Erick-Alejandro González-Barbosa

Automated wildlife monitoring systems are essential for studying bat populations in natural environments, where nocturnal behavior, high flight speeds, and limited illumination make conventional observation difficult. This paper presents a modular multi-sensor vision system that integrates RGB, near-infrared (NIR), and depth cameras for automated bat monitoring. The proposed architecture consists of one main module and two secondary modules that can be configured into multiple operating modes according to monitoring requirements. The main module operates independently to perform real-time habitat reconstruction using an integrated depth camera or bat detection using a YOLO-based model. When combined with one secondary module, it forms a stereo vision system for three-dimensional localization; when combined with both secondary modules, it generates panoramic images that substantially expand the field of view for monitoring large cave entrances and other complex environments. The proposed modular architecture enables flexible deployment while supporting multiple sensing configurations within a single platform. The modular design provides scalability, geometric consistency through multi-sensor calibration, and flexible deployment, enabling accurate bat detection, habitat reconstruction, and wide-area monitoring within a unified sensing framework. The proposed system provides a versatile and scalable solution for adapting wildlife monitoring to different environmental conditions and observation scenarios. Experimental results demonstrate a detection precision of 0.893, a panoramic field of view of 119°, and real-time processing at 60 fps, validating the effectiveness of the proposed modular architecture.

Bats are ecologically vital mammals, serving as pollinators, seed dispersers, and bioindicators of ecosystem health. Many species inhabit natural caves, which offer optimal conditions for survival but present challenges for direct ecological monitoring due to their dark, complex, and inaccessible environments. Traditional monitoring methods, such as mist-netting, are invasive and limited in scope, highlighting the need for non-intrusive alternatives. In this work, we present a portable multisensor platform designed to operate in underground habitats. The system captures multimodal data, including near-infrared (NIR) imagery, ultrasonic audio, 3D structural data, and RGB video. Focusing on NIR imagery, we evaluate the effectiveness of the YOLO object detection framework for automated bat detection and counting. Experiments were conducted using a dataset of NIR images collected in natural shelters. Three YOLO variants (v10, v11, and v12) were trained and tested on this dataset. The models achieved high detection accuracy, with YOLO v12m reaching a mean average precision (mAP) of 0.981. These results demonstrate that combining NIR imaging with deep learning enables accurate and non-invasive monitoring of bats in challenging environments. The proposed approach offers a scalable tool for ecological research and conservation, supporting population assessment and behavioral studies without disturbing bat colonies.

The study aimed to establish effective tools and methodologies for optimizing the bending process of metal wires, particularly focusing on the performance of SUS304 stainless steel in manufacturing torsion springs. This includes addressing challenges like spring-back and ensuring product quality and lifespan. The research employed a combination of analytical approaches, computer simulations using the Finite Element Method (FEM), and mechanical tests to validate the bending process. The mathematical analysis provided a theoretical framework, while FEA simulations allowed for the assessment of stress distribution and strain during bending. The simulations indicated that strains were distributed over a larger fiber than initially assumed, allowing for smaller bending radii without compromising material integrity. Using analytical models and supported by FEM, the study identified an effective range of bending radius values based on mechanical properties and wire radius. Laboratory tests confirmed that the bending process can be executed effectively, with no defects observed in the wire bending. Experimental tests validated these findings, showing consistent improvement in the accuracy, structural integrity, and durability of the formed wires. These results provide practical guidance for manufacturers seeking enhanced product quality and performance.

Context: Optical fiber ground wires (OPGWs) sometimes melt and rupture when exposed to extreme conditions, such as atmospheric discharges, short circuits, and corrosive agents, that affect their electrical and mechanical properties. These conditions depend on the geographical area where the cable is installed, with the most critical being industrial and coastal zones as well as marine and mountainous environments. This research analyzes a cable rupture due to lightning strikes from a coastal zone. Method: The analysis discusses cable selection criteria based on engineering specifications. It also discusses standardized test methods and procedures. The tests performed are based on visual and dimensional inspections, mechanical stress assessments, and chemical analysis. Results: The complete analysis allows determining the necessary basis for the characterization and mathematical parameterization of OPGWs, establishing considerations that contribute to proper functioning in order to reduce communication and power supply interruptions. Conclusions: This study helps to estimate the behavior of the entire structure and the quality of failed OPGWs, providing insights into improving cable design and maintenance practices in harsh environments.

In the modern industry, computer modeling and simulation tools have become fundamental to estimating the behavior of rotodynamic systems. These computational tools allow analyzing possible modifications as well as alternative solutions to changes in design, with the aim of improving performance. Nowadays, rotodynamic systems, present in various industrial applications, require greater efficiency and reliability. Although there are deep learning methodologies for monitoring and diagnosing failures which improve these standards, the main challenge is the lack of databases for learning, a problem that can be addressed through experimental monitoring and computer analysis. This work analyzes the vibrations of two induced-draft fans with excess vibration in a thermoelectric plant in Mexico. A vibration analysis was carried out through the instrumentation and monitoring of accelerometers located at crucial points in the fans. The results of this experimental analysis were validated by computer simulation based on FEM. The results show that the operating speed of the induced-draft fans is very close to their natural frequency, causing considerable stress and potential failures due to excessive vibration. Finally, this work presents a practical solution to modify the natural frequency of induced-draft fans, so that they can function correctly at the required operating speed, thus mitigating excessive vibration issues.

Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy.

This article presents a methodology to reduce the energy consumption of an industrial robot. We propose a design for a 3R serial manipulator of general geometry. We show an analytical model aiming to analyze the search space of architectures based on the torsion angles of the robot to determine the optimal architecture that allows the efficient use of energy. The analytical model provides a theoretical estimation of the energy consumption and is validated by monitoring the experimental robot. The numerical calculations obtained with a particular case reduced the energy consumption by approximately 7.5%.

Traditionally farmers monitor their crops employing their senses and experience. However, the human sensory system is inconsistent due to stress, health, and age. In this paper, we propose an agronomic application for monitoring the growth of Portos tomato seedlings using Kinect 2.0 to build a more accurate, cost-effective, and portable system. The proposed methodology classifies the tomato seedlings into four categories: The first corresponds to the seedling with normal growth at the time of germination; the second corresponds to germination that occurred days after; the third category entails exceedingly late germination where its growth will be outside of the estimated harvest time; the fourth category corresponds to seedlings that did not germinate. Typically, an expert performs this classification by analyzing ten percent of the randomly selected seedlings. In this work, we studied different methods of segmentation and classification where the Gaussian Mixture Model (GMM) and Decision Tree Classifier (DTC) showed the best performance in segmenting and classifying Portos tomato seedlings.