检索结果-内蒙古大学图书馆

Telecommunications, Electronics and Informatics (ICTEI), International Conference on

作者： Wenjia Ma Sichuan University Jinjiang College MeiShan Sichuan China

ISBN: (数字)9798350342963

ISBN: (纸本)9798350342970

In English learning, good pronunciation and intonation are not only the basis for cultivating good listening and speaking abilities, but also have a direct impact on learners’ reading and writing abilities. Traditional English pronunciation teaching methods almost all emphasize theoretical knowledge, while students have fewer practical opportunities to practice, which leads to students’ lack of interest in English pronunciation learning. This paper presents a speech signal recognition method based on ACA, which can help English pronunciation teaching and provide support for intelligent English teaching. The results show that the speech recognition accuracy of this algorithm can reach 98.76%, which is 2.56% higher than that of back propagation neural network (BPNN) and 4.22% higher than that of genetic algorithm (GA). As an auxiliary teaching method, virtual teaching platform is applied to English teaching, which reflects the change of modern teaching philosophy and teaching mode, effectively creates a real English language environment, provides a platform for mutual communication and learning, effectively makes up for the deficiency of traditional English classroom teaching, stimulates learning motivation, stimulates thinking, improves English ability and classroom teaching efficiency.

关键词： Training Accuracy Education Software algorithms Neural networks signal processing algorithms Speech recognition

来源：评论

学校读者我要写书评

暂无评论

High Performance VLSI Architecture of FIR Filter for Seismic signal processing

High Performance VLSI Architecture of FIR Filter for Seismic...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： S. Karunakaran Electronics and communication Engineering Vardhaman college of Engineering Hyderabad India

As a primary requirement, FIR filters(Finite Impulse response)used in real-time seismic alert systems are required to be low complexity, fast, and re-configurable. The CSE technique is commonly used to abate hardware complexity in digital FIR filters by decreasing logic operators and logic depths. In this paper, we present a new LO and LD minimization matrix grouped CSE algorithm that outperforms existing CSE algorithms. Additionally, the suggested design With low complexity and reduced truncation error, we developed a new biased-based rounding method that includes half units, as well as to lessen critical-path delay, use the cut-set retiming technique. This paper presents two hardware-efficient FIR filter topologies (I and II) that employ cut-set retiming, HUB rounding, and the canonical signed digit based MCSE algorithm. Additionally, architecture II implements a reconfigurable FIR filter in a hardware- efficient manner. FPGA and ASIC platforms are used to implement the architectures on the hardware side. Comparing the hardware implementation of proposed architectures, we mooted decrease of LOs, CPD, effective latency, area-delay product (ADP), and power- delay product using cutting-edge CSE- based architectures by a factor of 2 more than 35%, 47 %, 36 %, 34 %, and 29 %,*** comparison to the *** reconfigurable architecture II has an approximately 46 %, 10 %, and 11 % less in PDP, ADP and CPD.

关键词： Finite impulse response filters signal processing algorithms Very large scale integration signal processing Hardware Real-time systems Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 3693-3708页

作者： Gao, Zhan Koppel, Alec Ribeiro, Alejandro Univ Penn Dept Elect & Syst Engn Philadelphia PA 19104 USA Amazon Supply Chain Optimizat Technol Bellevue WA 98004 USA

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, which forms the bedrock of modern machine learning. In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster to a limiting error. To do so, rather than fixing the mini-batch and the step-size at the outset, we propose a strategy to allow parameters evolving adaptively. Specifically, the batch-size is set to be a piecewise-constant increasing sequence where the increase occurs when a suitable error criterion is satisfied. Moreover, the step-size is selected as that which yields the fastest convergence. The overall algorithm, two scale adaptive (TSA) scheme, is developed for both convex and non-convex problems. It inherits the exact convergence and more importantly, the optimal error decreasing rate and an overall computation reduction are achieved. Furthermore, we extended the TSA method to the generalized adaptive batching framework, which is a generic methodology modular to any stochastic algorithms pursuing a trade-off between convergence rates and stochastic variance. We evaluate the TSA method on the image classification problem on MNIST and CIFAR-10 datasets compared with standard SGD methods and existing adaptive batch-size methods, to corroborate theoretical findings.

关键词： Convergence Stochastic processes Optimization Training Statistics Sociology signal processing algorithms Stochastic optimization stochastic gradient descent adaptive batch-size optimal step-size

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Fractional Learning algorithms

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 5164-5177页

作者： Wahab, Abdul Khan, Shujaat Naseem, Imran Ye, Jong Chul Nazarbayev Univ Sch Sci & Humanities Dept Math Nur Sultan 010000 Kazakhstan Korea Adv Inst Sci & Technol Dept Bio & Brain Engn Daejeon 34141 South Korea Univ Western Australia Sch Elect Elect & Comp Engn Crawley Western 6009 Australia PM Karachi Inst Econ & Technol Coll Engn Korangi Creek 75190 Pakistan Korea Adv Inst Sci & Technol Kim Jaechul Grad Sch AI Daejeon 34141 South Korea

Fractional learning algorithms are trending in signal processing and adaptive filtering recently. However, it is unclear whether their proclaimed superiority over conventional algorithms is well-grounded or is a myth as their performance has never been extensively analyzed. In this article, a rigorous analysis of fractional variants of the least mean squares and steepest descent algorithms is performed. Some critical schematic kinks in fractional learning algorithms are identified. Their origins and consequences on the performance of the learning algorithms are discussed and swift ready-witted remedies are proposed. Apposite numerical experiments are conducted to discuss the convergence and efficiency of the fractional learning algorithms in stochastic environments. The analysis substantiates that the fractional learning algorithms have no advantage over the conventional least mean squares algorithm.

