发布求助
文献互助 智能选刊 最新文献

2019 27th European Signal Processing Conference (EUSIPCO)最新文献

筛选
英文 中文
A Novel Particle Filter for High-Dimensional Systems Using Penalized Perturbations 一种基于惩罚扰动的高维系统粒子滤波器
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8903178
Yousef El-Laham, Z. Krayem, Jessica Maghakian, M. Bugallo
{"title":"A Novel Particle Filter for High-Dimensional Systems Using Penalized Perturbations","authors":"Yousef El-Laham, Z. Krayem, Jessica Maghakian, M. Bugallo","doi":"10.23919/EUSIPCO.2019.8903178","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8903178","url":null,"abstract":"In order to efficiently perform inference on high-dimensional nonlinear non-Gaussian state-space models using particle filtering, it is critical that particles are generated from the optimal proposal distribution. However, finding a closed-form to the optimal proposal proves to be difficult in practice, as many application problems do not satisfy the requirement of conjugate state and observation equations. In this paper, we overcome this challenge by designing a novel method that introduces conjugate artificial noise into the system and optimally perturbs the particles in a way that balances a bias-variance tradeoff. Our method is validated through extensive numerical simulations applied to a gene regulatory network problem, and results show better performance than that of state-of-the-art methods, especially in cases where the state noise is heavy-tailed.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124223637","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
Deep Neural Network Based Poetic Meter Classification Using Musical Texture Feature Fusion 基于深度神经网络的音乐织体特征融合诗歌格律分类
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902998
R. Rajan, Anu Alphonsa Raju
{"title":"Deep Neural Network Based Poetic Meter Classification Using Musical Texture Feature Fusion","authors":"R. Rajan, Anu Alphonsa Raju","doi":"10.23919/EUSIPCO.2019.8902998","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902998","url":null,"abstract":"In this paper, a meter classification scheme is proposed using musical texture features (MTF) with a deep neural network (DNN) and a hybrid Gaussian mixture model-deep neural network(GMM-DNN) framework. The performance of the proposed system is evaluated using a newly created poetic corpus in Malayalam, one of the prominent languages in India and compared the performance with support vector machine (SVM) classifier. Initially, a baseline-mel-frequency cepstral coefficient (MFCC) based experiment is performed. Later, the MTF are fused with MFCC. Whilst the MFCC system reports an overall accuracy of 78.33%, the fused system reports an accuracy of 86.66% in the hybrid GMM-DNN framework. The overall accuracies obtained for DNN and GMM-DNN are 85.83%, and 86.66%, respectively. The architectural choice of DNN based classifier using GMM derived features on the feature fusion paradigm showed improvement in the performance. The proposed system shows the promise of deep learning methodologies and the effectiveness of MTF in recognizing meters from recited poems.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404766","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: 8
Multi-point Connectivity for Reliable mmWave 可靠毫米波的多点连接
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902984
Dileep Kumar, Jarkko Kaleva, Antti Tölli
{"title":"Multi-point Connectivity for Reliable mmWave","authors":"Dileep Kumar, Jarkko Kaleva, Antti Tölli","doi":"10.23919/EUSIPCO.2019.8902984","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902984","url":null,"abstract":"The fundamental challenge for mmWave communication is the sensitivity of mmWave signals to the blockage, which gives rise to unstable connectivity and impacts the reliability of a system. In this paper, we explore the viability of using coordinated multi-point connectivity, which facilitates multi-user precoding across spatially distributed transmitters, to ensure reliable connectivity even if one or more dominant links are under blockage. We provide successive convex approximation based algorithms for weighted sum-rate maximization and minimum user-rate maximization problems while considering the effects of random link blockage. For the downlink precoder design, a conservative estimate of the available rate per user is computed over all subset combinations of potentially blocked links. The trade-off between achievable sum-rate and reliable connectivity is illustrated via numerical examples. In the presence of random link blockage, the outage performance and effective throughput of the proposed transmit precoder design significantly outperforms several baseline scenarios, and results in more stable connectivity for highly reliable communication.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127996810","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: 6
Virtual Adversarial Training for Semi-supervised Verification Tasks 半监督验证任务的虚拟对抗训练
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902573
V. Noroozi, S. Bahaadini, Lei Zheng, Sihong Xie, Philip S. Yu
