首页 > 最新文献

2017 9th International Conference on Advanced Infocomm Technology (ICAIT)最新文献

英文 中文
Generation of optical vortex array by using a diffraction grating 利用衍射光栅产生光学涡旋阵列
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388822
Xinyu Zhang, Chunhua Hu, Ran Zhao, Qing Dai, P. Sun
The generation of an optical vortex array (OVA) by using diffraction grating is presented. At first a diffraction grating is produced with a computer and displayed on a spatial light modulator (SLM) which is controlled by the computer. Then let a plane light irradiate the SLM with the diffraction grating vertically. The transmitted lights after the SLM can produce a regular optical vortex array which can be observed by adjusting the diffraction distance of the grating. The principle of the generation is discussed and the distribution of the intensity of the optical vortex array is presented. The properties of the produced optical vortex array at different diffraction distance are also discussed. The simulations are completed and the results show that the optical vortex array can be generated well by using the diffraction grating, which is simple and easy to implement. And we measure the deformation phase by using the zero-contour of the real parts of the OVA, which provides a new method for deformation phase measurement.
介绍了利用衍射光栅产生光学涡旋阵列的方法。首先用计算机产生衍射光栅,并显示在由计算机控制的空间光调制器(SLM)上。然后用平面光垂直照射带衍射光栅的SLM。通过调整光栅的衍射距离,可以观察到经过SLM后的透射光形成规则的光学涡旋阵列。讨论了光涡旋阵的产生原理,给出了光涡旋阵的光强分布。讨论了所制备的光学涡旋阵列在不同衍射距离下的性能。仿真结果表明,利用衍射光栅可以很好地产生光学涡旋阵列,且结构简单,易于实现。利用OVA实部的零轮廓来测量变形相位,为变形相位的测量提供了一种新的方法。
{"title":"Generation of optical vortex array by using a diffraction grating","authors":"Xinyu Zhang, Chunhua Hu, Ran Zhao, Qing Dai, P. Sun","doi":"10.1109/ICAIT.2017.8388822","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388822","url":null,"abstract":"The generation of an optical vortex array (OVA) by using diffraction grating is presented. At first a diffraction grating is produced with a computer and displayed on a spatial light modulator (SLM) which is controlled by the computer. Then let a plane light irradiate the SLM with the diffraction grating vertically. The transmitted lights after the SLM can produce a regular optical vortex array which can be observed by adjusting the diffraction distance of the grating. The principle of the generation is discussed and the distribution of the intensity of the optical vortex array is presented. The properties of the produced optical vortex array at different diffraction distance are also discussed. The simulations are completed and the results show that the optical vortex array can be generated well by using the diffraction grating, which is simple and easy to implement. And we measure the deformation phase by using the zero-contour of the real parts of the OVA, which provides a new method for deformation phase measurement.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122558829","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}
引用次数: 1
Direct positioning of a stationary target in MIMO-OFDM system MIMO-OFDM系统中静止目标的直接定位
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388920
Tianzhu Qin, Bin Ba, Zhiyu Lu, Daming Wang
Multiple input multiple output orthogonal frequency division multiplexing (MIMO-OFDM) system, a new concept in recent years, is used extensively in civilian and military applications. We develop a novel direct position determination (DPD) approach in MIMO-OFDM system to locate a stationary target, reaching a superior performance than other conventional localization algorithms. Firstly, we obtain extend noise subspaces from all receivers by constructing and decomposing the extended covariance matrices. Then, the target position is estimated directly via fusing the extend noise subspace data, thereby avoiding the limitations of two-step method. Our proposed algorithm realizes low complexity and high robustness to noise by using the subspace of the extended Hadamard product. Simulation results demonstrate our proposed algorithm outperforms other localization methods, especially under the condition of low signal-to-noise ratio (SNR).