关键词： signal processing algorithms Convergence Prediction algorithms Performance analysis Costs Australia Iterative methods Least mean squares fractional least mean squares fractional derivatives gradient descent

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Ensemble Classification With Sequential and Networked Data

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2022年第10期34卷 5009-5022页

作者： Traganitis, Panagiotis A. Giannakis, Georgios B. Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA Univ Minnesota Digital Technol Ctr Minneapolis MN 55455 USA

Ensemble learning, the machine learning paradigm where multiple models are combined, has exhibited promising perfomance in a variety of tasks. The present work focuses on unsupervised ensemble classification. The term unsupervised refers to the ensemble combiner who has no knowledge of the ground-truth labels that each classifier has been trained on. While most prior works on unsupervised ensemble classification are designed for independent and identically distributed (i.i.d.) data, the present work introduces an unsupervised scheme for learning from ensembles of classifiers in the presence of data dependencies. Two types of data dependencies are considered: sequential data and networked data whose dependencies are captured by a graph. For both, novel moment matching and Expectation-Maximization algorithms are developed. Performance of these algorithms is evaluated on synthetic and real datasets, which indicate that knowledge of data dependencies in the meta-learner is beneficial for the unsupervised ensemble classification task.

关键词： Data models Task analysis signal processing algorithms Inference algorithms Tensors Distributed databases Tagging Ensemble learning unsupervised sequential classification crowdsourcing dependent data

来源：评论

学校读者我要写书评

暂无评论

FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 6080-6095页

作者： Gang, Arpita Bajwa, Waheed U. Rutgers Univ New Brunswick Dept Elect & Comp Engn New Brunswick NJ 08901 USA

Principal Component Analysis (PCA) is a fundamental data preprocessing tool in the world of machine learning. While PCA is often thought of as a dimensionality reduction method, the purpose of PCA is actually two-fold: dimension reduction and uncorrelated feature learning. Furthermore, the enormity of the dimensions and sample size in the modern day datasets have rendered the centralized PCA solutions unusable. In that vein, this paper reconsiders the problem of PCA when data samples are distributed across nodes in an arbitrarily connected network. While a few solutions for distributed PCA exist, those either overlook the uncorrelated feature learning aspect of the PCA, tend to have high communication overhead that makes them inefficient and/or lack 'exact' or 'global' convergence guarantees. To overcome these aforementioned issues, this paper proposes a distributed PCA algorithm termed FAST-PCA (Fast and exAct diSTributed PCA). The proposed algorithm is efficient in terms of communication and is proven to converge linearly and exactly to the principal components, leading to dimension reduction as well as uncorrelated features. The claims are further supported by experimental results.

关键词： Dimensionality reduction Representation learning Veins Data preprocessing signal processing algorithms Distributed databases Estimation Dimension reduction distributed learning exact convergence Krasulina's method principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A GNN-Based Supervised Learning Framework for Resource Allocation in Wireless IoT Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第3期9卷 1712-1724页

作者： Chen, Tianrui Zhang, Xinruo You, Minglei Zheng, Gan Lambotharan, Sangarapillai Loughborough Univ Wolfson Sch Mech Elect & Mfg Engn Signal Proc & Networks Res Grp Loughborough LE11 3TU Leics England Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ Essex England

The Internet of Things (IoT) allows physical devices to be connected over the wireless networks. Although device-to-device (D2D) communication has emerged as a promising technology for IoT, the conventional solutions for D2D resource allocation are usually computationally complex and time consuming. The high complexity poses a significant challenge to the practical implementation of wireless IoT networks. A graph neural network (GNN)-based framework is proposed to address this challenge in a supervised manner. Specifically, the wireless network is modeled as a directed graph, where the desirable communication links are modeled as nodes and the harmful interference links are modeled as edges. The effectiveness of the proposed framework is verified via two case studies, namely the link scheduling in D2D networks and the joint channel and power allocation in D2D underlaid cellular networks. Simulation results demonstrate that the proposed framework outperforms the benchmark schemes in terms of the average sum rate and the sample efficiency. In addition, the proposed GNN approach shows potential generalizability to different system settings and robustness to the corrupted input features. It also accelerates the D2D resource optimization by reducing the execution time to only a few milliseconds.

