检索结果-内蒙古大学图书馆

Morse code recognition using learning vector quantization for persons with physical disabilities

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2001年第1期E84A卷 356-362页

作者： Yang, CH Natl Kaohsiung Univ Appl Sci Dept Elect Engn Kaohsiung 807 Taiwan

For physically disabled persons, the conventional computer keyboard is insufficient as a useable communication device. In this paper, Morse code is selected as a communication adaptive device for persons with impaired hand coordination and dexterity. Morse code is composed of a series of dots, dashes, and space intervals. Each element is transmitted by sending a signal for a defined length of time. Maintaining a stable typing rate by the disabled is difficult. To solve this problem, a suitable adaptive automatic recognition method, which combines a variable degree variable step size LMS algorithm with a learning vector quantization method, was applied to this problem in the present study. The method presented here is divided into five stages: space recognition, tone recognition, learning process, adaptive processing, and character recognition. Statistical analyses demonstrated that the proposed method elicited a better recognition rate in comparison to alternative methods in the literature.

关键词： Morse code adaptive signal processing least-mean-square algorithm learning vector quantization

来源：评论

学校读者我要写书评

暂无评论

Adaptive electronic dispersion compensator for chromatic and polarization-mode dispersions in optical communication systems

引用

EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING 2005年第10期2005卷 1584-1592页

作者： Koc, UV Bell Labs Lucent Technol Murray Hill NJ 07974 USA

The widely-used LMS algorithm for coefficient updates in adaptive (feedforward/decision-feedback) equalizers is found to be suboptimal for ASE-dominant systems but various coefficient-dithering approaches suffer from slow adaptation rate without guarantee of convergence. In view of the non-Gaussian nature of optical noise after the square-law optoelectronic conversion, we propose to apply the higher-order least-mean 2Nth-order (LMN) algorithms resulting in OSNR penalty which is 1.5-2 dB less than that of LMS. Furthermore, combined with adjustable slicer threshold control, the proposed equalizer structures are demonstrated through extensive Monte Carlo simulations to achieve better performance.

关键词： electronic PMD compensation adaptive equalization signal processing optical communication least-mean fourth-order algorithm least-mean-square algorithm

来源：评论

学校读者我要写书评

暂无评论

Analysis and Compensation of the Effects of Analog VLSI Arithmetic on the LMS algorithm

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2011年第7期22卷 1046-1060页

作者： Carvajal, Gonzalo Figueroa, Miguel Sbarbaro, Daniel Valenzuela, Waldo Univ Concepcion Dept Elect Engn Concepcion 3349001 Chile Univ Concepcion Ctr Opt & Photon Concepcion 3349001 Chile

Analog very large scale integration implementations of neural networks can compute using a fraction of the size and power required by their digital counterparts. However, intrinsic limitations of analog hardware, such as device mismatch, charge leakage, and noise, reduce the accuracy of analog arithmetic circuits, degrading the performance of large-scale adaptive systems. In this paper, we present a detailed mathematical analysis that relates different parameters of the hardware limitations to specific effects on the convergence properties of linear perceptrons trained with the least-mean-square (LMS) algorithm. Using this analysis, we derive design guidelines and introduce simple on-chip calibration techniques to improve the accuracy of analog neural networks with a small cost in die area and power dissipation. We validate our analysis by evaluating the performance of a mixed-signal complementary metal-oxide-semiconductor implementation of a 32-input perceptron trained with LMS.

关键词： Analog very large scale integration least-mean-square algorithm on-chip learning silicon neural networks

来源：评论

学校读者我要写书评

暂无评论

A NOVEL APPROACH TO MANDARIN MORSE CODE RECOGNITION

引用

BIOMEDICAL ENGINEERING-APPLICATIONS BASIS COMMUNICATIONS 2005年第5期17卷 267-274页

作者： Yang, Cheng-Hong Chuang, Li-Yeh Chen, Shih-Chung Liang, Chih-Kuo Wu, Chung-Min Luo, Ching-Hsing Natl Kaohsiung Univ Appl Sci Dept Elect Engn Kaohsiung 807 Taiwan I Shou Univ Dept Chem Engn Kaohsiung Taiwan Southern Taiwan Univ Technol Dept Elect Engn Tainan Taiwan Kun Shan Univ Technol Dept Elect Engn Tainan Taiwan Natl Cheng Kung Univ Dept Elect Engn Tainan Taiwan

Morse code, with its single switch operation, has been shown to be a valuable tool in assistive technology, augmentative and alternative communication, and rehabilitation for people with various neuromuscular diseases, such as amyotrophic lateral sclerosis, multiple sclerosis, and muscular dystrophy. A major hindrance is a stable typing rate, which is strictly required for the recognition of Morse code characters, especially for persons with severe disabilities. In this paper, a combination of two methods, support vector machines and the variable degree variable step least-mean-square algorithm was used to increase the prediction accuracy for Mandarin Morse code recognition. Experimental findings revealed that the proposed method results in a better recognition rate when compared to alternative methods from the literature.

