98 Hits in 7.5 sec

Improved Ensemble-Learning Algorithm for Predictive Maintenance in the Manufacturing Process

Yu-Hsin Hung
2021 Applied Sciences  
Herein, semiconductor and blister packing machine data are used separately in manufacturing data analytics. The former data help in predicting yield failure in a semiconductor manufacturing process.  ...  Thus, the proposed method provides a practical approach for PDM in semiconductor manufacturing processes and blister packing machines.  ...  We successfully used the proposed method and ensemble-learning module in the semiconductor manufacturing process and the blister packing machine process.  ... 
doi:10.3390/app11156832 fatcat:luage4rgqngu5ce5z3koputp4a

An analytics-based method for performance anomaly classification in cyber-physical systems

Hugo Meyer, Uraz Odyurt, Andy D. Pimentel, Evangelos Paradas, Ignacio Gonzalez Alonso
2020 Proceedings of the 35th Annual ACM Symposium on Applied Computing  
ACKNOWLEDGMENTS This paper is composed as part of the research project 14208, titled "Interactive DSL for Composable EFB Adaptation using Bi-simulation and Extrinsic Coordination (iDAPT)", funded by The  ...  We have also described our experimental set-up and our anomaly detection method, based on process behaviour classification.  ...  We are the first, as far as we know, to study online anomaly detection methods in the context of industrial CPS using concepts such as software passports and software signatures to identify deviations  ... 
doi:10.1145/3341105.3373851 dblp:conf/sac/MeyerOPPA20 fatcat:bh7wlytsqffgzlwvz4p5tijtre

Quality prediction modeling for multistage manufacturing based on classification and association rule mining

Hung-An Kao, Yan-Shou Hsieh, Cheng-Hui Chen, Jay Lee, Gow-Yi Tzou
2017 MATEC Web of Conferences  
The method is demonstrated on a semiconductor data set.  ...  Nowadays, impressive progress has been made in process monitoring and industrial data analysis because of the Industry 4.0 trend.  ...  Data pre-processing Since manufacturing environment may have lot of anomaly events and situations, data pre-processing including cleaning and normalization is important.  ... 
doi:10.1051/matecconf/201712300029 fatcat:n6afnoa4xvd6xgpbwk6mad6d2y

Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects

Angelos Angelopoulos, Emmanouel T. Michailidis, Nikolaos Nomikos, Panagiotis Trakadas, Antonis Hatziefremidis, Stamatis Voliotis, Theodore Zahariadis
2019 Sensors  
In this survey, we focus on the vital processes of fault detection, prediction and prevention in Industry 4.0 and present recent developments in ML-based solutions.  ...  Towards this end, a detailed overview of ML-based human–machine interaction techniques is provided, allowing humans to be in-the-loop of the manufacturing processes in a symbiotic manner with minimal errors  ...  Detailed comparisons between ML methods were presented in Reference [47] for fault detection in semiconductor manufacturing with imbalanced data.  ... 
doi:10.3390/s20010109 pmid:31878065 pmcid:PMC6983262 fatcat:n4muoguq5jalrfwqkq4264vswe

A Review of Data Mining Applications in Semiconductor Manufacturing

Pedro Espadinha-Cruz, Radu Godina, Eduardo M. G. Rodrigues
2021 Processes  
The size of the semiconductors signifies a high number of units can be produced, which require huge amounts of data in order to be able to control and improve the semiconductor manufacturing process.  ...  Therefore, in this paper a structured review is made through a sample of 137 papers of the published articles in the scientific community regarding data mining applications in semiconductor manufacturing  ...  - [96] AdaBoost Tree-based method An altered AdaBoost tree-based method for defective products identification in wafer testing process Synthetic Minority Oversampling Technique (SMOTE) + Edited Nearest  ... 
doi:10.3390/pr9020305 fatcat:jyxg4mt3gvbahnu3snh4i3rxvm

AI-based Modeling and Data-driven Evaluation for Smart Manufacturing Processes [article]

Mohammadhossein Ghahramani, Yan Qiao, MengChu Zhou, Adrian OHagan, James Sweeney
2020 arXiv   pre-print
We propose a dynamic algorithm for gaining useful insights about semiconductor manufacturing processes and to address various challenges.  ...  With the widespread increase in deploying Industrial Internet of Things (IIoT) sensors in manufacturing processes, there is a progressive need for optimal and effective approaches to data management.  ...  ., anomaly detection methods, are employed. Finally, data acquisition and real-time processing are performed at the Production Process level and Sensing level, respectively.  ... 
arXiv:2008.12987v1 fatcat:shcmi54ju5flrjavuh77gxvpvq

Network Anomaly Detection and User Behavior Analysis using Machine Learning

Priti H. Vadgaonkar
2020 International Journal of Computer Applications  
In this study, the focus is to detect network anomaly using machine learning methods.  ...  Although signature-based detection methods are used to avert these attacks, they are failed against zero-day attacks.  ...  [14] give a deep-learning approach to fault monitoring in semiconductor manufacturing. A Stacked denoising Auto-encoder (SdA) approach is used to provide an unsupervised learning solution.  ... 
doi:10.5120/ijca2020920635 fatcat:o3mpakpe4rdshamg37txw6v74a

Pattern Detection Model Using a Deep Learning Algorithm for Power Data Analysis in Abnormal Conditions

