Varela Aldas, José
Thumbnail Image
Preferred name
Varela Aldas, José
Main Affiliation
Ambato
Email
josevarela@uti.edu.ec
ORCID
Scopus Author ID
57192546163

Research Output
Now showing 1 - 10 of 11
No Thumbnail Available
Publication

Sizing and Characterization of Load Curves of Distribution Transformers Using Clustering and Predictive Machine Learning Models

2025 , Pedro Torres-Bermeo , Kevin López-Eugenio , Carolina Del-Valle-Soto , Guillermo Palacios-Navarro , Varela Aldas, José

The efficient sizing and characterization of the load curves of distribution transformers are crucial challenges for electric utilities, especially given the increasing variability of demand, driven by emerging loads such as electric vehicles. This study applies clustering techniques and predictive models to analyze and predict the behavior of transformer demand, optimize utilization factors, and improve infrastructure planning. Three clustering algorithms were evaluated, K-shape, DBSCAN, and DTW with K-means, to determine which one best characterizes the load curves of transformers. The results show that DTW with K-means provides the best segmentation, with a cross-correlation similarity of 0.9552 and a temporal consistency index of 0.9642. For predictive modeling, supervised algorithms were tested, where Random Forest achieved the highest accuracy in predicting the corresponding load curve type for each transformer (0.78), and the SVR model provided the best performance in predicting the maximum load, explaining 90% of the load variability (R2 = 0.90). The models were applied to 16,696 transformers in the Ecuadorian electrical sector, validating the load prediction with an accuracy of 98.55%. Additionally, the optimized assignment of the transformers’ nominal power reduced installed capacity by 39.27%, increasing the transformers’ utilization factor from 31.79% to 52.35%. These findings highlight the value of data-driven approaches for optimizing electrical distribution systems.

View
No Thumbnail Available
Publication

A Literature Review on Real-Time Crime Detection Using Deep Learning and Edge Computing

2025 , Carlos Julio Fierro Silva , Carolina Del-Valle-Soto , Varela Aldas, José

The growing need for security in urban and commercial environments has driven the development of intelligent surveillance systems capable of detecting criminal activities in real time. While traditional cloud-based solutions offer advanced capabilities, they face limitations in terms of latency, privacy, and bandwidth usage. In this context, Edge Computing has emerged as a promising alternative, enabling local and fast processing of video data through embedded artificial intelligence models. This review article presents a comprehensive analysis of recent advances in real-time detection of thefts and weapons using Edge Artificial Intelligence (Edge AI). A total of 30 scientific articles published between 2018 and 2025 were selected and categorized, taking into account detection models, computing platforms, evaluation metrics, datasets, and real-world applications. The results highlight the predominant use of lightweight convolutional neural networks, especially YOLO-based models, implemented on devices such as Jetson Nano, Raspberry Pi, and Google Coral. Key challenges addressed include detection under lowlight conditions, identification of small or partially concealed weapons, and the reduction of false positives. The review identifies gaps in the current literature, such as the lack of annotated real-world datasets and the need for behavior-based models in retail contexts. Finally, emerging trends and future research directions are discussed, aiming at the development of efficient, accurate, and privacy-respecting Edge AI systems for real-time security surveillance. © 2025 IEEE.

View
No Thumbnail Available
Publication

Enhancing Elderly Care through Low-Cost Wireless Sensor Networks and Artificial Intelligence: A Study on Vital Sign Monitoring and Sleep Improvement

2024 , Carolina Del-Valle-Soto , Ramon A. Briseño , Ramiro Velázquez , Gabriel Guerra-Rosales , Santiago Perez-Ochoa , Isaac H. Preciado-Bazavilvazo , Paolo Visconti , Varela Aldas, José

This research explores the application of wireless sensor networks for the non-invasive monitoring of sleep quality and vital signs in elderly individuals, addressing significant challenges faced by the aging population. The study implemented and evaluated WSNs in home environments, focusing on variables such as breathing frequency, deep sleep, snoring, heart rate, heart rate variability (HRV), oxygen saturation, Rapid Eye Movement (REM sleep), and temperature. The results demonstrated substantial improvements in key metrics: 68% in breathing frequency, 68% in deep sleep, 70% in snoring reduction, 91% in HRV, and 85% in REM sleep. Additionally, temperature control was identified as a critical factor, with higher temperatures negatively impacting sleep quality. By integrating AI with WSN data, this study provided personalized health recommendations, enhancing sleep quality and overall health. This approach also offered significant support to caregivers, reducing their burden. This research highlights the cost-effectiveness and scalability of WSN technology, suggesting its feasibility for widespread adoption. The findings represent a significant advancement in geriatric health monitoring, paving the way for more comprehensive and integrated care solutions.

