فایل ورد کامل طبقه بندی تصویر بیولوژیکی با استفاده ازشبکه عصبی مصنوعی راف-فازی

توجه : به همراه فایل word این محصول فایل پاورپوینت (PowerPoint) و اسلاید های آن به صورت هدیه ارائه خواهد شد

این مقاله، ترجمه شده یک مقاله مرجع و معتبر انگلیسی می باشد که به صورت بسیار عالی توسط متخصصین این رشته ترجمه شده است و به صورت فایل ورد (microsoft word) ارائه می گردد

متن داخلی مقاله بسیار عالی، پر محتوا و قابل درک می باشد و شما از استفاده ی آن بسیار لذت خواهید برد. ما عالی بودن این مقاله را تضمین می کنیم

فایل ورد این مقاله بسیار خوب تایپ شده و قابل کپی و ویرایش می باشد و تنظیمات آن نیز به صورت عالی انجام شده است؛ به همراه فایل ورد این مقاله یک فایل پاور پوینت نیز به شما ارئه خواهد شد که دارای یک قالب بسیار زیبا و تنظیمات نمایشی متعدد می باشد

توجه : در صورت مشاهده بهم ریختگی احتمالی در متون زیر ،دلیل ان کپی کردن این مطالب از داخل فایل می باشد و در فایل اصلی فایل ورد کامل طبقه بندی تصویر بیولوژیکی با استفاده ازشبکه عصبی مصنوعی راف-فازی،به هیچ وجه بهم ریختگی وجود ندارد

تعداد صفحات این فایل: ۲۱ صفحه

بخشی از مقاله انگلیسیعنوان انگلیسی:Biological image classification using rough-fuzzy artificial neural network~~en~~

Abstract

This paper presents a methodology to biological image classification through a Rough-Fuzzy Artificial Neural Network (RFANN). This approach is used in order to improve the learning process by Rough Sets Theory (RS) focusing on the feature selection, considering that the RS feature selection allows the use of low dimension features from the image database. This result could be achieved, once the image features are characterized using membership functions and reduced it by Fuzzy Sets rules. The RS identifies the attributes relevance and the Fuzzy relations influence on the Artificial Neural Network (ANN) surface response. Thus, the features filtered by Rough Sets are used to train a Multilayer Perceptron Neuro Fuzzy Network. The reduction of feature sets reduces the complexity of the neural network structure therefore improves its runtime. To measure the performance of the proposed RFANN the runtime and training error were compared to the unreduced features.

۱ Introduction

In complex problems as biological cells image classification, the capture of the essential features must be carried out without a priori knowledge of the image. The increased amount of attributes requires computational complexity and runtime even bigger. Moreover, due to noise in the database caused by excessive image features can cause a reduction in capacity of representation. According to Shang and Qiang (2008), the employment of Rough-Fuzzy features selection mechanism allows the reduction for a low dimensionality features sets from samples descriptions.

For these complex cases from the real life the use of Rough Sets (RS) in the pre-processing of the database has been efficient, since only the most relevant features are used as input parameters for the neural network. The RS has recently emerged as another major mathematical approach for managing uncertainty that arises from inexact, noisy, or incomplete information. It is found to be particularly effective in the area of knowledge reduction (Petrosino & Salvi, 2006).

In these cases, Fuzzy Set theory (FS) and RS represent two different approaches to vagueness. FS addresses gradualness of knowledge, expressed by the fuzzy membership, whereas rough set theory addresses granularity of knowledge, expressed by the indiscernibility relation (Affonso & Sassi, 2010).

An option to simplify the structure of the Artificial Neural Network (ANN) and reduce the noise caused by non-significant features is to use the Rough Set (RS) approach in order to select the most important features. The present paper proposes a new algorithm to realize the feature selection, with the intention to use RS as a tool for structuring the ANN. The methodology consisted of generating rules from training examples by rough-set learning, and mapping the dependency factors of the rules into the connection weights of a four-layered neural network.

The advantage of the Rough-Fuzzy Artificial Neural Network (RFANN) approach consists in the synergy achieved by combining two or more technical capabilities to achieve a more powerful system regarding to learning and generalization (Gomide, Figueiredo, & Pedrycz, 1998). A sequential architecture is used in this work, in which RS and the FS have distinct functions: RS identifies the most critical features, while the FS generates the surface response (input, output) since the Neuro Fuzzy Network (NFN) has Learnability and can adapt itself to the real world.

The paper is organized as follows: Section 2 presents the Literature review, Section 3 presents the Experimental Methodology and Section 4 presents the Conduct of Experiments. The Conclusion is presented in Section 5.

$$en!!