关键词： Resource management Device-to-device communication Wireless networks Training Optimization Internet of Things signal processing algorithms Device to device (D2D) graph neural network (GNN) Internet of Things (IoT) link scheduling resource allocation

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning for MIMO Relay Networks

引用

IEEE JOURNAL OF SELECTED TOPICS IN signal processing 2022年第3期16卷 343-357页

作者： Wang, Rui Jiang, Yi Zhang, Wei Fudan Univ Sch Informat Sci & Technol Dept Commun Sci & Engn Key Lab Informat Sci Electromagnet Waves MoE Shanghai 200433 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

This paper studies a multi-antenna multi-user and multi-relay network, where the radio frequency (RF) power amplifiers (PA) of the nodes are subject to instantaneous power constraints. To optimize the nonlinear transceivers of the distributed nodes, we introduce a novel perspective of relating a relay network to an artificial neural network (ANN). With this perspective, we propose a distributed learning-based relay beamforming (DLRB) scheme. Based on a set of pilot sequences, the DLRB scheme can optimize the transceivers to minimize the mean squared error (MSE) of the data stream in a distributed manner. It can effectively coordinate the distributed relay nodes to form a virtual array to suppress interferences, even assuming neither the channel state information (CSI) nor information exchange between the relay nodes or between the users. We also present a frame design to support the DRLB so that it can adapt well with time-varying channels. Extensive simulations verify the effectiveness of the proposed scheme.

关键词： Relay networks (telecommunication) Artificial neural networks Interference Transceivers signal to noise ratio Array signal processing signal processing algorithms Artificial neural network distributed learning interference suppression instantaneous power constraints relay network

来源：评论

学校读者我要写书评

暂无评论

Nondominated-Solution-Based Multi-Objective Greedy Sensor Selection for Optimal Design of Experiments

引用

IEEE TRANSACTIONS ON signal processing 2022年 70卷 5694-5707页

作者： Nakai, Kumi Sasaki, Yasuo Nagata, Takayuki Yamada, Keigo Saito, Yuji Nonomura, Taku Natl Inst Adv Ind Sci & Technol Tsukuba 3058564 Japan Tohoku Univ Sendai 9808579 Japan Tohoku Univ Japan Soc Promot Sci Sendai 9808579 Japan Tohoku Univ Dept Aerosp Engn Sendai 9808579 Japan

In this study, a nondominated-solution-based multi-objective greedy method is proposed and applied to a sensor selection problem based on the multiple indices of the optimal design of experiments. The proposed method simultaneously considers multiple set functions and applies the idea of Pareto ranking for the selection of sets. Specifically, a new index is iteratively added to the nondominated solutions of sets, and the multi-objective functions are evaluated for new sets. The nondominated solutions are selected from the examined solutions, and the next sets are then considered. With this procedure, the multi-objective optimization of multiple set functions can be conducted with reasonable computational costs. This paper defines a new class of greedy algorithms which includes the proposed nondominated-solution-based multi-objective greedy algorithm and the group greedy algorithm, and the characteristics of those algorithms are theoretically discussed. Then, the proposed method is applied to the sensor selection problem and its performance is evaluated. The results of the test case show that the proposed method not only gives the Pareto-optimal front of the multi-objective optimization problem but also produces sets of sensors in terms of D-, A-, and E-optimality, that are superior to the sets selected by pure greedy methods that consider only a single objective function.

关键词： Indexes Optimization Linear programming signal processing algorithms Greedy algorithms Search problems Relaxation methods Greedy algorithm multi-objective optimization nondominated solution pareto front optimal experimental design data-driven sensor selection

来源：评论

学校读者我要写书评

暂无评论

A Feature Extraction Algorithm for Rolling Bearing Faults and Its Application

引用

IEEE ACCESS 2022年 10卷 83498-83506页

作者： Zhang, Zhen Liu, Baoguo Du, Wenliao Feng, Wei Henan Univ Technol Sch Mech & Elect Engn Zhengzhou 450001 Peoples R China Zhengzhou Univ Light Ind Sch Mech & Elect Engn Zhengzhou 450002 Peoples R China

Focusing on the difficulty of completely extracting the surface damage caused by rolling bearing lubrication failure, an algorithm for extracting bearing lubrication fault is proposed, which is based on periodic optimum singular value decomposition (O-SVD) cascaded fast spectral correlation (FSC). Initially, conventional T-SVD with energy leakage defects was modified into O-SVD, which was used as the preprocessing unit for signal processing. Then, FSC calculation was performed on the reconstructed signals, eventually obtaining enhanced envelope spectrum with obvious features that could well preserve local details. Simulation and experimental results show that the proposed algorithm allows rather complete extraction of slight fault features resulting from poor lubrication under small sampling length and low signal-to-noise ratio (SNR), and has good applicability in extracting compound and composite fault features. The extracted signals have advantages over existing algorithms regarding fault resolution and local details preservation.

关键词： Power capacitors Lubrication Feature extraction signal resolution signal processing algorithms Spectral estimation Reconstruction algorithms Rolling bearing singular value decomposition fast spectral correlation slight fault feature extraction underlubrication fault

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：