检索结果-南通市图书馆

维普期刊数据库

Detection and Classification of Diabetic Retinopathy Using DCNN and BSN Models

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第7期72卷 597-609页

作者： S.Sudha A.Srinivasan T.Gayathri Devi department of ece SRCSASTRA Deemed UniversityKumbakonamIndia

Diabetes is associated with many complications that could lead to *** retinopathy,a complication of diabetes,is difficult to diagnose and may lead to vision *** identification of micro features in fundus images for the diagnosis of DR is a complex and challenging task for *** clinical testing involves complex procedures and is timeconsuming,an automated system would help ophthalmologists to detect DR and administer treatment in a timelymanner so that blindness can be *** research works have focused on image processing algorithms,or neural networks,or signal processing techniques alone to detect diabetic ***,we aimed to develop a novel integrated approach to increase the accuracy of *** approach utilized both convolutional neural networks and signal processing *** this proposed method,the biological electro retinogram(ERG)sensor network(BSN)and deep convolution neural network(DCNN)were developed to detect and classify *** the BSN system,electrodes were used to record ERGsignal,which was preprocessed to be *** was performed in the frequency domain by the application of fast Fourier transform(FFT)and mel frequency cepstral coefficients(MFCCs)were *** neural network(ANN)classifier was used to classify the signals of eyes with DR and normal ***,fundus images were captured using a fundus camera,and these were used as the input for DCNN-based *** DCNN consisted of many layers to facilitate the extraction of features and classification of fundus images into normal images,non-proliferative DR(NPDR)or earlystage DR images,and proliferative DR(PDR)or advanced-stage DR ***,it classifiedNPDRaccording tomicroaneurysms,hemorrhages,cotton wool spots,and exudates,and the presence of new blood vessels indicated *** accuracy,sensitivity,and specificity of the ANNclassifier were found to be 94%,95%,and 93%,***

关键词： Deep convolution neural network artificial neural network nonproliferative diabetic retinopathy biological ERG sensor network

Berger code based concurrent online self-testing of embedded processors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Semiconductors 2018年第11期39卷 68-73页

作者： G.Prasad Acharya M.Asha Rani department of ece Sree Nidhi Institute of Science and Technology department of ece JNTUH College of Engineering JNTUH University

We propose an approach to detect the temporary faults induced by an environmental phenomenon called single event upset(SEU). Berger code based self-checking checkers provides an online detection of faults in digital circuits as well as in memory arrays. In this work, a concurrent Berger code based online self-testable architecture is proposed and integrated in 32-bit DLX reduced instruction set computer(RISC) processor on a single silicon chip. The proposed concurrent test methodology is implemented and verified for various arithmetic and logical operations of the DLX processor. The FPGA implementation of the proposed design shows that a meager increase in hardware utilization facilitates online self-testing to detect temporary faults.

关键词： single event upset Berger code DLX RISC online testing

维普期刊数据库

Enhanced Detection of Cerebral Atherosclerosis Using Hybrid Algorithm of Image Segmentation

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第4期36卷 733-744页

作者： Shakunthala Masi Helenprabha Kuttiappan department of ece RMD Engineering CollegeChennaiIndia

In medical science for envisaging human body’s phenomenal structure a major part has been driven by image processing *** objective of this work is to detect of cerebral atherosclerosis for image segmentation *** of some abnormal structures in human body has become a difﬁcult task to complete with some simple *** expounding and distinguishing neural architecture of human brain in an effective manner,MRI(Magnetic Reso-nance Imaging)is one of the most suitable and signiﬁcant *** we work on detection of Cerebral Atherosclerosis from MRI images of ***-ebral Atherosclerosis is a cerebral vascular disease causes narrowing of the arteries due to buildup of fatty plaque inside the blood vessels of the *** leads to Ischemic stroke if not diagnosed *** affects majorly old age people and percentage of affected women is more compared to ***:Preproces-sing is done by using alpha trimmed meanﬁlter which is used to remove noise and also it enhances the *** of cerebral atherosclerosis is done by using K-means clustering,Contextual clustering,and proposed Hybrid *** parameters like Correlation,Pixel density,energy is determined and from the analysis of parameters it is determined that proposed Hybrid algo-rithm is efﬁcient.

