最新刊期
卷 47 ， 期 1 ， 2019
- 摘要：Small sample condition of communication radio signal caused poor individual recognition on radios.To solve this problem,a method about communication radio individual recognition based on semi-supervised rectangular network was proposed innovatively.Firstly,the square integral bispectrum feature was extracted from radio signal and then was corrupted by Gaussian noise.The corrupted sample was passed to the encoder of semi-supervised rectangular network for supervised training.The trained parameterization was then mirrored to decoder through the lateral connection across the model.And the output was forced by decoder through unsupervised learning to be close to the clean input.Then the essential feature extracted was referred as the individual feature of radio signals.Individual recognition was finally accomplished by a softmax classifier.The experiment results on several radio datasets collected in actual environment indicated that the method had superior performance on identifying radio individuals with the same types under small sample condition.关键词：small sample condition;radio individual recognition;semi-supervised learning;square integral bispectra;auto-encoder201|455|5更新时间：2025-07-16
- 摘要：In response to the problem of dynamic channel state information in complex indoor environment,this paper proposes an adaptive and robust Kalman filter approach for indoor Wi-Fi/Pedestrian Dead Reckoning (PDR) fusion localization.This approach conducts the multiple location information fusion of Wi-Fi propagation model and PDR to infer the optimal location estimate of the user.At the same time,based on the filter feedback mechanism,the fusion localization result is used to dynamically modify the path loss exponent in weighted least square method as well as the observation covariance in filter model with the purpose of guaranteeing that the Wi-Fi propagation model is close to the real indoor environment.The experimental results indicate that the proposed method is capable of well solving the problems of low localization accuracy by using the Wi-Fi solely and accumulative error in PDR.Furthermore,the real-time modification of path loss exponent and observation covariance improves the stability of the proposed fusion localization system.关键词：indoor fusion localization;robust Kalman filter;Wi-Fi;pedestrian dead reckoning;environmental adaptation357|387|6更新时间：2025-07-16
- 摘要：As mobile devices usually have limited computing and storage resources,it is difficult to develop an anonymous two-party authentication scheme possessing performance efficiency and strong security simultaneously.The existing two-party authenticated key agreement schemes for roaming service do not resist the attack of ephemeral secrets reveal,and have high computation costs.Therefore,a new anonymous two-party authenticated key agreement scheme for roaming service was proposed in this paper,in which an efficiency identity-based signcryption scheme was adopted to achieve mutual authentication and unlinkability.The identity-based signcryption scheme is based on the Schnorr signature scheme,a very efficient elliptic curve digital signature algorithm,which greatly reduce the total computation cost during one authentication session in comparison with existing authentication schemes.Furthermore,to achieve the security of the ephemeral secrets reveal resistance in the new authentication scheme,we constructed a computational Diffie-Hellman problem instance that required two participants to compute a value by combining its own private key with its peer's public key,respectively.We extended the eCK model to model the two-party authenticated key agreement schemes for roaming service,discussed the distinction between the security game of authenticated key agreement schemes for mobile roaming service and the general one,and demonstrated that the new scheme was provably secure in the extended eCK model.The conclusion indicates that the security of the new scheme can be reduced to solve the computational Diffie-Hellman problem on an elliptic curve over finite field by a polynomial-time adversary.Comparative analysis shows that our scheme has stronger security,needs less cryptography library,and has lower computing and communication overheads.The new scheme can be used to provide secure roaming authentication for resource constrained mobile terminals in global mobility networks,Internet of things or ubiquitous networks.关键词：authenticated key agreement;mobile roaming service;identity-based cryptography;computational Diffie-Hellman problem;eCK (extended Canetti-Krawczyk) model126|283|5更新时间：2025-07-16
- 摘要：Fault localization is one of the most time-consuming activities in software debugging,and automatic fault localization technique can effectively improve the efficiency and reduce the cost.In this paper,a fault localization technique based on weakest pre-condition is proposed.Firstly,we compute the weakest pre-condition,and construct the fault analysis graph.Secondly,label the nodes according to the failing test case.Finally,label the graph top-down again while the output is limited to true,and the input cannot be changed.The conflicting nodes were found as the possible errors.The experimental results suggest that the proposed method in this paper has better performance compared to other methods.So that the debugger can only check fewer statements to find out the location of the error.关键词：debugging;fault localization;weakest pre-condition;counterexample explanation173|310|1更新时间：2025-07-16
