Pub Date : 2021-04-12DOI: 10.1177/1063293X211008586
A. Siva Kumar, S. Godfrey Winster, R. Ramesh
Data security in the cloud has become a dominant topic being discussed in recent times as the security of data in the cloud has been focused on by several researchers. However, the data security was enforced at the attribute level, the adversaries are capable of learning the method of data encryption even there are access restrictions are enforced at an attribute level. To challenge the adversaries with more sophisticated security measures, an efficient real-time service-centric feature sensitivity analysis (RSFSA) model is proposed in this paper. The RSFSA model analyses the sensitivity of different features being accessed by any service and at multiple levels. At each level, the method checks the set of features being accessed and the number of features the user has access grant to compute the FLAG value for the user according to the profile given. Based on the value of FLAG, the user has been granted or denied service access. On the other side, the method maintains different encryption schemes and keys for each level of features. As the features are organized in multiple levels, the method maintains a set of schemes and keys for each level dedicative. Based on the service level and data, the method selects an encryption scheme and key to perform data encryption. According to that, the service access data has been encrypted at the attribute level with a specific scheme and key. Data encrypted has been uploaded to the blockchain and the method modifies the reference part of the chain to connect only the blocks to which the user has access. The chain given to the user would do not contain any reference from a specific block to which the user has no access. The proposed method improves the performance of data security and access restriction greatly.
{"title":"Efficient sensitivity orient blockchain encryption for improved data security in cloud","authors":"A. Siva Kumar, S. Godfrey Winster, R. Ramesh","doi":"10.1177/1063293X211008586","DOIUrl":"https://doi.org/10.1177/1063293X211008586","url":null,"abstract":"Data security in the cloud has become a dominant topic being discussed in recent times as the security of data in the cloud has been focused on by several researchers. However, the data security was enforced at the attribute level, the adversaries are capable of learning the method of data encryption even there are access restrictions are enforced at an attribute level. To challenge the adversaries with more sophisticated security measures, an efficient real-time service-centric feature sensitivity analysis (RSFSA) model is proposed in this paper. The RSFSA model analyses the sensitivity of different features being accessed by any service and at multiple levels. At each level, the method checks the set of features being accessed and the number of features the user has access grant to compute the FLAG value for the user according to the profile given. Based on the value of FLAG, the user has been granted or denied service access. On the other side, the method maintains different encryption schemes and keys for each level of features. As the features are organized in multiple levels, the method maintains a set of schemes and keys for each level dedicative. Based on the service level and data, the method selects an encryption scheme and key to perform data encryption. According to that, the service access data has been encrypted at the attribute level with a specific scheme and key. Data encrypted has been uploaded to the blockchain and the method modifies the reference part of the chain to connect only the blocks to which the user has access. The chain given to the user would do not contain any reference from a specific block to which the user has no access. The proposed method improves the performance of data security and access restriction greatly.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"41 1","pages":"249 - 257"},"PeriodicalIF":0.0,"publicationDate":"2021-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76626322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-01DOI: 10.1177/1063293X211002169
M. Siiskonen, N. Mortensen, J. Malmqvist, S. Folestad
Emerging research within the field of personalised medicines has aimed to enhance patient treatment through the use of pharmaceutical products that are customised to the individual needs and preferences of the patient. The currently dominant production platforms of pharmaceutical products, however, regard a mass production paradigm and are thus unfeasible for the production and provision of personalised medicines. The production platforms are not designed or are intended for a customisation context. Operating such a context with the current supply chain entails challenges such as increasing costs, time to patient and efforts in quality assurance activities. To address these challenges, this paper presents four reconfigured pharmaceutical supply chain designs. A qualitative operational performance assessment elicits the strengths and weaknesses of the respective supply chain design operating in a customisation context. The results suggest that a later point of variegation, that is, the point in the supply chain where the final customisation is achieved, can relieve the operational effort of the stakeholders in the supply chain while providing the benefits of personalised medicines, that is, an enhanced treatment outcome of the patient. A trade-off remains, however, between the supply chain’s decreased operational effort and degree of necessary reconfigurations, such as introducing new functions to stakeholder operation, reallocating activities to other stakeholders or educating stakeholders.
