最新刊期
卷 50 ， 期 9 ， 2022
- 摘要：For non-smooth strongly convex problems, the logarithmic regret bound can be obtained by online gradient descent with the appropriate step size parameter. However, it cannot make the first order stochastic optimization algorithm achieve the optimal convergence rate. To solve this problem, researchers usually adopt two schemes: one is to modify the iterate of the algorithm, the other is to change the output mode of the algorithm. SAdam, a typical Adam-type algorithm, modify the algorithm by adding adaptive step size strategy and momentum technique. Although it obtains a tighter data dependent regret bound, it still cannot reach the optimal bound in the stochastic case. To solve this problem, this paper redesigns the step size scheme which is the same order as the previous algorithm, uses the weighted average algorithm output mode, and proposes an Adam-type algorithm named WSAdam. It is proved that WSAdam achieves the optimal convergence rate for non-smooth strongly convex problems. The validity of the proposed method is verified by the test of Reddi's problem and the experiment in the optimization of non-smooth strongly convex functions.关键词：non-smooth;strongly convex;adaptive step size;momentum methods;Adam-type algorithms;weighted average;convergence rate10|9|2更新时间：2025-12-08
- 摘要：The airborne system of military aircraft carries multiple applications that are interrelated with each other, such as air combat applications.But the current airborne system reliability evaluation methods evaluate system reliability by simply combining the subsystem reliability. The methods don't consider correlation of the internal and between subsystems, which unable to support the accurate evaluation of air combat application reliability. Therefore, this paper proposed the concept of airborne system air combat application reliability and the airborne system air combat application reliability evaluation method based on multi-parameter correlation. The application was decomposed to layers by application process and middleware application decomposition, then the parameters of each layer was extracted to form parameters system including application reliability parameters, sub-application reliability parameters, sensory parameters, middleware application related parameters, and specific service process related parameters. The application reliability evaluation model based on multi-parameters correlation was proposed by analyzing relationships between parameters which includes correlation and dependency. Finally, for airborne system air combat application, the reliability of air combat application is calculated. The innovations and advantages of proposed evaluation method are as follows. Firstly, the application was decomposed to layers by regular application process and middleware application decomposition, which could realize detailed description of application. Secondly, the airborne system air combat application reliability was accurately evaluated by considering correlation and dependency between parameters.关键词：airborne system air combat application reliability;application decomposition;multi-parameter correlation;reliability evaluation4|11|1更新时间：2025-12-08
- 摘要：Compared with the modern information processing and communication technology based on bits, the semantic-based way of processing and transmitting information used by humans is more efficient and natural in the face of the massive information that needs to be sent between agents. However, due to the lack of mathematical description of semantic measurement and characterization, semantics' applications cannot consider both interpretability and generalization. Therefore, they cannot give play to the advantages of efficient and natural semantics. This paper focuses on the measurement and characterization of semantics. Firstly, we discuss the connotation of semantics based on the relevant conclusions of information science and neuroscience, and concludes that semantics has the characteristics of modularity, multi-mode, and hierarchy. Then, a semantic description of multimodal signals and a mathematical description of their measurement are proposed. Next, to verify the feasibility and effectiveness of the characterization and measurement of the proposed signal semantics, experiments are carried out in two applications: MNIST (Mixed National Institute of Standards and Technology database) handwritten digital recognition and underwater acoustic target recognition, and the results are better than those of the traditional deep learning. Finally, the semantics is used for video coding, and a compression ratio far exceeding that of traditional methods is achieved. This lays a theoretical and practical foundation for establishing new information processing and communication technology based on semantics.关键词：semantic;semantic characterization;semantic measurement;semantic primitive;semantic computing;semantic recognition11|10|2更新时间：2025-12-08
