Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382403
Yan Sun, Xi Chen, Qiyong Lu
SSD-based object tracking has shown its improved performance compared with mean-shift and many people have made further improvements based on it. However, how kernels should be designed to better cooperate with SSD metric and Newton-style iteration remains unsolved. Our work is to find out the underlying principles for SSD kernel design, which can help make the tracker more sensitive to the object movement and make the iteration have better onestep performance. We also create a new kernel called “QPeak” to demonstrate our theorems.
{"title":"Robust kernel design for SSD tracker","authors":"Yan Sun, Xi Chen, Qiyong Lu","doi":"10.1109/YCICT.2009.5382403","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382403","url":null,"abstract":"SSD-based object tracking has shown its improved performance compared with mean-shift and many people have made further improvements based on it. However, how kernels should be designed to better cooperate with SSD metric and Newton-style iteration remains unsolved. Our work is to find out the underlying principles for SSD kernel design, which can help make the tracker more sensitive to the object movement and make the iteration have better onestep performance. We also create a new kernel called “QPeak” to demonstrate our theorems.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123899935","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382353
Ruolun Liu, Suping Li
Music source separation is relevant to many applications including automatic music transcription, remixing in studio, content related music indexing etc. Though source separation has been discussed for decades, there is no systematic summarization focuses on music source separation. Different methods and techniques have been proposed from the different point of views based on the researcher's own specialties. With certain advantages and limitations, they are scattering over different conference proceedings, journals of different subjects, reports, dissertations, and chapter of books. One purpose of this work is to collect them together in one place, thus facilitating the future research on this fascinating topic. The other one is to point out the possible directions of future research.
{"title":"A review on music source separation","authors":"Ruolun Liu, Suping Li","doi":"10.1109/YCICT.2009.5382353","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382353","url":null,"abstract":"Music source separation is relevant to many applications including automatic music transcription, remixing in studio, content related music indexing etc. Though source separation has been discussed for decades, there is no systematic summarization focuses on music source separation. Different methods and techniques have been proposed from the different point of views based on the researcher's own specialties. With certain advantages and limitations, they are scattering over different conference proceedings, journals of different subjects, reports, dissertations, and chapter of books. One purpose of this work is to collect them together in one place, thus facilitating the future research on this fascinating topic. The other one is to point out the possible directions of future research.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124141796","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382458
Tsung Lee, Hsiang-Hua Tsou
In this research, we designed a novel cache mapping scheme for dynamic set-based cache partitioning. The cache mapping scheme facilitates allocation of any non-power-of-2 number of physical cache segments as a private cache to each process. An efficient near-optimal cache partitioning algorithm was designed for capturing working sets of running processes. Transparent cache reconfiguration was designed to enable immediately continuing process execution after cache repartitioning is computed. Experimental results validate its effectiveness in improving the overall hit ratio, the total number of memory accesses, and overall program performance with small number of communications.
{"title":"A novel cache mapping scheme for dynamic set-based cache partitioning","authors":"Tsung Lee, Hsiang-Hua Tsou","doi":"10.1109/YCICT.2009.5382458","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382458","url":null,"abstract":"In this research, we designed a novel cache mapping scheme for dynamic set-based cache partitioning. The cache mapping scheme facilitates allocation of any non-power-of-2 number of physical cache segments as a private cache to each process. An efficient near-optimal cache partitioning algorithm was designed for capturing working sets of running processes. Transparent cache reconfiguration was designed to enable immediately continuing process execution after cache repartitioning is computed. Experimental results validate its effectiveness in improving the overall hit ratio, the total number of memory accesses, and overall program performance with small number of communications.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"265 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124307230","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382357
Chongjia Ni, Wenju Liu, Bo Xu
In this study, we combine the Mandarin characteristics with Mandarin acoustic attribute and text information and use hierarchical model based ensemble machine learning to predict Mandarin pitch accent. Our model could make the best of advantages of prosody hierarchical structure and ensemble machine learning. When comparing our model with classification and regression tree (CART), support vector machine (SVM), adaboost with CART at different experimental conditions, the hierarchical model obtains the best results, it can achieve 84.75% accuracy rate to Mandarin read speech. At the same time, we compare our proposed method with previous proposed method at the same training set and test set. There are 2.25% and 0.82% absolute accuracy rate improvements.
