Now showing 1 - 10 of 29
No Thumbnail Available
Publication

Real-time hardware emulation of neural cultures: A comparative study of in vitro, in silico and in duris silico models

2024 , Bernardo Vallejo-Mancero , Sergio Faci-Lázaro , Zapata, Mireya , Jordi Soriano , Jordi Madrenas

Biological neural networks are well known for their capacity to process information with extremely low power consumption. Fields such as Artificial Intelligence, with high computational costs, are seeking for alternatives inspired in biological systems. An inspiring alternative is to implement hardware architectures that replicate the behavior of biological neurons but with the flexibility in programming capabilities of an electronic device, all combined with a relatively low operational cost. To advance in this quest, here we analyze the capacity of the HEENS hardware architecture to operate in a similar manner as an in vitro neuronal network grown in the laboratory. For that, we considered data of spontaneous activity in living neuronal cultures of about 400 neurons and compared their collective dynamics and functional behavior with those obtained from direct numerical simulations (in silico) and hardware implementations (in duris silico). The results show that HEENS is capable to mimic both the in vitro and in silico systems with high efficient-cost ratio, and on different network topological designs. Our work shows that compact low-cost hardware implementations are feasible, opening new avenues for future, highly efficient neuromorphic devices and advanced human–machine interfacing.

No Thumbnail Available
Publication

Low-Cost Non-Wearable Fall Detection System Implemented on a Single Board Computer for People in Need of Care

2024 , Vanessa Vargas , Pablo Ramos , Edwin A. Orbe , Zapata, Mireya , Valencia-Aragón, Kevin

This work aims at proposing an affordable, non-wearable system to detect falls of people in need of care. The proposal uses artificial vision based on deep learning techniques implemented on a Raspberry Pi4 4GB RAM with a High-Definition IR-CUT camera. The CNN architecture classifies detected people into five classes: fallen, crouching, sitting, standing, and lying down. When a fall is detected, the system sends an alert notification to mobile devices through the Telegram instant messaging platform. The system was evaluated considering real daily indoor activities under different conditions: outfit, lightning, and distance from camera. Results show a good trade-off between performance and cost of the system. Obtained performance metrics are: precision of 96.4%, specificity of 96.6%, accuracy of 94.8%, and sensitivity of 93.1%. Regarding privacy concerns, even though this system uses a camera, the video is not recorded or monitored by anyone, and pictures are only sent in case of fall detection. This work can contribute to reducing the fatal consequences of falls in people in need of care by providing them with prompt attention. Such a low-cost solution would be desirable, particularly in developing countries with limited or no medical alert systems and few resources.

No Thumbnail Available
Publication

Planning and Management of Fiber Optic Networks Based on a Geographic Information System: A Case in Ecuador

2025 , Miguel Vargas-Bustamante , Zapata, Mireya , Jorge Álvarez-Tello

Lean management contributes to pursuit the quality, accessibility and efficiency of healthcare institutions. Its importance of the implementation of lean management in the healthcare sector using different strategies to improve services like: the supply chain in hospitals. In this review was used the model proposed by seuring and gold based on the analyze a sample of articles indexed in Scopus, web of science and also the simulation tool was used to in order to illustrate the approach. After implementation of lean thinking in different hospital in some countries improves the structure, process and outcome of care and management actions and management in healthcare promotes advantages in terms of quality, safety and efficiency of healthcare in hospitals

No Thumbnail Available
Publication

Design and Implementation of a Wastewater Heat Recovery System Prototype for Electric Showers in Quito-Ecuador

2020 , Remache Vinueza, Byron , Calderón G.E. , Zapata, Mireya

A wastewater heat recovery system was designed and implemented in the city of Quito - Ecuador. The prototype consists of adapting a heat exchanger to recover energy from wastewater and preheat the water that enters an electric shower. A temperature control system was designed and adapted to work based on a preset comfort temperature. A procedure for the manufacture of copper U-pipe fittings was developed for the construction of the heat exchanger coil, which consists of freezing water inside the pipe so that when rolled it avoids crushing and excessive loss of the inner diameter. Results show that for an average family of 4 members a reduction of energy consumption by 57% is possible. For the case of Ecuador, a reduction of 56.69 Mt of equivalent CO2 emissions was estimated if the system was implemented across the country. A payback period of 8.35 years was calculated for the initial investment. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

No Thumbnail Available
Publication

Optimizing Agriculture with LoRaWAN and HCI: A Smart Approach to Sustainable Farming

2025 , Valencia-Aragón, Kevin , Zapata, Mireya , Cristopher Toapanta , Arias Flores, Hugo Patricio

Modern agriculture faces challenges including water scarcity, excessive fertilizer use, and limited connectivity in rural areas, all exacerbated by climate change. This paper presents a smart agriculture system leveraging LoRaWAN technology and human-computer interfaces (HCI) to address these issues. The proposed system integrates low-cost sensors, a LoRaWAN-based network, and a user-friendly dashboard for real-time monitoring of critical variables such as soil moisture, ambient humidity and temperature. A proof-of-concept implementation demonstrates the system’s effectiveness in optimizing water and fertilizer use while maintaining scalability for large agricultural operations. The system operates reliably within rural environments without relying on traditional internet infrastructure, offering an affordable and sustainable solution. Field tests validate the system’s performance, highlighting its potential to enhance decision-making and resource efficiency in floriculture and beyond. Future work aims to expand the system’s capabilities with additional sensors, artificial intelligence for predictive analytics, and automated control mechanisms, further supporting sustainable farming practices.