- 摘要：App user reviews are an important source of user requirements. The requirements obtained from user reviews can not only help developers maintain the existing systems, but also quickly and accurately locate new user requirements. This work focuses on non-functional requirements in App user reviews, and further classifies them into behavioral requirements and representational requirements based on system model with machine learning and deep learning algorithms. When using machine learning to classify non-functional requirements, we combined two feature extraction techniques with five machine learning algorithms. When applying deep learning to classify non-functional requirements, we used two deep learning algorithms based on word embedding and one deep learning algorithm based on character embedding. We compared machine learning models and deep learning models from the performance and time consumption perspectives. The results show that, machine learning models perform better than the deep learning models. In addition, the combination of SVM(Support Vector Machine) and TF-IDF(Term Frequency⁃Inverse Document Frequency) achieves the best performance of classification, with a precision of 0.941, a recall of 0.990, and an F1-score of 0.965.关键词：user review;system model;non-functional requirement;automatic classification;machine learning;deep learning4|11|1更新时间：2025-12-08
- 摘要：Building a real-time and reliable transmission network to solve the problem of low latency and highly reliable large-scale data transmission in existing industrial networks is a challenge in the implementation of industrial networks. Most of the current industrial networks target specific applications so that they are viewed as heterogeneous, making them incapable of realizing large-scale inter-device communication. Also, the traditional best-effort Internet fails to provide real-time and reliable network performance. In this paper, according to the theories of time-sensitive networks, we propose and implement a traffic shaping policy based on the 802.1Qbv queue priority and a scheduling policy based on frame preemption. We develop a time-sensitive network switch based on the IEEE 802.1 and evaluate the queue scheduling mechanisms and techniques built on the IEEE 802.1. The experimental results indicate that our queue scheduling mechanism can effectively achieve real-time traffic transmission with controllable transmission delay, thus guaranteeing reliable traffic communication.关键词：time sensitive network;traffic scheduling strategy3|14|2更新时间：2025-12-08
- 摘要：Aiming at the characteristics of the underwater acoustic channel such as complex and changeable, strong multi-path and large fluctuation interference, this paper establishes an underwater acoustic communication system with polar code as the channel coding scheme to improve the reliability of underwater acoustic data transmission. Aiming at the channel with invariable sound velocity gradient(ISVG), negative sound velocity gradient(NSVG) and positive sound velocity gradient(PSVG), a Monte Carlo construction is proposed as a construction scheme of polar code. Performance simulations on each channel show that the polar code construction scheme proposed in this paper is feasible and effective under three channels. Compared with the low density parity check code(LDPC) with similar code length, the comprehensive performance of the polar code is better under the same signal-to-noise ratio(SNR). Relatively speaking, when the SNR of the polarization code is improved, its bit error rate curve drops faster, which means that it can obtain a higher coding gain. The simulation results improve the performance of the underwater acoustic communication system, and show a good application prospect in the complicated underwater acoustic channel.关键词：channel coding;polar codes;Monte Carlo construction;underwater acoustic communication;underwater acoustic channel6|15|0更新时间：2025-12-08
- 摘要：Users'reviews on items can reflect users'preference information. Migrating users'preferences in other fields to the target domain for cross domain recommendation can alleviate the cold start problem caused by sparse data in the target domain. Aiming at the two problems that the traditional cross domain recommendation methods can not migrate the complete user preferences and the prediction accuracy of the traditional aspect extraction methods is incorrect, this paper proposes a cross domain score prediction model based on aspect and capsule network(ACN). ACN uses capsule network to mine multiple aspects of review documents, and then selects the most important features for the target domain through attention mechanism, and migrate to the target domain for score prediction. Compared with the benchmark model, ACN has the highest performance improvement of 2.3% and 20.8% when using single source domain and multi-source domain.关键词：cross domain recommendation;rating prediction;capsule network;aspect extraction;attention2|9|0更新时间：2025-12-08
- 摘要：This paper proposes a near-field direction of arrival(DOA) estimation algorithm by using array partition. Firstly, the fourth-order cumulant and array partition are used to construct a Toeplitz matrix with only DOA information. Secondly, the spatial spectrum of multiple signal classification(MUSIC) algorithm at the spectrum peak is a breakpoint and approaches a larger value. Thus, to obtain high-resolution spectral peak, the first derivative of spatial spectrum is used to construct a new ‘spatial spectrum’. Finally, the range of near-field source is estimated by the one-dimensional MUSIC algorithm. The simulation results show that the proposed algorithm improves the accuracy of DOA estimation at low signal to noise ratio. In addition, the proposed algorithm does not require two-dimensional spectral peak search, and it requires K+1 one-dimensional spectral peak search.关键词：DOA estimation;near-field;array partition;fourth-order cumulant;spectral peak;range5|9|1更新时间：2025-12-08