{"title":"Mandarin pitch accent prediction using hierarchical model based ensemble machine learning","authors":"Chongjia Ni, Wenju Liu, Bo Xu","doi":"10.1109/YCICT.2009.5382357","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382357","url":null,"abstract":"In this study, we combine the Mandarin characteristics with Mandarin acoustic attribute and text information and use hierarchical model based ensemble machine learning to predict Mandarin pitch accent. Our model could make the best of advantages of prosody hierarchical structure and ensemble machine learning. When comparing our model with classification and regression tree (CART), support vector machine (SVM), adaboost with CART at different experimental conditions, the hierarchical model obtains the best results, it can achieve 84.75% accuracy rate to Mandarin read speech. At the same time, we compare our proposed method with previous proposed method at the same training set and test set. There are 2.25% and 0.82% absolute accuracy rate improvements.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116354336","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382379
K. Hong, Hong Liang, Chang-sheng Yang
The visual simulation of the Anti-torpedo system is proposed for surface ships defend torpedo. The whole visual real-time process of the surface ships defend torpedo is expounded vividly. 3D models are created with software Multigen Creator. Driving framework programming with Vega Prime API can integrate 3D models, operation rules, special effect and whole scene to a platform system based on visual simulation. Torpedo target echo parameters are estimated accurately by real-time signal processing algorithms, and dynamic data is displayed in the scene of system. As a result, the system realizes real-time simulation of Anti-torpedo and performs well in system test.
针对水面舰艇防御鱼雷的特点，提出了反鱼雷系统的可视化仿真方法。对水面舰艇防御鱼雷的整个可视化实时过程进行了生动的阐述。3D模型是用软件Multigen Creator创建的。使用Vega Prime API编程驾驶框架，可以将3D模型、操作规则、特效和整个场景集成到一个基于视觉仿真的平台系统中。采用实时信号处理算法对鱼雷目标回波参数进行准确估计，并在系统现场显示动态数据。结果表明，该系统实现了反鱼雷的实时仿真，并在系统测试中取得了良好的效果。
{"title":"Visual simulation of Anti-torpedo system","authors":"K. Hong, Hong Liang, Chang-sheng Yang","doi":"10.1109/YCICT.2009.5382379","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382379","url":null,"abstract":"The visual simulation of the Anti-torpedo system is proposed for surface ships defend torpedo. The whole visual real-time process of the surface ships defend torpedo is expounded vividly. 3D models are created with software Multigen Creator. Driving framework programming with Vega Prime API can integrate 3D models, operation rules, special effect and whole scene to a platform system based on visual simulation. Torpedo target echo parameters are estimated accurately by real-time signal processing algorithms, and dynamic data is displayed in the scene of system. As a result, the system realizes real-time simulation of Anti-torpedo and performs well in system test.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116876560","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382338
Chengtian Song, Keyong Wang
As there is lack of valid marking of oil sucker pipe, some pipes which exceeding time limits may break off. The character coding method is presented, soft touch flexible marking technology is used to marking characters on pipe, characters can hold for a long time in erosive environment. Each pipe has each code using character coding method. Pipe is automatically identified using CCD and image processing technology, the pipe which exceeding time limits can be identified in time. The dynamic management can be achieved for a single pipe from use, maintenance to abandon using database system.