- 摘要：Compressed holography combines the theory of compressed sensing with the holographic display technology.Using the theory of compressed sensing,3D objects can be accurately restored from the 2D hologram only by a small number of measurements.In this paper,the theory of compressed sensing is extended from the single-wavelength case to the compressed holography of the color object,and the 3DTV compressed reconstruction of 3D objects with more overlap in the axial direction is studied.Finally,the validity of the method is verified by numerical experiments and the effect of the filling ratio of complex objects on the quality of reconstruction as well as the effect of the position of overlap and noise on the reconstruction quality between different layers are explored.关键词：compressed holography;compressed sensing (CS);color holography;three-dimensional reconstruction181|262|0更新时间：2025-07-16
- 摘要：Considering that crow search algorithm (CSA) has low optimization accuracy and weak local-optimum escape ability in optimizing high-dimensional problems,an improved crow search algorithm(ICSA) is proposed by coupling the variable-factors' weighted learning mechanism of multiple individuals(Mi-VWL) and the adjacent-generations dimension crossover strategy of the best individual(Bi-ADC).In the proposed algorithm,the model parameters,i.e.awareness probability and flight length,are firstly modified dynamically with increasing number of iterations.Meanwhile,the Mi-VWL is introduced to guarantee that offspring individuals of crow population can inherit position information from the followed crow and the best individual of the last generation simultaneously,which is advantageous to avoid the over-rapid population intensification of single-individual learning and reduce the algorithm's risk on dropping into local optimum.Furthermore,Bi-ADC is constructed and the priority replacement principle of larger absolute value difference of dimensions between two-generations is adopted to update position of the best individual,which is beneficial to retain the optimal dimension information of historical best crows and enhance the local extreme escape ability of algorithms.Experimental results verify the influence of modal parameters on CSA's performance,the effectiveness and differences of different-type weighted learning factor on improving ICSA's capability and the superior optimization ability of the proposed algorithm,respectively.关键词：intelligent optimization algorithm;crow search algorithm;variable-factor weighted learning mechanism;adjacent-generations dimension crossover strategy;benchmark function210|315|13更新时间：2025-07-16
- 摘要：A novel coding method IVLAD (Improved Vector of Locally Aggregated Descriptors) based on the fusion of features was proposed in this paper.It obtained good performance in behavior recognition.In order to solve the problem that single feature descriptor cannot express space information well,location information was mapped into feature space and then jointly coded to get the video expression vector.In order to avoid the deficiency of the traditional VLAD methods which only consider the distances of features and clustering centers,the distance between each cluster and its most similar feature was also used in the coding stage.Finally concatenating the video expression vector with itself was proposed to raise the dimension of vectors to further improve the recognition accuracy.Furthermore,the influences of the visual dictionary size,the location dictionary size and the normalization method on the recognition accuracy were studied.The experimental results on two large databases UCF101 and HMDB51 have shown that the proposed method had better performance than the traditional VLAD method.关键词：action recognition;position information;concatenate;expression vector256|332|8更新时间：2025-07-16
- 摘要：Machine learning is widely applied in various intelligent devices including intrusion detection systems (IDS).We propose a novel approach called poising attack on IDS based on SVM.This attack is to degrade detection rate of IDS by misleading the SVM learning process with poisoned training data set.We model the poisoning attack as an optimization problem and solve it with numerical approach to get poisoned data set.At last,NSL-KDD data including several real attacks is used in our experiments,and two measures of precision and callback are used to evaluate the effectiveness.The result shows the poisoning attack approach can significantly degrade the IDS performance.This study may further understand the possible new attacks on machine learning,and provide the basis for the next study of the corresponding defense methods.关键词：machine learning;SVM;intrusion detection;poisoning attack;bilevel optimization398|441|7更新时间：2025-07-16