多输入多输出正交频分复用(MIMO-OFDM)系统是近年来提出的一个新概念,在民用和军用领域得到了广泛的应用。在MIMO-OFDM系统中,我们提出了一种新的直接定位(DPD)方法来定位静止目标,达到了比其他传统定位算法更好的性能。首先,通过构造和分解扩展协方差矩阵,得到所有接收机的扩展噪声子空间;然后,通过融合扩展噪声子空间数据直接估计目标位置,避免了两步法的局限性;该算法利用扩展Hadamard积的子空间实现了低复杂度和高鲁棒性。仿真结果表明,该算法在低信噪比条件下优于其他定位方法。
{"title":"Direct positioning of a stationary target in MIMO-OFDM system","authors":"Tianzhu Qin, Bin Ba, Zhiyu Lu, Daming Wang","doi":"10.1109/ICAIT.2017.8388920","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388920","url":null,"abstract":"Multiple input multiple output orthogonal frequency division multiplexing (MIMO-OFDM) system, a new concept in recent years, is used extensively in civilian and military applications. We develop a novel direct position determination (DPD) approach in MIMO-OFDM system to locate a stationary target, reaching a superior performance than other conventional localization algorithms. Firstly, we obtain extend noise subspaces from all receivers by constructing and decomposing the extended covariance matrices. Then, the target position is estimated directly via fusing the extend noise subspace data, thereby avoiding the limitations of two-step method. Our proposed algorithm realizes low complexity and high robustness to noise by using the subspace of the extended Hadamard product. Simulation results demonstrate our proposed algorithm outperforms other localization methods, especially under the condition of low signal-to-noise ratio (SNR).","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126933293","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}
引用次数: 0
Backstepping adaptive sliding mode control for the USV course tracking system USV航向跟踪系统的反步自适应滑模控制
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388927
Xiao Chen, Zhong Liu, Hongning Hu, Lian Wang, Jiao Dong
In order to realize the course tracking nonlinear control of an USV with single waterjet, firstly, the motion stability analysis of the USV's course is carried out, then, considering the modeling errors and external disturbances, an adaptive sliding mode control law was proposed, which is based on the sliding mode control theory and backstepping method. Finally, based on the Lyapunov stability theory, it is proved that the control law can ensure the global asymptotic stability of the heading tracking system. The comparisons of simulation results verify the effectiveness of the proposed controller.
为了实现单水射流无人潜航器的航向跟踪非线性控制,首先对无人潜航器的航向进行了运动稳定性分析,然后考虑建模误差和外部干扰,提出了一种基于滑模控制理论和反步法的自适应滑模控制律。最后,基于Lyapunov稳定性理论,证明了该控制律能够保证航向跟踪系统的全局渐近稳定。仿真结果的对比验证了所提控制器的有效性。
{"title":"Backstepping adaptive sliding mode control for the USV course tracking system","authors":"Xiao Chen, Zhong Liu, Hongning Hu, Lian Wang, Jiao Dong","doi":"10.1109/ICAIT.2017.8388927","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388927","url":null,"abstract":"In order to realize the course tracking nonlinear control of an USV with single waterjet, firstly, the motion stability analysis of the USV's course is carried out, then, considering the modeling errors and external disturbances, an adaptive sliding mode control law was proposed, which is based on the sliding mode control theory and backstepping method. Finally, based on the Lyapunov stability theory, it is proved that the control law can ensure the global asymptotic stability of the heading tracking system. The comparisons of simulation results verify the effectiveness of the proposed controller.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"30 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114262434","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}
引用次数: 5
Color demosaicking with the spatial alignment property of spectral Laplacians 利用光谱拉普拉斯算子空间对准特性的彩色去马赛克
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388949
Danhua Liu, Yufei Guo, Dahua Gao, Xueyan Song, Guangming Shi
We present a color demosaicking method which aims to improve the demosaicking performance by thoroughly exploiting domain knowledge to confine the solution space for the underlying true color image. We use a physically-induced model to infer spatial alignment property of spectral Laplacians. Specifically, the 2D Laplacians of different channels are sparse, and it benefits spatial alignment property across different color channels. Then, we establish an optimization model, using the image formation model and the spatial alignment property of spectral Laplacians, to solve the ill-posed problem of the color demosaicking. Finally, some extensive experiments have been done and show the availability of our approach in color image demosaicking.