- 摘要：The existing general deep learning target detection methods have good detection accuracy for medium and large targets, but the detection accuracy for small targets is low, mainly due to few data for small target training and low resolution of feature map after down sampling. To solve the above problems, on the one hand, a scale sensitive loss function is proposed for the training of classified heatmaps, so that small targets can have a greater impact on model updating; on the other hand, a top-down feature fusion method is proposed by using deconvolution and deformable convolution to obtain high-resolution and strong semantic feature map for target detection. On the basis of the above two aspects, a small target detection method based on scale sensitivity and feature fusion is designed. Experimental results on PASCAL VOC dataset show that compared with the existing target detection methods, the proposed method can maintain a faster detection speed and improve the accuracy of small object detection.关键词：deep learning;small object detection;scale-sensitivity loss;feature fusion6|10|2更新时间：2025-12-08
- 摘要：Phase is important for acquiring the high sea surface brightness temperature with high accuracy. The traditional phase calibration methods for one-dimensional synthetic aperture radiometer are difficulty to meet the requirements. This paper proposes a phase calibration method. Firstly, the fixed phase difference of receiving chain at different position is acquired by external point source and internal noise source. Then, the variable phase difference of receiving chain is acquired by internal noise source. Finally, the phase is calibrated by the two kinds of phase difference. This method separates the fix phase error and variable phase error, and has advantages of high accuracy, good repeatability and saving calibration time. The experiment results indicate that the accuracy is better than 0.7° and the repeatability is better than 0.35°.关键词：one-dimensional synthetic aperture radiometer;sea surface brightness temperature;phase calibration;visibility function;point source;noise source2|7|0更新时间：2025-12-08
- 摘要：In edge computing, waste of resources and inefficient offloading services are key issues caused by bad behaviors such as false deception and free-riding. To address the selfishness key issues, a task offloading scheme based on comprehensive trust evaluation(TOCTE) is proposed. By establishing nodes trust forgetting function, and taking task authenticity and nodes offloading cooperative behavior characteristics as constraints, the offloading request and cooperative trust evaluation models between nodes are constructed to identify and filter false tasks and bad cooperative nodes in the network. Particle swarm algorithm based on search discovery probability is designed to avoid the node overload caused by the repeatedly utilization of nodes, improve task offloading efficiency and resource utilization of edge computing. The simulation results show that the real task execution success rate and the lowest resource consumption rate of TOCTE are 59.22% and 6.35%. TOCTE model can effectively suppress and filter false tasks, and reduce resource consumption.关键词：edge computing;trusted offloading;task filtering;comprehensive evaluation;particle swarm algorithm6|12|3更新时间：2025-12-08
- 摘要：The 3D video based on multiview video plus depth(MVD) format can provide users with immersive experiences from different viewpoints. To solve the whole color frame losses in MVD video stream transmission, we propose a novel error concealment algorithm of whole-frames loss using visual saliency. Firstly, each region of the lost frame is classified into three different saliency levels. The low, medium and high saliency regions are recovered by direct temporal copy, adaptive pixel matching search between temporally and inter-view domains, and a new motion vector compensation, respectively. Compared with the recent algorithms, the lost frame concealed by the proposed algorithm achieves significant improvements in the average PSNR and SSIM with approximate gains of 0.99~2.61 dB and 0.005~0.012, respectively. In addition, our concealed results have better visual quality than compared methods.关键词：multiview video plus depth;error concealment;whole frame loss;visual saliency;motion compensation;disparity compensation2|15|0更新时间：2025-12-08
- 摘要：The current network embedding researches focus more on the information network structure and first-order or higher-order approximation of nodes, but less on the attributes of network nodes. This paper proposes a nested generative adversarial network model N-GAN(Nesting Generative Adversarial Networks for Network Embedding), which embeds the network structure and nodes' attributes into the low-dimensional vector at the same time, so as to preserve the feature of the original high-dimensional information network maximumly. N-GAN model is flexible in design and has good extensibility and expansibility. The performance and stability of N-GAN model are verified on real datasets. The embedded low-dimensional representation of N-GAN model shows good performance in different tasks.关键词：data mining;network embedding;generative adversarial learning;information network2|11|0更新时间：2025-12-08