{"title":"Adapting discrete goods supply chains to support mass customisation of pharmaceutical products","authors":"M. Siiskonen, N. Mortensen, J. Malmqvist, S. Folestad","doi":"10.1177/1063293X211002169","DOIUrl":"https://doi.org/10.1177/1063293X211002169","url":null,"abstract":"Emerging research within the field of personalised medicines has aimed to enhance patient treatment through the use of pharmaceutical products that are customised to the individual needs and preferences of the patient. The currently dominant production platforms of pharmaceutical products, however, regard a mass production paradigm and are thus unfeasible for the production and provision of personalised medicines. The production platforms are not designed or are intended for a customisation context. Operating such a context with the current supply chain entails challenges such as increasing costs, time to patient and efforts in quality assurance activities. To address these challenges, this paper presents four reconfigured pharmaceutical supply chain designs. A qualitative operational performance assessment elicits the strengths and weaknesses of the respective supply chain design operating in a customisation context. The results suggest that a later point of variegation, that is, the point in the supply chain where the final customisation is achieved, can relieve the operational effort of the stakeholders in the supply chain while providing the benefits of personalised medicines, that is, an enhanced treatment outcome of the patient. A trade-off remains, however, between the supply chain’s decreased operational effort and degree of necessary reconfigurations, such as introducing new functions to stakeholder operation, reallocating activities to other stakeholders or educating stakeholders.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"15 1","pages":"309 - 327"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89621469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-01DOI: 10.1177/1063293X211001956
Fu-Shin Lee, Chen-I Lin, Zhi-Yu Chen, Ruichen Yang
Based upon the CANopen communication protocol and the LabVIEW graphic programing procedures, this paper develops a closed-loop control architecture for a parallel three-axis (Delta) robotic arm mechanism. The accomplishments include prototyping a parallel three-axis robotic arm mechanism, assembling servomotors with associated encoders and gearsets, coding CANopen communication scripts for servomotor controllers and a host supervision GUI, coding forward/inverse kinematics scripts to compute the required servomotor rotations and the coordinates of a movable platform or the mechanism, coding tracking error compensation scripts for effective closed-loop griper control, and coding integration scripts to command and supervise the mechanism motion on the LabVIEW-based host GUI. During the development stage, this research designed and prototyped the parallel three-axis robotic arm mechanism based upon basic Delta robot kinematics. To control the mechanism effectively and accurately, this study implemented the CANopen communication protocol, which characterizes high speed and stable transmission. The protocol applies to the CANopen communication channels among the controllers and the host supervision GUI. On the LabVIEW development platform, the coded supervision GUI performs issuing/receiving messages to the CANopen-based controllers. The controllers excite the servomotors and actuate the parallel mechanism to track prescribed trajectories in a closed-loop control fashion. Meanwhile, an electromagnet attached to the movable platform of the robotic mechanism performs satisfactory picking/placing object actions.