本文提出了一种彩色去马赛克方法,该方法通过充分利用领域知识来限制底层真彩色图像的解空间,从而提高去马赛克性能。我们使用物理诱导模型来推断光谱拉普拉斯子的空间排列特性。具体来说,不同通道的二维拉普拉斯向量是稀疏的,这有利于不同颜色通道的空间对齐特性。然后,利用图像形成模型和光谱拉普拉斯算子的空间对准特性,建立优化模型,解决彩色去马赛克的不适定问题。最后,进行了大量的实验,证明了该方法在彩色图像去马赛克中的有效性。
{"title":"Color demosaicking with the spatial alignment property of spectral Laplacians","authors":"Danhua Liu, Yufei Guo, Dahua Gao, Xueyan Song, Guangming Shi","doi":"10.1109/ICAIT.2017.8388949","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388949","url":null,"abstract":"We present a color demosaicking method which aims to improve the demosaicking performance by thoroughly exploiting domain knowledge to confine the solution space for the underlying true color image. We use a physically-induced model to infer spatial alignment property of spectral Laplacians. Specifically, the 2D Laplacians of different channels are sparse, and it benefits spatial alignment property across different color channels. Then, we establish an optimization model, using the image formation model and the spatial alignment property of spectral Laplacians, to solve the ill-posed problem of the color demosaicking. Finally, some extensive experiments have been done and show the availability of our approach in color image demosaicking.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114637372","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}
引用次数: 0
Improving IPv6 transition management with IPv6 network virtualization 通过IPv6网络虚拟化改进IPv6过渡管理
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388896
Dujuan Gu, Y. Xue, Dongsheng Wang, Ze Luo, Baoping Yan
We have entered the transitional period between IPv4 and IPv6. However, IPv6 transition management involves entirely new challenges. To tackle these management challenges, we propose a management architecture (VNET6) to improve IPv6 transition manageability. Compared with the traditional network management architecture, VNET6 presents four different aspects: network layer virtualization for IPv4/IPv6 coexistence, service abstraction for IPv6 transition technologies, dynamic and autonomic management manner and end-to-end communication guarantee over heterogeneous networks. The implementation and evaluation demonstrate that VNET6 is a distributed enabler for the dynamic and autonomic management of IPv6 transition. This enabler facilitates incremental IPv6 deployment and simplifies the management of IPv4/IPv6 coexistence. Meanwhile, this enabler can effectively ensure application's end-to-end communication across multiple heterogeneous administrative domains. Especially, VNET6 makes it easier to provide performance-assured end-to-end paths for application's communication. Hence, VNET6 can improve the manageability for IPv6 transition. The manageability can facilitate IPv6 deployment and transition in a stable and manageable manner.
我们已经进入了IPv4和IPv6之间的过渡期。然而,IPv6转换管理涉及到全新的挑战。为了解决这些管理挑战,我们提出了一个管理架构(VNET6)来提高IPv6转换的可管理性。与传统网络管理体系结构相比,VNET6在IPv4/IPv6共存的网络层虚拟化、IPv6过渡技术的服务抽象、异构网络的动态自治管理方式和端到端通信保障等方面表现出了不同的特点。实现和评估表明,VNET6是IPv6过渡动态和自主管理的分布式使能器。使能器简化了IPv6的增量部署,简化了IPv4/IPv6共存的管理。同时,此启用程序可以有效地确保应用程序跨多个异构管理域的端到端通信。特别是,VNET6可以更容易地为应用程序的通信提供性能保证的端到端路径。因此,VNET6可以提高IPv6转换的可管理性。可管理性使IPv6的部署和过渡更加稳定、易于管理。
{"title":"Improving IPv6 transition management with IPv6 network virtualization","authors":"Dujuan Gu, Y. Xue, Dongsheng Wang, Ze Luo, Baoping Yan","doi":"10.1109/ICAIT.2017.8388896","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388896","url":null,"abstract":"We have entered the transitional period between IPv4 and IPv6. However, IPv6 transition management involves entirely new challenges. To tackle these management challenges, we propose a management architecture (VNET6) to improve IPv6 transition manageability. Compared with the traditional network management architecture, VNET6 presents four different aspects: network layer virtualization for IPv4/IPv6 coexistence, service abstraction for IPv6 transition technologies, dynamic and autonomic management manner and end-to-end communication guarantee over heterogeneous networks. The implementation and evaluation demonstrate that VNET6 is a distributed enabler for the dynamic and autonomic management of IPv6 transition. This enabler facilitates incremental IPv6 deployment and simplifies the management of IPv4/IPv6 coexistence. Meanwhile, this enabler can effectively ensure application's end-to-end communication across multiple heterogeneous administrative domains. Especially, VNET6 makes it easier to provide performance-assured end-to-end paths for application's communication. Hence, VNET6 can improve the manageability for IPv6 transition. The manageability can facilitate IPv6 deployment and transition in a stable and manageable manner.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126862439","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}
引用次数: 3
Fault location in distribution network based on discrete Fréchet distance algorithm 基于离散fr<s:1>距离算法的配电网故障定位
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388886
Sizu Hou, Siyu Han
With the development of power system, the power sector is more and more demanding on the reliability of distribution network fault location. We analyze the shortcomings of the algorithms used in the existing fault location system. In addition, combined with the development of existing distribution network automation, we transformed the fault location into a similarity curve question and it is proposed to use the discrete Fréchet distance algorithm to perform fault location. The comparison of the discrete Fréchet distance with the Hausdorff distance and euclidean distance is proved by simulation. The superiority of the discrete Fréchet distance is proved. Simulate a variety of metal ground fault type on the project by changing the location and direction of the coil and then achieve the function of fault location based on discrete Fréchet distance algorithm. It proves the feasibility of the algorithm in the fault location system.