- 摘要：Aiming at the accuracy and robustness of existing binocular scene flow calculation methods in complex scenes such as large displacement, motion occlusion and illumination changes, this paper proposes a binocular scene flow estimation method based on pyramid block matching. Firstly, we apply the superpixel segmentation and disparity estimation to the binocular image sequence to obtain the initial image segmentation results and disparity information. Secondly, we establish a motion model based on pyramid block matching. Then we fit the rigid motion model by using Ransac stochastic consensus algorithm and estimate the object motion parameters by minimizing the reprojection algorithm. Finally, this paper takes the matching result of the pyramid block as a constraint item, then we construct a binocular scene flow estimation energy function model based on the pyramid block matching by combines the object motion parameters and the superpixel plane parameters, and obtains the final scene flow by minimizing the energy function. The image sequences provided by the KITTI2015(Karlsruhe Institute of Technology and Toyota Technological Institute 2015) and MPI-Sintel(Max-Planck Institute and Sintel) databases were adopted to compare and analyze the proposed method in this paper and the existing representative scene flow method. The experimental results show that compared with other comparison methods, the method in this paper has high accuracy and robustness of scene flow estimatin, especially in large displacement, motion occlusion and lighting changes.关键词：binocular scene flow;pyramid block matching;motion model;large displacement motion;superpixel segmentation2|17|0更新时间：2025-12-08
- 摘要：Community search aims to search local communities containing query nodes, which is one of the most concerned studies in network analysis task. Most existing community search methods are oriented to simple network and can only detect the community where query nodes are located. They may fail to take user's preferences into account during searching process. To guide the process of community search via user's preferences for finding multi-communities that users are interested in, we propose a community search method that is capable of searching multi-communities with user's preference and simultaneously identify outliers via few given query nodes in attributed network. Clearly, we explicitly model interactions between query nodes with its neighbors and encode similar attributes to highlight the local structure, which could be beneficial for query nodes to mine potential candidates. And we define the average partition similarity on candidate set of query nodes to infer attribute subspace as user's latent interest. Multi-communities and outliers in the whole network are detected via fractional-core and structural constraints. Experiments on real and synthetic network datasets demonstrate the effectiveness of the proposed algorithm.关键词：attributed network;community search;average partition similarity;attribute subspace;outliers2|11|1更新时间：2025-12-08
- 摘要：Categorical data clustering is an important research content for data mining, and clustering data usually contains some sensitive information of user. In order to protect user privacy in clustering data, the privacy protection model based on trusted third-party is currently mainly adopted. However, in reality, the third-party also has the risk of privacy leakage. In this paper, we propose a privacy protection method for K-modes clustering data without trusted third-party by introducing local differential privacy technology. Our method first uses random sampling technology to sample the data, then perturbs the sampled data by using local differential privacy technology, and finally complete the clustering through the interaction between the server and the user. In the clustering process, our method does not require a trusted third-party to perform privacy preprocessing on the data, which avoids the risk of the third-party disclosing the user's privacy. Theoretical analysis proves the privacy and feasibility of our method. Experimental results show that our method guarantees the quality of the clustering results under the premise of satisfying the local differential privacy mechanism.关键词：privacy protection;local differential privacy;data mining;k-modes clustering;no trusted third-party9|10|3更新时间：2025-12-08
- 摘要：A lead-free barium titanate(BaTiO3, BTO)/graphene Oxide(GO)/Polydimethylsiloxane(PDMS) three-phase high-performance piezoelectric composite film is prepared. GO is used as a carbon-based conductive phase material to form micro-capacitors in the ferroelectric composite film, which improves the piezoelectric performance of the composite films. When the GO concentration is 0.6 wt%, the electrical and ferroelectric properties of the composite films are measured. The experimental results show that the prepared BTO/GO/PDMS composite film has a dielectric constant of 185 and a residual polarization of 13.47 μC per square centimeter (higher than the pure phase BTO/PDMS composite film). The maximum open circuit voltage of the BTO/GO/PDMS nanocomposite film generator is 2.78 times that of the BTO/PDMS nanocomposite film generator. Based on the above research results, this lead-free green-friendly flexible composite material has great application prospects in vibration energy harvesting and integrated ferroelectric devices.关键词：BaTiO3/GO/PDMS;three-phase composite film;flexible piezoelectric material;nanogenerator2|12|2更新时间：2025-12-08
