检索结果-南通市图书馆

Chinese Journal of Electrical Engineering 2022年第3期8卷 57-75页

作者： Sreedhar Madichetty Avram John Neroth sukumar Mishra B.Chitti Babu Department of Electrical and Electronics Engineering Mahindra University Ecole CentraleHyderabad 500043India Department of Electrical Engineering Indian Institute of TechnologyDelhi 110016India Department of Electronics and Communication Engineering Indian Institute of Information TechnologyDesign and ManufacturingKanchipuram 600127India

Medium-duty/heavy-duty trucks(MD/HDTs)are yet to be included in India’s electric mobility *** the improvement of electric vehicle(EV)technologies,there is a growing interest in battery-electric trucks(BETs)from original equipment manufacturers(OEMs).The time is opportune to consider electrification as a future direction for road freight in ***,this article presents the results of an energy consumption simulation study of a BET under Indian *** study specifically considered an MDBET over a domestic drive *** energy consumption figures can facilitate future studies that analyze the technical and practical feasibility of BETs in the *** addition,the article provides the requisite groundwork for BET modeling for a simulation study by reviewing available EV powertrain systems and *** powertrain considerations are thereby obtained for a typical medium-duty/heavy-duty battery-electric truck(MD/HDBET)in the Indian context.

关键词： Electric truck heavy-duty battery electric truck medium-duty battery electric truck energy consumption vehicle powertrain

Feature Enhanced Stacked Auto Encoder for Diseases Detection in Brain MRI

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第8期76卷 2551-2570页

作者： Umair Muneer Butt Rimsha Arif sukumar Letchmunan Babur Hayat Malik Muhammad Adil Butt School of Computer Sciences Universiti Sains MalaysiaPenang1180Malaysia Department of Computer Science and IT The University of ChenabGujrat50700Pakistan

The detection of brain disease is an essential issue in medical and research *** learning techniques have shown promising results in detecting and diagnosing brain diseases using magnetic resonance imaging(MRI)*** techniques involve training neural networks on large datasets of MRI images,allowing the networks to learn patterns and features indicative of different brain ***,several challenges and limitations still need to be addressed further to improve the accuracy and effectiveness of these *** paper implements a Feature Enhanced Stacked Auto Encoder(FESAE)model to detect brain *** standard stack auto encoder’s results are trivial and not robust enough to boost the system’s ***,the standard Stack Auto Encoder(SAE)is replaced with a Stacked Feature Enhanced Auto Encoder with a feature enhancement function to efficiently and effectively get non-trivial features with less activation energy froman *** proposed model consists of four ***,pre-processing is performed to remove noise,and the greyscale image is converted to Red,Green,and Blue(RGB)to enhance feature details for discriminative feature ***,feature Extraction is performed to extract significant features for classification using DiscreteWavelet Transform(DWT)and ***,classification is performed to classify MRI images into four major classes:Normal,Tumor,Brain Stroke,and Alzheimer’***,the FESAE model outperforms the state-of-theart,machine learning,and deep learning methods such as Artificial Neural Network(ANN),SAE,Random Forest(RF),and Logistic Regression(LR)by achieving a high accuracy of 98.61% on a dataset of 2000 MRI *** proposed model has significant potential for assisting radiologists in diagnosing brain diseases more accurately and improving patient outcomes.

关键词： Brain diseases deep learning feature enhanced stacked auto encoder stack auto encoder

Imbalanced Classification in Diabetics Using Ensembled Machine Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 4397-4409页

作者： M.Sandeep Kumar Mohammad Zubair Khan sukumar Rajendran Ayman Noor A.Stephen Dass J.Prabhu School of Information Technology and Engineering Vellore Institute of TechnologyVelloreTamil Nadu632014India Department of Computer Science and Information Taibah UniversityMedinaSaudi Arabia College of Computer Science and Engineering Taibah UniversityMedinaSaudi Arabia

Diabetics is one of the world’s most common diseases which are caused by continued high levels of blood *** risk of diabetics can be lowered if the diabetic is found at the early *** recent days,several machine learning models were developed to predict the diabetic presence at an early *** this paper,we propose an embedded-based machine learning model that combines the split-vote method and instance duplication to leverage an imbalanced dataset called PIMA Indian to increase the prediction of *** proposed method uses both the concept of over-sampling and under-sampling along with model weighting to increase the performance of *** measures such as Accuracy,Precision,Recall,and F1-Score are used to evaluate the *** results we obtained using K-Nearest Neighbor(kNN),Naïve Bayes(NB),Support Vector Machines(SVM),Random Forest(RF),Logistic Regression(LR),and Decision Trees(DT)were 89.32%,91.44%,95.78%,89.3%,81.76%,and 80.38%*** SVM model is more efficient than other models which are 21.38%more than exiting machine learning-based works.