关键词： Atherosclerosis Ischemic stroke Alpha trimmed meanﬁlter K-means Contextual clustering Hybrid algorithm

Artificial Neural Network-Based Development of an Efficient Energy Management Strategy for Office Building

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第7期37卷 1225-1242页

作者： Payal Soni J.Subhashini department of ece SRMISTKattankulathurChennai603203India

In the current context,a smart grid has replaced the conventional grid through intelligent energy management,integration of renewable energy sources(RES)and two-way communication infrastructures from power gen-eration to *** management from the distribution side is a critical problem for balancing load demand.A unique energy manage-ment strategy(EMS)is being developed for office building *** includes renewable energy integration,automation,and control based on the Artificial Neural Network(ANN)system using Matlab *** strategy reduces electric power consumption and balances the load demand of the traditional *** strategy is developed by taking inputs from an office building electricity consumption behavior study,a power generation study of a solar photovoltaic system,and the supply pattern of a grid in peak and non-peak *** this is done in consideration of the Indian scenario,where real-time data of month-wise ANN-based intelligent switching has been established for intermittent renewable sources and peak load reduction,as well as average load reduction,has been demonstrated along with the power control loop without the battery system.

关键词： HVAC ANN demand response power consumption smart grid Weather and temperature occupancy EMS

Reliability-aware mapping for various No C topologies and routing algorithms under performance constraints

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2015年第8期58卷 168-181页

作者： WU Chen DENG ChenChen LIU LeiBo YIN ShouYi HAN Jie WEI ShaoJun National Lab for Information Science and Technology Tsinghua University ece department University of Alberta

The flexibility of manycore systems to extensive applications is achieved by reconfiguring the interconnections between processing elements(PEs) and the function of PEs. The efficiency of the system is crucially determined by the mapping technique of applications. In this paper, a highly flexible reliability-aware application mapping approach is proposed for manycore network-on-chip(No C) systems. A reliability cost model(RCM) is first presented to measure the reliability cost for a mapping pattern. This model uses the binary number 0/1 to model the reliability cost of each communication path. The overall reliability cost of a mapping pattern is evaluated by taking the cost of each path as a discrete random variable. Based on RCM,a mapping method called reliability cost ratio based branch and bound(RCRBB) is used. With this method,the best mapping among all the possible patterns is found efficiently by discarding those nonoptimal candidate mappings at early stages. The proposed application mapping approach with reliability awareness is applicable to various No C topologies and routing algorithms, while other state-of-the-art approaches on the same topic are only limited to a specific topology and routing algorithm. Even for the same No C architecture, the proposed approach shows significant superiority in many aspects. Experiments show that RCRBB achieves up to 9.07%reliability enhancement on average. Also, it outperforms other approaches in throughput and latency with a relatively low run time.

关键词： reliability-aware network-on-chip(No C) mapping algorithm performance flexibility

Robust Hybrid Artificial Fish Swarm Simulated Annealing Optimization Algorithm for Secured Free Scale Networks against Malicious Attacks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第1期66卷 903-917页

作者： Ganeshan Keerthana Panneerselvam Anandan Nandhagopal Nachimuthu Anna University Chennai600025India department of ece C.Abdul Hakeem College of Engineering and TechnologyVelloreIndia department of ece Excel Engineering CollegeSalemIndia

Due to the recent proliferation of cyber-attacks,highly robust wireless sensor networks(WSN)become a critical issue as they survive node ***-free WSN is essential because they endure random attacks *** they are susceptible to malicious attacks,which mainly targets particular significant ***,the robustness of the network becomes important for ensuring the network *** paper presents a Robust Hybrid Artificial Fish Swarm Simulated Annealing Optimization(RHAFS-SA)*** is introduced for improving the robust nature of free scale networks over malicious attacks(MA)with no change in degree *** proposed RHAFS-SA is an enhanced version of the Improved Artificial Fish Swarm algorithm(IAFSA)by the simulated annealing(SA)*** proposed RHAFS-SA algorithm eliminates the IAFSA from unforeseen vibration and speeds up the convergence *** experimentation,free scale networks are produced by the Barabási–Albert(BA)model,and real-world networks are employed for testing the outcome on both synthetic-free scale and real-world *** experimental results exhibited that the RHAFS-SA model is superior to other models interms of diverse aspects.

