The goal of SPID is to provide the user with tools capable to simulate, preprocess, process and classify in vivo and ex vivo MRS signals. These tools are embedded in a matlab graphical user interface (GUI). (Pre)processing and CLASSification methods can also be automatically run in a row using the matlab command line
Recent advances in experimental methods have resulted in the generation
of enormous volumes of data across the life sciences. Hence clustering and
CLASSification techniques that were once predominantly the domain of ecologists
are now being used more widely. This book provides an overview of these
important data analysis methods, from long-established statistical methods
to more recent machine learning techniques. It aims to provide a framework
that will enable the reader to recognise the assumptions and constraints that
are implicit in all such techniques. Important generic issues are discussed first
and then the major families of algorithms are described. Throughout the focus
is on explanation and understanding and readers are directed to other resources
that provide additional mathematical rigour when it is required. Examples
taken from across the whole of biology, including bioinformatics, are provided
throughout the book to illustrate the key concepts and each technique’s
potential.
Semantic analysis of multimedia content is an on going research
area that has gained a lot of attention over the last few years.
Additionally, machine learning techniques are widely used for multimedia
analysis with great success. This work presents a combined approach
to semantic adaptation of neural network classifiers in multimedia framework.
It is based on a fuzzy reasoning engine which is able to evaluate
the outputs and the confidence levels of the neural network classifier, using
a knowledge base. Improved image segmentation results are obtained,
which are used for adaptation of the network classifier, further increasing
its ability to provide accurate CLASSification of the specific content.
Wavelet Subband coding for speaker recognition
The fn will calculated subband energes as given in the att tech paper of ruhi sarikaya and others. the fn also calculates the DCT part. using this fn and other algo for pattern CLASSification(VQ,GMM) speaker identification could be achived. the progress in extraction is also indicated by progress bar.
四種聚類算法源代碼及示例代碼,本程序的最終目的是形成一套標(biāo)準(zhǔn)的用于聚類、可擴(kuò)展的工具。包括的內(nèi)容有1. 聚類算法：Kmeans和Kmedoid算法、FCMclust, GKclust, GGclust算法 2. 評(píng)估分類原型：程序可以在二維圖像上繪制出聚類的結(jié)果 3. 驗(yàn)證：程序給每一個(gè)算法提供驗(yàn)證機(jī)制，每個(gè)聚類算法會(huì)統(tǒng)計(jì)Partition Coefficient (PC), CLASSification Entropy (CE), Partition Index (SC), Separation Index (S), Xie and Beni s Index (XB), Dunn s Index (DI) and Alternative Dunn Index (DII)幾種衡量指標(biāo)。
