检索结果-内蒙古大学图书馆

18th International workshop on Acoustic signal Enhancement (IWAENC)

作者： Mannanova, Alina Tesch, Kristina Lemercier, Jean-Marie Gerkmann, Timo Univ Hamburg Signal Proc SP Hamburg Germany

ISBN: (纸本)9798350361865;9798350361858

Nowadays deep neural networks are a common choice for multichannel speech processing as they may outperform the traditional concatenation of a linear beamformer and a post-filter in challenging scenarios. To obtain strong spatial selectivity, these approaches are typically trained for a specific microphone array configuration. However, it was recently shown that such models are sensitive even to small perturbations in the microphones placements. In this paper we propose a method for handling variable array configurations based on model-agnostic meta-learning. We demonstrate that the proposed approach increases robustness to changes in the array configurations, i.e., mismatched conditions, while maintaining the same performance as the array-specific model on matched conditions.

关键词： Multi-channel speech enhancement array geometry-robust processing meta-learning Reptile fast adaptation few-shot

来源：评论

学校读者我要写书评

暂无评论

GSP based subsampling of IoT sensor networks 12

GSP based subsampling of IoT sensor networks

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Sabatini, Anna Vollero, Luca Univ Campus Biomed Roma Comp Syst & Bioinformat Lab Rome Italy

ISBN: (纸本)9781665406338

Graph signal processing (GSP) can be applied as a modeling tool to study and optimally configure IoT sensor networks. Such networks are often characterized by stringent power requirements and a high probability of sensor fault. In this scenario, understanding and governing the response on a sample of the sensors is critical to maximizing network lifetime and spreading out maintenance time. The aim of this paper is to verify the ability of the GSP to model and provide answers to these goals.

关键词： GSP IoT sampling and interpolation

来源：评论

学校读者我要写书评

暂无评论

Efficient Parkinson's disease classification from dynamic foot pressure data: A combined approach of clustering and feature selection

引用

BIOMEDICAL signal processing AND CONTROL 2025年 105卷

作者： Jiao, Shupei Huo, Hua Liu, Wei Zhao, Changwei Ma, Lan Wang, Jinxuan Li, Dongfang Henan Univ Sci & Technol Luoyang Peoples R China

In this paper, we focus on diagnosing Parkinson's patients using dynamic plantar pressure data collected via sensor devices. We employ data preprocessing methods, including clustering, dimensionality reduction, and multichannel feature screening. Our approach proposes a comprehensive set of data processing techniques, including data cleaning, constrained clustering, and dimensionality reduction, to convert sensor data into a multichannel multivariate time series suitable for neural network input. Unlike current methods that use all features for automatic filtering by the network - adding complexity and resource burden - we introduce a data analysis method combining statistical features and Recursive Feature Elimination. This reduces the number of channels and simplifies the model. We used a simplified 1D-convnet model, achieving a 10-fold accuracy of 91.09%, segmentation accuracy of 95.54%, individual accuracy of 97.33%, weighted precision of 95.71%, weighted recall of 95.56%, and a weighted F1-score of 95.61%. Our results validate the effectiveness of our data acquisition and feature screening methods, and notably, our processing speed is nearly three times faster.

关键词： Pressure array sensor Dynamic plantar pressure Parkinson's disease Recursive feature elimination Statistical feature analysis Gait Recognition

来源：评论

学校读者我要写书评

暂无评论

Development of multichannel Quartz Tuning Fork sensor array System for the Detection of Volatile Organic Compounds

引用

IEEE sensorS JOURNAL 2024年第9期24卷 15082-15090页

作者： Vishwakarma, Satyendra Ray, Bishakha Krishna, Aarathi G. Datar, Suwarna Deemed Univ Def Inst Adv Technol Dept Appl Phys Pune 411025 Maharashtra India