{"title":"Development of a control architecture for a parallel three-axis robotic arm mechanism using CANopen communication protocol","authors":"Fu-Shin Lee, Chen-I Lin, Zhi-Yu Chen, Ruichen Yang","doi":"10.1177/1063293X211001956","DOIUrl":"https://doi.org/10.1177/1063293X211001956","url":null,"abstract":"Based upon the CANopen communication protocol and the LabVIEW graphic programing procedures, this paper develops a closed-loop control architecture for a parallel three-axis (Delta) robotic arm mechanism. The accomplishments include prototyping a parallel three-axis robotic arm mechanism, assembling servomotors with associated encoders and gearsets, coding CANopen communication scripts for servomotor controllers and a host supervision GUI, coding forward/inverse kinematics scripts to compute the required servomotor rotations and the coordinates of a movable platform or the mechanism, coding tracking error compensation scripts for effective closed-loop griper control, and coding integration scripts to command and supervise the mechanism motion on the LabVIEW-based host GUI. During the development stage, this research designed and prototyped the parallel three-axis robotic arm mechanism based upon basic Delta robot kinematics. To control the mechanism effectively and accurately, this study implemented the CANopen communication protocol, which characterizes high speed and stable transmission. The protocol applies to the CANopen communication channels among the controllers and the host supervision GUI. On the LabVIEW development platform, the coded supervision GUI performs issuing/receiving messages to the CANopen-based controllers. The controllers excite the servomotors and actuate the parallel mechanism to track prescribed trajectories in a closed-loop control fashion. Meanwhile, an electromagnet attached to the movable platform of the robotic mechanism performs satisfactory picking/placing object actions.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"65 1","pages":"197 - 207"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85669922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-23DOI: 10.1177/1063293X211003194
Maolin Yang, Auwal H. Abubakar, P. Jiang
Social manufacturing is characterized by its capability of utilizing socialized manufacturing resources to achieve value adding. Recently, a new type of social manufacturing pattern emerges and shows potential for core factories to improve their limited manufacturing capabilities by utilizing the resources from outside socialized manufacturing resource communities. However, the core factories need to analyze the resource characteristics of the socialized resource communities before making operation plans, and this is challenging due to the unaffiliated and self-driven characteristics of the resource providers in socialized resource communities. In this paper, a deep learning and complex network based approach is established to address this challenge by using socialized designer community for demonstration. Firstly, convolutional neural network models are trained to identify the design resource characteristics of each socialized designer in designer community according to the interaction texts posted by the socialized designer on internet platforms. During the process, an iterative dataset labelling method is established to reduce the time cost for training set labelling. Secondly, complex networks are used to model the design resource characteristics of the community according to the resource characteristics of all the socialized designers in the community. Two real communities from RepRap 3D printer project are used as case study.
{"title":"Deep learning and complex network theory based analysis on socialized manufacturing resources utilisations and an application case study","authors":"Maolin Yang, Auwal H. Abubakar, P. Jiang","doi":"10.1177/1063293X211003194","DOIUrl":"https://doi.org/10.1177/1063293X211003194","url":null,"abstract":"Social manufacturing is characterized by its capability of utilizing socialized manufacturing resources to achieve value adding. Recently, a new type of social manufacturing pattern emerges and shows potential for core factories to improve their limited manufacturing capabilities by utilizing the resources from outside socialized manufacturing resource communities. However, the core factories need to analyze the resource characteristics of the socialized resource communities before making operation plans, and this is challenging due to the unaffiliated and self-driven characteristics of the resource providers in socialized resource communities. In this paper, a deep learning and complex network based approach is established to address this challenge by using socialized designer community for demonstration. Firstly, convolutional neural network models are trained to identify the design resource characteristics of each socialized designer in designer community according to the interaction texts posted by the socialized designer on internet platforms. During the process, an iterative dataset labelling method is established to reduce the time cost for training set labelling. Secondly, complex networks are used to model the design resource characteristics of the community according to the resource characteristics of all the socialized designers in the community. Two real communities from RepRap 3D printer project are used as case study.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"101 1","pages":"236 - 248"},"PeriodicalIF":0.0,"publicationDate":"2021-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90360179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-06DOI: 10.1177/1063293X20982973
Ívar Örn Arnarsson, Otto Frost, E. Gustavsson, M. Jirstrand, J. Malmqvist
Product development companies collect data in form of Engineering Change Requests for logged design issues, tests, and product iterations. These documents are rich in unstructured data (e.g. free text). Previous research affirms that product developers find that current IT systems lack capabilities to accurately retrieve relevant documents with unstructured data. In this research, we demonstrate a method using Natural Language Processing and document clustering algorithms to find structurally or contextually related documents from databases containing Engineering Change Request documents. The aim is to radically decrease the time needed to effectively search for related engineering documents, organize search results, and create labeled clusters from these documents by utilizing Natural Language Processing algorithms. A domain knowledge expert at the case company evaluated the results and confirmed that the algorithms we applied managed to find relevant document clusters given the queries tested.
