Hybrid systems, which combine statistical and machine learning (ML) techniques using residual (error forecasting) modeling, have been highlighted in the literature due to their accuracy and ability to forecast time series with different characteristics. In these architectures, a crucial task is the proper modeling of the residuals since they may present random fluctuations, complex nonlinear patterns, and heteroscedastic behavior. Hence, the selection, specification, and training of one ML model to forecast the residuals are costly and challenging tasks since issues, such as underfitting, overfitting, and misspecification, can lead to a system with low accuracy or even deteriorate the linear forecast of the time series. This article proposes a hybrid system, named dynamic residual forecasting (DReF), that employs a modified dynamic selection (DS) algorithm to decide: the most suitable ML model to forecast a pattern of the residual series and if it is a promising candidate to increase the accuracy of the time series forecast from the linear combination. Thus, the DReF aims to reduce the uncertainty of the ML model selection and avoid the deterioration of the time series forecast. Furthermore, the proposed system searches for the most suitable parameters of the DS algorithm for each data set. In this article, the proposed method uses a pool of five ML models widely adopted in the literature: multilayer perceptron, support vector regression, radial basis function, long short-term memory, and convolutional neural network. An experimental evaluation was conducted using ten well-known time series. The results show that the DReF obtains superior results for the majority of the data sets compared with single and hybrid models of the literature.

The development of accurate forecasting systems for real-world time series modeling is a challenging task. Due to the presence of temporal patterns that change over time, the adoption of a single model can lead to underperformed forecasts. In this scenario, Multiple Predictor Systems (MPS) emerge as an alternative to adopting single models since they struggle to learn in the presence of temporal patterns that change over time. Dynamic prediction/ensemble selection is a special case of MPS where each model is an expert in the time series's specific patterns. In dynamic selection, instead of combining all models, the most competent models per test pattern are selected. A criterion commonly used is to evaluate the models' performance in the region of competence, formed by the patterns present in the in-sample set (training or validation sets) more similar to the test pattern. Thus, the region of competence's quality is a key factor in the precision of the MPS. However, adequately defining the similarity criterion and the size of the region of competence is challenging and problem-dependent. Furthermore, there is no guarantee that similar data exist in the in-sample set. This paper proposes a dynamic selection approach entitled Dynamic Selection based on the Nearest Windows (DSNAW) that selects one or more competent models according to their performance in the region of competence composed of the nearest antecedent windows to the new target time window. This strategy assumes that the temporal windows closer to a test pattern have a behavior more similar to the target than in-sample data. The experimental study using ten well-known time series showed that the DSNAW outperforms the literature approaches.

Machine Learning-based fault detection approaches in energy systems have gained prominence for their superior performance. These automated approaches can assist operators by highlighting anomalies and faults, providing a robust framework for improving Situation Awareness. However, existing approaches predominantly rely on monolithic models, which struggle with adapting to changing data, handling imbalanced datasets, and capturing patterns in noisy environments. To overcome these challenges, this study explores the potential of Multiple Classifier System (MCS) approaches. The results demonstrate that ensemble methods generally outperform single models, with dynamic approaches like META-DES showing remarkable resilience to noise. These findings highlight the importance of model diversity and ensemble strategies in improving fault classification accuracy under real-world, noisy conditions. This research emphasizes the potential of MCS techniques as a robust solution for enhancing the reliability of fault detection systems.

Context: Image enhancement is essential for advancing Optical Character Recognition (OCR), a technology widely applied across various Information Systems (IS) to enable accurate text extraction from scanned documents, IDs, invoices, and other document types. Problem: Despite OCR’s importance, challenges such as noise, variable illumination, and low-resolution scans often compromise recognition quality, leading to distorted and inaccurate results. These issues can impact the reliability and effectiveness of IS. Solution: This study presents a methodology to improve the quality of low-resolution images by combining image filtering techniques with OpenCV, super-resolution using the BSRGAN model, and EasyOCR for character extraction. IS Theory: The research is anchored in the Information Quality theory in IS, addressing the importance of improving input data to enhance system outputs and reliability. Method: The proposed methodology consists of two main stages. First, low-resolution images are processed using the BSRGAN super-resolution model, which enhances image quality for improved OCR performance. Then, the enhanced images are processed by an OCR system to extract and convert characters into text. Validation was conducted on three datasets: Brazilian Identity Document (BID), IIIT 5K-Word, and SVHN, simulating real-world application conditions. Summary of Results: The results demonstrate the proposed methodology’s effectiveness in enhancing OCR accuracy, significantly reducing error rates in various contexts. Contributions and Impact on IS: This work contributes to the IS field by providing a solution that enhances OCR input quality, benefiting academia through advanced image processing research and the industry by enabling more reliable text recognition in practical applications.

The reliable operation of power systems depends on rapid fault detection to trigger protection mechanisms and prevent further damage. Machine Learning-based fault detection systems have gained prominence for their superior performance. These automated systems can assist operators by highlighting anomalies and faults, providing a robust framework for improving Situation Awareness. However, existing approaches predominantly rely on monolithic models, which struggle with adapting to changing data, handling imbalanced datasets, and capturing patterns in noisy environments. To overcome these challenges, this study explores the potential of Multiple Classifier System (MCS) approaches. The results demonstrate that ensemble methods generally outperform single models, with dynamic approaches like META-DES showing remarkable resilience to noise. These findings highlight the importance of model diversity and ensemble strategies in improving fault classification accuracy under real-world, noisy conditions. This research emphasizes the potential of MCS techniques as a robust solution for enhancing the reliability of fault detection systems.