The rapid advancement in electronic technology has ushered in a new era for sensor array systems, particularly within the realm of electronic olfaction, often called "electronic nose." These sophisticated devices harness various sensors, each with unique responses to diverse gases, and amalgamate their data into distinctive gas "finger-prints" with the help of Artificial Intelligence (AI) and machine learning (ML) algorithms. In the present research we have developed a portable sensor array system endowed with heightened sensitivity and selectivity, ideally suited for field applications in volatile organic compound (VOC) detection. This system comprises three core components: the sensor unit, the sensor support circuitry, and the processing unit. Our approach incorporates polymer modified Quartz Tuning Forks (QTFs) as sensors. Two systems were developed: the first using a microcontroller-based system having 4 sensors in the array and the second employing a Raspberry Pi (RPi)-based system incorporating 12 sensors. Various tests were conducted to evaluate these systems and compared with the NI DAQ system used for data acquisition (DAQ), which has an excellent signal-to-noise ratio (SNR). The SNR was compared among these three systems, taking into account the number of input channels. We conducted tests using nine different gases with a maximum of 8 different sensors in the array: acetone, ethanol, acetaldehyde, ammonia, octane, decane, isoprene, methanol, and isopropanol, to produce fingerprint output for each which will be used in ML for classification.

关键词： sensors sensor arrays sensor systems Pins Oscillators Microcontrollers signal to noise ratio Electronic nose microcontroller-based system QTF Pi HAT circuit quartz tuning fork (QTF) sensor Raspberry Pi (RPi)-based system sensor array signal-to-noise ratio (SNR) volatile organic compounds (VOCs)

来源：评论

学校读者我要写书评

暂无评论

Sparse array Beamformer Design via ADMM 12

Sparse Array Beamformer Design via ADMM

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Huang, Huiping So, Hing Cheung Zoubir, Abdelhak M. Tech Univ Darmstadt Darmstadt Germany City Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781665406338

In this paper, we devise a sparse array design algorithm for adaptive beamforming. Our strategy is based on finding a sparse beamformer weight to maximize the output signal-tointerference-plus-noise ratio (SINR). The proposed method uses the alternating direction method of multipliers (ADMM), and admits closed-form solutions at each ADMM iteration. Numerical results exhibit excellent performance of the proposed method, which is comparable to that of the exhaustive search approach.

关键词： Adaptive beamforming ADMM sparse array design output SINR

来源：评论

学校读者我要写书评

暂无评论

Passive Angle-Doppler Profile Estimation for Narrowband Digitally Modulated Wireless signals 12

Passive Angle-Doppler Profile Estimation for Narrowband Digi...

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Argyriou, Antonios Univ Thessaly Dept Elect & Comp Engn Volos Greece

ISBN: (纸本)9781665406338

In this paper, we improve estimation of the Doppler shift present in signals that originate from multiple wireless digital communication transmitters. We deploy a uniform linear array (ULA) that overhears the frequency band of interest, hence an unauthorized wireless receiver (URx), and propose an algorithm for extracting the symbol duration from the unknown modulated data. The baseband wireless modulated signal is stripped from its data-induced phase shifts, allowing us to calculate high quality estimates of the periodogram, the spectrogram, and the angle-Doppler profile. Performance results show that high quality results without artifacts from digital modulation can be obtained.

关键词： Wireless communication Wireless sensor networks Transmitters Digital modulation Estimation Symbols signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Sparse signal Recovery Using a Binary Program 12

Sparse Signal Recovery Using a Binary Program

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Rahman, Muhammed Tahsin Valaee, Shahrokh Univ Toronto Elect & Comp Engn Toronto ON Canada

ISBN: (纸本)9781665406338

Sparsity based signal recovery has seen great success in solving underdetermined systems of equations. This success is due, in large part, to a relaxation: the l0-norm is replaced by the l1-norm, which results in a convex problem. However, such a relaxation may lead to a suboptimal solution, one that may even be asymptotically biased. We propose formulating sparse signal recovery as a binary program, and we derive the conditions under which such a formulation perfectly recovers the signal support. This derivation equips us with a constraint on the dictionary's spectrum. However, designing such a dictionary is a combinatorial problem, so we suggest a heuristic which can be readily satisfied using the alternating projections algorithm. Applied to angle of arrival (AoA) estimation using a sensor array, we show how this paradigm outperforms both the basis pursuit l1-norm relaxation and the Matrix Pencil method.