- 摘要：Aiming at the reliability and security problem of transmitting compressed images, videos and other files, a wiretap channel model with side information and state information and a secure lossy source transmission scheme based on double binning technique under this model are proposed. Moreover, the achievability and the converse of the triple rate-distortion-leakage are proved by the information theory. Considering the noise factors in the real environment, the Gaussian noise channel under this model is analyzed concretely as an example and the lower bounds of the rate and the distortion are derived based on the error estimation and the differential entropy theorem. In addition, the equivocation rate is introduced to transform the information leakage rate into the minimum mean square error of the estimated source and its upper bound is obtained. The simulation results show that the proposed scheme has higher rate and lower distortion and information leakage rate than the existing schemes under the optimal conditions, and has higher equivocation rate than the existing schemes under the non-optimal conditions.关键词：wiretap channel;double binning technique;secure lossy transmission;side information;state information;information leakage5|12|0更新时间：2025-12-08
- 摘要：Graph neural network (GNN) has become an important research field since 2005, and the most active branch is the graph convolutional network(GCN). In the real world, many applications are directly related to graphic data, so learning from graphic structure data is becoming more and more important, and can has a huge application prospect. However, most of the existing graph convolution neural network models can only support very few convoluted layers. This is mainly because of the over smoothing problem in GCNs, which has become one of the main bottlenecks in GCNs. In this paper, a novel GCN network: dri-GCN is proposed, which integrates the technologies of the Initial Residual, Identity Mapping and DropEdge into the traditional GCN. The main contributions include: using DropEdge to increase data diversity and prevent over-fitting; constructing the residual convolutional network under the constant mapping to extend the learning paths, which can effectively weaken the over smooth problem in GCNs. Experimental results show that dri-GCN model can help building the deeper graph convolution neural networks. There is no doubt that deeper GCNs can achieve better learning accuracy than shallower networks.关键词：graph neural network;graph convolutional neural networks;DropEdge;residual network2|9|0更新时间：2025-12-08
- 摘要：In this paper, based on the maximum likelihood ratio(MLR) criterion, the test statistics and the probability density function of non-linearity of the Page test are derived to detect the falling edge of underwater transient signals under the assumption of variance change of Gaussian distribution. The performance of the Page test is analyzed by FFT(Fast Fourier Transform) method again. The variance and detection threshold under certain detection probability and false alarm probability are calculated based on Newman Pearson criterion. The simulation signals of ship steering, torpedo ejecting and the measured signal of heavy falling obtained in the anechoic tank are exploited to verify the algorithm. The results show that,compared with the conventional method, this method has higher accuracy and better robustness in judging the falling edge of underwater transient signal at low SNR.关键词：Page Test;transient signal detection;passive sonar detection;falling edge detection3|12|0更新时间：2025-12-08
- 摘要：In order to solve the privacy leakage problem in location based service(LBS) when collecting user's location data, we proposed a time-serial location data publication model based on local differential privacy. Firstly, the model adapts a flexible location privacy preservation method, allows users to choose or customize their privacy policy(personalized privacy Settings), based on customized privacy policy, we designed a customized privacy policy location perturbation algorithm(CPLP); Secondly, we proposed and designed temporal relational location privacy publishing algorithm(TRLP) based on hidden Markov model(HMM), which can reduce the privacy leakage when releasing the time-serial location data. Finally, we verified the usability of the algorithm on data sets Geolife and Gowalla.关键词：differential privacy;location based service;time-series data;privacy releasing;hidden Markov model3|14|3更新时间：2025-12-08
PAPERS
