|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Clustering by Fast Search and Find of Density Peaks with Data Field显示文摘A clustering algorithm named 'Clustering by fast search and find of density peaks' is for finding the centers of clusters quickly. Its accuracy excessively depended on the threshold, and no efficient way was given to select its suitable value, i.e., the value was suggested be estimated on the basis of empirical experience. A new way is proposed to automatically extract the optimal value of threshold by using the potential entropy of data field from the original dataset. For any dataset to be clustered, the threshold can be calculated from the dataset objectively instead of empirical estimation. The results of comparative experiments have shown the algorithm with the threshold from data field can get better clustering results than with the threshold from empirical experience. | WANG Shuliang WANG Dakui LI Caoyuan LI Yan DING Gangyi | 2016 | Chinese Journal of Electronics2016，25，3： | 60 |
| 2 | Resemblance Coefficient Based Intrapulse Feature Extraction Approach for Radar Emitter Signals显示文摘Radar emitter signal recognition plays an important role in electronic intelligence and electronic support measure systems. To enhance accurate recognition rate of advanced radar emitter signals to meet the requirement of modern electronic warfare, Resemblance coefficient (RC) approach is proposed to extract features from radar emitter signals with different intrapulse modulation laws. Definition of RC is given. Properties and advantages of RC are analyzed. Feature extraction algorithm using RC is described in detail. The noise-suppression performances of RC features are also analyzed. Subsequently, neural networks are used to design classifiers. Because RC contains the change and distribution information of amplitude, phase and frequency of radar emitter signals, RC can reflect the intrapulse modulation laws effectively. The results of theoretical analysis and simulation experiments show that RC features have good characteristic of not being sensitive to noise. 9 radar emitter signals are chosen to make the experiment of RC feature extraction and automatic recognition. A large number of experimental results show that good accurate recognition rate can be achieved using the proposed approach. It is proved to be a valid and practical approach. | ZHANGGexiang JINWeidong HULaizhao | 2005 | Chinese Journal of Electronics2005，14，2： | 43 |
| 3 | The Wolf Colony Algorithm and Its Application显示文摘 | LIU Changan YAN Xiaohu LIU Chunyang WU Hua | 2011 | Chinese Journal of Electronics2011，20，2： | 34 |
| 4 | A Text Sentiment Classification Modeling Method Based on Coordinated CNN-LSTM-Attention Model显示文摘The major challenge that text sentiment classification modeling faces is how to capture the intrinsic semantic, emotional dependence information and the key part of the emotional expression of text. To solve this problem, we proposed a Coordinated CNNLSTM-Attention(CCLA) model. We learned the vector representations of sentence with CCLA unit. Semantic and emotional information of sentences and their relations are adaptively encoded to vector representations of document.We used softmax regression classifier to identify the sentiment tendencies in the text. Compared with other methods, the CCLA model can well capture the local and long distance semantic and emotional information.Experimental results demonstrated the effectiveness of CCLA model. It shows superior performances over several state-of-the-art baseline methods. | ZHANG Yangsen ZHENG Jia JIANG Yuru HUANG Gaijuan CHEN Ruoyu | 2019 | Chinese Journal of Electronics2019，28，1： | 32 |
| 5 | Quantum-Inspired Evolutionary Algorithm for Continuous Space Optimization显示文摘 | LI Panchi LI Shiyong | 2008 | Chinese Journal of Electronics2008，17，1： | 29 |
| 6 | Study of Sentiment Classification for Chinese Microblog Based on Recurrent Neural Network显示文摘The sentiment classification of Chinese Microblog is a meaningful topic.Many studies has been done based on the methods of rule and word-bag,and to understand the structure information of a sentence will be the next target.We proposed a sentiment classification method based on Recurrent neural network(RNN).We adopted the technology of distributed word representation to construct a vector for each word in a sentence;then train sentence vectors with fixed dimension for different length sentences with RNN,so that the sentence vectors contain both word semantic features and word sequence features;at last use softmax regression classifier in the output layer to predict each sentence's sentiment orientation.Experiment results revealed that our method can understand the structure information of negative sentence and double negative sentence and achieve better accuracy.The way of calculating sentence vector can help to learn the deep structure of sentence and will be valuable for different research area. | ZHANG Yangsen JIANG Yuru TONG Yixuan | 2016 | Chinese Journal of Electronics2016，25，4： | 29 |
