionally, it demonstrates the potential of LSTM models in smart-home energy management and serves as a solid foundation for future research in this field.

22 May 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
CRCarlos Eduardo Uc Ríos
Carlos Eduardo Uc Ríos
JSJavier E. Sierra
Javier E. Sierra
AHALEJANDRO SALLYTH GUERRERO HERNANDEZ
ALEJANDRO SALLYTH GUERRERO HERNANDEZ
Rising household electricity consumption, driven by technological advances and increased indoor activity, has led to higher energy costs and an increased reliance on non-renewable sources, exacerbating the carbon footprint. Home energy management systems (HEMS) are positioning themselves as an efficient alternative by integrating artificial intelligence to improve their accuracy. Predictive algorithms that provide accurate data on the future behavior of energy consumption and appliance usage time are required in these HEMS to achieve this goal. This study presents a predictive model based on recurrent neural networks with long short-term memory (LSTM), known to capture nonlinear relationships and long-term dependencies in time series data. The model predicts individual and total household energy consumption and appliance usage time. Training data were collected for 12 months from an HEMS installed in a typical Colombian house, using smart meters developed in this research. The model’s performance is evaluated using the mean squared error (MSE), reaching a value of 0.0168 kWh2. The results confirm the effectiveness of HEMS and demonstrate that the integration of LSTM-based predictive models can significantly improve energy efficiency and optimize household energy consumption.

22 May 2022 in Energies
Verified
Journal Article
Open access
PDF file
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
Ana Fernández-VilasAna Fernández-Vilas
Ana Fernández-Vilas
Rebeca P. Díaz RedondoRebeca P. Díaz Redondo
Rebeca P. Díaz Redondo
Since no solutions have been proposed in Colombia that seek to reduce the consumption of electricity at the residential level, this paper describes the design and implementation of a simple prototype of a low-cost home energy management system (HEMS). The objective of this platform is to monitor the energy consumption of typical household devices so that users can access the consumption of each device separately and then establish the strategy that allows them to reduce energy consumption at home. In order to demonstrate that our system is viable, the system has been evaluated by measuring weekly energy consumption with the on-line and off-line HEMS using a test bench with typical household devices in a Sincelejo typical household. The evaluation has shown that with the installation of this HEMS, consumption is reduced by 27%. This shows that it is possible to achieve a good reduction percentage with a low-cost system.

22 November 2023
Verified
Conference Paper
Closed access
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
WAWilson Arrubla-Hoyos
Wilson Arrubla-Hoyos
This paper presents an innovative model for efficient home energy management through a Home Energy Management System (HEMS) based on Deep Learning and Reinforcement Learning. Disaggregated consumption meters have been installed in five household devices (refrigerator, air conditioner, fan, personal computer and lights) and a meter that calculates total consumption. Consumption data have been collected for 12 weeks, with different time periods for each device. Average consumption data per appliance has been obtained and electricity consumption curves have been generated for each appliance. The developed model shows significant potential for optimizing household energy consumption, improving energy efficiency and promoting more sustainable practices.

22 November 2023
Verified
Conference Paper
Closed access
WAWilson Arrubla-Hoyos
Wilson Arrubla-Hoyos
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
KSKhalid Saeed
Khalid Saeed
JGJorge Eliecer Gómez Gómez
Jorge Eliecer Gómez Gómez
EDEmiro De-La-Hoz-Franco
Emiro De-La-Hoz-Franco
Dengue disease, spread by mosquitoes, affects a large part of the world's population. Early diagnosis is essential to avoid its severe impacts. This paper seeks to compare classical machine learning techniques with ensemble approaches in the early classification of dengue: Dengue without alarm signs (DNWS), Dengue with alarm signs (DWWS) and Severe Dengue (SD). A dataset available at https://www.datos.gov.co/ from the Colombian government with 53,814 records and 38 attributes is used. The data are processed in Google Colab using Pandas, Matplotlib and Numpy, while Scikit-learn is used for modeling. The results are supported by a detailed confusion matrix, revealing the actual performance of each model and highlighting the superiority of the ensemble approaches over classical techniques in early dengue classification. The Stacking method achieves an accuracy (Acc) of 88%, outperforming all other techniques employed. Among the classical techniques, Decision Tree (DT) achieved the best result with an Acc of 84%. In conclusion, when contrasting the performance of classical techniques and ensemble approaches in early dengue classification, it is highlighted that the latter demonstrate robustness in terms of quality metrics, such as accuracy, recall and F1-Score. This observation suggests that ensemble approaches have the potential to overcome the limitations associated with classical techniques, resulting in more robust and accurate achievements.

1 May 2018
Verified
Conference Paper
Closed access
Zurisaddai SevericheZurisaddai Severiche
Zurisaddai Severiche
AVAna Fernandez Vilas
Ana Fernandez Vilas
RRRebeca Diaz Redondo
Rebeca Diaz Redondo
The worldwide trend in the increase of energy consumption has led many researchers to be interested in proposing methods that allow the reduction of their consumption. It has been shown in various cases how positive changes in human behavior have been achieved through gamification. This article proposes a gamification approach that uses a system of energy management in the home to achieve greater energy saving.