检索结果-南通市图书馆

Color Image Super-Resolution and Enhancement with Inter-Channel Details at Trivial Cost

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 computer science & Technology 2020年第4期35卷 889-899页

作者： Chuang-Ye Zhang Yan Niu Tie-Ru Wu Xi-Ming Li College of computer science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic computer and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China school of Mathematics Jilin UniversityChangchun 130012China

Image super-resolution is essential for a variety of applications such as medical imaging,surveillance imaging,and satellite imaging,among ***,the most popular color image super-resolution is performed in each color channel *** this paper,we show that the super-resolution quality can be further enhanced by exploiting the cross-channel *** by the High-Quality Linear Interpolation(HQLI)demosaicking algorithm by Malvar et al.,we design an image super-resolution scheme that integrates intra-channel interpolation with cross-channel details by isotropic linear *** its simplicity,our super-resolution method achieves the accuracy comparable with the existing fastest state-of-the-art super-resolution algorithm at 20 times faster *** is well applicable to applications that adopt traditional interpolations,for improved visual quality at trivial computation *** comparative study verifies the effectiveness and efficiency of the proposed super-resolution algorithm.

关键词： image super-resolution isotropic linear interpolation inter-channel detail enhancement low cost

Quantum Particle Swarm Optimization Based Convolutional Neural Network for Handwritten Script Recognition

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6期71卷 5855-5873页

作者： Reya Sharma Baijnath Kaushik Naveen Kumar Gondhi Muhammad Tahir Mohammad Khalid Imam Rahmani school of computer science and Engineering SMVDUJ&KIndia College of Computing and Informatics Saudi Electronic UniversityRiyadhSaudi Arabia

Even though several advances have been made in recent years,handwritten script recognition is still a challenging task in the pattern recognition *** field has gained much interest lately due to its diverse application ***,different methods are available for automatic script *** most of the reported script recognition techniques,deep neural networks have achieved impressive results and outperformed the classical machine learning ***,the process of designing such networks right from scratch intuitively appears to incur a significant amount of trial and error,which renders them *** approach often requires manual intervention with domain expertise which consumes substantial time and computational *** alleviate this shortcoming,this paper proposes a new neural architecture search approach based on meta-heuristic quantum particle swarm optimization(QPSO),which is capable of automatically evolving the meaningful convolutional neural network(CNN)*** computational experiments have been conducted on eight different datasets belonging to three popular Indic scripts,namely Bangla,Devanagari,and Dogri,consisting of handwritten characters and ***,the results imply that the proposed QPSO-CNN algorithm outperforms the classical and state-of-the-art methods with faster prediction and higher accuracy.

关键词： Neuro-evolution quantum particle swarm optimization deep learning convolutional neural networks handwriting recognition

Automatic Extraction of the Sparse Prior Correspondences for Non-Rigid Point Cloud Registration

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 Modeling in Engineering & sciences 2023年第8期136卷 1835-1856页

作者： Yan Zhu Lili Tian Fan Ye Gaofeng Sun Xianyong Fang Department of Sports and Military Education Anhui UniversityHefei230601China school of computer science and Technology Anhui UniversityHefei230601China

Non-rigid registration of point clouds is still far from stable,especially for the largely deformed *** initial correspondences are often adopted to facilitate the ***,there are few studies on how to build them ***,in this paper,we propose a robust method to compute such priors automatically,where a global and local combined strategy is *** priors in different degrees of deformation are obtained by the locally geometrical-consistent point matches from the globally structural-consistent region *** further utilize the matches,this paper also proposes a novel registration method based on the Coherent Point Drift *** method takes both the spatial proximity and local structural consistency of the priors as supervision of the registration process and thus obtains a robust alignment for clouds with significantly different *** and quantitative experiments demonstrate the advantages of the proposed method.