| 7 | Radar Detection of Range Migrated Weak Target Through Long-Term Integration显示文摘A long-term integration method for weak target detection is proposed, which is based on Hough transformation. The method is able to integrate target return for a very long time period (even up to tens of seconds) by means of data fusion of multiple range resolution cells and can find the moving target in very low SNR environments where conventional detection techniques are inadequate. Also the 3D information of the target's Doppler frequency, distance and position can be derived. Under the hypothetic conditions that the simulation is carried out, about 6dB of SNR improvement is achieved by the non-coherent integration of Hough detector. | MOLi WUSiliang LIHai | 2003 | Chinese Journal of Electronics2003，12，4： | 27 |
| 8 | Review on the Technological Development and Application of UAV Systems显示文摘Unmanned aerial vehicles(UAVs) are products of deep integration of aviation technology and Information technology(IT). The core factor of why the UAV industry can become a relatively independent industry and experience rapid development is the full penetration of IT into the aviation industry. Under the networked environment, UAVs are now becoming datadriven mobile agents. With the development of information technology, information transmission networking, operation space digitizing, and flight platform intelligentizing will become the main trends of technological development of UAV systems. The application of UAV systems is not merely a paradigm in transportation, but will more importantly produce 'UAV+' novel production modes,service formats, and combat modes associated with UAVs.These emerging trends will have profound impacts on future economic and social development as well as the building of armed forces. | FAN Bangkui LI Yun ZHANG Ruiyu FU Qiqi | 2020 | Chinese Journal of Electronics2020，29，2： | 26 |
| 9 | Estimating In-pulse Characteristics of Radar Signal Based on Multi-index显示文摘 | HAN Jun HE Minghao TANG Zhikai WANG Jie | 2011 | Chinese Journal of Electronics2011，20，1： | 23 |
| 10 | Chinese Named Entity Recognition_via Joint Identification and Categorization显示文摘 | ZHOU Junsheng QU Weiguang ZHANG Fen | 2013 | Chinese Journal of Electronics2013，22，2： | 20 |
| 11 | PCNN Model Analysis and Its Automatic Parameters Determination in Image Segmentation and Edge Detection显示文摘The Pulse coupled neural network(PCNN)has been widely used in digital image processing, but the automatic parameters determination is still a difficult aspect, which becomes the focus of PCNN research. In this paper, by the classical solution to difference equations and the time-domain analysis of PCNN model, we provide the expressions of the firing time and the firing period of neurons, and reveal the 'mathematics firing' phenomenon of PCNN. Based on this, we propose a new method of automatic parameters determination based on both eliminating the 'mathematics firing' and getting the highest efficiency of PCNN. We also present an edge detection model on the basis of image segmentation of PCNN and a method to determine automatically the parameters of the model. Experimental results prove the validity and efficiency of our proposed algorithm for the segmentation and the edge detection of the test images. | DENG Xiangyu MA Yide | 2014 | Chinese Journal of Electronics2014，23，1： | 20 |
| 12 | Efficient Secure Multiparty Computational Geometry显示文摘 | LI Shundong WANG Daoshun DAI Yiqi | 2010 | Chinese Journal of Electronics2010，19，2： | 19 |
| 13 | Image Analysis for Tongue Characterization显示文摘Tongue diagnosis is one of the essential methods in traditional Chinese medical diagnosis. The ac-curacy of tongue diagnosis can be improved by tongue char-acterization. This paper investigates the use of image anal-ysis techniques for tongue characterization by evaluating visual features obtained from images. A tongue imaging and analysis instrument (TIAI) was developed to acquire digital color tongue images. Several novel approaches are presented for color calibration, tongue area segmentation,quantitative analysis and qualitative description for the colors of tongue and its coating, the thickness and moisture of coating and quantification of the cracks of the toilgue.The overall accuracy of the automatic analysis of the colors of tongue and the thickness of tongue coating exceeds 85%.This work shows the promising future of tongue character-ization. | SHENLansun WEIBaoguo CAIYiheng ZHANGXinfeng WANGYanqing CHENJing KONGLingbiao | 2003 | Chinese Journal of Electronics2003，12，3： | 19 |
