2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)最新文献_第8页

Policy Based Synthesis: Data Generation and Augmentation Methods For RF Machine Learning 基于策略的综合:射频机器学习的数据生成和增强方法

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969160

Rob Miller, S. Kokalj-Filipovic, Garrett M. Vanhoy, Joshua Morman

{"title":"Policy Based Synthesis: Data Generation and Augmentation Methods For RF Machine Learning","authors":"Rob Miller, S. Kokalj-Filipovic, Garrett M. Vanhoy, Joshua Morman","doi":"10.1109/GlobalSIP45357.2019.8969160","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969160","url":null,"abstract":"The current dataset generation methods for RF Machine Learning (RFML) tasks consist of either completely synthetically generated data or completely raw digitized data from an RF front end. The synthetic datasets are often unrealistic in terms of waveforms or protocols, and the raw captures are typically unlabeled (or often mislabeled), and can skew machine learning algorithms to focus on non-salient features. Further, the associated storage and processing requirements are quite large. In this work, a novel dataset generation and augmentation method called policy-based synthesis is presented that aims to address the short-comings of either approach by combining basic protocol knowledge with simulated channel and device impairments to supplement over-the-air captures made in a controlled environment. This method permits the learning of salient features and regularizes radio and device anomalies that are not of interest. Practical considerations for collecting and processing data for this hybridized approach are also detailed and examples are provided on a dataset that includes protocols commonly used in the 2.4 GHz ISM band such as Bluetooth and Wi-Fi.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126933941","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

A Study of Cross Sectional Stock Returns Using High-Dimensional SUR Model and Many Firm Level Characteristics 基于高维SUR模型和多公司层面特征的横截面股票收益研究

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969409

Qingliang Fan, Yong Han, Xiao-Ping Zhang

引用次数: 0

Multi-scale Generative Adversarial Networks for Speech Enhancement 语音增强的多尺度生成对抗网络

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969193

Yihang Li, Ting Jiang, Shan Qin

{"title":"Multi-scale Generative Adversarial Networks for Speech Enhancement","authors":"Yihang Li, Ting Jiang, Shan Qin","doi":"10.1109/GlobalSIP45357.2019.8969193","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969193","url":null,"abstract":"The generative adversarial networks can be used to recognize and eliminate noise from noisy speech after extensive training. The most representative model is Speech Enhancement Generative Adversarial Network (SEGAN). However, eliminating the noise without distortion is still a challenging task especially in a low SNR environment. To solve such problems, this paper proposes Speech Enhancement Multi-scale Generative Adversarial Networks (SEMGAN), whose generator and discriminator networks are structured on the basis of fully convolutional neural networks (FCNNs). Compared with SEGAN, the generator generates speeches in three different dimensions and makes multiple judgments in the discriminator. In addition, multiple types of noise and signal-noise ratios (SNRs) are used to train our model for improving the generalization capability. In the stage of testing, we further propose pre- SEMGAN, which solve the problem that the last frame of speech data was not processed well. As the experimental results indicated, the architecture (SEMGAN and pre- SEMGAN) proposed gain a superior performance in comparison with the optimally modified log-spectral amplitude estimator (OMLSA) and SEGAN in different noisy conditions. It is worth mentioning that SEMGAN's PESQ and STOI score increase about 7% and 3.6% over SEGAN respectively in the case of 2.5 dB SNR.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127265651","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

Communication without Interception: Defense against Modulation Detection 无拦截通信:防御调制检测

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969541

Muhammad Zaid Hameed, A. György, Deniz Gündüz

引用次数: 21

Adaptation of an EMG-Based Speech Recognizer via Meta-Learning 基于元学习的基于肌电图的语音识别器自适应

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969231

Krsto Prorokovic, Michael Wand, Tanja Schultz, J. Schmidhuber

引用次数: 4

Extended Logarithmic Frequency Domain Rulers for Joint Radar-Communications 联合雷达通信的扩展对数频域标尺

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969147

Alex Byrley, A. Fam

引用次数: 1

Majorization-Minimization Algorithms for Analog Beamforming with Large-Scale Antenna Arrays 大规模天线阵列模拟波束形成的最大化-最小化算法

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969518

A. Arora, C. Tsinos, Bhavani Shankar Mysore R, S. Chatzinotas, B. Ottersten

{"title":"Majorization-Minimization Algorithms for Analog Beamforming with Large-Scale Antenna Arrays","authors":"A. Arora, C. Tsinos, Bhavani Shankar Mysore R, S. Chatzinotas, B. Ottersten","doi":"10.1109/GlobalSIP45357.2019.8969518","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969518","url":null,"abstract":"Beamforming with large-scale antenna arrays (LSAA) is one of the predominant operations in designing wireless communication systems. However, the implementation of a fully digital system significantly increases the number of required radio-frequency (RF) chains, which may be prohibitive. Thus, analog beamforming based on a phase-shifting network driven by a variable gain amplifier (VGA) is a potential alternative technology. In this paper, we cast the beamforming vector design problem as a beampattern matching problem, with an unknown power gain. This is formulated as a unit-modulus leastsquares (ULS) problem where the optimal gain of the VGA is also designed in addition to the beamforming vector. We also consider a scenario where the receivers have the additional processing capability to adjust the phases of the incoming signals to mitigate specular multipath components. We propose efficient majorization-minimization (MM) based algorithms with convergence guarantees to a stationary point for solving both variants of the proposed ULS problem. Numerical results verify the effectiveness of the proposed solution in comparison with the existing state-of-the-art techniques.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116603514","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: 10

Incentivizing Crowdsourced Workers via Truth Detection 通过真相检测激励众包员工

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969240

Chao Huang, Haoran Yu, Jianwei Huang, R. Berry

{"title":"Incentivizing Crowdsourced Workers via Truth Detection","authors":"Chao Huang, Haoran Yu, Jianwei Huang, R. Berry","doi":"10.1109/GlobalSIP45357.2019.8969240","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969240","url":null,"abstract":"Crowdsourcing platforms often want to incentivize workers to finish tasks with high quality and truthfully report their solutions. A high quality solution requires a worker to exert effort; a platform can motivate such effort exertion and truthful reporting by providing a reward. We propose a novel rewarding mechanism based on using a truth detection technology, which can verify the correctness of workers’ responses to questions with an imperfect accuracy (e.g., questions regarding whether the workers exert effort finishing the tasks and whether they truthfully report their solutions). We model the interactions between the platform and workers as a two-stage Stackelberg game. In Stage I, the platform optimizes the reward design associated with truth detection to maximize its payoff. In Stage II, the workers decide their effort levels and reporting strategies to maximize their payoffs (which depend on the output of the truth detection). We analyze the game’s equilibrium and show that as the truth detection accuracy improves, the platform should incentivize more workers to exert effort finishing the tasks and truthfully report their solutions. Moreover, our mechanism performs well even when the detection accuracy is not very high. A 60% accurate detection can yield a platform payoff that is more than 85% of the maximum achieved under perfect (100% accurate) detection.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129570966","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

Energy Efficiency of Full-Duplex Two-Way Channels 全双工双向信道的能源效率

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969307

Wei Guo, Chuan Huang

引用次数: 2

Privacy Preserving Deep Learning with Distributed Encoders 分布式编码器的隐私保护深度学习

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969086

Yitian Zhang, H. Salehinejad, J. Barfett, E. Colak, S. Valaee

引用次数: 5