随着电力系统的发展,电力部门对配电网故障定位的可靠性要求越来越高。分析了现有故障定位算法的不足。此外,结合现有配电网自动化的发展情况,将故障定位问题转化为相似曲线问题,并提出采用离散fr距离算法进行故障定位。通过仿真证明了离散fr距离与Hausdorff距离和欧几里得距离的比较。证明了离散法的优越性。通过改变线圈的位置和方向,模拟工程上多种金属接地故障类型,实现基于离散fr距离算法的故障定位功能。验证了该算法在故障定位系统中的可行性。
{"title":"Fault location in distribution network based on discrete Fréchet distance algorithm","authors":"Sizu Hou, Siyu Han","doi":"10.1109/ICAIT.2017.8388886","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388886","url":null,"abstract":"With the development of power system, the power sector is more and more demanding on the reliability of distribution network fault location. We analyze the shortcomings of the algorithms used in the existing fault location system. In addition, combined with the development of existing distribution network automation, we transformed the fault location into a similarity curve question and it is proposed to use the discrete Fréchet distance algorithm to perform fault location. The comparison of the discrete Fréchet distance with the Hausdorff distance and euclidean distance is proved by simulation. The superiority of the discrete Fréchet distance is proved. Simulate a variety of metal ground fault type on the project by changing the location and direction of the coil and then achieve the function of fault location based on discrete Fréchet distance algorithm. It proves the feasibility of the algorithm in the fault location system.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127470417","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}
引用次数: 3
A joint uplink/downlink resource allocation algorithm in OFDMA wireless networks OFDMA无线网络中联合上行/下行资源分配算法
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388904
Bingfeng Liu, Yanfei Wei, Li Liu, Ran Hu, Guanyu Qiao
As the uplink resource and the downlink resource are separated to some extent, conventional resource allocation algorithms usually treat the total system resource allocation independently in wireless networks. However, for the interactive service, its performance is mainly determined by the service quality of uplink and that of downlink jointly, and it is important to allocate the uplink and downlink resource simultaneously. In this paper, we propose a new joint uplink/downlink resource allocation algorithm in orthogonal frequency division multiple access (OFDMA) wireless networks with interactive service. The uplink and downlink resource are allocated jointly to improve the system performance, and the issue is formulated as an optimization problem. The paper presents the solving processes of the optimization problem by dual optimization method. The results of simulation indicate that the proposed joint uplink/downlink resource allocation algorithm can effectively promote the resource efficiency of the OFDMA wireless networks with interactive service.