- 摘要：A credibility test method,based on the goodness-of-fit test of the exceedance distribution of the cross-correlation spectrum,is proposed to evaluate blind processing results of LFM/BPSK hybrid modulation signals.A reference signal is constructed depending on the identified modulation format and the corresponding estimated parameters,and the spectrum of the cross-correlation between the observed signal and the constructed reference signal is calculated.By using the property of the maximum distribution of the cross-correlation spectrum,the credibility test is transformed to the goodness-of-fit test of the exceedance distribution to the cross-correlation spectrum.It is proved that the exceedance distribution under null hypothesis is approximated to a generalized Pareto distribution according to the maximum distribution attraction theory.The effectiveness of the algorithm is demonstrated in extensive simulations.关键词：credibility evaluation;LFM/BPSK hybrid modulation;generalized extreme distribution;generalized Pareto distribution101|234|1更新时间：2025-07-16
-
Edge-Modified Superpixel Based Spectral-Spatial Kernel Method for Hyperspectral Image Classification
摘要：In order to alleviate the drawback that the spatial information of any pixel in a superpixel for generating the spatial-spectral kernel is totally determined by the same biased superpixel feature,especially for spatial information of the pixels located at the boundary,we propose an edge-modified superpixel based spatial-spectral kernel method for hyperspectral classification.On one hand,we combine the fixed window and superpixel to determine the homogeneous regions in a weighting strategy,in which the weights for pixels outside the fixed window are set to zero.Then we obtain the modified spectral-spatial kernel based on the weighted homogeneous regions.On the other hand,by considering the correlation among adjacent superpixels,we extract the spatial features among those superpixels to generate the inter-superpixel based spectral-spatial kernel.Finally,we combine the two spatial-spectral kernels in a convex way and employ support vector machine (SVM) for classification.Experimental results on two real hyperspectral data sets indicate that the proposed method could overcome the instability caused by superpixel-based spatial information extraction technique,and lead to better classification results than other state-of-the-art classifiers.关键词：hyperspectral classification;spatial-spectral kernel;superpixel based kernel;kernel-based method94|290|8更新时间：2025-07-16 - 摘要：Aiming at the problem that the block cipher algorithm mapping based on coarse-grained reconfigurable array structure is complex and the evaluation standard is not uniform,this paper adopted a multi-objective decision-making means to evaluate the performance and power consumption parameters,and proposed a weighted metric model for map of block cipher algorithm.At the same time,the method of weighting parameters is defined by comprehensive subjective and objective factors,so as to provide differentiated mapping scheme by configuring reasonable weight parameters.In order to reduce the decision time,this paper introduced the algorithm of enumeration search based on binary coding,and realized the parallelism between the optimal scheme search and the generate mapping matrix,so that the time complexity of decision decrease to O(2 n).The experimental results show that the weighted metric model can achieve efficient block cipher algorithm mapping,and the throughout per chip area has improved about 14.2%,with a 100% improvement in energy efficiency per workload bit.关键词：coarse-grained;block cipher;mapping;weighted metric;energy efficiency88|230|5更新时间：2025-07-16
- 摘要：With the rapid development of Web3D technology,the demand to use and retrieve 3D model is becoming urgent.Especially,sketch-based shape retrieval is very important.In the paper,a framework is proposed,which includes lightweight for shape,SVM-based learning algorithm.In particular,the model is simplified and then projected into multi-views images.Besides,a SVM classifier is used to classify these images.Moreover,histogram of oriented gradient (HOG) features is extracted from the input sketch image.Furthermore,K-means algorithm is used to cluster and index these features in order to generate a features dictionary.Finally,the related experiments are conducted to verify the feasibility of the approach in open source datasets.The result shows that the proposed method is robust and superior,compared with other methods.关键词：sketch-based shape retrieval;SVM;simplified;HOG;features dictionary101|275|2更新时间：2025-07-16
- 摘要：Membrane systems (also called P systems) are a class of distributed parallel computing models.In this work,a new variant of tissue P systems is proposed,called homeostasis tissue P systems with object evolutional rules,where there is no infinitely many objects in the environment.We prove that any Turing computable set of numbers can be generated by such a P system by simulating register machines.Moreover,we introduce the time-free method into such P systems and construct a time-free uniform solution in the framework of such recognizer P systems to solve the 3-coloring problem in linear time.It is proved that the system constructed in our work is effective to NP-complete problem.关键词：membrane computing;P system;tissue P system;time-free;homeostasis66|219|0更新时间：2025-07-16
