{"title":"The quantization effects of different probability distribution on multilayer feedforward neural networks","authors":"Minghu Jiang, G. Gielen, Beixong Deng, Xiaofang Tang, Q. Ruan, Baozong Yuan","doi":"10.1109/ICOSP.2002.1179999","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1179999","url":null,"abstract":"A statistical model of quantization was used to analyze the effects of quantization in digital implementation, and the performance degradation caused by number of quantized bits in multilayer feedforward neural networks (MLFNN) of different probability distribution. The performance of the training was compared with and without clipping weights for MLFNN. We established and analyzed the relationships between inputs and outputs among bit resolution, network-layer number, and performance degradation of MLFNN which are based on statistical models on-chip and off-chip training.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127061133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An adaptive interference cancellation receiver","authors":"Cuiran Li, Chengshu Li","doi":"10.1109/ICOSP.2002.1180023","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180023","url":null,"abstract":"The paper proposes an adaptive interference cancellation receiver for code-division multiple access (CDMA). In the receiver, we first introduce a set of reliable factors based on the output signal of the i/sup th/ user for its m/sup th/ bit, then we can calculate MAI according to reliable factors and finally the symbol decision is performed by interference cancellation. By simulation in both the additive white Gaussian noise (AWGN) and multipath fading channels, the results show that the proposed scheme can outperform the classical RAKE receiver and some of the existing interference cancellation algorithms in terms of BER performance and implementation complexity.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127331417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Superquadric-based reconstruction from 2D images","authors":"Weibin Liu, Chaopeng Zhang, Baozong Yuan","doi":"10.1109/ICOSP.2002.1181144","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1181144","url":null,"abstract":"An approach for superquadric-based reconstruction from 2D images is developed, which computes and reconstructs the parametric models of the VE objects from the 2D images of the counterpart real objects. The superquadric-based hierarchical description as the universal parametric description of the 3D objects is proposed. On one hand, according to the complexity of the real objects, the superquadric curves and their deformations are implemented to fit the contour data of projection images, and the superquadric-based shape descriptions of the real objects are obtained according to the spherical product of superquadrics. On the other hand, the actual size and position are calculated by using epipolar technique for vision reconstruction from multiple uncalibrated images. Combining the two sets of parametric data, the whole superquadric-based descriptions of the real objects are obtained.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"1973 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129954885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Joint estimation of time-frequency parameters using modified RID","authors":"Hongfeng Qin, Jianguo Huang","doi":"10.1109/ICOSP.2002.1180105","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180105","url":null,"abstract":"Joint estimation of time-frequency parameters plays a very important role for source localization in many research areas, such as radar, sonar, communication, geological exploration, and biomedical engineering. A novel and efficient modified reduced interference distribution (MRID) by windowing in the time domain and smoothing in segmentation is proposed for the joint estimation of time and frequency parameters of multiple source signals. The MRID method can obviously improve the processing speed with less loss in estimation performance. Computer simulations and experiments are conducted to show the performance in precision and resolution as well as the reduction in computation by using the MRID.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SAR image feature extraction and classification with fractal-based description","authors":"Jia Xu, Ling Lu, Zhenming Feng, Yingning Peng","doi":"10.1109/ICOSP.2002.1180052","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180052","url":null,"abstract":"In the field of synthetic aperture radar (SAR) image analysis, an effective feature extraction method based on a fractal Brownian increment random field (FBRIR) is introduced, and an effective classification method with a neuron network based on adaptive resonance theory (ART) is designed accordingly. At last the validity of this systematic approach is tested and compared using real data of Ku band SAR images.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132149396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A learnable genetic algorithm for QoS multicast routing","authors":"Feng Xiao-Jun, Liu Fang","doi":"10.1109/ICOSP.2002.1180987","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180987","url":null,"abstract":"By improving the conventional genetic algorithm, we put forward a learnable genetic algorithm combining machine learning and genetic algorithm. The central idea of the algorithm is that it generates new individuals by processes of hypothesis generation and instantiation, rather than by mutation and/or recombination as in conventional genetic algorithms. The algorithm is then used for the bandwidth-delay-constrained least-cost multicast routing problem. The features of this new algorithm are simplicity and effectivity.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130967479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Speech retrieval for TV news programs by fusing the audio and video information","authors":"Xinbo Gao, Jie Li, H. Ji","doi":"10.1109/ICOSP.2002.1179955","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1179955","url":null,"abstract":"A typical news story contains a brief report by the anchor person(s) in the studio, as well as news footage in the field. Investigation shows that our recognizer performs better when indexing audio from the studio than that from the field. In order to automatically extract the \"reliable\" audio segments for speech retrieval, we attempt to detect studio-to-field transitions by means of video parsing. Our research is based on 146 news stories collected from Hong Kong TVB Jade station. Retrieval using the entire audio track gave (average inverse rank) AIR=0.759 while, with the incorporation of video parsing, we performed retrieval based only on the studio recordings, which produced AIR=0.765.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127866771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"On the comparisons between two outer-supervised learning algorithms for finding the inversion of arbitrary nonsingular matrix","authors":"De-shuang Huang, Haiyan Hu, Xiaofeng Wang","doi":"10.1109/ICOSP.2002.1180130","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180130","url":null,"abstract":"This paper discusses using two kinds of outer-supervised learning algorithms, i.e., the constrained learning algorithm and recursive least squares algorithm, for finding the inversion of arbitrary nonsingular matrix (including the complex ones). We present the details of two kinds of outer-supervised learning algorithms respectively in this paper, and how to use them based on linear feedforward neural networks for finding the inversion of the arbitrary nonsingular matrix. Finally, to compare the corresponding performance for two learning methods, several simulation results are reported and discussed.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129030809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance evaluation of Gray-mapped constant weight modulation code on a two-dimensional ISI/AWGN channel","authors":"D. Chen, C. Xie, Xiandeng Pei","doi":"10.1109/ICOSP.2002.1180149","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180149","url":null,"abstract":"A new encoding method of modulation code for page-oriented optical memories (POMs) based on Gray-code is introduced. The Gray-mapped constant weight modulation code (GCWMC) is evaluated by use of simulated POM data pages. It is illustrated that in the statistical sense the proposed GCWMC has an advantage of bit-error ratio (BER) performance over the binary-mapped constant weight modulation code (BCWMC) on a severe two-dimensional intersymbol interference (ISI) channel with additive white Gaussian noise (AWGN).","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"467 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125420228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Simulation on characteristic of angle-tracking for semi-continuous wave radar","authors":"Wei Liu, T. Zeng, T. Long","doi":"10.1109/ICOSP.2002.1180063","DOIUrl":"https://doi.org/10.1109/ICOSP.2002.1180063","url":null,"abstract":"The distance shield problem may occur with the use of high-PRF semi-continuous wave radar. The conventional solutions are to employ an uneven PRF wave, which increases the complexity of the equipment. Thus, a blind tracking arithmetic, which is implemented by combining /spl alpha/-/spl beta/ filtering arithmetic with smooth extrapolation, is put forward. The arithmetic has been simulated in the Matlab Simulink environment The simulation result proves the validity of the arithmetic in various noise conditions, especially in the period of the distance shield problem.","PeriodicalId":159807,"journal":{"name":"6th International Conference on Signal Processing, 2002.","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123387600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}