关键词： Diabetics classification imbalanced data split-vote instance duplication

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 5017-5033页

作者： Umair Muneer Butt Hadiqa Aman Ullah sukumar Letchmunan Iqra Tariq Fadratul Hafinaz Hassan Tieng Wei Koh School of Computer Sciences Universiti Sains MalaysiaPenang1180Malaysia Department of Computer Science The University of ChenabGujrat50700Pakistan Department of Software Engineering and Information System Universiti Putra MalaysiaSelangor43400Malaysia

Human Activity Recognition(HAR)is an active research area due to its applications in pervasive computing,human-computer interaction,artificial intelligence,health care,and social ***,dynamic environments and anthropometric differences between individuals make it harder to recognize *** study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world *** uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural ***,the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification *** state-of-the-art pre-trained models are exploited to find the best model for spatial feature *** temporal sequence,this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short TermMemory(BiLSTM)to capture *** state-of-the-art datasets,UCF101 and HMDB51,are used for evaluation *** addition,seven state-of-the-art optimizers are used to fine-tune the proposed network ***,this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network(CNN),where two streams use RGB *** contrast,the other uses optical flow ***,the proposed ensemble approach using max hard voting outperforms state-ofthe-art methods with 96.30%and 90.07%accuracies on the UCF101 and HMDB51 datasets.

关键词： Human activity recognition deep learning transfer learning neural network ensemble learning spatio-temporal

A comprehensive review of the effect of different kinetic promoters on methane hydrate formation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2021年第4期34卷 1-16页

作者： Ekta Chaturvedi sukumar Laik Ajay Mandal Gas Hydrates Laboratory Petroleum Engineering DepartmentIndian Institute of Technology(ISM)DhanbadIndia

Gas hydrates have recently emerged as a better alternative for the production,storage,and transportation of natural ***,factors like slow formation rate and limited storage capacity obstruct the possible industrial application of this *** types of promoters and synergists have been developed that can improve the kinetics and storage capacity of gas *** review focuses on different kinetic promoters and synergists that can be utilized to enhance the storage capacity of *** main characteristics,structure and the possible limitations of the use of these promoters are likewise portrayed in *** relationship between structure and storage capacity of hydrates have also been discussed in the *** status of production of gas from hydrates,their restrictions,and future difficulties have additionally been addressed in the ensuing areas of the review.

关键词： Gas hydrates Structure Storage capacity Kinetic promoters Nano-materials Surfactants

An Efficient Approach for Simulation of Water Levels due to the Nonlinear Interaction of Tide and Surge Along the Coast of Bangladesh

在线全文

学校读者我要写书评

暂无评论

China Ocean Engineering 2020年第4期34卷 537-546页

作者： Gour Chandra Paul sukumar Senthilkumar Rana Pria Department of Mathematics University of RajshahiRajshahi-6205Bangladesh School of Mathematical Sciences Universiti Sains MalaysiaPulau Pinang-11800Malaysia Mathematics Discipline ScienceEngineering&Technology SchoolKhulna UniversityKhulna-9208.Bangladesh

The ultimate goal and highlight of this paper are to explore water levels along the coast of Bangladesh efficiently due to the nonlinear interaction of tide and surge by employing the method of lines(MOLs)with the aid of newly proposed RKAHeM(4,4)*** this regard,the spatial derivatives of shallow water equations(SWEs)were discretized by means of a finite difference method to obtain a system of ordinary differential equations(ODEs)of initial valued with time as an independent *** obtained system of ODEs was solved by the RKAHeM(4,4)***-way nested grid technique was exercised to incorporate coastal complexities closely with minimum computational cost.A stable tidal oscillation was produced over the region of interest by applying the most influential tidal constituent M2 along the southern open boundary of the outer *** newly developed model was applied to estimate water levels due to the non-linear interaction of tide and surge associated with the catastrophic cyclone April 1991 along the coast of *** approach employed in the study was found to perform well and ensure conformity with real-time observations.

关键词： method of lines RKAHeM(4 4)technique error estimation storm surge nested grid

Discrete Event System Framework for Fault Diagnosis with Measurement Inconsistency:Case Study of Rogue DHCP Attack

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第3期6卷 789-806页

作者： Mayank Agarwal Santosh Biswas sukumar Nandi IEEE the Department of Computer Science and Engineering Indian Institute of Technology Guwahati