- 摘要：In the data transmission process of the delay tolerant mobile sensor networks,the data is easy to get lost and the network lifetime decreases due to energy exhaustion.We propose an energy-efficient reliable transmission strategy based on the optimal distance.The transmission strategy addresses three important requirements for DTMSN:reliability,energy-efficiency and network lifetime.First,the notions of "reliable energy-efficient distance" and "reliable energy-balanced distance" are introduced under the link quality assurance.In addition,the comprehensive utility value of the node is determined by analyzing the distance between nodes,the moving direction of the node and the current residual energy of the node.Finally,the messages are forward according to the comprehensive utility value.The simulation results show that the strategy can improve the energy utilization of the sensor nodes and prolong the network lifetime in the guarantee of delivery ratio and the reliability of the messages.关键词：delay tolerant mobile sensor networks;optimal distance;energy-efficient reliable transmission strategy71|219|2更新时间：2025-07-16
- 摘要：To improve search efficiency in large space and high dimension for the algorithm,an opposite based chaos optimization algorithm (VILOC) with variable interval length is proposed,which is verified to converge global optimum solution with probability one.Meanwhile,an opposite optimization approach to increase the diversity of the algorithm is also introduced,which gives rise to decrease of the optimized variable interval.In the implementation procedure of VILOC,an anti-chaotic optimization strategy based on Fuch chaotic map is accommodated to escape the local extremum,and the two-stage optimization strategy to increase the convergence precision.The comparisons are carried out through experiments and the numerical results demonstrate that the proposed algorithm is superior to other improved chaos optimization algorithms and intelligent optimization algorithms.关键词：chaos optimization;variable interval length;opposite optimization;chaotic map73|289|2更新时间：2025-07-16
- 摘要：To improve the antinoise robustness of frequency and direction of arrival in the temporal-spatial undersampling case,this paper presents two aspects of improvements.On one hand,in the configuration of sparse array arrangement,this paper constructs a relaxed coprime sparse array consisting of 3 sensors,whose element spacings are configured in terms of TRRNS (Towards Robustness in Residue Number System) reconstruction algorithm;On the other hand,in the design of recovery algorithm,the original CRT (Chinese Remainder Theorem) based algorithm is replaced by the TRRNS algorithm,from which the mechanism of the anti-noise robustness scalable adjustment will be derived and verified by numerical simulations.Compared to the original CRT based joint estimator,the proposed estimator at least achieves 9dB improvement of the SNR threshold without increasing the hardware complexity and system cost,which presents vast applications in radar,remote sensing and other passive sensing fields.关键词：signal processing;undersampling;direction of arrival estimation;frequency estimation;antinoise robustness;relaxed coprime array86|245|1更新时间：2025-07-16
- 摘要：Aiming at the optimization of advanced encryption standard (AES) S-box,an enhanced delay-aware common subexpression elimination algorithm is proposed.Under different delay constraints,the proposed algorithm can not only optimize multiple constant multiplication circuit,but also provide all of the design trade-offs,from the shortest feasible delay to the smallest area.Two constructions of S-box based on redundant finite field arithmetic which have optimal delay or the optimal area are derived using the algorithm.The results obtained through optimizing examples show the algorithm achieves high optimization efficiency and better overall delay optimization effect.In 65nm CMOS technology,the proposed S-box circuit which has the optimal area has the minimum area-delay product among the S-boxes based on composite field architecture.Compared with the smallest S-box and the shortest delay S-box,it saves about 17.58% and 19.74% of the area-delay product respectively.关键词：advanced encryption standard (AES);S-box;composite fields;delay-aware common subexpression elimination69|213|1更新时间：2025-07-16
- 摘要：Reversible information hiding technology is widely used in many fields,this paper designed a new reversible data hiding algorithm with high payload based on the interpolation images.Firstly,we design a linear interpolation method and determine the ideal interpolation image,then a model is set up,with the value of the parabola as the reference,two mean values as the expectation interpolation,the embeddable position and number are determined according to the difference interval,and then the final interpolation is determined by the interval adjustment factor and the secret information.no additional information,no data spillover,and the average payload of algorithm is approach 4bit/pixel.Compared with the experimental results of 5 excellent algorithms,it is shown that the algorithm has some advantages over the algorithm in terms of embedding capacity,invisibility and operation efficiency.关键词：information security;reversible data hiding;image interpolation;parabola62|316|2更新时间：2025-07-16