{"title":"Natural language processing methods for knowledge management—Applying document clustering for fast search and grouping of engineering documents","authors":"Ívar Örn Arnarsson, Otto Frost, E. Gustavsson, M. Jirstrand, J. Malmqvist","doi":"10.1177/1063293X20982973","DOIUrl":"https://doi.org/10.1177/1063293X20982973","url":null,"abstract":"Product development companies collect data in form of Engineering Change Requests for logged design issues, tests, and product iterations. These documents are rich in unstructured data (e.g. free text). Previous research affirms that product developers find that current IT systems lack capabilities to accurately retrieve relevant documents with unstructured data. In this research, we demonstrate a method using Natural Language Processing and document clustering algorithms to find structurally or contextually related documents from databases containing Engineering Change Request documents. The aim is to radically decrease the time needed to effectively search for related engineering documents, organize search results, and create labeled clusters from these documents by utilizing Natural Language Processing algorithms. A domain knowledge expert at the case company evaluated the results and confirmed that the algorithms we applied managed to find relevant document clusters given the queries tested.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"7 1","pages":"142 - 152"},"PeriodicalIF":0.0,"publicationDate":"2021-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87956907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-01DOI: 10.1177/1063293X21991808
Babymol Kurian, V. Jyothi
A wide reach on cancer prediction and detection using Next Generation Sequencing (NGS) by the application of artificial intelligence is highly appreciated in the current scenario of the medical field. Next generation sequences were extracted from NCBI (National Centre for Biotechnology Information) gene repository. Sequences of normal Homo sapiens (Class 1), BRCA1 (Class 2) and BRCA2 (Class 3) were extracted for Machine Learning (ML) purpose. The total volume of datasets extracted for the process were 1580 in number under four categories of 50, 100, 150 and 200 sequences. The breast cancer prediction process was carried out in three major steps such as feature extraction, machine learning classification and performance evaluation. The features were extracted with sequences as input. Ten features of DNA sequences such as ORF (Open Reading Frame) count, individual nucleobase average count of A, T, C, G, AT and GC-content, AT/GC composition, G-quadruplex occurrence, MR (Mutation Rate) were extracted from three types of sequences for the classification process. The sequence type was also included as a target variable to the feature set with values 0, 1 and 2 for classes 1, 2 and 3 respectively. Nine various supervised machine learning techniques like LR (Logistic Regression statistical model), LDA (Linear Discriminant analysis model), k-NN (k nearest neighbours’ algorithm), DT (Decision tree technique), NB (Naive Bayes classifier), SVM (Support-Vector Machine algorithm), RF (Random Forest learning algorithm), AdaBoost (AB) and Gradient Boosting (GB) were employed on four various categories of datasets. Of all supervised models, decision tree machine learning technique performed most with maximum accuracy in classification of 94.03%. Classification model performance was evaluated using precision, recall, F1-score and support values wherein F1-score was most similar to the classification accuracy.
在当前医疗领域的场景中，人工智能应用的下一代测序(NGS)在癌症预测和检测方面的广泛影响受到高度赞赏。下一代序列从NCBI (National Centre for Biotechnology Information)基因库中提取。提取正常智人(1类)、BRCA1(2类)和BRCA2(3类)序列用于机器学习(ML)目的。该过程提取的数据集总量为1580个，分为50、100、150和200个序列。乳腺癌预测过程分为特征提取、机器学习分类和性能评估三个主要步骤。以序列为输入提取特征。从3类序列中提取ORF (Open Reading Frame)计数、A、T、C、G、AT和GC含量的单个核碱基平均计数、AT/GC组成、G-四重体发生率、MR(突变率)等10个特征进行分类。序列类型也被作为目标变量包含到特征集中，分别为第1类、第2类和第3类的值分别为0、1和2。九种不同的监督机器学习技术，如LR(逻辑回归统计模型)，LDA(线性判别分析模型)，k- nn (k近邻算法)，DT(决策树技术)，NB(朴素贝叶斯分类器)，SVM(支持向量机算法)，RF(随机森林学习算法)，AdaBoost (AB)和Gradient Boosting (GB)在四种不同类别的数据集上使用。在所有监督模型中，决策树机器学习技术的分类准确率最高，达到94.03%。采用准确率、召回率、F1-score和支持度值评价分类模型的性能，其中F1-score与分类准确率最接近。