关键词： Mandarin Morse code Adaptive signal processing least-mean-square algorithm Support vector machines Friedman test Multiple comparison test

来源：评论

学校读者我要写书评

暂无评论

The application of the neural network on Morse code recognition for users with physical impairments

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART H-JOURNAL OF ENGINEERING IN MEDICINE 2001年第H3期215卷 325-331页

作者： Yang, CH Yang, CH Chuang, LY Truong, TK Natl Kaohsiung Univ Appl Sci Dept Elect Engn Kaohsiung 807 Taiwan Natl Cheng Kung Univ Dept Elect Engn Tainan 70101 Taiwan I Shou Univ Dept Gen Courses Kaohsiung Taiwan I Shou Univ Dept Informat Engn Kaohsiung Taiwan

Morse code is a simple, speedy and low cost means of communication composed of a series of dots, dashes and space intervals. Each tone element (either a dot, dash or space interval) is transmitted by sending a signal for a defined length of time. This poses a challenge as the automatic recognition of Morse code is dependent upon maintaining a stable typing rate. In this paper, a suitable adaptive automatic recognition method, combining the least-mean-square (LMS) algorithm with a neural network, was applied to this problem. The method presented in this paper is divided into five modules: space recognition, tone recognition, learning process, adaptive processing and character recognition. Statistical analyses demonstrated that the proposed method elicited a better recognition rate in comparison with other methods in the literature.

关键词： Morse code adaptive signal processing least-mean-square algorithm neural network

来源：评论

学校读者我要写书评

暂无评论

Equalizer Optimization using Flower Pollination algorithm 1

Equalizer Optimization using Flower Pollination Algorithm

引用

1st IEEE International Conference on Power Electronics, Intelligent Control, and Energy Systems (ICPEICES)

作者： Banerjee, Subhabrata Chattopadhyay, Sudipta Future Inst Engn & Management Dept Elect & Commun Engn Kolkata India Jadavpur Univ Dept Elect & Telecommun Engn Kolkata India

ISBN: (纸本)9781467385879

Transmission of information from the source to the receiver involves automatic inclusion of random errors to the signal due to noise, interference or other system imperfections. Equalizers can be fruitfully utilized to minimize this error. Since the channel condition is always dynamic, the coefficients of the equalizer have to be set in an adaptive manner. This leads to the necessity of using Adaptive Equalizer (AE) in the communication system. Efficient optimization techniques add up an extra dimension to it. In this regard, a novel Flower Pollination algorithm (FPA) based Adaptive Equalizer (AE) has been proposed in this paper to minimize the channel errors with minimum number of iterations. The convergence behavior of the adaptive algorithm has been studied to establish the effectiveness of our proposition. Moreover, the Bit Error Rate (BER) performance of the proposed adaptive equalizer has been studied which shows considerable improvement over the entire range of SNR. Finally, the superiority of the proposed FPA optimized Adaptive Equalizer has been established over the existing techniques like least-mean-square (LMS) and Constant Modulus algorithm (CMA) based Adaptive Equalizer in terms of convergence as well as BER performance.

关键词： Adaptive Equalizer BER Constant Modulus algorithm Flower Pollination algorithm least-mean-square algorithm

来源：评论

学校读者我要写书评

暂无评论

The Research of Adaptive Filtering algorithm and System Modeling

The Research of Adaptive Filtering Algorithm and System Mode...

引用

International Conference on Mechatronics Engineering and Computing Technology (ICMECT)

作者： Zhang, Shengping Chen, Dongya Jining Univ Dept Phys & Informat Engn Qufu 273155 Peoples R China Shandong Coll Elect Technol Dept Elect Engn Jinan 250200 Peoples R China China Univ Min & Technol Sch Informat & Elect Engn Xuzhou 221116 Peoples R China

ISBN: (纸本)9783038351153

This paper introduces an adaptive adjusting FIR filter's parameters (LMS) method and presents a system recognition model based on the adaptive filter theory. The adaptive filter is directly with adjustable coefficient h(0),h(1),...h(N-1). The unknown system and FIR model have the same input sequence. The simulation result confirms the feasibility of the model.

