A Comparison of Machine Learning Methods for Extremely Unbalanced Industrial Quality Data

Pereira, Pedro; Pereira, Adriana Soares; Cortez, Paulo; Pilastri, André

doi:10.1007/978-3-030-86230-5_44

Cited by 7 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the scope of this research, the classification framework has been constructed, employing algorithms of distinct methodological underpinnings. Specifically, the selected algorithms include Naive Bayes, esteemed for its probabilistic foundation, alongside the ensemble-based Random Forest, and the individually decisive Decision Tree, each chosen for their unique attributes and relevance to the study's objectives [23][24][25][26][27].…”

Section: Model Selectionmentioning

confidence: 99%

Enhancing wildfire risk assessment through weather modeling and machine learning: a case study in Orange County, USA

Kahono

2024

p.ISST

View full text Add to dashboard Cite

Forest wildfire is a significant threat, causing extensive environmental damage and loss of life. Accurate and effective risk assessments are essential for better understanding and mitigating this risk. In this study, we propose a novel approach that combines weather modeling and machine learning for improved wildfire risk assessment. Our case study focuses on Orange County, USA, known for its high wildfire susceptibility. The methodology involves collecting historical weather and wildfire data in the region. We employ a machine learning model that integrates weather data with other factors, including vegetation and topography, to predict wildfire risk. Through machine learning techniques, we analyze the relationships among these variables and generate accurate risk predictions for Orange County. Results indicate a significant enhancement in wildfire risk assessment with this approach. The developed model provides valuable insights into the factors influencing wildfires, aiding authorities, and policymakers in implementing effective mitigation strategies. By leveraging weather modeling and machine learning, we can enhance our understanding and management of wildfire risks, safeguarding the environment and communities. This research highlights the potential of these technologies to improve wildfire mitigation efforts. The findings contribute to a proactive approach to addressing the serious threat of forest wildfires.

show abstract

Section: Model Selectionmentioning

confidence: 99%

Enhancing wildfire risk assessment through weather modeling and machine learning: a case study in Orange County, USA

Kahono

2024

p.ISST

View full text Add to dashboard Cite

show abstract

“…For all the datasets, Random UnderSampling (RUS) [69,70] is applied to balance the class distribution by making the cardinality of the majority class comparable to that of the minority class. RUS has demonstrated its effectiveness in diverse fields where the class imbalance is common, such as astrophysics [71,72], geoscience [73], and industrial informatics [74][75][76]. The algorithm randomly selects and removes observations from the majority class until it achieves the desired equilibrium between the two classes.…”

Section: Class Unbalancementioning

confidence: 99%

Predicting Machine Failures from Multivariate Time Series: An Industrial Case Study

Pinciroli Vago,

Forbicini,

Fraternali

2024

Machines

View full text Add to dashboard Cite

Non-neural machine learning (ML) and deep learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three datasets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM, and Transformers) are compared on multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure.

show abstract

“…In summary, these results are encouraging and consist of a promising research direction towards a more efficient identification of the stability of slopes, particularly for minority classes. Thus, as a future development, we intend to explore other feature selection approaches as well as different strategies to handle imbalanced data (e.g., the usage of Tomek links or Gaussian copula transformations [72]). In addition, considering the high number of data available for each of the three slope types, a deep learning approach may provide an important contribution toward the prediction models' efficiency.…”

Section: Final Remarksmentioning

confidence: 99%

An Evolutionary Neural Network Approach for Slopes Stability Assessment

Tinoco,

Gomes Correia,

Cortez

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

A current big challenge for developed or developing countries is how to keep large-scale transportation infrastructure networks operational under all conditions. Network extensions and budgetary constraints for maintenance purposes are among the main factors that make transportation network management a non-trivial task. On the other hand, the high number of parameters affecting the stability condition of engineered slopes makes their assessment even more complex and difficult to accomplish. Aiming to help achieve the more efficient management of such an important element of modern society, a first attempt at the development of a classification system for rock and soil cuttings, as well as embankments based on visual features, was made in this paper using soft computing algorithms. The achieved results, although interesting, nevertheless have some important limitations to their successful use as auxiliary tools for transportation network management tasks. Accordingly, we carried out new experiments through the combination of modern optimization and soft computing algorithms. Thus, one of the main challenges to overcome is related to the selection of the best set of input features for a feedforward neural network for earthwork hazard category (EHC) identification. We applied a genetic algorithm (GA) for this purpose. Another challenging task is related to the asymmetric distribution of the data (since typically good conditions are much more common than bad ones). To address this question, three training sampling approaches were explored: no resampling, the synthetic minority oversampling technique (SMOTE), and oversampling. Some relevant observations were taken from the optimization process, namely, the identification of which variables are more frequently selected for EHC identification. After finding the most efficient models, a detailed sensitivity analysis was applied over the selected models, allowing us to measure the relative importance of each attribute in EHC identification.

show abstract

A Comparison of Machine Learning Methods for Extremely Unbalanced Industrial Quality Data

Cited by 7 publications

References 11 publications

Enhancing wildfire risk assessment through weather modeling and machine learning: a case study in Orange County, USA

Enhancing wildfire risk assessment through weather modeling and machine learning: a case study in Orange County, USA

Predicting Machine Failures from Multivariate Time Series: An Industrial Case Study

An Evolutionary Neural Network Approach for Slopes Stability Assessment

Contact Info

Product

Resources

About