检索结果-南通市图书馆

Effective and Efficient Video Compression by the deep Learning Techniques

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第5期45卷 1047-1061页

作者： karthick Panneerselvam k.Mahesh V.L.Helen Josephine A.Ranjith kumar Department of Computer Applications Alagappa UniversityKaraikudiIndia Department of Computer Science and Engineering lovely professional UniversityPhagwaraPunjabIndia School of Business and Management Christ UniversityBengaluruKarnatakaIndia

deep learning has reached many successes in Video *** has become a growing important part of our daily digital *** advancement of better resolution content and the large volume offers serious challenges to the goal of receiving,distributing,compressing and revealing highquality video *** this paper we propose a novel Effective and Efficient video compression by the deep Learning framework based on the flask,which creatively combines the deep Learning Techniques on Convolutional Neural Networks(CNN)and Generative Adversarial Networks(GAN).The video compression method involves the layers are divided into different groups for data processing,using CNN to remove the duplicate frames,repeating the single image instead of the duplicate images by recognizing and detecting minute changes using GAN and recorded with Long Short-Term Memory(LSTM).Instead of the complete image,the small changes generated using GAN are substituted,which helps with frame-level *** wise comparison is performed using k-nearest Neighbours(kNN)over the frame,clustered with k-means and Singular Value Decomposition(SVD)is applied for every frame in the video for all three colour channels[Red,Green,Blue]to decrease the dimension of the utility matrix[R,G,B]by extracting its latent *** frames are packed with parameters with the aid of a codec and converted to video format and the results are compared with the original *** experiments on several videos with different sizes,duration,Frames per second(FPS),and quality results demonstrated a significant resampling *** normal,the outcome delivered had around a 10%deviation in quality and over half in size when contrasted,and the original video.

关键词： Convolutional neural networks(CNN) generative adversarial network(GAN) singular value decomposition(SVD) k-nearest neighbours(kNN) stochastic gradient descent(SGD) long short-term memory(LSTM)

deep Convolutional Network Based Machine Intelligence Model for Satellite Cloud Image Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2023年第1期6卷 32-43页

作者： kalyan kumar Jena Sourav kumar Bhoi Soumya Ranjan Nayak Ranjit Panigrahi Akash kumar Bhoi Department of Computer Science and Engineering Parala Maharaja Engineering CollegeBerhampur 761003India Amity School of Engineering and Technology Amity UniversityUttar Pradesh 201303India Department of Computer Applications Sikkim Manipal Institute of TechnologySikkim Manipal UniversitySikkim 737102India Directorate of Research Sikkim Manipal UniversityGangtokSikkim 737102India

As a huge number of satellites revolve around the earth,a great probability exists to observe and determine the change phenomena on the earth through the analysis of satellite images on a real-time ***,classifying satellite images plays strong assistance in remote sensing communities for predicting tropical *** this article,a classification approach is proposed using deep Convolutional Neural Network(DCNN),comprising numerous layers,which extract the features through a downsampling process for classifying satellite cloud *** is trained marvelously on cloud images with an impressive amount of prediction *** time decreases for testing images,whereas prediction accuracy increases using an appropriate deep convolutional network with a huge number of training dataset *** satellite images are taken from the Meteorological&Oceanographic Satellite Data Archival Centre,the organization is responsible for availing satellite cloud images of India and its *** proposed cloud image classification shows 94% prediction accuracy with the DCNN framework.

关键词： satellite images satellite image classification cyclone prediction deep Convolutional Neural Network(DCNN) features layers down-sampling process

Diagnosis and Detection of Alzheimer’s Disease Using Learning Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2023年第4期6卷 504-512页

作者： Gargi Pant Shukla Santosh kumar Saroj kumar Pandey Rohit Agarwal Neeraj Varshney Ankit kumar the Department of Management Doon Business SchoolDehradun 248001India. Jaipuria Institute of Management Jaipur 302033India Department of Computer Engineering and Apllications GLA UniversityMathura 281406India.

In Computer-Aided Detection(CAD)brain disease classification is a vital ***’s Disease(AD)and brain tumors are the primary reasons of *** studies of these diseases are carried out by Magnetic Resonance Imaging(MRI),Positron Emission Tomography(PET),and Computed Tomography(CT)scans which require expertise to understand the *** disease is the most prevalent in the elderly and can be fatal in its later *** result can be determined by calculating the mini-mental state exam score,following which the MRI scan of the brain is *** from that,various classification algorithms,such as machine learning and deep learning,are useful for diagnosing MRI ***,they do have some limitations in terms of *** paper proposes some insightful pre-processing methods that significantly improve the classification performance of these MRI ***,it reduced the time it took to train the model of various pre-existing learning algorithms.A dataset was obtained from Alzheimer’s Disease Neurological Initiative(ADNI)and converted from a 4D format to a 2D *** clipping,grayscale image conversion,and histogram equalization techniques were used to pre-process the *** pre-processing,we proposed three learning algorithms for AD classification,that is random forest,XGBoost,and Convolution Neural Networks(CNN).Results are computed on dataset and show that it outperformed with exiting work in terms of accuracy is 97.57%and sensitivity is 97.60%.