No Thumbnail Available
Publication

Real-time execution of SNN models with synaptic plasticity for handwritten digit recognition on SIMD hardware

2024 , Bernardo Vallejo-Mancero , Jordi Madrenas , Zapata, Mireya

Recent advancements in neuromorphic computing have led to the development of hardware architectures inspired by Spiking Neural Networks (SNNs) to emulate the efficiency and parallel processing capabilities of the human brain. This work focuses on testing the HEENS architecture, specifically designed for high parallel processing and biological realism in SNN emulation, implemented on a ZYNQ family FPGA. The study applies this architecture to the classification of digits using the well-known MNIST database. The image resolutions were adjusted to match HEENS' processing capacity. Results were compared with existing work, demonstrating HEENS' performance comparable to other solutions. This study highlights the importance of balancing accuracy and efficiency in the execution of applications. HEENS offers a flexible solution for SNN emulation, allowing for the implementation of programmable neural and synaptic models. It encourages the exploration of novel algorithms and network architectures, providing an alternative for real-time processing with efficient energy consumption.

No Thumbnail Available
Publication

Mechanical Design of a Spatial Mechanism for the Robot Head Configuration in Social Robotics

2020 , Alvarez-Tello, Jorge , Zapata, Mireya , Paillacho D.

The manuscript presents the mechanical design of the head configuration in the Human Robot Interaction (HRI) used for the message transmission of emotions through nonverbal communications styles. The evolution of this structure results on a natural movement reproduction for the implementation of non-verbal communication strategies in a normal behavior, achieve the main patterns to evaluate the social interaction with the robotic platform. The mechanical design result from a biomechanical evaluation of the Pitch, Roll, and Yaw trajectories of the human head and neck. The spatial mechanisms, according to the Grübber formula for Spatial Robots, allows 4 degrees of freedom. The spatial chain has universal, prismatic, spiral and revolute joins of the mechanical model-ling. This CAD model permit the 3D print of cardan elements to performance the structure of the mechanisms. The appearance is friendly and the interface reach similar capabilities than a human would have for communication. Finally, human interaction through the head movement gives the opportunity in the future for the evaluation of more parameters of the social robotic interaction between robots-humans and robots-robots. © Springer Nature Switzerland AG 2020.

No Thumbnail Available
Publication

Enhancing mathematics learning with 3D augmented reality escape room

2024 , Zapata, Mireya , Ramos Galarza, Carlos , Valencia-Aragón, Kevin , Lidia Guachi

Learning mathematics is a challenge for many students, especially because of the traditionalist method with which its contents are taught. To a large extent, mathematics classes generate little motivation in students, so in this research, a novel technological method based on augmented reality is applied to improve the mathematics learning process, particularly the techniques of solving systems of linear equations. The research design used was a two-phase mixed sequential confirmatory type. The research worked with a sample of 65 students (Mage=17.72, SD=0.65; 58.5% female and 41.5% male). In the first phase, a quasi-experimental study was designed with an experimental group (M=32) and a control group (M=33). The experimental group received a mathematics teaching and learning intervention based on augmented reality vs. the control group, which received a traditional educational process. The experimental group showed improvements in acquired knowledge and motivation compared to the control group students. In the qualitative phase, two focus groups were conducted with students from their respective groups. In the experimental group, the following categories were identified: interesting, fun, innovative, and entertaining. The control group identified the following categories: little attention, low interest in learning, tired knowledge, and lack of motivation. The results are discussed in relation to the need to generate educational processes that benefit mathematics learning

No Thumbnail Available
Publication

MobileTestPro: Testing Framework for Mobile Application

2025 , Jorge Romero-Collaguazo , Danilo Martinez , Zapata, Mireya , Xavier Ferre

In the last decade, both the mobile market and app development have seen exponential growth, with millions of apps in online stores and billions of downloads recorded. Several development processes are used for app development, with agile approaches being the best fit for the market model. However, there is a weakness in testing activities and tasks. To provide a tool to improve software quality, we present a proposal for a framework for software testing in apps. Our proposal combines a series of tools used to evaluate an application in key areas such as consistency, security, compatibility, stress, among others, the development activities that provide a deliverable, and Mobile Ilities. To evaluate the feasibility of using the proposal, a toy app was used. The results reflect situations where the app’s behavior is not desired and its relationship with mobile ilities. The main contribution of the paper is to guide app developers in evaluating apps and contributing to improving app quality.

No Thumbnail Available
Publication

Attentional responses in toddlers: A protocol for assessing the impact of a robotic animated animal and a real dog

2025 , Zapata, Mireya , Ramos Galarza, Carlos , Kevin Valencia-Aragón , Jorge Alvarez-Tello , Maheshkumar Baladaniya

Attentional processes in toddlers are characterized by a state of alertness in which they focus their waking state for short periods. It is essential to develop assessment and attention stimulation protocols from an early age to improve this cognitive function and detect possible deficits in the early stages of cognitive development. Methods: This protocol-based article presents a technological approach to assessing the impact of two animated stimuli on toddlers’ attention. The protocol involves presenting a robotic and a real dog to evaluate attentional activation in early development. This dual-stimulus framework may also inform therapeutic and educational programs aimed at fostering cognitive growth in early childhood. Discussion: This protocol contributes to assessing physiological attentional responses in toddlers, offering insights into attention evaluation and stimulation during early cognitive development. By incorporating both a robotic and a live dog, it enables the exploration of individual differences in attentional engagement and identifies which stimulus elicits a stronger response.