Data Preprocessing Combination to Improve the Performance of Quality Classification in the Manufacturing Process

Abstract

The recent introduction of smart manufacturing, also called the ‘smart factory’, has made it possible to collect a significant number of multi-variate data from Internet of Things devices or sensors. Quality control using these data in the manufacturing process can play a major role in preventing unexpected time and economic losses. However, the extraction of information about the manufacturing process is limited when there are missing values in the data and a data imbalance set. In this study, we improve the quality classification performance by solving the problem of missing values and data imbalances that can occur in the manufacturing process. This study proceeds with data cleansing, data substitution, data scaling, a data balancing model methodology, and evaluation. Five data balancing methods and a Generative Adversarial Network (GAN) were used to proceed with data imbalance processing. The proposed schemes achieved an F1 score that was 0.5 higher than the F1 score of previous studies that used the same data. The data preprocessing combination proposed in this study is intended to be used to solve the problem of missing values and imbalances that occur in the manufacturing process.

Polycystic Ovary Syndrome Detection Machine Learning Model Based on Optimized Feature Selection and Explainable Artificial Intelligence

“…Due to this, information about the minority class in the majority class is lost. By doing this, the bias towards the majority class is lessened, which enhances the performance of machine learning models [ 30 ].…”

Efficiency due to data balancing in the prediction of essential proteins

“…In this technique, the majority class of the pairs is removed. Through this process, the distance between the classes is increased which helps the classification problem easier [10]. It also helps to reduce noise.…”

Machine learning's model-agnostic interpretability on The Prediction of Students' Academic Performance in Video-Conference-Assisted Online Learning During the Covid-19 Pandemic

“…From September 2022 to January 2023, data was collected from university students at numerous universities in the Jakarta area using Google Form questionnaire. The data pre-processing step includes data quality assessment, data cleansing, data transformation, and data reduction [22]. Because all the statements in the questionnaire were previously designated as required inquiries, all inquiries must be answered, as a result, the missing value was not found during this activity.…”

“…Many previous studies focused on developing prediction models and evaluating results using the ML technique, with little attention focused on comprehending classi cation models for understanding predictive features [6][7][8][9][10][11][12][13][14][15][16][17][18]. Understanding the black-box output of a machine-learning model was crucial for computing and examining the in uence of features on individual and overall predictions, as well as evaluating useful features and investigating their interpretability and characteristics.…”

“…A model-agnostic interpretation approach, such as the SHapley Additive exPlanations (SHAP) framework, takes as inputs a dataset and several prediction models, applies these models to the data, and then determines the characteristics of data features inside each prediction model. [11].…”