关键词： Free scale networks robustness malicious attacks fish swarm algorithm

Analysis of EMD Algorithm for Identification and Extraction of An Acoustic Signal in Underwater Channel Against Wind Driven Ambient Noise

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Ocean Engineering 2014年第5期28卷 645-657页

作者： S.Sakthivel MURUGAN V.NATARAJAN K.MAHESWARAN ece department SSN College of Engineering Instrumentation department MIT Campus Anna University Infosys Chennai India

Sonar generated acoustic signals transmitted in underwater channel for distant communications are affected by numerous factors like ambient noise, making them nonlinear and non-stationary in nature. In recent years, the application of Empirical Mode Decomposition(EMD) technique to analyze nonlinear and non-stationary signals has gained much attention. It is an empirical approach to decompose a signal into a set of oscillatory modes known as intrinsic mode functions(IMFs). In general, Hilbert transform is used in EMD for the identification of oscillatory signals. In this paper a new EMD algorithm is proposed using FFT to identify and extract the acoustic signals available in the underwater channel that are corrupted due to various ambient noises over a range of 100 Hz to 10 kHz in a shallow water region. Data for analysis are collected at a depth of 5 m and 10 m offshore Chennai at the Bay of Bengal. The algorithm is validated for different sets of known and unknown reference signals. It is observed that the proposed EMD algorithm identifies and extracts the reference signals against various ambient noises. Significant SNR improvement is also achieved for underwater acoustic signals.

关键词： EMD IMF SNR ambient noises underwater acoustic signals FFT

维普期刊数据库

Grey Wolf Optimizer Based Deep Learning for Pancreatic Nodule Detection

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第4期36卷 97-112页

作者： T.Thanya S.Wilfred Franklin department of ece Universal College of Engineering and Technology627117Tamil NaduIndia department of ece CSI Institute of TechnologyThovalai629302Tamil NaduIndia

At an early point,the diagnosis of pancreatic cancer is mediocre,since the radiologist is skill deﬁ*** threats have been posed due to the above reasons,hence became mandatory for the need of skilled ***,it also became a time-consuming *** the need for automated diagnosis became *** order to identify the tumor accurately,this research pro-poses a novel Convolution Neural Network(CNN)based superior image classi-ﬁcation *** proposed deep learning classiﬁcation strategy has a precision of 97.7%,allowing for more effective usage of the automatically exe-cuted feature extraction technique to diagnose cancer *** analysis with CNN-Grey Wolf Optimization(GWO)is carried based on varied testing and training *** suggested study is carried out at a rate of 90%–10%,80%–20%,and 70%–30%,indicating the robustness of the proposed research *** show that the suggested method is ***-CNN is reli-able and accurate relative to other detection methods available in the literatures.

关键词： Convolution neural network deep learning technique feature extraction grey wolf optimizer

Thinned array antenna synthesis using modified binary particle swarm optimization with minimization of sidelobes

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2023年第1期16卷 158-170页

作者： Gayatri Allu M.Surendra Kumar A.M.Prasad Eece GITAMVisakhapatnamIndia department of ece KLR College of Engineering and TechnologyKhammamIndia department of ece University College of Engineering JNTUKKakinadaIndia

Purpose-The purpose of this paper is to propose radiating system by avoiding electromagnetic interference in unwanted directions and to radiate the energy in the required direction with an optimization ***/methodology/approach-Practically,multiple,incompatible variables require concurrent boost on a synthesis of systematic antenna *** authors have worked out the main statistic penalty function to ensure all the ***,MBPSO(Modified Binary Particle Swarm Optimization)is developed and introduced thin planar synthesis *** sigmoid function is used to update the particle *** analytical demonstrations have been carried out,and the exhibited methods are predominant than the ***-A 20310 planar antenna array is synthesized using modified *** authors have suppressed the PSLL in two principal planes and as well as in the entire f *** results state that MBPSO outperforms the other binary BPSO,BCSO,ACO,RGA,GAoptimization *** achieved a51.84 dB PSLL level,whereas BPSO achieved48.57 dB with the same 50%***/value-Planar array antenna formation is one of the most complex syntheses because the array gets filled with more antenna *** machine-like complication and implementation of such an antenna arrangement with a broad opening would be *** is not easy to control the required radiation patterns shape by using a uniform feeding *** get better flexibility for sustaining the sidelobe levelheaded along with consistent amplitude *** as far as prominence has been given to the evolutionary algorithm,find an ideal solution for objective array combinational problems.

关键词： Planar array Thinning PSO Antenna array Sidelobe level Constraints Paper type Research paper