2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)最新文献

Linear Discriminant Analysis with Bayesian Risk Parameters for Myoelectric Control 基于贝叶斯风险参数的肌电控制线性判别分析

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969237

Evan Campbell, A. Phinyomark, E. Scheme

{"title":"Linear Discriminant Analysis with Bayesian Risk Parameters for Myoelectric Control","authors":"Evan Campbell, A. Phinyomark, E. Scheme","doi":"10.1109/GlobalSIP45357.2019.8969237","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969237","url":null,"abstract":"The linear discriminant analysis (LDA) classifier remains a standard in myoelectric control due to its simplicity, ease of implementation, and robustness. Despite this, challenges associated with the temporal evolution of the myoelectric signal may require flexibility beyond the capabilities of standard LDA. Recently proposed approaches have leveraged more complex systems, such as adaptive window framing or temporal convolutional neural networks to incorporate temporal structure. In this work, we explore the potential of exploiting parameters inherent to the LDA, which is conventionally applied assuming static and equal prior probabilities and uniform cost functions, to improve myoelectric control. First, a cost-modified version of the LDA (cLDA) is introduced to better reflect the comparatively high cost of active errors. Second, an adaptive priors version of the LDA (pLDA) is introduced to reflect the changing prior probabilities of classes in the myoelectric signal time series. Results are compared against the standard LDA classifier using a novel dataset comprised of continuous class transitions. Although no significant differences were observed in total error, the proposed cLDA algorithm yielded significantly lower active error rates than the LDA alone. Furthermore, both the cLDA and pLDA classification schemes produced significantly lower instability than the LDA classifier alone, as measured by spurious changes in the output decision stream. This work lays the groundwork for future research on these flexible classification schemes including context dependent cost arrays, different methods of priors adaptation, and combinations of the proposed cLDA and pLDA frameworks.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"75 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":"115226835","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: 11

Adaptive Feedback Active Noise Control (AFB-ANC) System Equipped with Online Adaptation and Convergence Monitoring of the Cancellation-Path Estimation (CPE) Filter 基于在线自适应和收敛监测的自适应反馈有源噪声控制(AFB-ANC)系统

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969111

M. Akhtar

{"title":"Adaptive Feedback Active Noise Control (AFB-ANC) System Equipped with Online Adaptation and Convergence Monitoring of the Cancellation-Path Estimation (CPE) Filter","authors":"M. Akhtar","doi":"10.1109/GlobalSIP45357.2019.8969111","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969111","url":null,"abstract":"This papers aims to develop an Adaptive Feedback Active Noise Control (AFB-ANC) system comprising two adaptive filters. The first adaptive filter is the same as found in the traditional AFB-ANC systems and is adapted using the classical Filtered-x Least Mean Square (FxLMS) algorithm. The stability of the FxLMS algorithm requires filtering the reference signal via a ‘good’ estimate of the cancellation path (CP) present between the cancellation loudspeaker and the error microphone. Since the CP may be time-varying in the practical situations, the task of the second adaptive filter is to provide estimation of the CP during operation of the AFB-ANC system. The Cancellation-Path Estimation (CPE) filter is excited by a probe signal and is adapted using a delay-based Normalized Least Mean Square (NLMS) algorithm. The proposed system is equipped with a simple strategy to monitor the convergence status of the CPE filter. The developed strategy allows to inject a large (small) probe signal during the transient (steady) state of the AFB-ANC system. Computer simulation are carried out which demonstrate the effective performance of the developed system.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"182 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":"121276993","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

A Robust Algorithm for Multichannel Eeg Compressed Sensing with Mixed Noise 一种鲁棒的混合噪声多通道脑电信号压缩感知算法

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969357

Wei Tao, Chang Li, Juan Cheng

引用次数: 0

Butterfly Classification with Machine Learning Methodologies for an Android Application 蝴蝶分类与机器学习方法的Android应用程序

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969441

Lili Zhu, P. Spachos

引用次数: 4

Generative-Discriminative Crop Type Identification using Satellite Images 利用卫星图像进行作物类型的生成判别

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969151

Nan Qiao, Yi-Jie Zhao, Ruei-Sung Lin, Bo Gong, Zhongxiang Wu, Mei Han, Jiashu Liu

引用次数: 5

Low-correlation Low-cost Stochastic Number Generators for Stochastic Computing 用于随机计算的低相关低成本随机数发生器

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969375

S. A. Salehi

引用次数: 2

Training of Deep Bidirectional Rnns for Hand Motion Filtering Via Multimodal Data Fusion 基于多模态数据融合的手部运动滤波深度双向rnn训练

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969080

Soroosh Shahtalebi, S. F. Atashzar, Rajni V. Patel, Arash Mohammadi

{"title":"Training of Deep Bidirectional Rnns for Hand Motion Filtering Via Multimodal Data Fusion","authors":"Soroosh Shahtalebi, S. F. Atashzar, Rajni V. Patel, Arash Mohammadi","doi":"10.1109/GlobalSIP45357.2019.8969080","DOIUrl":"https://doi.org/10.1109/GlobalSIP45357.2019.8969080","url":null,"abstract":"Pathological Hand Tremor (PHT) is one of the most prevalent symptoms of some neurological movement disorders such as Parkinson’s Disease (PD) and Essential Tremor (ET). Characterization, estimation, and extraction of PHT is a crucial requirement for assistive and robotic rehabilitation technologies that aim to counteract or resist PHT as an input noise to the system. In general, research in the literature on the topic of PHT removal can be categorized into two major categories, namely, classic and data-driven methods. Classic techniques use hand-crafted features and statistical processing pipelines to model and then extract the tremor while data-driven approaches are trained based on a sizable dataset to allow a computational model (such as neural networks) learn how to estimate the PHT. Since the availability of large datasets, especially in PHT estimation field is a bottleneck, in this feasibility study, we investigate the possibility of combining different recording modalities of PHT to generate a neural network for this purpose. This work explores the potential of jointly using accelerometer data and gyroscope recordings to produce a larger dataset for training a relatively complex network, which can potentially be extended for a deeper generalization.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"23 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":"128740917","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

Scene Text Aware Image Retargeting 场景文本感知图像重定位

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969407

D. Patel, S. Raman

引用次数: 0

On Amelioration Of Human Cognitive Biases In Binary Decision Making 二元决策中人类认知偏差的改善

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969431

Baocheng Geng, P. Varshney, M. Rangaswamy

引用次数: 8

A Tensor-Based Spectrum Sensing Technique for MIMO Cognitive Radio Networks 基于张量的MIMO认知无线网络频谱感知技术

2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Pub Date : 2019-11-01 DOI: 10.1109/GlobalSIP45357.2019.8969440

T. Getu, W. Ajib, R. Landry, Georges Kaddoum

引用次数: 0