{"title":"Breast cancer prediction using an optimal machine learning technique for next generation sequences","authors":"Babymol Kurian, V. Jyothi","doi":"10.1177/1063293X21991808","DOIUrl":"https://doi.org/10.1177/1063293X21991808","url":null,"abstract":"A wide reach on cancer prediction and detection using Next Generation Sequencing (NGS) by the application of artificial intelligence is highly appreciated in the current scenario of the medical field. Next generation sequences were extracted from NCBI (National Centre for Biotechnology Information) gene repository. Sequences of normal Homo sapiens (Class 1), BRCA1 (Class 2) and BRCA2 (Class 3) were extracted for Machine Learning (ML) purpose. The total volume of datasets extracted for the process were 1580 in number under four categories of 50, 100, 150 and 200 sequences. The breast cancer prediction process was carried out in three major steps such as feature extraction, machine learning classification and performance evaluation. The features were extracted with sequences as input. Ten features of DNA sequences such as ORF (Open Reading Frame) count, individual nucleobase average count of A, T, C, G, AT and GC-content, AT/GC composition, G-quadruplex occurrence, MR (Mutation Rate) were extracted from three types of sequences for the classification process. The sequence type was also included as a target variable to the feature set with values 0, 1 and 2 for classes 1, 2 and 3 respectively. Nine various supervised machine learning techniques like LR (Logistic Regression statistical model), LDA (Linear Discriminant analysis model), k-NN (k nearest neighbours’ algorithm), DT (Decision tree technique), NB (Naive Bayes classifier), SVM (Support-Vector Machine algorithm), RF (Random Forest learning algorithm), AdaBoost (AB) and Gradient Boosting (GB) were employed on four various categories of datasets. Of all supervised models, decision tree machine learning technique performed most with maximum accuracy in classification of 94.03%. Classification model performance was evaluated using precision, recall, F1-score and support values wherein F1-score was most similar to the classification accuracy.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"10 1","pages":"49 - 57"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72812683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-01DOI: 10.1177/1063293X21994361
Ya Zhang, Q. Xiong
Aiming at the problem that the traditional color perception and recognition method for Guangdong embroidery image has poor color stereo restoring ability, a color perception, and recognition method for Guangdong embroidery image based on discrete mathematical model is proposed. Through histogram equalization, the input image with centralized gray distribution is transformed into the output image with approximate uniform distribution to enhance the dynamic range of the gray value of the pixels; the median filtering method is used to smooth the Guangdong embroidery image and remove the noise in the Guangdong embroidery image. The RGB spatial model and HSI spatial model of image color are constructed by normalizing the coordinates and color attributes of pixels. Using these two models to transform RGB color space and HSI color space, image color perception, and recognition model is established to realize color perception and recognition of Guangdong embroidery image. In order to verify the color stereo restoring ability of the method, the method is compared with the traditional method for color perception and recognition of Guangdong embroidery image, which proves that the color stereo restoring ability of the method is better than that of the traditional method.