View
No Thumbnail Available
Publication

Bridging the Digital Divide in Mexico: A Critical Analysis of Telecommunications Infrastructure and Predictive Models for Policy Innovation

2024 , Carolina Del-Valle-Soto , Ramon A. Briseño , Juan-Carlos López-Pimentel , Ramiro Velázquez , Leonardo J. Valdivia , Varela Aldas, José

This work presents an in-depth evaluation of the telecommunications landscape in Mexico from 2015 to 2023. The study’s primary focus is on the disparities in broadband access, telecommunications infrastructure, and digital inclusion across various regions, particularly between urban and rural areas. By employing predictive models and correlation analysis, the paper identifies key factors influencing technology adoption and service bundling in households. A significant contribution of this research lies in its identification of strong correlations between broadband access, GDP growth, and the penetration of multiple telecommunication services such as fixed telephony, broadband internet, and television. The predictive models developed offer crucial insights into the regional inequalities of digital access, revealing patterns that policymakers can use to prioritize infrastructure investments. The findings underscore the essential role of public policy innovation in promoting digital inclusion, particularly in underdeveloped regions, and provide a robust analytical framework for understanding how advanced telecommunications services contribute to socio-economic development. Through this analytical approach, the study demonstrates the critical relationship between telecommunications infrastructure and regional economic performance, offering data-driven recommendations to bridge the digital divide and enhance connectivity in underserved areas. The results offer significant value for future research and policy initiatives aimed at fostering equitable access to Information and communication technologies, promoting economic growth, and ensuring broader societal inclusion in the digital age.

View
No Thumbnail Available
Publication

Genre-Sensitive Prediction of Emotional Arousal in Virtual Reality: A Neural Modeling Approach Using Skin Conductance Peaks

2025 , Carolina Del-Valle-Soto , Demián Velasco Gómez Llanos , Santiago Arreola Munguía , Marco Antonio Manjarrez Fernandez , Juan Pablo Villaseñor Navares , Violeta Corona , Varela Aldas, José , Jesus GomezRomero-Borquez

Understanding how different virtual reality (VR) game genres modulate physiological arousal is crucial for designing emotionally adaptive immersive systems. This study introduces a novel experimental framework combining high-resolution Skin Conductance Response (SCR) data and neural predictive modeling to compare emotional activation across horror, skill-based, and exercise VR games. Using Galvanic Skin Response (GSR) sensors, we recorded phasic peaks in SCR from 25 university-aged participants during gameplay sessions with controlled exposure times and standardized transitions. However, given the minimal difference relative to the large variability, this observation should be considered preliminary and specific to the tested games and cohort. A feed-forward neural network was developed to forecast individual arousal levels based solely on genre-induced features, achieving strong predictive performance. This dual contribution empirical genre comparison and lightweight predictive modeling offers a scalable tool for integrating emotional responsiveness into VR systems without continuous biosignal monitoring. The findings not only advance the state of the art in affective computing but also open new avenues for therapeutic, educational, and entertainment applications grounded in physiological adaptation

View
No Thumbnail Available
Publication

Acceptance of an IoT System for Strawberry Cultivation: A Case Study of Different Users

2024 , Varela Aldas, José , Gavilanes, Alex , Nancy Velasco , Carolina Del-Valle-Soto , Carlos Bran

The Internet of Things (IoT) has been impacting multiple industries worldwide for over a decade. However, less developed countries have yet to make the transition to these technologies. South America is among the regions with the least IoT influence in all sectors, indicating a need for studies to explore IoT acceptance among various users in this region. This study analyzes two different users of a monitoring and irrigation system for strawberry (Fragaria × ananassa) farming. Monitored variables include soil moisture, and ambient temperature and humidity, with irrigation performed via water pumping from a reservoir. The system is based on the M5Core2 development kit for the local station and the IoT platform ThingSpeak for remote access. It features a web user interface consisting of an application developed in HTML using a plugin on ThingSpeak. Thus, the system can be used locally via a touchscreen and remotely through a web browser. Measurements are cross-verified with commercial meters to ensure their reliability, and users are asked to fill out a Technology Acceptance Model (TAM) for IoT to gauge their acceptance level. Additionally, an interview is conducted that explores four critical factors, aimed at understanding their experience and interaction with the system after a period of usage. The findings confirm the validity of the monitored variables and demonstrate a global acceptance rate of slightly over 80%, albeit with varying user acceptance perspectives. Specifically, the technical user exhibits greater acceptance than the crop administrator, evidenced by a mean discrepancy of 1.85 points on the TAM scale.