{"title":"Virtual Adversarial Training for Semi-supervised Verification Tasks","authors":"V. Noroozi, S. Bahaadini, Lei Zheng, Sihong Xie, Philip S. Yu","doi":"10.23919/EUSIPCO.2019.8902573","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902573","url":null,"abstract":"The goal in verification tasks is to determine the similarity of two samples or verifies if they belong to the same category or not. In this paper, we propose a semi-supervised embedding technique for verification tasks using deep neural networks. The proposed model exploits the unlabeled data by making the model robust to the perturbation of the input with virtual adversarial training. It increases the generalization of the embedding function and prevents overfitting which are crucial in verification tasks. The proposed algorithm, named VerVAT, is evaluated on several verification tasks and compared with state-of-the-art algorithms. Experiments show the effectiveness of VerVAT especially in cases where limited labeled data is available.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122245586","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
Free Registration Based Shape Prior for Active Contours 基于自由注册的活动轮廓形状先验
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902638
Ines Sakly, M. Mezghich, S. M'hiri, F. Ghorbel
{"title":"Free Registration Based Shape Prior for Active Contours","authors":"Ines Sakly, M. Mezghich, S. M'hiri, F. Ghorbel","doi":"10.23919/EUSIPCO.2019.8902638","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902638","url":null,"abstract":"A novel method of active contours with shape prior knowledge is presented in this research in order to improve its robustness for partially occluded objects. Our prior is based on a free-registration shape template estimation by using a complete and stable set of invariant descriptors. The prior template is then incorporated into the level set model, using a stopping function that updates the evolving curve only in the region of variability between the active contour and the researched template so that the computation time is reduced considerably. The proposed framework is demonstrated using both simulated and real data involving the segmentation of occluded and noisy images. Results show better robustness and stability compared to the well-known methods using statistics.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122253221","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
Spectral Coexistence of 5G Networks and Satellite Communication Systems Enabled by Coordinated Caching and QoS-Aware Resource Allocation 协同缓存和qos感知资源分配实现5G网络与卫星通信系统频谱共存
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8903063
K. Ntougias, C. Papadias, G. Papageorgiou, G. Haßlinger
{"title":"Spectral Coexistence of 5G Networks and Satellite Communication Systems Enabled by Coordinated Caching and QoS-Aware Resource Allocation","authors":"K. Ntougias, C. Papadias, G. Papageorgiou, G. Haßlinger","doi":"10.23919/EUSIPCO.2019.8903063","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8903063","url":null,"abstract":"The combination of underlay spectrum sharing and coordinated multi-point technologies promises substantial spectral efficiency (SE) gains for 5G cellular networks. In this work, we present a family of simple cooperative mobile edge caching strategies that create joint transmission (JT) opportunities and make use of the non-computational-demanding score-gated least recently used (SG-LRU) caching scheme to achieve high cache hit rate, thus increasing the sum-SE and reducing both the backhaul traffic and the content access latency. In addition, we derive a low-complexity coordinated quality-of-service (QoS) aware resource allocation scheme that maximizes the sum-SE of coordinated beamforming (CBF) under given transmission power per base station, inter-system interference power, and per-user QoS constraints as well as simple alternatives for both CBF and JT. We consider a use case where a cellular network coexists with a fixed satellite service earth station in the 3.7-4.2 GHz C-band. Numerical simulations illustrate the performance gains of the proposed coordinated caching and resource allocation strategies and shed light on the impact of various parameters on their efficiency.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122273022","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
Variational Inference for DOA Estimation in Reverberant Conditions 混响条件下DOA估计的变分推理
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902672
Yosef Soussana, S. Gannot
{"title":"Variational Inference for DOA Estimation in Reverberant Conditions","authors":"Yosef Soussana, S. Gannot","doi":"10.23919/EUSIPCO.2019.8902672","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902672","url":null,"abstract":"A concurrent speaker direction of arrival (DOA) estimator in a reverberant environment is presented. The reverberation phenomenon, if not properly addressed, is known to degrade the performance of DOA estimators. In this paper, we investigate a variational Bayesian (VB) inference framework for clustering time-frequency (TF) bins to candidate angles. The received microphone signals are modelled as a sum of anechoic speech and the reverberation component. Our model relies on Gaussian prior for the speech signal and Gamma prior for the speech precision. The noise covariance matrix is modelled by a time-invariant full-rank coherence matrix multiplied by time-varying gain with Gamma prior as well. The benefits of the presented model are verified in a simulation study using measured room impulse responses.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127927936","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
