Structure Optimization of Ensemble Learning Methods and Seasonal Decomposition Approaches to Energy Price Forecasting in Latin America: A Case Study about Mexico

This review delves into the critical role of automation and sensor technologies in optimizing parameters for thermal treatments within electrical power generation. The demand for efficient and sustainable power generation has led to a significant reliance on thermal treatments in power plants. However, ensuring precise control over these treatments remains challenging, necessitating the integration of advanced automation and sensor systems. This paper evaluates the pivotal aspects of automation, emphasizing its capacity to streamline operations, enhance safety, and optimize energy efficiency in thermal treatment processes. Additionally, it highlights the indispensable role of sensors in monitoring and regulating crucial parameters, such as temperature, pressure, and flow rates. These sensors enable real-time data acquisition, facilitating immediate adjustments to maintain optimal operating conditions and prevent system failures. It explores the recent technological advancements, including machine learning algorithms and IoT integration, which have revolutionized automation and sensor capabilities in thermal treatment control. Incorporating these innovations has significantly improved the precision and adaptability of control systems, resulting in heightened performance and reduced environmental impact. This review underscores the imperative nature of automation and sensor technologies in thermal treatments for electrical power generation, emphasizing their pivotal role in enhancing operational efficiency, ensuring reliability, and advancing sustainability in power generation processes.

Section: Artificial Intelligence Applicationsmentioning

confidence: 99%

A Review of Automation and Sensors: Parameter Control of Thermal Treatments for Electrical Power Generation

Buratto,

Muniz,

Nied

et al. 2024

“…Their approach reduced the cost and improved the quality control efficiency for insulators, which is crucial for their efficient production and confident operation. Models based on the ensemble approach are promising as they usually need less computational effort compared to deep learning [ 58 ].…”

Section: Related Workmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Klaar,

Seman,

Mariani

et al. 2024

Self Cite

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from the time series data. This paper proposes a combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods, combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

“…Another frequently used strategy is that of streams, in which various types of input are processed in different networks, the most common is the two-stream network that processes RGB video frames in one and an optical stream in the other; Hao and Zhang employed this architecture [ 29 ]. The use of artificial intelligence models is growing in line with increased processing power, making deep learning applications increasingly popular [ 30 ]; these applications include time series prediction [ 31 , 32 , 33 ] and classification, especially in computer vision [ 34 , 35 , 36 ].…”

Section: Related Workmentioning

confidence: 99%

Video-Based Human Activity Recognition Using Deep Learning Approaches

Surek

Seman

Stefenon

et al. 2023

Self Cite

Due to its capacity to gather vast, high-level data about human activity from wearable or stationary sensors, human activity recognition substantially impacts people’s day-to-day lives. Multiple people and things may be seen acting in the video, dispersed throughout the frame in various places. Because of this, modeling the interactions between many entities in spatial dimensions is necessary for visual reasoning in the action recognition task. The main aim of this paper is to evaluate and map the current scenario of human actions in red, green, and blue videos, based on deep learning models. A residual network (ResNet) and a vision transformer architecture (ViT) with a semi-supervised learning approach are evaluated. The DINO (self-DIstillation with NO labels) is used to enhance the potential of the ResNet and ViT. The evaluated benchmark is the human motion database (HMDB51), which tries to better capture the richness and complexity of human actions. The obtained results for video classification with the proposed ViT are promising based on performance metrics and results from the recent literature. The results obtained using a bi-dimensional ViT with long short-term memory demonstrated great performance in human action recognition when applied to the HMDB51 dataset. The mentioned architecture presented 96.7 ± 0.35% and 41.0 ± 0.27% in terms of accuracy (mean ± standard deviation values) in the train and test phases of the HMDB51 dataset, respectively.