Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wi...Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.展开更多
In today’s digital era,e-healthcare systems exploit digital technologies and telecommunication devices such as mobile devices,computers and the inter-net to provide high-quality healthcare services.E-healthcare decis...In today’s digital era,e-healthcare systems exploit digital technologies and telecommunication devices such as mobile devices,computers and the inter-net to provide high-quality healthcare services.E-healthcare decision support sys-tems have been developed to optimize the healthcare services and enhance a patient’s health.These systems enable rapid access to the specialized healthcare services via reliable information,retrieved from the cases or the patient histories.This phenomenon reduces the time taken by the patients to physically visit the healthcare institutions.In the current research work,a new Shuffled Frog Leap Optimizer with Deep Learning-based Decision Support System(SFLODL-DSS)is designed for the diagnosis of the Cardiovascular Diseases(CVD).The aim of the proposed model is to identify and classify the cardiovascular diseases.The proposed SFLODL-DSS technique primarily incorporates the SFLO-based Feature Selection(SFLO-FS)approach for feature subset election.For the pur-pose of classification,the Autoencoder with Gated Recurrent Unit(AEGRU)model is exploited.Finally,the Bacterial Foraging Optimization(BFO)algorithm is employed tofine-tune the hyperparameters involved in the AEGRU method.To demonstrate the enhanced performance of the proposed SFLODL-DSS technique,a series of simulations was conducted.The simulation outcomes established the superiority of the proposed SFLODL-DSS technique as it achieved the highest accuracy of 98.36%.Thus,the proposed SFLODL-DSS technique can be exploited as a proficient tool in the future for the detection and classification of CVD.展开更多
文摘Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.
文摘In today’s digital era,e-healthcare systems exploit digital technologies and telecommunication devices such as mobile devices,computers and the inter-net to provide high-quality healthcare services.E-healthcare decision support sys-tems have been developed to optimize the healthcare services and enhance a patient’s health.These systems enable rapid access to the specialized healthcare services via reliable information,retrieved from the cases or the patient histories.This phenomenon reduces the time taken by the patients to physically visit the healthcare institutions.In the current research work,a new Shuffled Frog Leap Optimizer with Deep Learning-based Decision Support System(SFLODL-DSS)is designed for the diagnosis of the Cardiovascular Diseases(CVD).The aim of the proposed model is to identify and classify the cardiovascular diseases.The proposed SFLODL-DSS technique primarily incorporates the SFLO-based Feature Selection(SFLO-FS)approach for feature subset election.For the pur-pose of classification,the Autoencoder with Gated Recurrent Unit(AEGRU)model is exploited.Finally,the Bacterial Foraging Optimization(BFO)algorithm is employed tofine-tune the hyperparameters involved in the AEGRU method.To demonstrate the enhanced performance of the proposed SFLODL-DSS technique,a series of simulations was conducted.The simulation outcomes established the superiority of the proposed SFLODL-DSS technique as it achieved the highest accuracy of 98.36%.Thus,the proposed SFLODL-DSS technique can be exploited as a proficient tool in the future for the detection and classification of CVD.
