Background: Smartphone-based learning, or mobile learning (m-learning), has become a popular learning-and-teaching strategy in educational environments. Blended learning combines strategies such as m-learning with conventional learning to offer continuous training, anytime and anywhere, via innovative learning activities. Objective: The main aim of this work was to examine the short-term (ie, 2-week) effects of a blended learning method using traditional materials plus a mobile app—the iPOT mobile learning app—on knowledge, motivation, mood state, and satisfaction among undergraduate students enrolled in a health science first-degree program. Methods: The study was designed as a two-armed, prospective, single-blind, randomized controlled trial. Subjects who met the inclusion criteria were randomly assigned to either the intervention group (ie, blended learning involving traditional lectures plus m-learning via the use of the iPOT app) or the control group (ie, traditional on-site learning). For both groups, the educational program involved 13 lessons on basic health science. The iPOT app is a hybrid, multiplatform (ie, iOS and Android) smartphone app with an interactive teacher-student interface. Outcomes were measured via multiple-choice questions (ie, knowledge), the Instructional Materials Motivation Survey (ie, motivation), the Profile of Mood States scale (ie, mood state), and Likert-type questionnaires (ie, satisfaction and linguistic competence). Results: A total of 99 students were enrolled, with 49 (49%) in the intervention group and 50 (51%) in the control group. No difference was seen between the two groups in terms of theoretical knowledge gain (P=.92). However, the intervention group subjects returned significantly higher scores than the control group subjects for all postintervention assessed items via the motivation questionnaire (all P<.001). Analysis of covariance (ANCOVA) revealed a significant difference in the confusion and bewilderment component in favor of the intervention group (P=.01), but only a trend toward significance in anger and hostility as well as total score. The intervention group subjects were more satisfied than the members of the control group with respect to five out of the six items evaluated: general satisfaction (P<.001), clarity of the instructions (P<.01), clarity with the use of the learning method (P<.001), enough time to complete the proposed exercises (P<.01), and improvement in the capacity to learn content (P<.001). Finally, the intervention group subjects who were frequent users of the app showed stronger motivation, as well as increased perception of greater gains in their English-language competence, than did infrequent users. Conclusions: The blended learning method led to significant improvements in motivation, mood state, and satisfaction compared to traditional teaching, and elicited statements of subjective improvement in terms of competence in English. Trial Registration: ClinicalTrials.gov NCT03335397; https://clinicaltrials.gov/ct2/show/NCT03335397

This research proposes implementing a system to recognize the static signs of the Mexican Sign Language (MSL) dactylological alphabet using the MediaPipe frame and Convolutional Neural Network (CNN) models to correctly interpret the letters that represent the manual signals coming from a camera. The development of these types of studies allows the implementation of technological advances in artificial intelligence and computer vision in teaching Mexican Sign Language (MSL). The best CNN model achieved an accuracy of 83.63% over the sets of 336 test images. In addition, considering samples of each letter, the following results are obtained: an accuracy of 84.57%, a sensitivity of 83.33%, and a specificity of 99.17%. The advantage of this system is that it could be implemented on low-consumption equipment, carrying out the classification in real-time, contributing to the accessibility of its use.

Direct current motors are widely used in industry applications, and it has become necessary to carry out studies and experiments for their optimization. In this manuscript, a comparison between heuristic and metaheuristic algorithms is presented, specifically, the Steiglitz–McBride, Jaya, Genetic Algorithm (GA), and Grey Wolf Optimizer (GWO) algorithms. They were used to estimate the parameters of a dynamic model that approximates the actual responses of current and angular velocity of a DC motor. The inverse of the Euclidean distance between the current and velocity errors was defined as the fitness function for the metaheuristic algorithms. For a more comprehensive comparison between algorithms, other indicators such as mean squared error (MSE), standard deviation, computation time, and key points of the current and velocity responses were used. Simulations were performed with MATLAB/Simulink 2010 using the estimated parameters and compared to the experiments. The results showed that Steiglitz–McBride and GWO are better parametric estimators, performing better than Jaya and GA in real signals and nominal parameters. Indicators say that GWO is more accurate for parametric estimation, with an average MSE of 0.43%, but it requires a high computational cost. On the contrary, Steiglitz–McBride performed with an average MSE of 3.32% but required a much lower computational cost. The GWO presented an error of 1% in the dynamic response using the corresponding indicators. If a more accurate parametric estimation is required, it is recommended to use GWO; however, the heuristic algorithm performed better overall. The performance of the algorithms presented in this paper may change if different error functions are used.

This paper presents an intelligent system for the dynamic estimation of sheep body weight (BW). The methodology used to estimate body weight is based on measuring seven biometric parameters: height at withers, rump height, body length, body diagonal length, total body length, semicircumference of the abdomen, and semicircumference of the girth. A biometric parameter acquisition system was developed using a Kinect as a sensor. The results were contrasted with measurements obtained manually with a flexometer. The comparison gives an average root mean square error (RMSE) of 9.91 and a mean $R^2$ of 0.81. Subsequently, the parameters were used as input in a back-propagation artificial neural network. Performance tests were performed with different combinations to make the best choice of architecture. In this way, an intelligent body weight estimation system was obtained from biometric parameters, with a 5.8% RMSE in the weight estimations for the best architecture. This approach represents an innovative, feasible, and economical alternative to contribute to decision-making in livestock production systems.

Urban Heat Islands are a major environmental and public health concern, causing temperature increase in urban areas. This study used satellite imagery and machine learning to analyze the spatial and temporal patterns of land surface temperature distribution in the Metropolitan Area of Merida (MAM), Mexico, from 2001 to 2021. The results show that land surface temperature has increased in the MAM over the study period, while the urban footprint has expanded. The study also found a high correlation ($r>$ 0.8) between changes in land surface temperature and land cover classes (urbanization/deforestation). If the current urbanization trend continues, the difference between the land surface temperature of the MAM and its surroundings is expected to reach 3.12 °C ± 1.11 °C by the year 2030. Hence, the findings of this study suggest that the Urban Heat Island effect is a growing problem in the MAM and highlight the importance of satellite imagery and machine learning for monitoring and developing mitigation strategies.

The study of dynamic models and their parameterization remains a relevant topic in research. Motors and their models have been extensively analyzed, studied, and parameterized using various techniques due to their broad applicability in motorering and industrial settings. However, most methods for obtaining model parameters require at least two averaged signals from the motor, such as torque, current, speed, position, or acceleration. In this work, we propose the parameterization of a motor’s dynamic model using only the speed signal and the steady-state values of the variables. Through evolutionary computation, the mechanical and electrical equations of the motor are reconstructed based on this signal. This approach offers a significant advantage, as it enables parameter estimation without requiring the instrumentation needed for full current signal measurement or, alternatively, torque measurement. To achieve this, the transfer function representing the motor’s speed is utilized. The function reconstruction is performed with a Root Mean Square Error (RMSE) of less than 1% for both the speed and current signals. Since the original current signal is not required for this estimation, this work presents an innovative approach to estimating a system of dynamic equations using only a single measured variable and the dynamic relationships of its step-input response.