Trained convolutional neural networks (CNNs) are among the leading tools used for the automatic classification of images. They are nevertheless exposed to attacks: Given an input clean image classified by a CNN in a c...
详细信息
In recently years, intelligent manufacturing system is getting grown up. There are many manufacturing vendors that investigate to develop their intelligent manufacturing systems in their product line. Our government a...
详细信息
In molded pulp packaging manufacturing, defect detection and classification processes are critical to ensuring the products meet quality criteria. Yet most manufacturers still rely on human-based manual visual defect ...
详细信息
ISBN:
(纸本)9798350300505
In molded pulp packaging manufacturing, defect detection and classification processes are critical to ensuring the products meet quality criteria. Yet most manufacturers still rely on human-based manual visual defect classification which can be inconsistent and labor intensive. In this research, we introduce the conjunction of machine vision hardware and machine learning to build a framework for an automated molded pulp packaging defect detection system. The framework consists of two modules. First, the image acquisition module setups appropriate hardware and configuration such t hat high-quality images can be acquired. The second is a machine learning module that constructs a deep learning model with hyper-parameter tuning to automatically detect the defects on the surface of molded pulp products. Our proposed model is based on deep learning model - the Xception architecture, which is recently developed and expected to be more robust on defect detection. In comparison with Traditional machine learning algorithms - SVM and Naive bayes have been widely used in the field of industrial detection. The oriented FAST and rotated BRIEF (ORB) and Bag-of-Visual-Word (BoVW) are implemented for pre-feature extraction. Since molded pulp packaging has obstacles on surface fluctuation by color, grain pulp fiber and non-repeating defect pattern, the Negative Monochrome (NGMC) image preprocessing is proposed to enhance the visibility of defects on the surface and reduce undesired features. The extracted features must be able to describe and distinguish images categories, which could be a limitation for traditional algorithms that required pre-feature extraction. The results demonstrate that the Xception model trained with NGMC images resolution 192x192 and learning rate 0.001 achieved more than 92.98% accuracy and best generalize across datasets from different production lots, which suggests that the robustness of our framework has the potential to be utilized in industrial applica
The sky has always been the crucial element in modeling the background of an outdoor scene. The position of the sun during the day gives a different impact on the sky colour. The sky colour indirectly affects the colo...
详细信息
ExploreCSEd is a collaborative project funded by the HE Academy - information and computersciences. The aim of the project is to investigate the skills and difficulties involved in learning to program by gathering da...
详细信息
ISBN:
(纸本)1595930248
ExploreCSEd is a collaborative project funded by the HE Academy - information and computersciences. The aim of the project is to investigate the skills and difficulties involved in learning to program by gathering data from students and educators in multiple institutions and bringing these together for analysis.
This paper contributes to the convergence analysis of iterative learning control(ILC) for a linear time-varying system with measurement data dropouts,where the data dropout problem is formulated by a Markov chain *** ...
详细信息
ISBN:
(纸本)9781538629185
This paper contributes to the convergence analysis of iterative learning control(ILC) for a linear time-varying system with measurement data dropouts,where the data dropout problem is formulated by a Markov chain *** widely used Bernoulli model for data dropout is a special case of the Markov chain model.A regulating parameter is added to the classic P-type update *** mean square and almost sure convergence are strictly *** illustrative example is provided to verify the theoretical results.
computer security has always been threatened by viruses and worms. Buffer overflow type of worm attacks are the most common attack methods because of the existence of buffer overflow vulnerability in huge number of so...
详细信息
ISBN:
(纸本)9789746152969
computer security has always been threatened by viruses and worms. Buffer overflow type of worm attacks are the most common attack methods because of the existence of buffer overflow vulnerability in huge number of software. A great deal of research has been done to detect buffer overflow attacks, but all the work is mainly focused around highly volatile and flexible patterns such as detecting network patterns, software code patterns, system call patterns. In this paper we are presenting a new approach, which is mainly focused around static information such as published vulnerability, enterprise architecture and published attack information. These knowledge bases have been used to form generalized behavior patterns and enterprise architecture to then compare the anomalous behavior of the vulnerable software. After all the study and experiments our research work has proved that this approach is a positive step forward towards detecting buffer overflow attacks and reducing false positives and false negatives.
This paper presents a salary prediction system using a profile of graduated students as a model. A data mining technique is applied to generate a model to predict a salary for individual students who have similar attr...
详细信息
Automation software need to be continuously updated by addressing software bugs contained in their ***,bugs have different levels of importance;hence,it is essential to prioritize bug reports based on their sever-ity ...
详细信息
Automation software need to be continuously updated by addressing software bugs contained in their ***,bugs have different levels of importance;hence,it is essential to prioritize bug reports based on their sever-ity and *** managing the deluge of incoming bug reports faces time and resource constraints from the development team and delays the resolu-tion of critical ***,bug report prioritization is *** study pro-poses a new model for bug prioritization based on average one dependence estimator;it prioritizes bug reports based on severity,which is determined by the number of *** more the number of attributes,the more the *** proposed model is evaluated using precision,recall,F1-Score,accuracy,G-Measure,and Matthew’s correlation *** of the proposed model are compared with those of the support vector machine(SVM)and Naive Bayes(NB)*** and Mozilla datasetswere used as the sources of bug *** proposed model improved the bug repository management and out-performed the SVM and NB ***,the proposed model used a weaker attribute independence supposition than the former models,thereby improving prediction accuracy with minimal computational cost.
Software development effort estimation is vital to project success. Both underestimates and overestimates of software effort are universal phenomenon in the software industry, which is critical for resource allocation...
详细信息
暂无评论