Jeong-Hee Lee, Jongseok Kang, We Shim, Hyun-Sang Chung, Tae-Eung Sung
2020 Electronics  
Our proposition for the model and our method of preprocessing the data greatly helps in understanding the abnormal pattern of unlabeled big data produced at the manufacturing site, and can be a strong  ...  Building a pattern detection model using a deep learning algorithm for data collected from manufacturing sites is an effective way for to perform decision-making and assess business feasibility for enterprises  ...  which enables us to detect anomalies that cannot be found in the existing time domain.  ... 
doi:10.3390/electronics9071140 fatcat:3xe6zmikk5h3xiuh7ez3patimy

Application of Machine Learning Techniques in Injection Molding Quality Prediction: Implications on Sustainable Manufacturing Industry

Hail Jung, Jinsu Jeon, Dahui Choi, Jung-Ywn Park
2021 Sustainability  
In this manner, this article may be helpful for businesses that are considering the significance of machine learning algorithms in their manufacturing processes.  ...  With sustainable growth highlighted as a key to success in Industry 4.0, manufacturing companies attempt to optimize production efficiency.  ...  Acknowledgments: We thank Hanguk Mold for providing the manufacturing data. We also thank Inter X for preprocessing the data and providing us the rich data for analysis.  ... 
doi:10.3390/su13084120 fatcat:fyiwe5zh2jduph2wevyo5hp24a

Deep learning combined with de-noising data for network intrusion detection

Phai Vu Dinh, Tran Nguyen Ngoc, Nathan Shone, Aine MacDermott, Qi Shi
2017 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES)  
Anomaly-based Network Intrusion Detection Systems (NIDSs) are a common security defense for modern networks. The success of their operation depends upon vast quantities of training data.  ...  Promising results have been obtained from our model thus far, demonstrating improvements over existing approaches and the strong potential for use in modern NIDSs.  ...  In addition, there is other relevant work, including the fault monitoring in semiconductor manufacturing as proposed by Lee et al. [19] .  ... 
doi:10.1109/iesys.2017.8233561 fatcat:dj6k6f3vw5ezpmnfh6jk6m4e3a


2021 2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)  
Manli Zhang, Min Wu, Shengnan Tian, Jinhua She 734 Anomaly Detection Method Based on Multi-criteria Evaluation for Energy Data of Steel Industry ……...……………………………………………………………….Hao Wu, Feng Jin, Jun Zhao  ...  with Application to Fault Diagnosis…………………….Yanlin He, Lilong Liang, Yuan Xu, Qunxiong Zhu 463 Auto-Detection of Tibial Plateau Angle in Canine Radiographs Using a Deep Learning Approach……………………….Masuda  ... 
doi:10.1109/ddcls52934.2021.9455485 fatcat:7n7tpgqsuvg55og6dwwuj6g2xe


Phaik-Ling Ong, Yun-Huoy Choo, Azah Kamilah Muda
2015 Jurnal Teknologi  
The goal of using weighted support is to make use of the weight in the mining process and priorities the selection of the selection of targeted itemsets according to their significance, rather than frequency  ...  Graphical abstract Abstract Root cause analysis is key issue for manufacturing processes.  ...  Statistical Process Control (SPC) [11] [12] and Design of Experiments (DOE) [13] are very common statistical methods to detect and analyze variations in manufacturing process.  ... 
doi:10.11113/jt.v77.6496 fatcat:7r6ou7il7nawrov5nhcymu6rei

An Automobile Environment Detection System Based on Deep Neural Network and its Implementation Using IoT-Enabled In-Vehicle Air Quality Sensors

Jae-joon Chung, Hyun-Jung Kim
2020 Sustainability  
The deep network employs long short-term memory (LSTM), skip-generative adversarial network (GAN), and variational auto-encoder (VAE) models to build an air quality anomaly detection model.  ...  Multimodal signals are collected by the assistant using five sensors that measure the levels of CO, CO2, and particulate matter (PM), as well as the temperature and humidity.  ...  Generally, the model is trained using only normal data and is then applied to the test data [47] . Unsupervised anomaly detection is the most widely used anomaly detection method for unlabeled data.  ... 
doi:10.3390/su12062475 fatcat:evpix6gvn5cf5dnpk7rwt532ju

Handling imbalanced datasets through Optimum-Path Forest

Leandro Aparecido Passos, Danilo S. Jodas, Luiz C.F. Ribeiro, Marco Akio, Andre Nunes de Souza, João Paulo Papa
2022 Knowledge-Based Systems  
In this paper, we propose three OPF-based strategies to deal with the imbalance problem: the O^2PF and the OPF-US, which are novel approaches for oversampling and undersampling, respectively, as well as  ...  Despite the considerable amount of machine learning methods, a graph-based approach has attracted considerable notoriety due to the outstanding performance over many applications, i.e., the Optimum-Path  ...  Each sample is composed of 10 numerical attributes. • Secom 11 : it is omposed of 1, 567 samples from a semiconductor manufacturing process with 591 features each, where 104 samples denote fail in a manufacturing  ... 
doi:10.1016/j.knosys.2022.108445 fatcat:x4f2csarxzdf3nq6qhq2i5jmda

A Review of Data Mining with Big Data towards Its Applications in the Electronics Industry

Shengping Lv, Hoyeol Kim, Binbin Zheng, Hong Jin
2018 Applied Sciences  
data handling, applications of DM, or Big Data at different lifecycle stages, and the software used in the applications.  ...  Abstract: Data mining (DM) with Big Data has been widely used in the lifecycle of electronic products that range from the design and production stages to the service stage.  ...  detection, and anomaly detection.  ... 
doi:10.3390/app8040582 fatcat:o4ohxbymuzcudbb7wx6uffmloi
« Previous Showing results 1 — 15 out of 98 results