教育學院

Permanent URI for this communityhttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/1

教育學院成立於民國44年6月5日，時值臺灣省立師範學院改制為臺灣省立師範大學，初設教育、社會教育、體育衛生教育、家政教育、工業教育五個學系，發展迄今，本院共設有7個學系（均含學士、碩士及博士班）、5個獨立研究所、1個院級在職碩士專班。

本院為國內歷史最久之教育學院，系所規模、師資，及學生品質向為國內首屈一指，培育英才無數，畢業校友或擔任政府教育行政單位首長及中堅人才、或為大學校長及教育相關領域研究人員、或為國內中等教育師資之骨幹、或投入民間文教事業相關領域，皆為提升我國教育品質竭盡心力。此外，本學院長期深耕學術，研究領域多元，發行4本 TSSCI 期刊，學術聲望備受國內外學界肯定，根據 2015 年 QS 世界大學各學科排名結果，本校在教育學科名列第22名，不僅穩居臺灣第一，更躍居亞洲師範大學龍頭。

Browse

Author: search.filters.author.Chen, Sei-WangSubject: search.filters.subject.ART neural classifier

Search Results

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Neural-fuzzy classification for segmentation of remotely sensed images
    (Institute of Electrical and Electronics Engineers, 1997-11-01) Chen, Sei-Wang; Chen, Chi-Farn; Chen, Meng-Seng; Cherng, Shen; Fang, Chiung-Yao; Chang, Kuo-En
    An unsupervised classification technique conceptualized in terms of neural and fuzzy disciplines for the segmentation of remotely sensed images is presented. The process consists of three major steps: 1) pattern transformation; 2) neural classification; 3) fuzzy grouping. In the first step, the multispectral patterns of image pixels are transformed into what we call coarse patterns. In the second step, a delicate classification of pixels is attained by applying an ART neural classifier to the transformed pixel patterns. Since the resultant clusters of pixels are usually too keen to be of practical significance, in the third step, a fuzzy clustering algorithm is invoked to integrate pixel clusters. A function for measuring clustering validity is defined with which the optimal number of classes can be automatically determined by the clustering algorithm. The proposed technique is applied to both synthetic and real images. High classification rates have been achieved for synthetic images. We also feel comfortable with the results of the real images because their spectral variances are even smaller than the spectral variances of the synthetic images examined.