The purpose of this research is to deal with effective block chain framework for secure transactions.The rate of effective data transactions and the interoperability of the ledger are the two major obstacles involved ...The purpose of this research is to deal with effective block chain framework for secure transactions.The rate of effective data transactions and the interoperability of the ledger are the two major obstacles involved in Blockchain and to tackle this issue,Cross-Chain based Transaction(CCT)is introduced.Traditional industries have been restructured by the introduction of Internet of Things(IoT)to become smart industries through the feature of data-driven decision-making.Still,there are a few limitations,like decentralization,security vulnerabilities,poor interoperability,as well as privacy concerns in IoTs.To overcome this limitation,Blockchain has been employed to assure a safer transaction process,especially in asset exchanges.In recent decades,scalable local ledgers implement Blockchains,simultaneously sustaining peer validations of transactions which can be at local or global levels.From the single Hyperledger-based blockchains system,the CCT takes the transaction amid various chains.In addition,the most significant factor for this registration processing strategy is the Signature to ensure security.The application of the Quantum cryptographic algorithm amplifies the proposed Hyperledger-based blockchains,to strengthen the safety of the process.The key has been determined by restricting the number of transactions that reach the global Blockchain using the quantum-based hash function and accomplished by scalable local ledgers,and peer validations of transactions at local and global levels without any issues.The rate of transaction processing for entire peers has enhanced with the ancillary aid of the proposed solution,as it includes the procedure of load distribution.Without any boosted enhancement,the recommended solution utilizes the current transaction strategy,and also,it’s aimed at scalability,resource conservation,and interoperability.The experimental results of the system have been evaluated using the metrics like block weight,ledger memory,the usage of the central processing unit,and the communication overhead.展开更多
Diabetic Retinopathy(DR)is a vision disease due to the long-term prevalenceof Diabetes Mellitus.It affects the retina of the eye and causes severedamage to the vision.If not treated on time it may lead to permanent vi...Diabetic Retinopathy(DR)is a vision disease due to the long-term prevalenceof Diabetes Mellitus.It affects the retina of the eye and causes severedamage to the vision.If not treated on time it may lead to permanent vision lossin diabetic patients.Today’s development in science has no medication to cureDiabetic Retinopathy.However,if diagnosed at an early stage it can be controlledand permanent vision loss can be avoided.Compared to the diabetic population,experts to diagnose Diabetic Retinopathy are very less in particular to local areas.Hence an automatic computer-aided diagnosis for DR detection is necessary.Inthis paper,we propose an unsupervised clustering technique to automatically clusterthe DR into one of its five development stages.The deep learning based unsupervisedclustering is made to improve itself with the help of fuzzy rough c-meansclustering where cluster centers are updated by fuzzy rough c-means clusteringalgorithm during the forward pass and the deep learning model representationsare updated by Stochastic Gradient Descent during the backward pass of training.The proposed method was implemented using python and the results were takenon DGX server with Tesla V100 GPU cards.An experimental result on the publicallyavailable Kaggle dataset shows an overall accuracy of 88.7%.The proposedmodel improves the accuracy of DR diagnosis compared to the existingunsupervised algorithms like k-means,FCM,auto-encoder,and FRCM withalexnet.展开更多
文摘The purpose of this research is to deal with effective block chain framework for secure transactions.The rate of effective data transactions and the interoperability of the ledger are the two major obstacles involved in Blockchain and to tackle this issue,Cross-Chain based Transaction(CCT)is introduced.Traditional industries have been restructured by the introduction of Internet of Things(IoT)to become smart industries through the feature of data-driven decision-making.Still,there are a few limitations,like decentralization,security vulnerabilities,poor interoperability,as well as privacy concerns in IoTs.To overcome this limitation,Blockchain has been employed to assure a safer transaction process,especially in asset exchanges.In recent decades,scalable local ledgers implement Blockchains,simultaneously sustaining peer validations of transactions which can be at local or global levels.From the single Hyperledger-based blockchains system,the CCT takes the transaction amid various chains.In addition,the most significant factor for this registration processing strategy is the Signature to ensure security.The application of the Quantum cryptographic algorithm amplifies the proposed Hyperledger-based blockchains,to strengthen the safety of the process.The key has been determined by restricting the number of transactions that reach the global Blockchain using the quantum-based hash function and accomplished by scalable local ledgers,and peer validations of transactions at local and global levels without any issues.The rate of transaction processing for entire peers has enhanced with the ancillary aid of the proposed solution,as it includes the procedure of load distribution.Without any boosted enhancement,the recommended solution utilizes the current transaction strategy,and also,it’s aimed at scalability,resource conservation,and interoperability.The experimental results of the system have been evaluated using the metrics like block weight,ledger memory,the usage of the central processing unit,and the communication overhead.
文摘Diabetic Retinopathy(DR)is a vision disease due to the long-term prevalenceof Diabetes Mellitus.It affects the retina of the eye and causes severedamage to the vision.If not treated on time it may lead to permanent vision lossin diabetic patients.Today’s development in science has no medication to cureDiabetic Retinopathy.However,if diagnosed at an early stage it can be controlledand permanent vision loss can be avoided.Compared to the diabetic population,experts to diagnose Diabetic Retinopathy are very less in particular to local areas.Hence an automatic computer-aided diagnosis for DR detection is necessary.Inthis paper,we propose an unsupervised clustering technique to automatically clusterthe DR into one of its five development stages.The deep learning based unsupervisedclustering is made to improve itself with the help of fuzzy rough c-meansclustering where cluster centers are updated by fuzzy rough c-means clusteringalgorithm during the forward pass and the deep learning model representationsare updated by Stochastic Gradient Descent during the backward pass of training.The proposed method was implemented using python and the results were takenon DGX server with Tesla V100 GPU cards.An experimental result on the publicallyavailable Kaggle dataset shows an overall accuracy of 88.7%.The proposedmodel improves the accuracy of DR diagnosis compared to the existingunsupervised algorithms like k-means,FCM,auto-encoder,and FRCM withalexnet.