- 摘要：With the continuous expansion and complexity of network structure,the traditional overlapping community detection algorithm can not effectively discover reasonable community structure in large-scale network structure.Based on the concept of vertex gravity proposed in this paper,we introduce vertex cohesion and community cohesion as indexes for community structure-close internal structure and sparse external structure,and then put forward overlapping community structure algorithm OCSC.The steps of OCSC algorithm include pre-processing,core sub-mapping and core community expansion.Finally,NMI and F1Score confirm the rationality and superiority of OCSC algorithm by experimentation on synthetic and real network structures.关键词：community discovery;overlapping community;core community;large-scale network structure;Spark76|309|8更新时间：2025-07-16
- 摘要：Community detection is a significant research direction in the research of social networks.To improve the quality of seeds selection and expansion,we propose an influence seeds extension overlapping community detection (i-SEOCD) algorithm for overlapping community detection.First,i-SEOCD uses a node influence strategy to find the seed communities with tight structures.Second,on the basis of the seed communities,we calculate the similarity among communities and their neighbor nodes.The nodes whose similarity is greater than a predefined threshold are selected.Third,the strategy of optimizing a self-adaptive function is adopted to expand the communities.Finally,the free nodes in the network are assigned to their corresponding communities in order to find out all the overlapping community structures.Experiments on the real and artificial networks show that i-SEOCD is capable of discovering overlapping communities in complex social networks efficiently.关键词：local community detection;seeds extension;node influence;overlapping community124|305|5更新时间：2025-07-16
- 摘要：Influence maximization problem in social networks deals with finding a small subset of nodes,which could maximize the spread of influence.It has been proved that this problem is NP-hard under the commonly used diffusion models.Although many algorithms have been proposed to solve this problem approximately,it is still a challenge to guarantee the spread of influence within a low time complexity.For this,we propose a novel method based on tree-coritivity theory and give a polynomial-time algorithm,for finding the initial active nodes required in the influence maximization problem.Our algorithm considers both the structure and the propagation characteristics of a network. Moreover,by experiment,we compare this algorithm with other conventional node-selection methods such as Random,Degree and Greedy.The results demonstrate that the proposed algorithm can find the node set that can widely spread the information efficiently.关键词：tree-coritivity;tree-core;social network;algorithm;influence maximization;diffusion models100|222|2更新时间：2025-07-16
- 摘要：Grey wolf optimization (GWO) algorithm is a relatively novel optimization technique which has been shown to be competitive to other population-based algorithms.However,there is still an insufficiency in canonical GWO regarding its position update equation,which is good at exploitation but poor at exploration.Inspired by differential evolution and particle swarm optimization,the personal best information and the random selected individual from population are used to construct a modified position update equation for enhancing the exploration.Inspired by particle swarm optimization,a random adjustment strategy of control parameterais proposed.In addition,to enhance the global convergence,when producing the initial population,the chaos method is employed.Simulation experiments were conducted on the 18 high-dimensional conventional test functions.The simulation results show that the proposed algorithm provides better performance than basic GWO algorithms in the same or less number of maximum fitness function evaluation in most cases.关键词：grey wolf optimization algorithm;differential evolution;particle swarm optimization;control parameter;chaotic initialization114|422|34更新时间：2025-07-16
- 摘要：Deep learning is bringing revolution to pattern recognition and machine learning,which has been successfully applied to language processing,image processing,signal processing,business economy and so on.Restricted Boltzmann machine (RBM) is a strong representation and generative mod el,however,the learning time of deep belief nets (DBN),which consists of multiple stacking RBM,will be longer.In this paper,the improved momentum method is used not only in gradient ascent algorithm but also in gradient descent algorithm for both classification accuracy enhancement and training time decreasing.According to the characteristics of the gradient ascent algorithm,a rapidly ascending momentum method is used in the RBM pre-training phase,which greatly improves the speed of learning.According to the characteristics of the gradient descent algorithm,an improved slowly descending momentum term is also used in the fine-tuning stage to accurately find the best point.Through the recognition experiments on the MNIST dataset and CMU-PIE face dataset,the achieved results show that the improved momentum algorithm can effectively enhance the ability of image feature expression and improve both accuracy and computation efficiency.关键词：deep learning;restricted Boltzmann machine;Kullback-Leibler (KL) divergence;Monte Carlo method;momentum225|279|4更新时间：2025-07-16