关键词： adaptive filtering LMS least-mean-square algorithm system modeling

来源：评论

学校读者我要写书评

暂无评论

Joint Estimation of Complex Gain and Fractional Delay for Tx Leakage Compensation in FDD Transceivers 21

Joint Estimation of Complex Gain and Fractional Delay for Tx...

引用

2014 21st IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Gerzaguet, Robin Ros, Laurent Belveze, Fabrice Brossier, Jean-Marc GIPSA Lab Image & Signal Dept BP 46 F-38402 St Martin Dheres France ST Microelect Grenoble France

ISBN: (纸本)9781479942428

This paper deals with a joint estimation algorithm dedicated to the digital compensation of the Tx leakage in FDD transceivers. Such transceivers are affected from transmitter-receiver signal leakage. Combined with non linearity of components in the received path, it leads to a pollution in the baseband signal. The baseband polluting term depends on the equivalent Tx leakage channel, modeling leakages and the received path. In this paper we consider a first-order autoregressive model to approximate Tx-Leakage channel gain variations, and the presence of a fractional delay, modeling propagation effects. We first express asymptotic performance of a gain estimator based on a least-mean-square (LMS) approach in the synchronized case and then derive the influence of the fractional delay. We show that in practice, the fractional delay can not be neglected and we propose a joint estimation of the fractional delay and the cross-channel gain to perform the digital compensation. The proposed method is recursive, online and exhibits low complexity.

关键词： Tx Leakage FDD transceiver Digital Compensation least-mean-square algorithm Joint Estimation

来源：评论

学校读者我要写书评

暂无评论

Minimizing Uplink Data in Wireless Free-Viewpoint Video Transmission Applications

Minimizing Uplink Data in Wireless Free-Viewpoint Video Tran...

引用

3rd International Conference on Next Generation Mobile Applications, Services, and Technologies

作者： Debono, Carl J. De Raffaele, Clifford Univ Malta Dept Commun & Comp Engn Msida Malta

ISBN: (纸本)9780769537863

The increase in processing power of mobile multimedia terminals, the improvements in camera technology and efficient video compression algorithms have made the implementation of mobile Free-Viewpoint Video (FVV) technology possible. However, the use of this technology in wireless environments poses a number of challenges. Amongst these there are issues in bandwidth utilisation and the limited supply power of the mobile device. To this effect, this paper compares the implementation of two prediction algorithms to forecast the next viewpoint in an attempt to minimise the amount of viewpoint requests uploaded to the server. Simulation results demonstrate that a reduction of up to 72% in uplink transmission traffic is achieved when emulating a conventional usage scenario. This means that the application of prediction schemes can drastically reduce the power consumption and resource requirements of mobile multimedia terminals.

关键词： Free-viewpoint Kalman filter least-mean-square algorithm wireless transmission

来源：评论

学校读者我要写书评

暂无评论

Design of Improved Adaptive Equalizers using Intelligent Computational Techniques: Extension to WiMAX System

Design of Improved Adaptive Equalizers using Intelligent Com...

引用

IEEE-Uttar-Pradesh-Section International Conference on Electrical, Computer, and Electronics Engineering (UPCON)

作者： Dey, Ananya Banerjee, Subhabrata Chattopadhyay, Sudipta Jadavpur Univ Dept Elect & Telecommun Engn Kolkata India Future Inst Engn & Management Dept Elect & Commun Engn Kolkata India

ISBN: (纸本)9781509053841

During transmission of signal through a channel the signal becomes distorted noise and the transmitted signal also suffers from Inter Symbol Interference (ISI). Adaptive Equalizers (AEs) are used to reduce the ISI and the noise by updating the filter coefficients without having the prior information about the noise. So the necessity of designing more efficient adaptive filters has been emerged as one of the interesting research areas over last decades. In recent past some optimization techniques have been developed which provide better results than conventional Adaptive Equalizers (AEs). In this context, an attempt has been made to explore some efficient AEs based on the intelligent computational techniques. Three optimization techniques namely Harmony Search (HS), Cuckoo Search (CS) and Flower Pollination algorithm (FPA) have been used in this paper. Moreover, the comparative analysis of the convergence behavior and BER performances of the proposed AEs have been investigated and also compared with least mean square (LMS) algorithms and Constant Modulus algorithms (CMA) based AEs. Furthermore, performance analysis of the proposed AEs under different fading channel conditions like Rayleigh, Rician and Nakagami Fading have also been studied. Finally, the performances of the proposed equalizers have been evaluated in WiMAX system.

关键词： Adaptive Equalizer BER Constant Modulus algorithm Harmony Searh Cuckoo Search least-mean-square algorithm

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：