- 摘要：In order to meet the increasing integration demand from integrated microwave photonics, the devices based on subwavelength grating waveguide is proposed and studied. The subwavelength grating waveguide is mainly used in filters and optical delay lines in integrated microwave photonics, with design freedom in refractive index. We review and discuss the developments of these applications, and provide the outlook on the application of the subwavelength grating waveguide devices in integrated microwave photonics at the end.关键词：silicon photonics;subwavelength grating waveguide;integrated microwave photonics;filters;EO modulators;optical delay lines5|10|1更新时间：2025-12-08
- 摘要：Knowledge base question answering(KBQA) provides accurate and short answers to complex factoid questions with the help of high-precision and highly relevant structured knowledge in the knowledge base(KB). Semantic parsing has become one of the mainstream methods of KBQA. Under the given form of question meaning representation, this kind of method maps unstructured questions into structured meaning representations, and then rewrites them as KB queries to obtain answers. At present, semantic parsing for KBQA mainly faces three challenges: first how to choose a suitable meaning representation form to express the semantics of questions, then how to parse the complex semantics of questions and output the corresponding meaning representations, and finally how to deal with the high cost of labeling datasets and the lack of annotated data in specific domains. Starting from the above challenges, this paper first analyzed the characteristics and shortcomings of meaning representations commonly used in KBQA and then combed out how existing methods deal with the complex semantics of questions. After that, this paper introduced the current attempts in low-resource scenarios and finally discussed the future directions of semantic parsing for KBQA.关键词：knowledge base;question answering;meaning representation;semantic parsing;low resource3|10|2更新时间：2025-12-08
- 摘要：Image super-resolution reconstruction is one of the basic image processing techniques in computer vision, which can not only improve image resolution and image quality, but also assist other computer vision tasks. In recent years, with the rise of artificial intelligence, deep-learning-based image super-resolution reconstruction has also made remarkable progress. Based on a brief description of the image super-resolution reconstruction methodology, this paper comprehensively reviews the technical architecture and research process of deep-learning-based single image super-resolution reconstruction, including the method of datasets construction, the basic framework of the network model, the subjective and objective evaluation metrics for image quality evaluation. The methods based on convolutional neural networks, generative adversarial networks and Transformer, which are divided according to network structure and image reconstruction effect are mainly introduced, and related network models are reviewed and compared. Finally, the future development trend of image super-resolution reconstruction is prospected according to the related content of network model and super-resolution reconstruction challenges.关键词：super-resolution reconstruction;deep learning;single image;convolutional neural network;generative adversarial network;Transformer;challenges10|15|7更新时间：2025-12-08
SURVEYS AND REVIEWS
- 摘要：A novel three-phase resonant DC link inverter with low energy consumption is proposed to achieve the high efficiency operation of the inverter. When the DC-bus voltage forms a zero-state in each switching cycle via the auxiliary resonant circuit set in the DC link of the inverter, the main switch can achieve zero-voltage turn on and zero-current turn off. The working state of the circuit in a switching period is explained. The experimental results on the three-phase prototype of 2.5kW show that the switching devices achieve the soft switching. Therefore, the novel topology is significant for improving the efficiency of the inverter.关键词：inverter;DC link;resonance;zero-voltage turn on;zero-current turn off5|15|0更新时间：2025-12-08
- 摘要：To cater to the needs of further miniaturization of antenna array in massive multiple input multiple output (MIMO) base station of the fifth generation(5G) communication system, a new single dipole is proposed in this paper to replace the original 1 × 2 array. To achieve equivalent substitution, the beam width of a single dipole should be halved. Therefore, a two-layered metasurface equipped with phase gradient property is placed above the traditional dipole. It concentrates the energy radiated from the dipole. The simulated half power beam width(HPBW) of the dipole is decreased to 37°, the simulated gain is enhanced to 14.1dBi, and the average cross polarization discrimination(XPD) within the main beam is improved by 3.3~8.5dB. To verify the antenna design, a prototype is manufactured and tested. Good agreement between the simulation and measurement results are obtained. In conclusion, the single dipole with metasurface added can replace the ordinary 1×2 array, equivalent to reduce the ordinary array size by half. The above scheme is very potential in 5G massive MIMO application.关键词：beam contracted;dipole antenna;dual-polarized antenna;massive MIMO system;base station antenna;antenna miniaturization4|13|0更新时间：2025-12-08
CORRESPONDENCE
- 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