Defect detection of seals in multilayer aseptic packages using deep learning

Adem, Kemal; Közkurt, Cemil

doi:10.3906/elk-1903-112

Cited by 21 publications

(9 citation statements)

References 15 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The relevant studies in this category mainly use image data (Adem & Közkurt, 2019; Kodors et al., 2020; Patsekin et al., 2019; Song et al., 2019; Vo et al., 2020), sensor data (mainly from spectroscopy and electronic noses) (Liang, Sun et al., 2020; Liu et al., 2020; Mithun et al., 2018; Tsakanikas et al., 2020; Weng et al., 2020), and text data derived from online media, emails, and reports (Mao et al., 2018; Vo et al., 2020). The most frequently used sources of unstructured data related to food safety have been reviewed recently (Jin et al., 2020; Zhou et al., 2019).…”

Section: Resultsmentioning

confidence: 99%

“…Selected studies mainly focus on the bacteria and parasites classification and identification (Adem & Közkurt, 2019;Wasikowska et al, 2018), bacteria source attribution (Lupolova et al, 2017;Munck et al, 2020;Zhang et al, 2019) and managing the presence of bacteria by controlling the food storage process (Kuzuoka et al, 2020), classification of various types of crop insects (Ayan et al, 2020;Bisgin et al, 2018), and bacteria growth (Li et al, 2013;Qin et al, 2018). Munck et al (2020)…”

Section: Biological Hazardsmentioning

confidence: 99%

See 1 more Smart Citation

Application of machine learning to the monitoring and prediction of food safety: A review

Wang

Bouzembrak

Lansink

et al. 2021

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

Machine learning (ML) has proven to be a useful technology for data analysis and modeling in a wide variety of domains, including food science and engineering. The use of ML models for the monitoring and prediction of food safety is growing in recent years. Currently, several studies have reviewed ML applications on foodborne disease and deep learning applications on food. This article presents a literature review on ML applications for monitoring and predicting food safety. The paper summarizes and categorizes ML applications in this domain, categorizes and discusses data types used for ML modeling, and provides suggestions for data sources and input variables for future ML applications. The review is based on three scientific literature databases: Scopus, CAB Abstracts, and IEEE. It includes studies that were published in English in the period from January 1, 2011 to April 1, 2021. Results show that most studies applied Bayesian networks, Neural networks, or Support vector machines. Of the various ML models reviewed, all relevant studies showed high prediction accuracy by the validation process. Based on the ML applications, this article identifies several avenues for future studies applying ML models for the monitoring and prediction of food safety, in addition to providing suggestions for data sources and input variables.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Biological Hazardsmentioning

confidence: 99%

Application of machine learning to the monitoring and prediction of food safety: A review

Wang

Bouzembrak

Lansink

et al. 2021

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

show abstract

“…Evrişimli Sinir Ağları (CNN), yapay sinir ağlarının aksine, özniteliklerin çıkarılmasına izin veren katmanlara sahip derin öğrenme yaklaşımıdır [26][27][28]. Görüntü işlemede performans sonuçları için iyi değerler üreten CNN'ler, çok katmanlı yapay sinir ağı tabanlıdır ve özelleştirilmiş derin öğrenme mimarisi yapısına sahiptir [29,30].…”

