2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)最新文献_第6页

Cooperative modular neural predictive coding 协同模块化神经预测编码

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318063

M. Chetouani, B. Gas, J. Zarader

引用次数: 1

Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines 使用支持向量机识别孤立的手写波斯语/阿拉伯语字符和数字

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318054

A. Mowlaei, K. Faez

{"title":"Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines","authors":"A. Mowlaei, K. Faez","doi":"10.1109/NNSP.2003.1318054","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318054","url":null,"abstract":"We propose a system for recognition of isolated handwritten Persian/Arabic characters and numerals. Wavelet transform has been used for feature extraction in this system using Haar wavelet. The support vector machine (SVM), which is a new learning machine with very good generalization ability, and has been used widely in pattern recognition and regression estimation, uses as classifier in this system. The training and test patterns were gathered from various people with different ages and different educational backgrounds. The 32 characters in Persian language were categorized into 8 different classes in which characters of each class are very similar to each other. There are ten digits in Persian/Arabic languages where two of them are not used in zip codes in Iran. So, we have 8 different extra classes for digits. This system was used for recognizing the isolated handwritten postal addresses, which contain the name of cities and their zip codes. Our database contains 579 postal addresses in Iran. The system yields the recognition rate of 98.96% for these postal addresses. The results show an increment in recognition rates in comparison with our previous work in which we used the MLP neural network as classifier.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123254909","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: 47

ART-R: a novel reinforcement learning algorithm using an ART module for state representation ART- r:一种使用ART模块进行状态表示的新型强化学习算法

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318082

L. Brignone, M. Howarth

引用次数: 4

Neural speech enhancement in the time-frequency domain 时频域的神经语音增强

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318061

M. Volkmer

引用次数: 1

A self-organizing method for map reconstruction 一种地图重建的自组织方法

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318067

I. K. Altinel, N. Aras, B. Oommen

引用次数: 1

Adaptive room acoustic response simulation: a virtual 3D application 自适应房间声响应模拟:虚拟三维应用

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318066

G. Costantini, D. Casali, A. Uncini

{"title":"Adaptive room acoustic response simulation: a virtual 3D application","authors":"G. Costantini, D. Casali, A. Uncini","doi":"10.1109/NNSP.2003.1318066","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318066","url":null,"abstract":"In this paper we propose a method to simulate a 3D acoustical environment in which sound sources are positioned in well defined sides. Our method is real-time applications oriented, due to the low computational cost of the implemented operations. The spatial position that the human brain assigns to a sound is influenced mainly by the differences between the sound signals that reach the listener's ears, related to the sound source angulation with respect to the listener's head. The reverberation effect, on the other side, depends on the type of environment. All this elements have to be simulated in order to give the illusion that a sound comes from a particular position in a particular environment. To obtain this result, we perform a suitable sound processing, that can be separated in two main tasks: reverberation and spatialization. The first one is mainly related to the environment itself: it depends on the shape of the environment and on the absorption coefficients of the walls. This is the most computational intensive component, if we want to reproduce it accurately, so we approximate it by an adaptive IIR filter. By the spatialization, the listener hears the sound as coming from a particular direction. This task, carried out by using the head related transfer functions (HRTFs), has to be applied to every sound source differently.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127930134","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

An algorithm based on the even moments of the error 一种基于误差偶矩的算法

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318087

A. Barros, J. Príncipe, Y. Takeuchi, C. H. Sales, N. Ohnishi

引用次数: 10

Local Hammerstein modeling based on self-organizing map 基于自组织映射的局部Hammerstein建模

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318080

Jeongho Cho, J. Príncipe, M. Motter

引用次数: 3

Bayesian and RBF structures for wireless communications detection 无线通信检测中的贝叶斯和RBF结构

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318074

L. M. San-José-Revuelta, Jesús Cid-Sueiro

引用次数: 10

Tracking of feature points in a scene of moving rigid objects by Bayesian switching structure model with particle filter 基于粒子滤波的贝叶斯切换结构模型在运动刚体场景中的特征点跟踪

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 1900-01-01 DOI: 10.1109/NNSP.2003.1318071

N. Ikoma, Yasutake Miyahara, H. Maeda

引用次数: 3