关键词： Non-rigid registration point clouds coherent point drift

Identity-Based Key-Insulated Proxy Signature Without Random Oracles

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 Shanghai Jiaotong university(science) 2011年第5期16卷 557-566页

作者：陈剑洪龙宇陈克非王永涛 Department of computer science and Engineering Shanghai Jiaotong University school of computer Engineering Huaiyin Institute of Technology Shanghai Key Laboratory of Scalable Computing and System Shanghai Jiaotong University

In an identity based proxy signature (IBPS) scheme, a designated proxy signer can generate the signature on behalf of an original signer. Traditional IBPS schemes normally rely on the assumption that private keys are kept perfectly secure. However, due to viruses, worms or other break-ins allowed by operating-system holes, key exposure seems inevitable. To minimize the damage caused by key exposure in IBPS, we propose an identity-based key-insulated proxy signature (IBKIPS) scheme in the standard model, i.e. without random oracles.

关键词： key-insulated proxy signature identity-based standard model

RankXGB-Based Enterprise Credit Scoring by Electricity Consumption in Edge Computing Environment

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4期75卷 197-217页

作者： Qiuying Shen Wentao Zhang Mofei Song State Grid Suzhou Power Supply Company Suzhou215004China school of computer science and Engineering Southeast UniversityNanjing210000China

With the rapid development of the internet of things(IoT),electricity consumption data can be captured and recorded in the IoT cloud *** provides a credible data source for enterprise credit scoring,which is one of the most vital elements during the financial decision-making ***,this paper proposes to use deep learning to train an enterprise credit scoring model by inputting the electricity consumption *** of predicting the credit rating,our method can generate an absolute credit score by a novel deep ranking model–ranking extreme gradient boosting net(rankXGB).To boost the performance,the rankXGB model combines several weak ranking models into a strong *** to the high computational cost and the vast amounts of data,we design an edge computing framework to reduce the latency of enterprise credit ***,we design a two-stage deep learning task architecture,including a cloud-based weak credit ranking and an edge-based credit score *** the first stage,we send the electricity consumption data of the evaluated enterprise to the computing cloud server,where multiple weak-ranking networks are executed in parallel to produce multiple weak-ranking *** the second stage,the edge device fuses multiple ranking results generated in the cloud server to produce a more reliable ranking result,which is used to calculate an absolute credit score by score *** experiments demonstrate that our method can achieve accurate enterprise credit evaluation quickly.

关键词： Electricity consumption enterprise credit scoring edge computing deep learning

Scale-free brain ensemble modulated by phase synchronization

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 Zhejiang University-science C(computers and Electronics) 2014年第10期15卷 821-831页

作者： Dan WU Chao-yi LI Jie LIU Jing LU De-zhong YAO Department of Biomedical Engineering School of Computer and Information TechnologyBeijing Jiaotong University NeuroInformation of Ministry of Education University of Electronic Science and Technology of China

To listen to brain activity as a piece of music, we proposed the scale-free brainwave music(SFBM) technology, which could translate the scalp electroencephalogram(EEG) into music notes according to the power law of both EEG and music. In the current study, this methodology was further extended to a musical ensemble of two channels. First, EEG data from two selected channels are translated into musical instrument digital interface(MIDI) sequences, where the EEG parameters modulate the pitch, duration, and volume of each musical note. The phase synchronization index of the two channels is computed by a Hilbert transform. Then the two MIDI sequences are integrated into a chorus according to the phase synchronization index. The EEG with a high synchronization index is represented by more consonant musical intervals, while the low index is expressed by inconsonant musical intervals. The brain ensemble derived from real EEG segments illustrates differences in harmony and pitch distribution during the eyes-closed and eyes-open states. Furthermore, the scale-free phenomena exist in the brainwave ensemble. Therefore, the scale-free brain ensemble modulated by phase synchronization is a new attempt to express the EEG through an auditory and musical way, and it can be used for EEG monitoring and bio-feedback.

关键词： Brainwave Ensemble Music Scale-free Synchronization

Stock Price Prediction Using Predictive Error Compensation Wavelet Neural Networks

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 2021年第9期68卷 3577-3593页

作者： Ajla Kulaglic Burak Berk Ustundag Graduate school of science Engineering and Technology Istanbul Technical UniversityIstanbulTurkey Department of computer Engineering Istanbul Technical UniversityIstanbulTurkey

:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through *** this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that improves the prediction of next day closing *** the proposed model we use multiple neural networks where the first one uses the closing stock prices from multiple-scale time-domain *** additional network is used for error estimation to compensate and reduce the prediction error of the main network instead of using *** performance of the proposed model is evaluated using six different stock data samples in the New York stock *** results have demonstrated significant improvement in forecasting accuracy in all cases when the second network is used in accordance with the first one by adding the *** RMSE error is 33%improved when the proposed PEC-WNN model is used compared to the Long ShortTerm Memory(LSTM)***,through the analysis of training mechanisms,we found that using the updated training the performance of the proposed model is *** contribution of this study is the applicability of simultaneously different time frames as *** the predictive error compensation not only reduces the error rate but also helps in avoiding overfitting problems.

