Failure analysis has become an important part of guaranteeing good quality in the electronic component manufacturing process. The conclusions of a failure analysis can be used to identify a component’s flaws and to better understand the mechanisms and causes of failure, allowing for the implementation of remedial steps to improve the product’s quality and reliability. A failure reporting, analysis, and corrective action system is a method for organizations to report, classify, and evaluate failures, as well as plan corrective actions. These text feature datasets must first be preprocessed by Natural Language Processing techniques and converted to numeric by vectorization methods before starting the process of information extraction and building predictive models to predict failure conclusions of a given failure description. However, not all-textual information is useful for building predictive models suitable for failure analysis. Feature selection has been approached by several variable selection methods. Some of them have not been adapted for use in large data sets or are difficult to tune and others are not applicable to textual data. This article aims to develop a predictive model able to predict the failure conclusions using the discriminating features of the failure descriptions. For this, we propose to combine a Genetic Algorithm with supervised learning methods for an optimal prediction of the conclusions of failure in terms of the discriminant features of failure descriptions. Since we have an unbalanced dataset, we propose to apply an F1 score as a fitness function of supervised classification methods such as Decision Tree Classifier and Support Vector Machine. The suggested algorithms are called GA-DT and GA-SVM. Experiments on failure analysis textual datasets demonstrate the effectiveness of the proposed GA-DT method in creating a better predictive model of failure conclusion compared to using the information of the entire textual features or limited features selected by a genetic algorithm based on a SVM. Quantitative performances such as BLEU score and cosine similarity are used to compare the prediction performance of the different approaches.
Alarms data is a very important source of information for network operation center (NOC) teams to aggregate and display alarming events occurring within a network element. However, on a large network, a long list of alarms is generated almost continuously. Intelligent analytical reporting of these alarms is needed to help the NOC team to eliminate noise and focus on primary events. Hence, there is a need for an anomaly detection model to learn from and use historical alarms data to achieve this. It is also important to indicate the root cause of anomalies so that immediate corrective action can be taken. In this paper, we aim to design an anomaly detection model in the context of alarms data (categorical data) in the field of telecommunication and that can be used as a first step for further root cause analysis. To do this, we introduce a new algorithm to derive four features based on historical data and aggregate them to generate a final score that is optimized through supervised labels for greater accuracy. These four features reflect the likelihood of occurrence of events, the sequence of events and the importance of relatively new events not seen in the historical data. Certain assumptions are tested on the data using the relevant statistical tests. After validating these assumptions, we measure the accuracy on labelled data, revealing that the proposed algorithm performs with a high anomaly detection accuracy.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.