{"title":"Automatic identification of oil sucker pipe using character coding","authors":"Chengtian Song, Keyong Wang","doi":"10.1109/YCICT.2009.5382338","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382338","url":null,"abstract":"As there is lack of valid marking of oil sucker pipe, some pipes which exceeding time limits may break off. The character coding method is presented, soft touch flexible marking technology is used to marking characters on pipe, characters can hold for a long time in erosive environment. Each pipe has each code using character coding method. Pipe is automatically identified using CCD and image processing technology, the pipe which exceeding time limits can be identified in time. The dynamic management can be achieved for a single pipe from use, maintenance to abandon using database system.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125795825","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382434
Weng Bin, Pan Ri-jing, Yao Zhi-qiang, Xiao Jun, Yang Shan-chao
T-Spline surface is an important parametric surface, which is widely used in entertainment, engineering, science and medicine. A fragile watermarking algorithm is proposed for integrity authentication of T-Spline surfaces. In this algorithm, some points on T-Spline surfaces are selected by a special algorithm, then the watermark is embedded by modifing the selected points, and then the watermarked surfaces is acquired by modifying the control points with constrained optimization method. The experiment results show that the watermark is fragile to many attacks, and the tampered area can be detected. Additionally, when preprocessing is used before watermark extracting, the algorithm can modified to be semi-fragile that is robust to translating, rotating and uniformly scaling.
{"title":"A fragile watermarking algorithm for T-Spline surfaces","authors":"Weng Bin, Pan Ri-jing, Yao Zhi-qiang, Xiao Jun, Yang Shan-chao","doi":"10.1109/YCICT.2009.5382434","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382434","url":null,"abstract":"T-Spline surface is an important parametric surface, which is widely used in entertainment, engineering, science and medicine. A fragile watermarking algorithm is proposed for integrity authentication of T-Spline surfaces. In this algorithm, some points on T-Spline surfaces are selected by a special algorithm, then the watermark is embedded by modifing the selected points, and then the watermarked surfaces is acquired by modifying the control points with constrained optimization method. The experiment results show that the watermark is fragile to many attacks, and the tampered area can be detected. Additionally, when preprocessing is used before watermark extracting, the algorithm can modified to be semi-fragile that is robust to translating, rotating and uniformly scaling.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128311019","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382455
Haitao Zhao, Shan Wang, Dongtang Ma, Jibo Wei
With the widespread of IEEE 802.11 based ad hoc networks as the extend of wired networks and the importance of knowing available bandwidth to network operators, users, and bandwidth-sensitive applications, available bandwidth estimation in 802.11 based ad hoc networks has been a focus of recent research. However no consensus has arrived on how to precisely measure the available bandwidth in ad hoc networks, which makes all existing approaches are on the stage of experiment and simulation and no standard is agreed yet. We review the state of the art and present a comprehensive analysis of the challenges to estimate available bandwidth in 802.11 based ad hoc networks.
{"title":"Challenges to estimate end-to-end available bandwidth in IEEE 802.11-based ad hoc networks","authors":"Haitao Zhao, Shan Wang, Dongtang Ma, Jibo Wei","doi":"10.1109/YCICT.2009.5382455","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382455","url":null,"abstract":"With the widespread of IEEE 802.11 based ad hoc networks as the extend of wired networks and the importance of knowing available bandwidth to network operators, users, and bandwidth-sensitive applications, available bandwidth estimation in 802.11 based ad hoc networks has been a focus of recent research. However no consensus has arrived on how to precisely measure the available bandwidth in ad hoc networks, which makes all existing approaches are on the stage of experiment and simulation and no standard is agreed yet. We review the state of the art and present a comprehensive analysis of the challenges to estimate available bandwidth in 802.11 based ad hoc networks.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128423225","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382454
Xu Yubin, Z. Mu, Ma Lin
WLAN hybrid indoor location method based on fuzzy c-mean clustering (FCM) and artificial neural network (ANN) is proposed in this paper. For any pattern matching based algorithm in WLAN environment, characteristics of received signal strength (RSS) or signal to noise ratio (SNR) to multiple access points (APs) are utilized to establish radio map in the off-line phase, and in the on-line phase, actual two or three dimensional coordinates of the mobile terminals (MTs) are estimated based on the comparison between the new recorded RSS or SNR and fingerprints stored in radio map. Although the feed-forward ANN with three layers is sufficient to approximate any continuous functions to a desired accuracy and optimize any mapping relationship between training inputs and targets, generalization ability is difficult to be guaranteed. So in order to bridge this gap, FCM method is proposed to select the reference points (RPs) affected by the multi-path effect. Based on this method, RSS or SNR recorded at these RPs is modified by the linear regression. Feasibility and effectiveness of this hybrid FCM and ANN method are verified according to the experimental comparison with ANN method without FCM modification.