在无线网络中,由于上行资源和下行资源在一定程度上是分离的,传统的资源分配算法通常是独立地对整个系统的资源分配进行处理。而对于交互式业务来说,其性能主要是由上下行业务质量共同决定的,上下行资源的同时分配是很重要的。在具有交互业务的正交频分多址(OFDMA)无线网络中,提出了一种新的联合上行/下行资源分配算法。为了提高系统性能,将上下行资源共同分配,并将该问题表述为优化问题。本文给出了用对偶优化方法求解优化问题的过程。仿真结果表明,所提出的联合上行/下行资源分配算法能够有效地提高具有交互业务的OFDMA无线网络的资源效率。
{"title":"A joint uplink/downlink resource allocation algorithm in OFDMA wireless networks","authors":"Bingfeng Liu, Yanfei Wei, Li Liu, Ran Hu, Guanyu Qiao","doi":"10.1109/ICAIT.2017.8388904","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388904","url":null,"abstract":"As the uplink resource and the downlink resource are separated to some extent, conventional resource allocation algorithms usually treat the total system resource allocation independently in wireless networks. However, for the interactive service, its performance is mainly determined by the service quality of uplink and that of downlink jointly, and it is important to allocate the uplink and downlink resource simultaneously. In this paper, we propose a new joint uplink/downlink resource allocation algorithm in orthogonal frequency division multiple access (OFDMA) wireless networks with interactive service. The uplink and downlink resource are allocated jointly to improve the system performance, and the issue is formulated as an optimization problem. The paper presents the solving processes of the optimization problem by dual optimization method. The results of simulation indicate that the proposed joint uplink/downlink resource allocation algorithm can effectively promote the resource efficiency of the OFDMA wireless networks with interactive service.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131318813","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}
引用次数: 0
The effect of kernel size of CNNs for lung nodule classification cnn核大小对肺结节分类的影响
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388942
Jing Chen, Yao Shen
Early detection in lung nodule will be helpful for lung cancer diagnosis. Computer-aided detection (CAD) system to automatic detection of pulmonary nodules is one of the most effective methods to decrease the burden on radiologists where they have to analyze a huge number of thoracic Computed Tomography (CT) scans to find out suspicious nodules. Lung nodule classification is crucial to implement a trustable lung nodule detection system. With the rapid development of deep learning in the field of object recognition, good performance on lung nodules classification has been achieved with Convolutional Neural Network (CNN). In this study, we propose three CNN architectures which are adapted to represent small, normal and large networks. We implement different CNN architectures with various kernel sizes to compare the performances of different combinations of CNN architectures and convolution kernels. The method is evaluated on the public Lung Image Database Consortium (LIDC) dataset of 1018 patients scans. The experiment shows the relation of convolution layers and kernel size has affection on the sensitivity of result in our model. The proposed method achieved a sensitivity of 88.22%∼94.18%.
早期发现肺结节有助于肺癌的诊断。计算机辅助检测(CAD)系统对肺结节进行自动检测是减轻放射科医生分析大量胸部CT扫描以发现可疑结节负担的最有效方法之一。肺结节分类是建立可靠的肺结节检测系统的关键。随着深度学习在目标识别领域的快速发展,卷积神经网络(CNN)在肺结节分类上取得了很好的效果。在本研究中,我们提出了三种CNN架构,分别适用于表示小型、普通和大型网络。我们用不同的内核大小实现了不同的CNN架构,比较了CNN架构和卷积核不同组合的性能。该方法在1018例患者扫描的公共肺图像数据库联盟(LIDC)数据集上进行了评估。实验表明,卷积层数与核大小的关系对模型结果的灵敏度有影响。该方法的灵敏度为88.22% ~ 94.18%。
{"title":"The effect of kernel size of CNNs for lung nodule classification","authors":"Jing Chen, Yao Shen","doi":"10.1109/ICAIT.2017.8388942","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388942","url":null,"abstract":"Early detection in lung nodule will be helpful for lung cancer diagnosis. Computer-aided detection (CAD) system to automatic detection of pulmonary nodules is one of the most effective methods to decrease the burden on radiologists where they have to analyze a huge number of thoracic Computed Tomography (CT) scans to find out suspicious nodules. Lung nodule classification is crucial to implement a trustable lung nodule detection system. With the rapid development of deep learning in the field of object recognition, good performance on lung nodules classification has been achieved with Convolutional Neural Network (CNN). In this study, we propose three CNN architectures which are adapted to represent small, normal and large networks. We implement different CNN architectures with various kernel sizes to compare the performances of different combinations of CNN architectures and convolution kernels. The method is evaluated on the public Lung Image Database Consortium (LIDC) dataset of 1018 patients scans. The experiment shows the relation of convolution layers and kernel size has affection on the sensitivity of result in our model. The proposed method achieved a sensitivity of 88.22%∼94.18%.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131645660","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}
引用次数: 13
Research on data fusion algorithm for attitude detection systems based on MEMS and magnetoresistive sensors 基于MEMS和磁阻传感器的姿态检测系统数据融合算法研究
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388891
Xiang Wang, R. Bai, Xiaoyang Cui, Tao Wu, Z. Qian
The attitude detection system based on MEMS and magnetoresistive sensors is widely used in a variety areas. The magnetoresistive sensor acts as an auxiliary sensor to correct the measured value of MEMS inertial sensor. It is necessary to design an appropriate data fusion algorithm to process multiple sensor data. According to the output characteristics of each sensor, the data fusion algorithm take advantage of each sensor and reduce the unreliability of a single sensor in the measurement process to obtain the optimal attitude estimation. The performance of data fusion algorithm will affect the accuracy and stability of whole system. Focused and reviewed in this paper are the present situation and development trend of data fusion algorithm for attitude detection system based on MEMS and magnetoresistive sensors.