{"title":"Color perception and recognition method for Guangdong embroidery image based on discrete mathematical model","authors":"Ya Zhang, Q. Xiong","doi":"10.1177/1063293X21994361","DOIUrl":"https://doi.org/10.1177/1063293X21994361","url":null,"abstract":"Aiming at the problem that the traditional color perception and recognition method for Guangdong embroidery image has poor color stereo restoring ability, a color perception, and recognition method for Guangdong embroidery image based on discrete mathematical model is proposed. Through histogram equalization, the input image with centralized gray distribution is transformed into the output image with approximate uniform distribution to enhance the dynamic range of the gray value of the pixels; the median filtering method is used to smooth the Guangdong embroidery image and remove the noise in the Guangdong embroidery image. The RGB spatial model and HSI spatial model of image color are constructed by normalizing the coordinates and color attributes of pixels. Using these two models to transform RGB color space and HSI color space, image color perception, and recognition model is established to realize color perception and recognition of Guangdong embroidery image. In order to verify the color stereo restoring ability of the method, the method is compared with the traditional method for color perception and recognition of Guangdong embroidery image, which proves that the color stereo restoring ability of the method is better than that of the traditional method.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"63 1","pages":"68 - 74"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91137354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-01DOI: 10.1177/1063293X21998083
Bo Guo, Fu-Shin Lee, Chen-I Lin, Yuan-Jun Lin
This paper suggests an optimization strategy to train a CNN deep-learning network, which successfully recognizing working status on the HMI panels of CNC machines. To verify the developed strategy, the research experiments using a prototype that consists of a CNC milling machine and an industrial robot. In the optimization strategy, the research first defines a length-varying hyperparameter list for the deep-learning network, and the entities in the list adjust themselves to optimize the model scales. During the optimization process, this paper adopts a two-stage training scheme that gradually augments image datasets to improve HMI control-panel recognition performances, such as recognition accuracy and recognition speed to identify the CNC machine working status. Using an open-source PyTorch platform, this research establishes a cloud-based distributed architecture to build training codes for the deep-learning network, in which an applicable optimization model is deployed to recognize the CNC control-panel working status. The optimization strategy employs minimal codes to rebuild the architecture and the least efforts to reform the manufacturing system. The optimally trained model provides up to a 99.34% CNC panel-message recognition accuracy and a high-speed recognition of 100 images in 0.6 s. Moreover, the developed optimization strategy enables the prediction of necessitated dataset augmentation to training a practically implemented CNN network.
{"title":"An optimization strategy for HMI panel recognition of CNC machines using a CNN deep-learning network","authors":"Bo Guo, Fu-Shin Lee, Chen-I Lin, Yuan-Jun Lin","doi":"10.1177/1063293X21998083","DOIUrl":"https://doi.org/10.1177/1063293X21998083","url":null,"abstract":"This paper suggests an optimization strategy to train a CNN deep-learning network, which successfully recognizing working status on the HMI panels of CNC machines. To verify the developed strategy, the research experiments using a prototype that consists of a CNC milling machine and an industrial robot. In the optimization strategy, the research first defines a length-varying hyperparameter list for the deep-learning network, and the entities in the list adjust themselves to optimize the model scales. During the optimization process, this paper adopts a two-stage training scheme that gradually augments image datasets to improve HMI control-panel recognition performances, such as recognition accuracy and recognition speed to identify the CNC machine working status. Using an open-source PyTorch platform, this research establishes a cloud-based distributed architecture to build training codes for the deep-learning network, in which an applicable optimization model is deployed to recognize the CNC control-panel working status. The optimization strategy employs minimal codes to rebuild the architecture and the least efforts to reform the manufacturing system. The optimally trained model provides up to a 99.34% CNC panel-message recognition accuracy and a high-speed recognition of 100 images in 0.6 s. Moreover, the developed optimization strategy enables the prediction of necessitated dataset augmentation to training a practically implemented CNN network.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"6 1","pages":"35 - 48"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79123734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-01DOI: 10.1177/1063293X211001573
K. Vijayakumar
In the current scenario, automated approaches are widely adopted in various domains to implement the computerized monitoring and regulation. The massive advancement in the machine-driven technologies such as computational intelligence, machine-learning scheme, deep-learning scheme, and the Internet of Things (IoT) helped to advance the industrial automation to the next level, in which the automated detection and classification is easily implemented. Computerized systems are essential in a variety of domains to achieve an error free monitoring and the control without compromising the accuracy. Further, the availability of advanced computational facilities helps to achieve superior outcomes, in a variety of domains, such as industry, manufacturing, agriculture, medical, and other engineering and science domains. The integration of traditional approach with the recent computational intelligence technique also helps to achieve a better result during the problem solving practice. The integration of the recent approach along with the IoT helped to automate the entire system using the current internet technology and also supports the remote monitoring and control. When an industry is equipped with all these facility is also called as an industry ready with the essential future enhancement essential to implement ‘‘Industry 4.0’’ an essential keyword to indicate the present trend of automation and data exchange in industries which includes; cyber-physical systems, IoT, cloud computing, and cognitive computing with essential smart facilities.
