Loading...
Publicado recientemente
Hybrid Convolutional Vision Transformer for Robust Low-Channel sEMG Hand Gesture Recognition: A Comparative Study with CNNs
Rodríguez Serrezuela, Ruthber (2025-12-12)
Hand gesture classification using surface electromyography (sEMG) is fundamental for prosthetic control and human–machine interaction. However, most existing studies focus on high-density recordings or large gesture sets, leaving limited evidence on performance in low-channel, reduced-gesture configurations. This study addresses this gap by comparing a classical convolutional neural network (CNN), inspired by Atzori’s design, with a Convolutional Vision Transformer (CViT) tailored for compact sEMG systems. Two datasets were evaluated: a proprietary Myo-based collection (10 subjects, 8 channels, six gestures) and a subset of NinaPro DB3 (11 transradial amputees, 12 channels, same gestures). Both models were trained using standardized preprocessing, segmentation, and balanced windowing procedures. Results show that the CNN performs robustly on homogeneous signals (Myo:94.2% accuracy) but exhibits increased variability in amputee recordings (NinaPro: 92.0%). In contrast, the CViT consistently matches or surpasses the CNN, reaching 96.6% accuracy on Myo and 94.2% on NinaPro. Statistical analyses confirm significant differences in the Myo dataset. The objective of this work is to determine whether hybrid CNN–ViT architectures provide superior robustness and generalization under low-channel sEMG conditions. Rather than proposing a new architecture, this study delivers the first systematic benchmark of CNN and CViT models across amputee and non-amputee subjects using short windows, heterogeneous signals, and identical protocols, highlighting their suitability for compact prosthetic–control systems.
Agroforestry as a strategy for soil conservation in Colombia
Saavedra Mora, David (2025-05-28)
In the tropical region of Colombia, land use and the expansion of the agricultural frontier are rapidly increasing, leading to declines in soil quality and health. Agroforestry has recently been proposed as a sustainable agricultural system that provides ecosystem services such as ecosystem restoration and soil conservation. In this context, a synthesis of the ecosystem services of agroforestry was carried out, focusing on the contributions of tree diversification and its relationship with soil conditions. The findings indicate that agroforestry systems directly provide organic matter through leaf litter, which contributes to macrofaunal richness and increases the availability of N, K, P, Mg, and Ca. Moreover, soils in agroforestry systems (SAF) represent important carbon sinks. Accordingly, the present study aims to analyze the contribution of SAF to soil conservation, as well as its role in promoting increases in arthropod and vertebrate populations and in regulating water and nutrient cycles.
Turismo patrimonial como estrategia de desarrollo local: un análisis socioeconómico de su incidencia en el municipio de San Agustín (Colombia)
Bilver Adrian Astorquiza‑Bustos; Palencia Fajardo, Ofelia; Diana Molina‑Argote (2026-08-08)
El turismo patrimonial representa una oportunidad para impulsar el desarrollo socioeconómico en regiones con fuerte identidad cultural. Este estudio examina su incidencia en la infraestructura, la competitividad y la economía local en San Agustín, Huila, a partir de un enfoque mixto basado en encuestas a turistas y actores del sector. Los resultados reflejan una alta satisfacción de los visitantes con la infraestructura (58 respuestas positivas) y un gasto promedio entre USD500 y USD750 por estancia. No obstante, los actores turísticos perciben limitaciones en accesibilidad, promoción y rentabilidad. Se encontraron correlaciones significativas entre el gasto, la duración de la visita y la percepción de seguridad. La sostenibilidad del destino se relaciona con el aprecio por el patrimonio y la colaboración local. El estudio subraya la importancia de fortalecer la infraestructura, diversificar las experiencias turísticas y fomentar una gobernanza participativa que permita equilibrar el crecimiento económico con la protección cultural.
Supporting Technology for Frozen Shoulder Rehabilitation: A Randomized Controlled Trial
Rodríguez Serrezuela, Ruthber (2026-06-07)
Adhesive capsulitis (AC), commonly known as frozen shoulder, is an enigmatic and poorly defined shoulder disorder characterized by a painful, progressive, and disabling loss of active and passive mobility in the
glenohumeral joint across multiple planes. To evaluate the effectiveness of robotic therapy in the rehabilitation of patients diagnosed with AC, a therapeutic intervention study was conducted involving 40 patients treated at the Department of Physical Medicine and Rehabilitation of the General Hospital “Dr. Juan Bruno Zayas Alfonso” in Santiago de Cuba. Patients were randomly assigned to one of two groups: robotic therapy (experimental) and regular therapy (control). The Constant–Murley (CM) scale for pain and shoulder range of motion, as well as the Disabilities of the Arm, Shoulder, and Hand (DASH) questionnaire, were measured before and after treatment. All patients treated with robotic therapy showed improvement; 70% advanced to pain grade 3 (almost normal), five to grade 2 (slight omalgia), and one subject
reached grade 4 (no pain). In the control group, however, only nine patients (45%) advanced to grade 3, and one achieved grade 4, while the rest experienced mild, moderate, or severe pain. At the conclusion of the study, the CM scale indicated excellent or good results in 20 patients, 12 of whom were in the robotic therapy group. In the experimental group, 18 patients (90%) had final DASH scores below 50%.
Obtención de Datos Climatológicos Utilizando un Sistema de Comunicación 4G Para el Cultivo de Cacao
Rafael Olaya; Mauricio Cifuentes; Aroca Trujillo, Jorge Luis (2022-01-01)
