Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition

Feature extraction is an important component of a pattern recognition system. It performs two tasks: transforming input parameter vector into a feature vector and/or reducing its dimensionality. A well-defined feature extraction algorithm makes the classification process more effective and efficient. Two popular methods for feature extraction are linear discriminant analysis (LDA) and principal component analysis (PCA). In this paper, the minimum classification error (MCE) training algorithm (which was originally proposed for optimizing classifiers) is investigated for feature extraction. A generalized MCE (GMCE) training algorithm is proposed to mend the shortcomings of the MCE training algorithm. LDA, PCA, and MCE and GMCE algorithms extract features through linear transformation. Support vector machine (SVM) is a recently developed pattern classification algorithm, which uses non-linear kernel functions to achieve non-linear decision boundaries in the parametric space. In this paper, SVM is also investigated and compared to linear feature extraction algorithms.     

Integration of GIS and multicriteria decision analysis for urban aquaculture development in Bangladesh

Site selection is a key factor in any aquaculture operation, affecting both success and sustainability as well as solving land or water use conflicts. This study was conducted to identify suitable sites for carp farming development in urban water bodies (UWBs) of Chittagong, Bangladesh using Geographical Information Systems (GIS) based MultiCriteria Evaluation (MCE) of water, soil and infrastructure database. ASTER imagery and 14 thematic layers were analyzed with ENVI and GIS capabilities, and developed a series of GIS models to identify and prioritize the appropriate UWBs for carp farming. The study identified 487 UWBs occupying 362 ha and revealed 280 ha (77%) is the most suitable, 36 ha (10%) is moderately suitable and 46 ha (13%) is not suitable which was consistent with field verification. The results are encouraging for extension of carp culture and diversify the economic activities of the urban dwellers.     

GIS and Multi-Criteria Evaluation: Robust Tools for Integrated Water Resources Management

Abstract

Integrated water resources planning and management are considered very complex issues. These issues are usually addressed through the multi-sectoral, interdisciplinary and hierarchal decomposition approaches. In general, integrated resource management indicates the consideration of water, social, socio-economic, economic and environmental issues. The current study aims at merging the GIS and Multi-Criteria Evaluation (MCE) techniques for the integrated water resource management of a cropped area. An area of about 120,000 Hectares located in the Northern Nile River Delta area with a coastal zone on the Mediterranean was selected and GIS was applied to represent the area's different environment, social, economic, and water factors. Different randomization cropping pattern distribution scenarios were proposed. Through the merging of GIS and MCE approaches, three scenarios were run and evaluated at three different levels: farm, canal catchment area and whole area. This merging resulted in a very powerful tool for the evaluation of different plans. The merging of GIS and MCE really facilitated the decision making process for these types of integrated water management problems.     

GIS和MCE在旧城更新中的应用

不同的城市化特点使得一批贫困区于1949年到1978年期间在中国城市出现.本文主要介绍了怎样利用GIS(地理信息系统)和MCE(多因素评价)对这类贫困区进行旧城更新的研究.然后以武汉市的黄家墩小区为例,展示利用此方法所得到的研究成果.     

基于GIS的OWA在唐山市地下管道评价中的应用

引入有序权重平均法（OWA）,应用层次分析程序（AHP）构建比较矩阵计算唐山市各地质灾害因子的权重系数,将地质灾害因子图像进行了标准化处理并得到影响管道破坏的土地适宜度多准则评价结果,对唐山市的管道铺设提出了建议。     

一种极具发展潜力的制冷技术--磁制冷

介绍了一种历史悠久但又极具发展潜力的制冷方式-磁制冷技术.从磁制冷的基本原理-磁热效应(MCE)出发,分别从熵和热力学的角度分析了MCE,给出了MCE的表征参数及常用测试方法,列举了常见的磁制冷循环及几种典型的磁制冷机,总结了磁制冷技术的研究历史,并对其进行了展望.     

毛细管电泳技术在蛋白质生物制品分析中的应用研究进展

毛细管电泳技术作为一种快速的分离分析技术,具有分析速度快、分辨率高、重现性好、定量分析准确、分离模式多样等特点,在蛋白质生物制品的定性定量分析中发挥着重大作用。就毛细管电泳技术的演变、分类及其在蛋白质生物制品分析中的应用研究进展进行了综述。     

S变换在心肌声学造影图像降噪中的应用

提出一种基于二维S变换的时频滤波方法。S变换融合了短时傅里叶变换和小波变换的优点,适合医学图像处理。该方法在局部频谱利用硬阈值去噪,可用于心肌声学造影图像降噪。降噪实验表明了该方法的有效性和临床应用价值。     

室温磁热效应直接测量仪的误差分析

简单介绍了室温磁热效应测量仪的组成、工作原理及其优点;用金属G d作为标准样品,用两个不同尺寸的温度传感器,测量了两个大小不同的样品。结果表明,相同条件下测量的数据重复性很好,而不同条件下测量的数据有一些差别,对此进行了分析,发现测量样品时特别是样品较小时,温度传感器的热容以及绝热条件等因素是引起误差的主要原因。     

A numerical analysis of an active magnetic regenerative cascade system

Magnetic refrigeration is an emerging green technology based on the magnetocaloric effect (MCE) in solid‐state refrigerants with environmentally desirable characteristics. The active magnetic regenerator is a special kind of regenerator for the active magnetic regenerative cycle (AMR), in which the magnetic material matrix works both as a refrigerating medium and as a heat regenerating medium, while the fluid flowing in the porous matrix works as a heat transfer medium. The MCE is maximal at the Curie temperature, and is large only in the temperature interval around this temperature. It is therefore advantageous that the operating point of the refrigeration plant and this temperature interval of optimal MCE coincide. Therefore a good solution is to work with a cascade system, where each unit has its own optimally adapted working temperature. In the present paper, a practical model for predicting the performance and efficiency of an AMRC (Active Magnetic Regenerative Cascade cycle) system has been developed. The model simulates both the ferromagnetic material and the entire cycle of an AMRC operating in conformity with a Brayton regenerative cycle. In addition, the model simulates a two‐stage cascade systems with each stage operating at its optimal point. The program simulates a cascade system working with the Gd_?x Tb_1?x alloys as constituent materials for the regenerator of the first and of the second stage, varying the composition of the alloy. The heat transfer medium is a water–glycol mixture (50% by weight). With this model, the refrigeration capacity, the power consumption and consequently the coefficient of performance can be predicted. The aim of this paper is to provide some useful indications for the design of an AMR prototype. In this simulation attention is paid on both the temperature span enlargement and the compactness of the AMR system. Copyright © 2010 John Wiley & Sons, Ltd.