关键词： Predictive error compensating wavelet neural network time series prediction stock price prediction neural networks wavelet transform

Extended Forgery Detection Framework for COVID-19 Medical Data Using Convolutional Neural Network

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 2021年第9期68卷 3773-3787页

作者： Sajid Habib Gill Noor Ahmed Sheikh Samina Rajpar Zain ul Abidin N.Z.Jhanjhi Muneer Ahmad Mirza Abdur Razzaq Sultan S.Alshamrani Yasir Malik Fehmi Jaafar Department of computer science Shah Abdul Latif UniversityKhairpur66020SindhPakistan National College of Business Administration&Economics Lahore54000Pakistan school of computer science and Engineering SCETaylor’s UniversityMalaysia Department of Information Systems Faculty of Computer Science&Information TechnologyUniversiti MalayaMalaysia Department of Information Technology College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of computer science College of Engineering&Computing SciencesNew York Institute of TechnologyVancouverCanada The computer Research Institute of Montreal QuebecCanada

Medical data tampering has become one of the main challenges in the field of secure-aware medical data *** of normal patients’medical data to present them as COVID-19 patients is an illegitimate action that has been carried out in different ways ***,the integrity of these data can be *** detection is a method of detecting an anomaly in manipulated forged *** appropriate number of features are needed to identify an anomaly as either forged or non-forged data in order to find distortion or tampering in the original *** neural networks(CNNs)have contributed a major breakthrough in this type of *** has been much interest from both the clinicians and the AI community in the possibility of widespread usage of artificial neural networks for quick diagnosis using medical data for early COVID-19 patient *** purpose of this paper is to detect forgery in COVID-19 medical data by using CNN in the error level analysis(ELA)by verifying the noise pattern in the *** proposed improved ELA method is evaluated using a type of data splicing forgery and sigmoid and ReLU phenomenon *** proposed method is verified by manipulating COVID-19 data using different types of forgeries and then applying the proposed CNN model to the data to detect the data *** results show that the accuracy of the proposed CNN model on the test COVID-19 data is approximately 92%.

关键词： Data security data privacy medical-data forgery COVID-19 convolutional neural network machine learning deep learning

Information Capacity and Transmission in a Courbage-Nekorkin-Vdovin Map-Based Neuron Model

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 Physics Letters 2017年第4期34卷 120-123页

作者： Yuan Yue Yu-Jiang Liu Ya-Lei Song Yong Chen Lian-Chun Yu Institute of Theoretical Physics Lanzhou University Lanzhou 730000 school of Mathematics and computer science Northwest University for Nationalities Lanzhou 730000 school of Physics and Nuclear Energy Engineering Beihang University Beijing 100191

The map-based neuron models have received attention as valid phenomenological neuron models due to their computational efficiency and flexibility to generate rich patterns. Here we evaluate the information capacity and transmission of the Courbage-Nekorkin Vdovin （CNV） map-based neuron model with a bursting and tonic firing mode in response to external pulse inputs, in both temporal and rate coding schemes. We find that for both firing modes, the CNV model could capture the essential behavior of the stochastic Hodgkin-Huxley model in information transmission for the temporal coding scheme, with regard to the dependence of total entropy, noise entropy, information rate, and coding efficiency on the strength of the input signal. However, in tonic firing mode, it fails to replicate the input strength-dependent information rate in the rate coding scheme. Our results suggest that the CNV map-based neuron model could capture the essential behavior of information processing of typical conductance-based neuron models.

关键词： PHENOMENOLOGICAL theory (Physics) NEURONS STOCHASTIC models ENTROPY DATA transformations (Statistics)