Fault detection and diagnosis(FDD) facilitates reliable operation of systems. Various approaches have been proposed for FDD like Analytical redundancy(AR), Principal component analysis(PCA), Discrete event system(DES) model etc., in the literature. Performance of FDD schemes greatly depends on accuracy of the sensors which measure the system *** to various reasons like faults, communication errors etc.,sensors may occasionally miss or report erroneous values of some system parameters to FDD engine, resulting in measurement inconsistency of these parameters. Schemes like AR, PCA etc.,have mechanisms to handle measurement inconsistency, however,they are computationally heavy. DES based FDD techniques are widely used because of computational simplicity, but they cannot handle measurement inconsistency efficiently. Existing DES based schemes do not use Measurement inconsistent(MI)parameters for FDD. These parameters are not permanently unmeasurable or erroneous, so ignoring them may lead to weak diagnosis. To address this issue, we propose a Measurement inconsistent discrete event system(MIDES) framework, which uses MI parameters for FDD at the instances they are measured by the sensors. Otherwise, when they are unmeasurable or erroneously reported, the MIDES invokes an estimator diagnoser that predicts the state(s) the system is expected to be in, using the subsequent parameters measured by the other sensors. The efficacy of the proposed method is illustrated using a pumpvalve system. In addition, an MIDES based intrusion detection system has been developed for detection of rogue dynamic host configuration protocol(DHCP) server attack by mapping the attack to a fault in the DES framework.

关键词： Fault diagnosis instrasion detection system (IDS) measurement inconsistent discrete event system (DES) rogue dynamic host configuration protocol (DHCP) server

Effect of SDS/THF on thermodynamic and kinetic properties of formation of hydrate from a mixture of gases(CH_4+C_2H_6+C_3H_8) for storing gas as hydrate

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2016年第3期25卷 409-417页

作者： Himangshu Kakati Ajay Mandal sukumar Laik Gas Hydrate Laboratory Department of Petroleum Engineering Indian School of Mines

In this work, the effect of sodium dodecyl sulfate(SDS) and combined effect of sodium dodecyl sulfate(SDS) and tetrahydrofuran(THF) on thermodynamic and kinetic properties of CH4+C2H6+C3H8hydrate formation have been studied. Four different concentrations of sodium dodecyl sulfate(100 ppm, 500 ppm,1000 ppm and 1500 ppm) have been used to see its effect on phase equilibrium condition and formation kinetics. Though sodium dodecyl sulfate(SDS) does not vary the pressure–temperature condition of hydrate formation, it has a prominent favorable effect on induction time, gas consumption, storage capacity and formation rate. The addition of 3%(mol) tetrahydrofuran(THF) to water + SDS system results in large shifts in phase equilibrium boundary to lower pressure and higher temperature. It has been noticed that the addition of tetrahydrofuran further enhances the formation rate. So the mixture of sodium dodecyl sulfate(SDS) and tetrahydrofuran(THF) can be effectively used as promoter for storing natural gas as hydrate.

关键词： Phase equilibrium Induction time Formation rate Storage capacity

Memristor based object detection using neural network

在线全文

学校读者我要写书评

暂无评论

High-Confidence Computing 2022年第4期2卷 52-56页

作者： Ravikumar KI sukumar R Department of E&CE Jain UniversityBangaloreKarnatakaIndia Department of E&CE Jain Institute of TechnologyDavangereKarnatakaIndia

With the increasing growth of AI,big data analytics,cloud computing,and Internet of Things applications,devel-oping memristor devices and related hardware systems to compute the deep learning application needs extensive data calculations with low power consumption and lesser chip *** learning model is one of the AI methods which is gaining importance in object detection,natural language processing,and pattern recognition.A large amount of data handling is essential for driving the deep learning model with less power *** address these issues,the paper proposed the Memristor-based object detection on the CIFAR-10 dataset and achieved an accuracy of 85 *** memtorch package in python is employed to predict the objects for implementation.

关键词： Memristor Deep learning Object detection CIFAR-10

Emphasizing privacy and security of edge intelligence with machine learning for healthcare

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 2022年第1期15卷 92-109页

作者： sukumar Rajendran Sandeep Kumar Mathivanan Prabhu Jayagopal Kumar Purushothaman Janaki Benjula Anbu Malar Manickam Bernard Suganya Pandy Manivannan Sorakaya Somanathan Vellore Institute of Technology VelloreIndia

Purpose-Artificial Intelligence(AI)has surpassed expectations in opening up different possibilities for machines from different walks of *** service providers are *** computing reduces latency,improving availability and saving ***/methodology/approach-The exponential growth in tensor processing unit(TPU)and graphics processing unit(GPU)combined with different types of sensors has enabled the pairing of medical technology with deep learning in providing the best patient care.A significant role of pushing and pulling data from the cloud,big data comes into play as velocity,veracity and volume of data with IoT assisting doctors in predicting the abnormalities and providing customized treatment based on the patient electronic health record(EHR).Findings-The primary focus of edge computing is decentralizing and bringing intelligent IoT devices to provide real-time computing at the point of presence(PoP).The impact of the PoP in healthcare gains importance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of *** impact edge computing of the PoP in healthcare gains significance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of ***/value-The utility value of sensors data improves through the Laplacian mechanism of preserved PII response to each query from the *** scalability is at 50%with respect to the sensitivity and preservation of the PII values in the local ODL.

关键词： Edge computing Deep learning Cloud computing Fog computing Electronic health record Tensor processing unit Graphics processing unit Point of presence