Municipal Solid Waste (MSW) management presents a significant challenge for traditional separation practices, due to a considerable increase in quantity, diversity, complexity of types of solid waste, and a high demand for accuracy in classification. Image recognition and classification of waste using computer vision techniques allow for optimizing administration and collection processes with high precision, achieving intelligent management in separation and final disposal, mitigating environmental impact, and contributing to sustainable development objectives. This research consisted of evaluating and comparing the effectiveness of four Convolutional Neural Network models for MSW detection, using a Raspberry Pi 4 Model B. To this end, the models YOLOv4-tiny, YOLOv7-tiny, YOLOv8-nano, and YOLOv9-tiny were trained, and their performance was compared in terms of precision, inference speed, and resource usage in an embedded system with a custom dataset of 1883 organic and inorganic waste images, labeled with Roboflow by delimiting the area of interest for each object. Image preprocessing was applied, with resizing to 640 × 640 pixels and contrast auto-adjustments. Training considered 85% of images and testing considered 15%. Each training stage was conducted over 100 epochs, adjusting configuration parameters such as learning rate, weight decay, image rotation, and mosaics. The precision results obtained were as follows: YOLOv4-tiny, 91.71%; YOLOv7-tiny, 91.34%; YOLOv8-nano, 93%; and YOLOv9-tiny, 92%. Each model was applied in an embedded system with an HQ camera, achieving an average of 86% CPU usage and an inference time of 1900 ms. This suggests that the models are feasible for application in an intelligent container for classifying organic and inorganic waste, ensuring effective management and promoting a culture of environmental care in society.

Municipal solid waste (MSW) accumulation is a critical global challenge for society and governments, impacting environmental and social sustainability. Efficient separation of MSW is essential for resource recovery and advancing sustainable urban management practices. However, manual classification remains a slow and inefficient practice. In response, advances in artificial intelligence, particularly in machine learning, offer more precise and efficient alternative solutions to optimize this process. This research presents the development of a light deep neural network called R3sNet (three “Rs” for Reduce, Reuse, and Recycle) with residual modules trained end-to-end for the binary classification of MSW, with the capability for faster inference. The results indicate that the combination of processing techniques, optimized architecture, and training strategies contributes to an accuracy of 87% for organic waste and 94% for inorganic waste. R3sNet outperforms the pre-trained ResNet50 model by up to 6% in the classification of both organic and inorganic MSW, while also reducing the number of hyperparameters by 98.60% and GFLOPS by 65.17% compared to ResNet50. R3sNet contributes to sustainability by improving the waste separation processes, facilitating higher recycling rates, reducing landfill dependency, and promoting a circular economy. The model’s optimized computational requirements also translate into lower energy consumption during inference, making it well-suited for deployment in resource-constrained devices in smart urban environments. These advancements support the following Sustainable Development Goals (SDGs): SDG 11: Sustainable Cities and Communities, SDG 12: Responsible Consumption and Production, and SDG 13: Climate Action.

Since 2019, the Mexican Government has implemented the Sembrando Vida Program (SVP) to address environmental degradation and social marginalization in rural areas. This research analyzed the SVP’s targeting mechanisms to assess the fulfillment of its objectives in the central region of the state of Guerrero, Mexico. The methodology included an analysis of the Operating Rules; a review of the beneficiary registry; the construction of environmental, social, and economic indicators; proportional stratified sampling with a 90% confidence level; and an SVP evaluation using indicators and confidence intervals. Targeting mechanisms identified agrarian subjects aged ≥ 18 years with 2.5 hectares living below the poverty line. Changes in the indicator matrix highlight a focus on food self-sufficiency and poverty levels, among others. Key results from the indicators include 100% social recovery, 62.3% of beneficiaries increased their agricultural income, and 100% application of learned environmental techniques. The intervals showed that between 26.49–42.19% of individuals joined the agricultural sector; 55.68–71.58% diversified their crops; and 86.15–95.65% made improvements in health, housing, or education. The evaluation of the SVP demonstrated its impact on environmental preservation and the improvement of the socioeconomic well-being of the rural population in the study area.

Los modelos de Redes Neuronales Convolucionales (RNC) requieren datos procesados que aprendan patrones de imágenes para evitar la memorización. Esta investigación presenta la conformación de un dataset de 3208 imágenes de clasificación de Residuos Sólidos Urbanos (RSU) en orgánicos e inorgánicos para modelos de RNC. El procesamiento se realizó con una metodología de tres fases: 1. Identificación y selección de dataset: Kaggle y Github; 2. Creación del dataset: uniformidad de imágenes y ajustes de color; y 3. Conformación del dataset de residuos orgánicos e inorgánicos. Los resultados obtenidos fueron los conjuntos de datos de RSU orgánicos conformado por 1574 imágenes y 1634 inorgánicos. Esto permitirá el entrenamiento en modelos de Deep Learning para la clasificación binaria de RSU.

The effects of climate change have altered precipitation patterns, causing extreme weather events that impact crop yields and increase the demand for agricultural production, which drives the need to implement emerging technologies. This research presents the design, construction, and validation of a real-time monitoring system for environmental parameters in open-field avocado orchards. A four-phase methodology was employed: (1) Establishment of required parameters and construction of the IoT architecture; (2) Design of the geometry and final elaboration of the system: modeling in SolidWorks, circuit diagrams in Fritzing, and system assembly; (3) Development of a mobile application: Android Studio and development of the autoencoder model with machine learning; and (4) Validation: Evaluation of the wireless link; system implementation and deployment of the mobile application. The results obtained include a system with a transmitter node equipped with sensors and a receiver, both incorporating ESP32 and nRF24L01+PA+LNA modules, with a wireless transmission range of 2300 m. A total of 2016 data records were stored on microSD and in the cloud, which can be queried, visualized, and analyzed through the mobile application via Bluetooth or Wi-Fi; the system also detects outlier data that can be used for decision-making in the agricultural sector.

El Análisis de Clifford ha ayudado a interpretar eficientemente muchas de las ecuaciones de la Física Matemática, y en particular de la Mecánica de Medios Continuos. En el presente artículo se estudia una generalización natural del clásico operador de Lamé-Navier sobre álgebras de Clifford. El uso de operadores de Dirac construidos con bases ortonormales arbitrarias conduce a una gran variedad de sistemas de ecuaciones diferenciales parciales de interés matemático y físico. Primeramente, se estudian varias propiedades esenciales como la invariancia sobre campos k-vectoriales y la elipticidad. Además, se presenta una reescritura del sistema de Lamé-Navier en términos de los módulos longitudinal y transversal. Finalmente, se considera el problema de Dirichlet asociado a funciones que anulan dicho operador y se determina la condición que provoca que este problema, en general, sea mal planteado en el sentido de Hadamard.