{"title":"Hybrid FCM/ANN indoor location method in WLAN environment","authors":"Xu Yubin, Z. Mu, Ma Lin","doi":"10.1109/YCICT.2009.5382454","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382454","url":null,"abstract":"WLAN hybrid indoor location method based on fuzzy c-mean clustering (FCM) and artificial neural network (ANN) is proposed in this paper. For any pattern matching based algorithm in WLAN environment, characteristics of received signal strength (RSS) or signal to noise ratio (SNR) to multiple access points (APs) are utilized to establish radio map in the off-line phase, and in the on-line phase, actual two or three dimensional coordinates of the mobile terminals (MTs) are estimated based on the comparison between the new recorded RSS or SNR and fingerprints stored in radio map. Although the feed-forward ANN with three layers is sufficient to approximate any continuous functions to a desired accuracy and optimize any mapping relationship between training inputs and targets, generalization ability is difficult to be guaranteed. So in order to bridge this gap, FCM method is proposed to select the reference points (RPs) affected by the multi-path effect. Based on this method, RSS or SNR recorded at these RPs is modified by the linear regression. Feasibility and effectiveness of this hybrid FCM and ANN method are verified according to the experimental comparison with ANN method without FCM modification.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128582043","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}
Pub Date : 2009-09-01DOI: 10.1109/YCICT.2009.5382327
Hui Wang, Taifun Liu, Yan Ye, T. Xu
This paper discusses the influence of phase and gain imbalances between two branches of LINC transmitter on the recombined signals. Experiments are carried out on a model of LINC transmitter using a 3 dB Wilkinson RF combiner which is designed with micro-strip line. Then the phase and gain errors that can be tolerated in the LINC transmitter with high efficiency and good linearity are discussed. The signal used in the Validation experiment is a two-carrier WCDMA signal with the sample rate of 61.44 M Sample/s. The Validation results demonstrate that the correction for phase and gain imbalances is necessary in LINC transmitter.
本文讨论了LINC发射机两支路的相位和增益不平衡对复合信号的影响。在采用微带线设计的3db威尔金森射频合成器的LINC发射机模型上进行了实验。然后讨论了在高效率和良好线性度的情况下，LINC发射机所能容忍的相位和增益误差。验证实验中使用的信号为双载波WCDMA信号，采样率为61.44 M sample /s。验证结果表明，对相位和增益不平衡进行校正是必要的。
{"title":"Influence of phase and gainimbalances on recombined signals in LINC transmitters","authors":"Hui Wang, Taifun Liu, Yan Ye, T. Xu","doi":"10.1109/YCICT.2009.5382327","DOIUrl":"https://doi.org/10.1109/YCICT.2009.5382327","url":null,"abstract":"This paper discusses the influence of phase and gain imbalances between two branches of LINC transmitter on the recombined signals. Experiments are carried out on a model of LINC transmitter using a 3 dB Wilkinson RF combiner which is designed with micro-strip line. Then the phase and gain errors that can be tolerated in the LINC transmitter with high efficiency and good linearity are discussed. The signal used in the Validation experiment is a two-carrier WCDMA signal with the sample rate of 61.44 M Sample/s. The Validation results demonstrate that the correction for phase and gain imbalances is necessary in LINC transmitter.","PeriodicalId":138803,"journal":{"name":"2009 IEEE Youth Conference on Information, Computing and Telecommunication","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128666183","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：