- 摘要：The imperfect self-interference cancellation in full-duplex cooperative relay networks can make the system performance reduced when the relay forwards signals.We considered the downlink non-ideal full duplex cooperative relay in non-orthogonal multiple access system with eavesdropper (NFCR-E-NOMA),based on which,the impact of self-interference to the NFCR-E-NOMA system was analyzed by outage probabilities and intercept probabilities respectively,and whose exact closed-form expressions were derived.Simulation results show that the self-interference have great influence on the system performance.We also find that there exists optimal relay retransmitting power in the NFCR-E-NOMA system.Moreover,the power allocation ratio also has different influence on the system performance under various transmitting power in base station and relay.In addition,the intercept probability of eavesdropper can be reduced by setting higher data rate under the permission of main link.关键词：non-orthogonal multiple access;cooperative relay;physical layer security;outage probability;intercept probability284|270|3更新时间：2025-07-16
- 摘要：Unmanned aerial vehicle(UAV) swarm cooperative situation awareness(SA) consensus plays a key role in swarm cooperative decision and control,and the existing studies of SA focus on multi-sensors situation data fusion,but the discuss of SA consensus is not sufficient.The evaluation method of swarm cooperative situation perception consensus is designed.Combined with the characteristics of swarm cooperative engagement,the swarm cooperative SA consensus is analyzed.The swarm cooperative situation perception consensus analysis models are established and the possible usages are given.Considering the uncertainty of battlefield information and the relevance of indexes,we design the consensus calculation method based on nonlinear dispose and the variable weights.The calculating example analysis shows that compared with the method via combination weight,the proposed method can have a better performance in the accuracy and distinction,and can be used for the study of swarm cooperative engagement simulation and the swarm system optimization design.关键词：unmanned aerial vehicle (UAV);UAV swarm;situation awareness;situation perception;situation awareness consensus;consensus evaluation558|439|8更新时间：2025-07-16
- 摘要：To improve the positioning accuracy of a mobile transmitter under the non-line-of-sight (NLOS) condition,an enhanced interacting particle filtering algorithm is proposed.The multiple motion models of the target and the multiple measurement noise distribution models of the time difference of arrival (TDOA) of the target signal are jointly built.In the state update phase of the interacting multiple models,the particle filtering is utilized to estimate the time-varying state of the target and the line-of-sight (LOS)/NLOS mixed channel parameters,thus the effect of NLOS measurement errors on mobile localization can be eliminated.Simulation results demonstrate that the proposed method performs better than the existing multiple motion model positioning method under the LOS condition and single motion model positioning method under the LOS/NLOS condition,and is close to the derived posterior Cramer-Rao lower bound.关键词：mobile localization;line-of-sight (LOS);non-line-of-sight (NLOS);particle filter;interacting multiple models;time difference of arrival (TDOA);posterior Cramer-Rao lower bound (PCRLB)225|275|5更新时间：2025-07-16
- 摘要：For wireless communication in high speed environment,aiming at doubly-selective fading and non-stationary channel features,this paper proposes a Bayesian filtering and smoothing channel estimation method based on basis expansion model (BEM).Aiming at the double-selection of channels,the BEM is adopted to reduce the estimation complexity and eliminate inter carrier interference.Aiming at the channel non-stationary characteristics,a channel estimation based on Bayesian filtering which is able to jointly estimate the time-varying correlation coefficients and channel impulse response is proposed.Simulation results show that the proposed methods have better estimation accuracy and overall performance than the least squares (LS) method and other traditional methods in high-speed scenarios.This method is suitable for the wireless communication system for high speed railway particularly.关键词：orthogonal frequency division multiplexing (OFDM);channel estimation;non-stationary channel;doubly-selective channel;basis expansion model (BEM);Bayesian filtering415|330|5更新时间：2025-07-16
- 摘要：We have investigated the application demands and status of extended interaction klystrons (EIKs) at millimeter-wave and terahertz band in detail.The applications of EIKs in the fields such as space detection,active denial system and biomedicine are presented in this paper,indicating the scientific value and good application value of EIKs in millimeter-wave and terahertz technical domain.The latest development and trend,technical difficulties and challenges of EIKs are technically analyzed and summarized.关键词：extended interaction klystron;distributed interaction klystron;terahertz152|266|5更新时间：2025-07-16