关键词： alzheimer’s disease deep learning random forest XGBoost

Climatology, trend of aerosol-cloud parameters and their correlation over the Northern Indian Ocean

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geoscience Frontiers 2023年第4期14卷 173-186页

作者： Harshbardhan kumar Shani Tiwari Academy of Scientific and Innovative Research(AcSIR) Ghaziabad201002India Aerosol and Cloud Research Lab Geological Oceanography DivisionCSIR–National Institute of OceanographyGoa403004India

Aerosols are one of the important atmospheric constituents and exert indirect impact on climate through the modification of microphysical and radiative properties of clouds that in turn perturb the precipitation ***,the long term quantification of changes in aerosol and cloud characteristics and their interactions on both temporal as well as spatial scale will provide a crucial information for the better assessment of future climate *** present study,18 years(2003-2020)MODerate Resolution Imaging Spectro-radiometer(MODIS)derived aerosol-cloud dataset over the Northern Indian Ocean(NIO)were analysed to assess climatology and trend of aerosol,cloud characteristics and their *** found a strong heterogeneity in spatio-temporal variation of aerosol and cloud parameters over the NIO that are more prominent for the coastal *** climatological mean of aerosol loading is found high(AOD≥0.5)over the outflow region along the Indian sub-continent and low(AOD≤0.2)over the northern equatorial open *** climatological mean of cloud properties shows dominance of optically thicker deep convective(CTPk)clouds over the southern Bay of Bengal(BoB)and thinner shallow(CTP>700 hPa and CTT>273 k)over the northwestern Arabian Sea(AS).Similarly,bigger effective radii(>17µm)observed along the equatorial open ocean whereas smaller CER(k yr^(-1) and-1.160 hPa yr^(-1),*** also perform similar analysis for seven sub-region of interest(R1 to R7)across the NIO and results show a decreasing pattern in AOD(-0.001 yr^(-1))at R4 against maximum mean AOD(0.44±0.03).However,coastal sub-regions R1 and R5 illustrate maximum increase in aerosol loading(>0.

关键词： Aerosol Cloud properties Northern Indian Ocean Climatology Trend Correlation

A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Research 2022年第2期7卷 204-219页

作者： Rakesh kumar Pandey Anil kumar Ajay Mandal Department of Petroleum and Energy Studies School of Engineering and TechnologyDIT UniversityDehradun248009India Data Science Research Group School of ComputingDIT UniversityDehradun248009India Department of Petroleum Engineering Indian Institute of Technology(Indian School of Mines)Dhanbad826004India

A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant pressure outer boundary *** pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and,further,regression to estimate output *** noise was added to analytical models while generating the synthetic training *** hyperparameters were regulated to perform model optimization,resulting in a batch size of 64,Adam optimization algorithm,learning rate of 0.01,and 80:10:10 data split ratio as the best choices of *** perfor-mance accuracy also increased with an increase in the number of samples during *** classification and regression metrics have been used to evaluate the performance of the *** paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test *** proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308,respectively,in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.

关键词： Well test Reservoir characterization Automatic interpretation Prediction model Hyperparameter tuning Performance indicator

Piecewise linear programming approach to solve multi-objective matrix games with I-fuzzy goals

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 Control and Decision 2021年第1期8卷 1-13页

作者： Sandeep.kumar Department of Mathematics Ch.Charan Singh UniversityMeerut 250004Uttar PradeshIndia

The intuitionistic fuzzy set(I-fuzzy set)plays an effective role in game theory when players face‘neither this nor that’situation to set their *** study presents a maxmin–minmax solution to multi-objective two person zero-sum matrix games with I-fuzzy *** this article,a class of piecewise linear membership and non-membership functions for I-fuzzy goals is *** functions are more effective in real games because marginal rate of increase(decrease)of such membership functions(non-membership functions)is different in different intervals of tolerance ***,one numerical example is given to examine the effectiveness and advantages of the proposed results.