基于MEMS和磁阻传感器的姿态检测系统被广泛应用于各个领域。磁阻传感器作为辅助传感器,对MEMS惯性传感器的测量值进行校正。有必要设计一种合适的数据融合算法来处理多传感器数据。根据每个传感器的输出特性,数据融合算法利用每个传感器的优势,减少单个传感器在测量过程中的不可靠性,从而获得最优姿态估计。数据融合算法的性能直接影响到整个系统的准确性和稳定性。本文重点综述了基于MEMS和磁阻传感器的姿态检测系统数据融合算法的现状和发展趋势。
{"title":"Research on data fusion algorithm for attitude detection systems based on MEMS and magnetoresistive sensors","authors":"Xiang Wang, R. Bai, Xiaoyang Cui, Tao Wu, Z. Qian","doi":"10.1109/ICAIT.2017.8388891","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388891","url":null,"abstract":"The attitude detection system based on MEMS and magnetoresistive sensors is widely used in a variety areas. The magnetoresistive sensor acts as an auxiliary sensor to correct the measured value of MEMS inertial sensor. It is necessary to design an appropriate data fusion algorithm to process multiple sensor data. According to the output characteristics of each sensor, the data fusion algorithm take advantage of each sensor and reduce the unreliability of a single sensor in the measurement process to obtain the optimal attitude estimation. The performance of data fusion algorithm will affect the accuracy and stability of whole system. Focused and reviewed in this paper are the present situation and development trend of data fusion algorithm for attitude detection system based on MEMS and magnetoresistive sensors.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121110512","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}
引用次数: 2
Seamless converging system for IPv4/IPv6 transition 无缝融合系统,实现IPv4/IPv6过渡
Pub Date : 2017-11-01 DOI: 10.1109/ICAIT.2017.8388898
Zhao Qin
The IPv4 address pool of ICANN has been depleted. Internet service providers are accelerating the research and deployment of IPv6 transition solution. Dual stack and tunneling technologies can only allow IPv4 and IPv6 to coexist, but can't make IPv4 and IPv6 network interact with each other. For alleviating the shortage of IPv4 address, accelerating the deployment of IPv6 and promoting the seamless converging of IPv4 and IPv6 network, this paper illustrate the design and implementation of an IPv4/IPv6 seamless converging system. The system is mainly composed by stateful and stateless protocol translation modules and can make hosts with shared IPv4 address or global IPv6 address access IPv4 Internet across IPv6 backbone.
ICANN的IPv4地址池已经用完。互联网服务提供商正在加快对IPv6过渡解决方案的研究和部署。双栈和隧道技术只能允许IPv4和IPv6共存,不能使IPv4和IPv6网络相互作用。为了缓解IPv4地址的紧缺,加快IPv6的部署,促进IPv4与IPv6网络的无缝融合,本文设计并实现了一种IPv4/IPv6无缝融合系统。该系统主要由有状态和无状态协议转换模块组成,可以使共享IPv4地址或全局IPv6地址的主机通过IPv6骨干网接入IPv4互联网。
{"title":"Seamless converging system for IPv4/IPv6 transition","authors":"Zhao Qin","doi":"10.1109/ICAIT.2017.8388898","DOIUrl":"https://doi.org/10.1109/ICAIT.2017.8388898","url":null,"abstract":"The IPv4 address pool of ICANN has been depleted. Internet service providers are accelerating the research and deployment of IPv6 transition solution. Dual stack and tunneling technologies can only allow IPv4 and IPv6 to coexist, but can't make IPv4 and IPv6 network interact with each other. For alleviating the shortage of IPv4 address, accelerating the deployment of IPv6 and promoting the seamless converging of IPv4 and IPv6 network, this paper illustrate the design and implementation of an IPv4/IPv6 seamless converging system. The system is mainly composed by stateful and stateless protocol translation modules and can make hosts with shared IPv4 address or global IPv6 address access IPv4 Internet across IPv6 backbone.","PeriodicalId":376884,"journal":{"name":"2017 9th International Conference on Advanced Infocomm Technology (ICAIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130854473","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}
引用次数: 4
期刊
2017 9th International Conference on Advanced Infocomm Technology (ICAIT)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1