Section: Evrişimli Sinir Ağları (Convolutional Neural Network)unclassified

Çok kanallı CNN mimarisi ile X-Ray görüntülerinden COVID-19 tanısı

Yilmaz

2021

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Proposed multi-channel CNN deep learning architecture with channel selection formula  A new method for diagnosing Covid-19  High performance valuesDeep learning has been widely used in a variety of applications to solve a scope of complex problems that require extremely high accuracy and precision, especially in the medical field. In this study, the Covid-19 is diagnosed automatically using a proposed multichannel CNN method. Patients and healthy individuals' Lung X-Ray images data sets were obtained from three separate online databases. Simple recurrent networks (SRN) architecture was also applied for the same problem to compare the results and demonstrate the efficiency of the proposed method. The study proposes a new CNN-based method for early detection of Covid-19, which is a major risk to human life worldwide. Differently from the studies in the literature, the multi-channel CNN architecture with five convolution channels is proposed and the channel selection formulas are presented. It is used for selecting the most distinctive feature filters among the results produced by these channels. The architecture consists of the following components (Figure A). Figure A. Proposed model architecturePurpose: This study aims to diagnose the Covid-19 with deep learning methods to design an assistive technology system that can be used by doctors and health employee Theory and Methods: The proposed multi-channel CNN, and simple recurrent networks (SRN) models were trained on the three different dataset, which was obtained from the Kaggle data repository. The first dataset has 50 images, the second dataset has 1125 images and the third dataset has 5856 images. Their performances were compared with each other. Results:It was observed that the proposed multi-channel CNN model is better than other models in diagnosing Covid-19 with %99,41-%97,75-%96,74 accuracy, %99,554-%98,221-%96,923 F1-score and 0,89-1,13-1,92 RMSE values. The training process took 981546 seconds and the proposed model can also be used in real-time systems. Conclusion:In this study; A new method based on CNN is proposed for the early detection of Covid-19 from lung X-Ray images, which is a major risk to human life worldwide. Differently the studies in the literature, the multichannel CNN architecture with five convolution channels is proposed and the channel selection formulas is presented which are used for selecting the most distinctive feature filters among the results produced by these channels.

show abstract

“…Convolutional Neural Networks (CNNs), in contrast to the artificial neural networks, are a deep learning approach that has a layer, which allows the extraction of features [ 18,19,20,21,22]. CNNs that produce good values for performance results in image processing [23,24].…”

Section: Convolutional Neural Network (Cnns)mentioning

confidence: 99%

Risk Assessment for Cardiac Arrest : A Deep Learning Approach

Yilmaz¹

2021

Preprint

View full text Add to dashboard Cite

Background:Risk of developing cardiovascular diseases, in the world, is increasing day by day. Accordingly, the number of deaths due to heart attacks is quite remarkable. Early risk assessment and diagnosis of heart disease are vital to prevent heart attacks by providing effective treatment planning and evaluation of outcomes. When a patient with high risk of heart attack is not treated correctly, chances of survival may reduce dramatically. Methods: In this study, individuals who has heart attack risks are predicted by using a CNN method. A set of medical data from patients with heart attacks and healthy individuals are provided from the UCI database. Reinforced deep learning and ANFIS architectures are also applied to the same problem in order to compare the results and put forth the efficiency of applied method. In addition, ROC analysis and measurements of processing times for the applied methods were performed to reveal the performance, accuracy and efficiency of the study. Results: The applied CNN method and other methods are tested and evaluated. The accuracy performance of the methods were 94.34% for the applied CNN method, 91.58% for the ANFIS, and 92.66% for the deep multilayer neural network. Highest accuracy has been obtained by using the applied CNN method, which is 94.34%. The reasons why the applied CNN method is better than other methods is the number of convolution and pooling layers, the filter size used in these layers, and the functions used in the loss and activation layers. Conclusions: In the study, the applicability of proposed CNN method with images obtained from numerical data has been demonstrated. With the early prediction system proposed, it is now possible to take precautionary measures against possible cardiac arrest. In this study; a new method based on CNN is proposed for early detection of possible heart attack, which is a great risk for human life. Different from studies in the literature, it was used in the applied CNN method by converting all numerical data from dataset into 2D images. Afterwards, to show whether this the proposed method is applicable or not, the dataset which is numerical form was applied to other methods and compared.

show abstract

Defect detection of seals in multilayer aseptic packages using deep learning

Cited by 21 publications

References 15 publications

Application of machine learning to the monitoring and prediction of food safety: A review

Application of machine learning to the monitoring and prediction of food safety: A review

Çok kanallı CNN mimarisi ile X-Ray görüntülerinden COVID-19 tanısı

Risk Assessment for Cardiac Arrest : A Deep Learning Approach

Contact Info

Product

Resources

About