| 14 | A New Method for Sorting Unknown Radar Emitter Signal显示文摘Sorting rate of common method is not high and it is sensitive to the Signal noise ratio(SNR), in order to solve these problems, bispectrum two dimensions characteristics complexity is applied to sort unknown complicated radar signal and a high sorting rate would be got. The bispectrum of received signal is extracted and it is predigested to two dimensions characteristic, the box dimension and information dimension are extracted from the two dimensions characteristic and used as the sorting characteristics, and the last sorting is accomplished by using KFCM algorithm. For the bispectrum of different signal is distinguishing and it is not sensitive to SNR, the box dimension and information dimension are divisible and steady, the advantage of this new method is validated by simulation results, and the lowest sorting rate is 90% at SNR equals to 10 dB. | CHEN Changxiao HE Minghao XU Jing HAN Jun | 2014 | Chinese Journal of Electronics2014，23，3： | 19 |
| 15 | A Dynamic Programming Track-Before-Detect Algorithm Based on Local Linearization for Non-Gaussian Clutter Background显示文摘The Dynamic programming track before detect(DP-TBD) algorithm has been widely used for detection and tracking of weak targets. The selection of the merit function has an immediate influence on the performance of the DP-TBD. The amplitude merit function is easy to calculate, but the performance of which will decrease in the presence of non-Gaussian clutter. The likelihood ratio merit function in closed analytical form is difficult to derive under non-Gaussian background without target signal parameters. To solve this problem, a novel DPTBD algorithm based on local linearization is proposed.Taking maximum of the state conditional probability ratio of the target as the optimal criteria, a recursive integration equation is derived. The equation is locally linearized by Taylor series expansion and a suboptimal multi-frame test statistic is developed. The calculation of new merit function in the statistic needs only clutter distribution model,and heavy clutter peak can be restrained by making use of clutter distribution characters. So the proposed algorithm can efficiently extract weak target in strong non-Gaussian clutter. Numerical simulations are provided to assess and compare the performance of the proposed algorithm. It turns out that the proposed algorithm has better detection and tracking performance than the widely used DPTBD algorithm at present and is resilient to various clutter distribution models. | ZHENG Daikun WANG Shouyong QIN Xing | 2016 | Chinese Journal of Electronics2016，25，3： | 18 |
| 16 | A Secure Protocol for Determining Whether a Point is Inside a Convex Polygon显示文摘 | LUO Yonglong HUANG Liusheng ZHONG Hong CHEN Guoliang | 2006 | Chinese Journal of Electronics2006，15，4： | 18 |
| 17 | Differential Fault Attack on Camellia显示文摘 | ZHOU Yongbin WU Wenling XU Nannan FENG Dengguo | 2009 | Chinese Journal of Electronics2009，18，1： | 15 |
| 18 | Adaptive Dwell Scheduling for Digital Array Radar Based on Online Pulse Interleaving显示文摘 | CHENG Ting HE Zishu LI Huiyong | 2009 | Chinese Journal of Electronics2009，18，3： | 15 |
| 19 | A Short Text Classification Method Based on N-Gram and CNN显示文摘Text classification is a fundamental task in Nature language process(NLP) application. Most existing research work relied on either explicate or implicit text representation to settle this kind of problems, while these techniques work well for sentence and can not simply apply to short text because of its shortness and sparseness feature. Given these facts that obtaining the simple word vector feature and ignoring the important feature by utilizing the traditional multi-size filter Convolution neural network(CNN) during the course of text classification task, we offer a kind of short text classification model by CNN, which can obtain the abundant text feature by adopting none linear sliding method and N-gram language model, and picks out the key features by using the concentration mechanism, in addition employing the pooling operation can preserve the text features at the most certain as far as possible. The experiment shows that this method we offered, comparing the traditional machine learning algorithm and convolutional neural network, can markedly improve the classification result during the short text classification. | WANG Haitao HE Jie ZHANG Xiaohong LIU Shufen | 2020 | Chinese Journal of Electronics2020，29，2： | 15 |
| 20 | Privacy-Preserving Distance Measurement and Its Applications显示文摘 | LUO Yonglong HUANG Liusheng CHEN Guoliang SHEN Hong | 2006 | Chinese Journal of Electronics2006，15，2： | 15 |
您所在的机构暂未开通此部分的功能，请联系管理员