{"title":"Computational intelligence, machine learning techniques, and IOT","authors":"K. Vijayakumar","doi":"10.1177/1063293X211001573","DOIUrl":"https://doi.org/10.1177/1063293X211001573","url":null,"abstract":"In the current scenario, automated approaches are widely adopted in various domains to implement the computerized monitoring and regulation. The massive advancement in the machine-driven technologies such as computational intelligence, machine-learning scheme, deep-learning scheme, and the Internet of Things (IoT) helped to advance the industrial automation to the next level, in which the automated detection and classification is easily implemented. Computerized systems are essential in a variety of domains to achieve an error free monitoring and the control without compromising the accuracy. Further, the availability of advanced computational facilities helps to achieve superior outcomes, in a variety of domains, such as industry, manufacturing, agriculture, medical, and other engineering and science domains. The integration of traditional approach with the recent computational intelligence technique also helps to achieve a better result during the problem solving practice. The integration of the recent approach along with the IoT helped to automate the entire system using the current internet technology and also supports the remote monitoring and control. When an industry is equipped with all these facility is also called as an industry ready with the essential future enhancement essential to implement ‘‘Industry 4.0’’ an essential keyword to indicate the present trend of automation and data exchange in industries which includes; cyber-physical systems, IoT, cloud computing, and cognitive computing with essential smart facilities.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"91 1","pages":"3 - 5"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75845912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-01DOI: 10.1177/1063293X21994953
Eddy Sánchez-Delacruz, Juan P Salazar López, David Lara Alabazares, Edgar TELLO LEAL, Mirta Fuentes-Ramos
Foliar disease is common problem in plants; it appears as an abnormal change in the plant’s characteristics, such as the presence of lesions and discolorations, among others. These problems may be related to plant growth, which causes a decrease in crop production, impacting the agricultural economy. The causes of leaf damage can be variable, such as bacteria, viruses, nutritional deficiencies, or even consequences of climate change. Motivated to find a solution for this problem, we aim that using image processing and machine learning algorithms (MLA), these symptomatic characteristics of the leaf can be used to classify diseases. Then, contributions of this research are (i) the use of image processing methods in the feature extraction (characteristics), and (ii) the combination of assembled algorithms with deep learning to classify foliar features of Valencia orange (Citrus Sinensis) tree leaves. Combining these two classification approaches, we get optimal rates in binary datasets and highly competitive percentages in multiclass sets. This, using a database of images of three types of foliar damage of local plants. Result of combination of these two classification strategies is an exceptional reliable alternative for leaf damage identification of orange and other citrus plants.
{"title":"Deep learning framework for leaf damage identification","authors":"Eddy Sánchez-Delacruz, Juan P Salazar López, David Lara Alabazares, Edgar TELLO LEAL, Mirta Fuentes-Ramos","doi":"10.1177/1063293X21994953","DOIUrl":"https://doi.org/10.1177/1063293X21994953","url":null,"abstract":"Foliar disease is common problem in plants; it appears as an abnormal change in the plant’s characteristics, such as the presence of lesions and discolorations, among others. These problems may be related to plant growth, which causes a decrease in crop production, impacting the agricultural economy. The causes of leaf damage can be variable, such as bacteria, viruses, nutritional deficiencies, or even consequences of climate change. Motivated to find a solution for this problem, we aim that using image processing and machine learning algorithms (MLA), these symptomatic characteristics of the leaf can be used to classify diseases. Then, contributions of this research are (i) the use of image processing methods in the feature extraction (characteristics), and (ii) the combination of assembled algorithms with deep learning to classify foliar features of Valencia orange (Citrus Sinensis) tree leaves. Combining these two classification approaches, we get optimal rates in binary datasets and highly competitive percentages in multiclass sets. This, using a database of images of three types of foliar damage of local plants. Result of combination of these two classification strategies is an exceptional reliable alternative for leaf damage identification of orange and other citrus plants.","PeriodicalId":10680,"journal":{"name":"Concurrent Engineering","volume":"53 1","pages":"25 - 34"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74403992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：