关键词： Binary program sparsity compressed sensing angle of arrival estimation antenna array

来源：评论

学校读者我要写书评

暂无评论

Non-Coherent Source Localization with Distributed sensor array Networks 12

Non-Coherent Source Localization with Distributed Sensor Arr...

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Wan, Zhengyu Liu, Wei Willett, Peter Univ Sheffield Dept Elect & Elect Engn Sheffield S Yorkshire England Univ Connecticut Dept Elect & Comp Engn Storrs CT USA

ISBN: (纸本)9781665406338

The non-coherent source localization problem based on distributed sensor arrays can be formulated into a group sparsity based phase retrieval problem where only the magnitude (absolute value) of the received signals is available. Under such a framework, a two-dimensional localization method is proposed. Unlike traditional source localization methods, random phase errors at sensors of the distributed array will not affect estimation results by the proposed method. Simulation results indicate that the proposed non-coherent source localization method outperforms the traditional one in the presence of large phase errors, while still maintains an acceptable accuracy in the absence of phase errors.

关键词： Target localization distributed sensor array magnitude-only measurements group sparsity non-coherent detection

来源：评论

学校读者我要写书评

暂无评论

FLEXIBLE multichannel SPEECH ENHANCEMENT FOR NOISE-ROBUST FRONTEND

FLEXIBLE MULTICHANNEL SPEECH ENHANCEMENT FOR NOISE-ROBUST FR...

引用

IEEE workshop on Applications of signal processing to Audio and Acoustics (WASPAA)

作者： Jukic, Ante Balam, Jagadeesh Ginsburg, Boris NVIDIA Santa Clara CA 95051 USA

ISBN: (纸本)9798350323726

This paper proposes a flexible multichannel speech enhancement system with the main goal of improving robustness of automatic speech recognition (ASR) in noisy conditions. The proposed system combines a flexible neural mask estimator applicable to different channel counts and configurations and a multichannel filter with automatic reference selection. A transform-attend-concatenate layer is proposed to handle cross-channel information in the mask estimator, which is shown to be effective for arbitrary microphone configurations. The presented evaluation demonstrates the effectiveness of the flexible system for several seen and unseen compact array geometries, matching the performance of fixed configuration-specific systems. Furthermore, a significantly improved ASR performance is observed for configurations with randomly-placed microphones.

关键词： multichannel speech enhancement array processing mask estimator mask-based neural beamformer

来源：评论

学校读者我要写书评

暂无评论

Decentralized Online Direction-of-Arrival Estimation and Tracking 12

Decentralized Online Direction-of-Arrival Estimation and Tra...

引用

IEEE 12th sensor array and multichannel signal processing workshop (SAM)

作者： Fan, Yufan Ardic, Cemil Emre Minh Trinh-Hoang Pesavento, Marius Tech Univ Darmstadt Commun Syst Grp Darmstadt Germany

ISBN: (纸本)9781665406338

The problem of the decentralized Direction-ofArrival (DoA) estimation and tracking is addressed, where the sample covariance matrix is represented as a recursive update of rank-one components. Due to the fact that the conventional decentralized power method is a batch approach and involves high communication costs, we propose a distributed DoA estimation method combining the decentralized online eigenvalue decomposition and the ESPRIT algorithm. The Push-Sum protocol is applied to realize the local interactions among neighboring subarrays. The simulation results show that the Root Mean Square Error (RMSE) performance of our distributed algorithm surpasses that of the power method based d-ESPRIT algorithm in the DoA estimation with lower total communication cost, and that of the decentralized Normalized Oja (d-NOja) method in DoA tracking applications with faster convergence speed.

关键词： Direction-of-arrival estimation Costs Protocols Simulation signal processing algorithms Estimation Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：