View
No Thumbnail Available
Publication

Projection of Photovoltaic System Adoption and Its Impact on a Distributed Power Grid Using Fuzzy Logic

2025 , Kevin López-Eugenio , Pedro Torres-Bermeo , Carolina Del-Valle-Soto , Varela Aldas, José

The increasing adoption of photovoltaic systems presents new challenges for energy planning and grid stability. This study proposes a fuzzy logic-based methodology to identify potential PV adopters by integrating variables such as energy consumption, electricity tariff, solar radiation, and socioeconomic level. The approach was applied to a real distribution grid and compared against a previously presented method that selects users based solely on high energy consumption. The fuzzy logic model demonstrated superior performance by identifying 77.03 [%] of real adopters, outperforming the previous selection strategy. Additionally, the study evaluates the technical impact of PV integration on the distribution grid through power flow simulations, analysing energy losses, voltage stability, and asset loadability. Findings highlight that while PV systems reduce energy losses, they can also introduce voltage regulation challenges under high penetration. The proposed methodology serves as a decision-support tool for utilities and regulators, enhancing the accuracy of adoption projections and informing infrastructure planning. Its flexibility and rule-based nature make it adaptable to different regulatory and technical environments, allowing it to be replicated globally for sustainable energy transition initiatives.

View
No Thumbnail Available
Publication

Visual Servoing Using Sliding-Mode Control with Dynamic Compensation for UAVs’ Tracking of Moving Targets

2024 , Christian P. Carvajal , Víctor H. Andaluz , Varela Aldas, José , Flavio Roberti , Carolina Del-Valle-Soto , Ricardo Carelli

An Image-Based Visual Servoing Control (IBVS) structure for target tracking by Unmanned Aerial Vehicles (UAVs) is presented. The scheme contains two stages. The first one is a sliding-model controller (SMC) that allows one to track a target with a UAV; the control strategy is designed in the function of the image. The proposed SMC control strategy is commonly used in control systems that present high non-linearities and that are always exposed to external disturbances; these disturbances can be caused by environmental conditions or induced by the estimation of the position and/or velocity of the target to be tracked. In the second instance, a controller is placed to compensate the UAV dynamics; this is a controller that allows one to compensate the velocity errors that are produced by the dynamic effects of the UAV. In addition, the corresponding stability analysis of the sliding mode-based visual servo controller and the sliding mode dynamic compensation control is presented. The proposed control scheme employs the kinematics and dynamics of the robot by presenting a cascade control based on the same control strategy. In order to evaluate the proposed scheme for tracking moving targets, experimental tests are carried out in a semi-structured working environment with the hexarotor-type aerial robot. For detection and image processing, the Opencv C++ library is used; the data are published in an ROS topic at a frequency of 50 Hz. The robot controller is implemented in the mathematical software Matlab.

View
No Thumbnail Available
Publication

Electrodermal Response Patterns and Emotional Engagement Under Continuous Algorithmic Video Stimulation: A Multimodal Biometric Analysis

2026 , Carolina Del-Valle-Soto , Violeta Corona , Jesus GomezRomero-Borquez , David Contreras-Tiscareno , Diego Sebastian Montoya-Rodriguez , Jesus Abel Gutierrez-Calvillo , Bernardo Sandoval , Varela Aldas, José

Excessive use of short-form video platforms such as TikTok has raised growing concerns about digital addiction and its impact on young users’ emotional well-being. This study examines the relationship between continuous TikTok exposure and emotional engagement in young adults aged 20–23 through a multimodal experimental design. The purpose of this research is to determine whether emotional engagement increases, remains stable, or declines during prolonged exposure and to assess the degree of correspondence between facially inferred engagement and physiological arousal. To achieve this, multimodal biometric data were collected using the iMotions platform, integrating galvanic skin response (GSR) sensors and facial expression analysis via Affectiva’s AFFDEX SDK 5.1. Engagement levels were binarized using a logistic transformation, and a binomial test was conducted. GSR analysis, merged with a 50 ms tolerance, revealed no significant differences in skin conductance between engaged and non-engaged states. Findings indicate that although TikTok elicits strong initial emotional engagement, engagement levels significantly decline over time, suggesting habituation and emotional fatigue. The results refine our understanding of how algorithm-driven, short-form content affects users’ affective responses and highlight the limitations of facial metrics as sole indicators of physiological arousal. Implications for theory include advancing multimodal models of emotional engagement that account for divergences between expressivity and autonomic activation. Implications for practice emphasize the need for ethical platform design and improved digital well-being interventions. The originality and value of this study lie in its controlled experimental approach that synchronizes facial and physiological signals, offering objective evidence of the temporal decay of emotional engagement during continuous TikTok use and underscoring the complexity of measuring affect in highly stimulating digital environments.

View
No Thumbnail Available
Publication

Adaptive Jamming Mitigation for Clustered Energy-Efficient LoRa-BLE Hybrid Wireless Sensor Networks

2025 , Carolina Del-Valle-Soto , Leonardo J. Valdivia , Ramiro Velázquez , José A. Del-Puerto-Flores , Varela Aldas, José , Paolo Visconti

View