- 摘要：Advances in medical imaging technologies and equipment play an important role in the biomedical researches.Cross-modality image-prediction technology predicts one modal image from that of another modal.This paper presents an overview of the literatures on medical imaging prediction technology and its applications,such as predicting Computed Tomography images from Magnetic Resonance (MR) images,7T-like MR image reconstruction,and predicting positron emission tomography images.The aim is twofold:the necessity and challenge for different modality medical image prediction technology;the overview and comparison of various methods in the field.We conclude that the cross-modality image prediction based on the deep learning technology has superiority in both predicting time and precision.关键词：deep learning;computed tomography (CT) image prediction;7T-like image reconstruction;positron emission tomography (PET) image prediction169|690|7更新时间：2025-07-16
- 摘要：In this paper,a single channel speech enhancement method is proposed by constructing a priori binaural cue codebook of speech and noise based on binaural cue coding principle.Firstly,as a priori information,the binaural cues of speech and noise are offline trained to form a priori codebook.Then,the weighted codebook mapping (WCBM) algorithm is used to estimate the clean cue.At last,the noisy speech is enhanced with binaural cue coding (BCC) model.Moreover,an estimation method of the clean cue is proposed for further improving performance based on deep neural network,namely stacked auto-encoders (SAE),instead of WCBM algorithm.Objective test results show that the proposed method is superior to the reference methods.关键词：speech enhancement;binaural cue coding;codebook driven;deep neural network172|286|1更新时间：2025-07-16
- 摘要：In order to improve the measurement accuracy and long-term stability of OCT in low SNR(signal-noise ratio) environment,this paper starts from the algorithm that one of the key factors affects the performance of OCT.Basing on the analysis on existing variable step size adaptive algorithm,combining the characteristics of the output signal of OCT and the working circumstance of OCT,we proposed an improved double Sigmoid function variable step size adaptive algorithm,and compared this algorithm with the existing variable step size adaptive algorithm through simulation.Then,the algorithm is tested in OCT based on ActiveX.The results demonstrated the advantage of this algorithm in improving the measurement accuracy and long-term stability of OCT in low SNR environment.关键词：optical current transducer;variable step size adaptive algorithm;double sigmoid function;ActiveX210|235|7更新时间：2025-07-16
- 摘要：In this paper,we give some results on the Galois extension of the finite non-chain ring Fpm+vFpm. We also determine the generators of trace codes and subring subcodes of cyclic codes over the finite non-chain ring Fpm+vFpm.关键词：finite non-chain ring;trace codes;subring subcodes159|272|0更新时间：2025-07-16
- 摘要：The scheduling of workflows is a well-known non-deterministic (NP) problem because it contains multiple targets constraints.This paper proposed a time-quality optimization scheduling algorithm by layering the workflow model into three layers,such as mapping layer,dominant layer,and decision layer,respectively.The algorithm has two stages,stage one is called detection,it can improve the production quality by means of cycle machining in this stage;another stage is virtualization,which uses iterative way to virtualize nodes in mutual constraints into a new virtual node,abstracts the services,and simplifies the selection of services eventually.In comparison,the proposed algorithm was more effective than the traditional minimum critical path algorithm in the same experimental environment.关键词：scheduling optimization;workflow;virtual node;production quality98|201|1更新时间：2025-07-16
- 摘要：On-chip photonic integration of light source and straight waveguide on the GaN-on-silicon platform is fabricated by wafer-level technique.With focused ion beam,a high reflective distributed Bragg reflector (DBR) is etched on the straight waveguide using a Ga ion beam.And the photon modulation function of the device is studied.Complicated backside alignment and etching processes are saved and silicon substrate can be kept intact because of the particularity of InGaN waveguide structures.The experimental results show that the multiple-quantum-well light emitting diode (MQW-LED) has an excellent I-V performance.As the MQW-LED is switched on,some photons are coupled into the straight waveguide,and are transmitted forward in the waveguide,some light is total reflected at DBR,and partially diffracted into free space.According to the electroluminescence spectra of the devices,photons in the waveguide is effectively modulated by the DBR fabricated on the waveguide.关键词：GaN-on-silicon;MQW-LED;waveguide;DBR92|266|0更新时间：2025-07-16
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0