5 research outputs found
Development and Optimisation of Drying Parameters for Low-Cost Hybrid Solar Dryer Using Response Surface Method
No full textA Shoveling-related Pain Intensity Prediction Expert System for Workers’ Manual Movement of Material
No full textIn
this study, a fuzzy-based expert system called the Pain Intensity Prediction
Expert System (PIPES) was developed to predict pain severity risk (PSR) in
shoveling-related tasks. The primary objective was to develop a non-changing rating risk assessment ergonomics
tool that both efficient
and comparable with those obtained from human ergonomics experts in the field
of application. PIPES used fuzzy set
theory (FST) to make decisions about the level of pain associated with a
selected worker base on the measured task variables, namely scooping rate, scooping time, shovel load, and
throw distance as input and PSR as the result. Values obtained from variable measurements from a sand shoveling task
were run with PIPES, and the results were compared with the workers’
self-reported pain (WSRP) intensity using a numeric rating scale (NRS) tool. The result of validation showed that there was a
strong positive relationship between WSRP NRS and PIPES NRS, with a correlation
coefficient of 0.70. The independent sample t-test for mean difference showed that WSRP had a statistically significantly lower level of NRS (4.35 ± 2.1)
compared to PIPES (4.75 ± 2.2), t (38) = - 0.591, p = 0.558. With a
significance level of 0.001 at 95% confidence, the groups’ means were not
significantly different. The study developed an expert system, PIPES, which can be used as a computerized
representation of ergonomics experts, who are scarce. PIPES can be applied to construction industries, sand mine locations,
and any workplace where materials are manually moved using a shovel
Effects of Graphene Nanoplatelets Dispersion on the Enhancement of Tensile Strength, Thermal and Electrical Conductivity of Polymer Nano-Composites
No full textMulti-agent reinforcement learning framework for autonomous traffic signal control in smart cities
No full textIntroductionThe increasing urbanization across the world necessitate efficient traffic management especially in the emerging economies. This paper presents an intelligent framework aimed at enhancing traffic signal management within complex road networks through the creation and evaluation of a multi-agent reinforcement learning (MARL) framework.MethodsThe research explored how Reinforcement Learning (RL) algorithms can be employed to optimize the flow of traffic, lessen bottleneck, and enhance overall transportation safety and efficiency. Additionally, the research explored the design and simulation of a typical traffic environment that is, an intersection, defined and implemented a Multi-Agent System (MAS), and developed a Multi-Agent reinforcement learning model for traffic management within a simulated environment this model leverages actor-critics and deep Q Network (DQN) strategies for learning and coordination, and performed the evaluation of the MARL model. Novel approaches for decentralized decision-making and dynamic resource allocation were developed to enable real-time adaptation to changing traffic conditions and emergent situations. Performance evaluation using metrics such as waiting time, queue length, and congestion were carried out in the SUMO simulation platforms (Simulation of Urban Mobility) to evaluate the efficiency of the proposed solution in various traffic scenarios.Results and DiscussionThe outcome of the simulation conducted in this study showed an improvement in queue management and traffic flow by 64.5% and 70.0% respectively with improvement in performance of the proposed model over the episodes. The results show that the RL model policy showed better performance compared to the baseline policy, indicating that the model learned over different episodes. The results also show that the MARL-based approach performs better for decentralized traffic control systems in both scalability and adaptability. The proposed solution supports real-time decision-making, reduces traffic congestion, and improves the efficiency of the urban transportation system
Diseño de prototipo de sistema para control de planta invasiva en cuerpos de agua
No full textTrabajo de InvestigaciónEn este trabajo de investigación se hizo el estudio y diseño de un prototipo acuático para poder recolectar plantas invasivas en cuerpos de agua, por medio de sistema de control remoto, sistema de posición y propulsión del prototipo. (Tomado de la fuente).PregradoIngeniero Electrónico de TelecomunicacionesINTRODUCCIÓN
1. ANTECEDENTES
2. PLANTEAMIENTO DEL PROBLEMA
3. JUSTIFICACIÓN
4. OBJETIVOS
5. ALCANCES Y LIMITACIONES
6. MARCO DE REFERENCIA
7. MARCO TEÓRICO
8. METODOLOGÍA
9. DESARROLLO
10. RESULTADOS Y ANÁLISIS DE RESULTADOS
11. CONCLUSIONES
12. REFERENCIA
