Repositorio Nacional

La Lengua de Señas Mexicana (LSM) es la lengua utilizada por la comunidad Sorda en México, y, a menudo, subestimada y pasada por alto por la comunidad oyente, lo que resulta en la exclusión sistemática de las personas Sordas en diversos aspectos de la vida. Sin embargo, la tecnología puede desempeñar un papel fundamental en acercar a la comunidad Sorda con la comunidad oyente, promoviendo una mayor inclusión y comprensión entre ambas. El objetivo principal de este trabajo es diseñar, implementar y evaluar un sistema de reconocimiento continuo de señas estáticas en LSM mediante, visión por computadora y técnicas de aprendizaje máquina. Se establecieron objetivos específicos, que incluyen la generación de un conjunto de datos de señas estáticas, pertenecientes al alfabeto manual de la LSM, el diseño de un modelo de reconocimiento, y la evaluación del sistema, tanto en la modalidad aislada como en la continua. La metodología involucra dos evaluaciones distintas. La primera se enfoca en el reconocimiento de señas estáticas en el dominio aislado, para ello se capturaron datos de 20 participantes realizando movimientos de la mano en múltiples ángulos. Se evaluaron diversas técnicas de aprendizaje automático, destacando que el enfoque basado en Máquinas de Soporte Vectorial (SVM) obtuvo los mejores resultados (F1-Score promedio del 0.91). La segunda evaluación se concentra en el reconocimiento continuo de señas estáticas, con datos recopilados de seis participantes con diferentes niveles de competencia en LSM, logrando un rendimiento sólido con errores cercanos al 7 %. Además, se evaluó la viabilidad del sistema en aplicaciones de tiempo real, demostrando un excelente desempeño (velocidad promedio de procesamiento de 45 cuadros por segundo). A pesar de los logros alcanzados, es importante reconocer que este proyecto se centró en el reconocimiento continuo de señas estáticas en LSM. Queda pendiente, como un desafío interesante, la exploración del reconocimiento continuo de señas dinámicas en LSM para futuras investigaciones. Se considera esencial explorar enfoques orientados a la escalabilidad y aplicaciones en tiempo real en investigaciones posteriores.

This study focuses on the continuous recognition of static signs in Mexican Sign Language (Lengua de Señas Mexicana (LSM)), the language used by the Deaf community in Mexico. Despite its significance, LSM is often underestimated and overlooked, leading to the systematic exclusion of Deaf individuals in various aspects of life. The primary objective of this work is to design, implement, and evaluate a continuous static sign recognition system in LSM using computer vision and machine learning techniques. Specific goals were established, including the creation of a dataset of static signs belonging to the manual alphabet of LSM, the design of a recognition model, and the evaluation of the system in both isolated and continuous modes. The methodology involves two distinct evaluations. The first one focuses on the recognition of static signs in the isolated domain, for which data from 20 participants performing hand movements at various angles were collected. Various machine learning techniques were evaluated, with the Máquinas de Soporte Vectorial (SVM)-based approach achieving the best results (average F1-Score of 0.91). The second evaluation centers on the continuous recognition of static signs, using data collected from six participants with varying levels of competence in LSM, achieving robust performance with errors close to 7 %. Furthermore, the feasibility of the system in real-time applications was assessed, demonstrating excellent performance (average processing speed of 45 frames per second). Despite the achievements, it is important to recognize that this project focused on continuous recognition of static signs in LSM. It remains an interesting challenge to explore the continuous recognition of dynamic signs in LSM for future research. It is considered essential to explore scalability-oriented approaches and real-time applications in subsequent investigations.

Lengua de Señas Mexicana (LSM), visión por computadora, aprendizaje automático, alfabeto manual de la LSM, reconocimiento automático de señas estáticas, reconocimiento aislado de señas, reconocimiento continuo de señas, aplicacion Mexican Sign Language (LSM), computer vision, machine learning, LSM manual alpahbet, automatic recognition of static signs, isolated sign recognition, continuous sign recognition, real-time aplications INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES ENSEÑANZA CON AYUDA DE ORDENADOR ENSEÑANZA CON AYUDA DE ORDENADOR

The water crisis in the south-central region of the Chihuahua State and the 1997 UN Convention

Jorge Arturo Salas Plata Mendoza Thelma J. Garcia (2022, [Artículo, Artículo])

The present writing focuses on the water crisis in the south-central part of Chihuahua State in the year 2020. Recent literature points to the drought, excess demand for the vital liquid and overpopulation of this region, among other issues, as the causes of the emergency. This paper argues that the reasons mentioned above are not causes, but effects of an economic policy of capital valorization and accumulation, which go far beyond the carrying capacity of the ecosystems and their capacity to regulate the polluting processes. The obsolescence of the water treaties between Mexico and the US make it necessary to consider other alternatives such as the 1997 UN Convention on water.