State Space Models with Dynamical and Sparse Variances, and Inference by EM Message Passing 具有动态和稀疏方差的状态空间模型及EM消息传递推理
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902815
Federico Wadehn, Thilo Weber, Hans-Andrea Loeliger
{"title":"State Space Models with Dynamical and Sparse Variances, and Inference by EM Message Passing","authors":"Federico Wadehn, Thilo Weber, Hans-Andrea Loeliger","doi":"10.23919/EUSIPCO.2019.8902815","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902815","url":null,"abstract":"Sparse Bayesian learning (SBL) is a probabilistic approach to estimation problems based on representing sparsitypromoting priors by Normals with Unknown Variances. This representation blends well with linear Gaussian state space models (SSMs). However, in classical SBL the unknown variances are a priori independent, which is not suited for modeling group sparse signals, or signals whose variances have structure. To model signals with, e.g., exponentially decaying or piecewiseconstant (in particular block-sparse) variances, we propose SSMs with dynamical and sparse variances (SSM-DSV). These are two-layer SSMs, where the bottom layer models physical signals, and the top layer models dynamical variances that are subject to abrupt changes. Inference and learning in these hierarchical models is performed with a message passing version of the expectation maximization (EM) algorithm, which is a special instance of the more general class of variational message passing algorithms. We validated the proposed model and estimation algorithm with two applications, using both simulated and real data. First, we implemented a block-outlier insensitive Kalman smoother by modeling the disturbance process with a SSM-DSV. Second, we used SSM-DSV to model the oculomotor system and employed EM-message passing for estimating neural controller signals from eye position data.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132046176","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
2-D non-separable integer implementation of paraunitary filter bank based on the quaternionic multiplier block-lifting structure 基于四元数乘法器块提升结构的准酉滤波器组二维不可分整数实现
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902489
Eugene V. Rybenkov, N. Petrovsky
{"title":"2-D non-separable integer implementation of paraunitary filter bank based on the quaternionic multiplier block-lifting structure","authors":"Eugene V. Rybenkov, N. Petrovsky","doi":"10.23919/EUSIPCO.2019.8902489","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902489","url":null,"abstract":"This paper presents a novel technique of factorization for 2-D non-separable quaternionic paraunitary filter banks (2-D NS Q-PUFB) based on the integer-to-integer invertible quaternionic multipliers. Two-dimensional factorization structures called ”16in-16out” and ”64in-64out” respectively for 4-channel and 8-channel Q-PUFB based on the proposed technique are shown. Comparison of the energy compaction level between the 2-D separable Q-PUFB based on the 1D Q-PUFB $(8 times 24 Q$-PUFB one-dimensional coding gain is $CG_{1D},= 9.38$ dB) and 2D non-separable Q-PUFB $(8 times 242mathrm{D}$-NS Q-PUFB, multidimensional coding gain is $CG_{MD},= 17.15$ dB) for the Barbara image shows that the 2-D non-separable Q-PUFB generates a higher percentage of small-value coefficients, hence creates a significant increase in the number of zero trees. This holds the key to our coder’s superior performance.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132245332","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
Convex Optimization Based Sparse Learning Over Networks 基于网络稀疏学习的凸优化
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902625
Ahmed Zaki, S. Chatterjee
{"title":"Convex Optimization Based Sparse Learning Over Networks","authors":"Ahmed Zaki, S. Chatterjee","doi":"10.23919/EUSIPCO.2019.8902625","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902625","url":null,"abstract":"In this paper, we consider the problem of estimating a sparse signal over a network. The main interest is to save communication resource for information exchange over the network and hence reduce processing time. With this aim, we develop a distributed learning algorithm where each node of the network uses a locally optimized convex optimization based algorithm. The nodes iteratively exchange their signal estimates over the network to refine the local estimates. The convex cost is constructed to promote sparsity as well as to include influence of estimates from the neighboring nodes. We provide a restricted isometry property (RIP)-based theoretical guarantee on the estimation quality of the proposed algorithm. Using simulations, we show that the algorithm provides competitive performance vis-a-vis a globally optimum distributed LASSO algorithm, both in convergence speed and estimation error.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130004703","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书