关键词： Intuitionistic fuzzy set multi-objective matrix game I-fuzzy goals maxmin-minmax solution piecewise linear function

kinematic Modeling for Biped Robot Gait Trajectory Using Machine Learning Techniques

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 Bionic Engineering 2022年第2期19卷 355-369页

作者： Bharat Singh Ankit Vijayvargiya Rajesh kumar Department of Electrical Engineering Malaviya National Institute of TechnologyJaipur 302017India

This paper presents the predictive models for biped robot trajectory *** models are parametrizing as a continuous function of joint angle *** a previous work,the authors had collected the human locomotion dataset at RAMAN Lab,MNIT,Jaipur,*** MNIT gait dataset consists of walking data on a plane surface of 120 human subjects from different age groups and ***-two machine learning models(linear,support vector,k-nearest neighbor,ensemble,probabilistic,and deep learning)trained using the collected *** addition,two types of mapping,(a)one-to-one and(b)many-to-one,are presented for each *** mapping models act as a reference policy for the control of joints and prediction of state for the next time instant in advance if the onboard sensor *** show that the deep learning and probabilistic learning models perform better for both types of ***,the probabilistic model outperforms the deep learning-based models in terms of maximum error,because the probabilistic model effectively deals with the prediction *** addition,many-to-one outperforms the one-to-one mapping because it captures the correlation between knee,hip,and ankle ***,this study suggests a many-to-one mapping using the probabilistic model for biped robot trajectory generation.

关键词： kinematic Locomotion Machine learning Prediction Regression

Freeze–dried synthesized bifunctional biopolymer nanocomposite for efficient fluoride removal and antibacterial activity

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 Environmental Sciences 2020年第8期32卷 52-63页

作者： Sapna Nehra Ankita Dhillon Dinesh kumar Department of Chemistry Banasthali VidyapithBanasthaliRajasthan 304022India School of Chemical Sciences Central University of GujaratGandhinagar 382030India

Local fluoride contamination and bacterial infections in potable water have dangerous effects on the human body and are today a global *** this study,we have synthesized a pH-responsive bifunctional biopolymer nanocomposite(HAZ)of humic acid with incorporating aluminum zirconium bimetallic oxide by deep freeze–drying *** nucleation and interconnection of nanoparticles form a highly porous network because of sublimation of frozen *** duo nanocomposite has efficiently worked for fluoride removal and showed potent antibacterial activity against the Escherichia coli Gram-negative and Staphylococcus aureus Gram-positive *** X-ray photoelectron spectroscopy(XPS)analysis demonstrates that the hydroxyl groups act as a pivot in the ion exchange process of adsorption,each element of bimetallic oxide primarily takes part in the adsorption *** maximum adsorption capacity of the adsorbent was 180.62 mg/g at pH *** parameters like Gibbs free energy change(△G0),entropy(△S0),and enthalpy(△H0)indicate that the process was endothermic,feasible,and taken place by a chemisorption *** is the first novel freeze–dried bifunctional biopolymer nanocomposite composed of humic acid natural polymer incorporated with Al–Zr metal oxide,and it exhibited three times higher adsorption efficacy with excellent antibacterial action at a concentration of 5μg/mL of the nanocomposite.

关键词： Bifunctional Disinfection Freeze–dried Langmuir Spontaneous

Modeling a Novel Hyper-Parameter Tuned deep Learning Enabled Malaria Parasite Detection and Classification

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第12期77卷 3289-3304页

作者： Tamal kumar kundu Dinesh kumar Anguraj S.V.Sudha Department of Computer Science&Engineering Koneru Lakshmaiah Education FoundationVaddeswaramAndhra PradeshIndia Department of Artificial Intelligence and Data Science KPR Institute of Engineering and TechnologyCoimbatoreTamil Nadu641407India

A theoretical methodology is suggested for finding the malaria parasites’presence with the help of an intelligent hyper-parameter tuned deep Learning(DL)based malaria parasite detection and classification(HPTDL-MPDC)in the smear images of human peripheral *** existing approaches fail to predict the malaria parasitic features and reduce the prediction *** trained model initiated in the proposed system for classifying peripheral blood smear images into the non-parasite or parasite classes using the available online *** Adagrad optimizer is stacked with the suggested pre-trained deep Neural Network(DNN)with the help of the contrastive divergence method to *** features are extracted from the images in the proposed system to train the DNN for initializing the visible *** smear images show the concatenated feature to be utilized as the feature vector in the proposed ***,hyper-parameters are used to fine-tune DNN to calculate the class labels’*** suggested system outperforms more modern methodologies with an accuracy of 91%,precision of 89%,recall of 93%and F1-score of 91%.The HPTDL-MPDC has the primary application in detecting the parasite of malaria in the smear images of human peripheral blood.

关键词： Malaria parasite classification hyper-parameter deep neural network the feature vector