Chihuahua water crisis hydro-agricultural crisis carrying capacity expansive growth 1997 UN Convention Ecological Economics crisis del agua crisis hidroagrícola capacidad de carga crecimiento expansivo Convención de la ONU de 1997 Economía Ecológica CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA

Solar Irrigation Pump (SIP) sizing tool: user manual (Beta version)

Santosh Mali Paresh Shirsath (2022, [Libro])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA SOLAR POWERED IRRIGATION SYSTEMS PUMPS IRRIGATION WATER MANUALS

Bundling subsurface drip irrigation with no-till provides a window to integrate mung bean with intensive cereal systems for improving resource use efficiency

Manish Kakraliya madhu choudhary Mahesh Gathala Parbodh Chander Sharma ML JAT (2024, [Artículo])

The future of South Asia’s major production system (rice–wheat rotation) is at stake due to continuously aggravating pressure on groundwater aquifers and other natural resources which will further intensify with climate change. Traditional practices, conventional tillage (CT) residue burning, and indiscriminate use of groundwater with flood irrigation are the major drivers of the non-sustainability of rice–wheat (RW) system in northwest (NW) India. For designing sustainable practices in intensive cereal systems, we conducted a study on bundled practices (zero tillage, residue mulch, precise irrigation, and mung bean integration) based on multi-indicator (system productivity, profitability, and efficiency of water, nitrogen, and energy) analysis in RW system. The study showed that bundling conservation agriculture (CA) practices with subsurface drip irrigation (SDI) saved ~70 and 45% (3-year mean) of irrigation water in rice and wheat, respectively, compared to farmers’ practice/CT practice (pooled data of Sc1 and Sc2; 1,035 and 318 mm ha−1). On a 3-year system basis, CA with SDI scenarios (mean of Sc5–Sc8) saved 35.4% irrigation water under RW systems compared to their respective CA with flood irrigation (FI) scenarios (mean of Sc3 and Sc4) during the investigation irrespective of residue management. CA with FI system increased the water productivity (WPi) and its use efficiency (WUE) by ~52 and 12.3% (3-year mean), whereas SDI improved by 221.2 and 39.2% compared to farmers practice (Sc1; 0.69 kg grain m−3 and 21.39 kg grain ha−1 cm−1), respectively. Based on the 3-year mean, CA with SDI (mean of Sc5–Sc8) recorded −2.5% rice yield, whereas wheat yield was +25% compared to farmers practice (Sc1; 5.44 and 3.79 Mg ha−1) and rice and wheat yield under CA with flood irrigation were increased by +7 and + 11%, compared to their respective CT practices. Mung bean integration in Sc7 and Sc8 contributed to ~26% in crop productivity and profitability compared to farmers’ practice (Sc1) as SDI facilitated advancing the sowing time by 1 week. On a system basis, CA with SDI improved energy use efficiency (EUE) by ~70% and partial factor productivity of N by 18.4% compared to CT practices. In the RW system of NW India, CA with SDI for precise water and N management proved to be a profitable solution to address the problems of groundwater, residue burning, sustainable intensification, and input (water and energy) use with the potential for replication in large areas in NW India.

Direct Seeded Rice Subsurface Drip Irrigation Economic Profitability Energy and Nitrogen Efficiency CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CONSERVATION AGRICULTURE RICE SUBSURFACE IRRIGATION IRRIGATION SYSTEMS WATER PRODUCTIVITY ECONOMIC VIABILITY ENERGY EFFICIENCY NITROGEN-USE EFFICIENCY

Expanding the WOFOST crop model to explore options for sustainable nitrogen management: A study for winter wheat in the Netherlands

João Vasco Silva Pytrik Reidsma (2024, [Artículo])

Nitrogen (N) management is essential to ensure crop growth and to balance production, economic, and environmental objectives from farm to regional levels. This study aimed to extend the WOFOST crop model with N limited production and use the model to explore options for sustainable N management for winter wheat in the Netherlands. The extensions consisted of the simulation of crop and soil N processes, stress responses to N deficiencies, and the maximum gross CO2 assimilation rate being computed from the leaf N concentration. A new soil N module, abbreviated as SNOMIN (Soil Nitrogen for Organic and Mineral Nitrogen module) was developed. The model was calibrated and evaluated against field data. The model reproduced the measured grain dry matter in all treatments in both the calibration and evaluation data sets with a RMSE of 1.2 Mg ha−1 and the measured aboveground N uptake with a RMSE of 39 kg N ha−1. Subsequently, the model was applied in a scenario analysis exploring different pathways for sustainable N use on farmers' wheat fields in the Netherlands. Farmers' reported yield and N fertilization management practices were obtained for 141 fields in Flevoland between 2015 and 2017, representing the baseline. Actual N input and N output (amount of N in grains at harvest) were estimated for each field from these data. Water and N-limited yields and N outputs were simulated for these fields to estimate the maximum attainable yield and N output under the reported N management. The investigated scenarios included (1) closing efficiency yield gaps, (2) adjusting N input to the minimum level possible without incurring yield losses, and (3) achieving 90% of the simulated water-limited yield. Scenarios 2 and 3 were devised to allow for soil N mining (2a and 3a) and to not allow for soil N mining (2b and 3b). The results of the scenario analysis show that the largest N surplus reductions without soil N mining, relative to the baseline, can be obtained in scenario 1, with an average of 75%. Accepting negative N surpluses (while maintaining yield) would allow maximum N input reductions of 84 kg N ha−1 (39%) on average (scenario 2a). However, the adjustment in N input for these pathways, and the resulting N surplus, varied strongly across fields, with some fields requiring greater N input than used by farmers.

Crop Growth Models WOFOST CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CROPS NITROGEN-USE EFFICIENCY WINTER WHEAT SOIL WATER

Conservation agriculture based sustainable intensification: India updates

ML JAT (2021, [Objeto de congreso])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CONSERVATION AGRICULTURE SUSTAINABLE INTENSIFICATION LAND MANAGEMENT TILLAGE PLANT ESTABLISHMENT BIOMASS WATER MANAGEMENT