Buğday Sınıflandırma

Öncelikle Orjinal çalışmadan bahsedelim ;

Complete Gradient Clustering Algorithm for Features Analysis of X-Ray Images





Abstract

Methods based on kernel density estimation have been successfully applied for various data mining tasks. Their natural interpretation together with suitable properties make them an attractive tool among others in clustering problems. In this paper, the Complete Gradient Clustering Algorithm has been used to investigate a real data set of grains. The wheat varieties, Kama, Rosa and Canadian, characterized by measurements of main grain geometric features obtained by X-ray technique, have been analyzed. The proposed algorithm is expected to be an effective tool for recognizing wheat varieties. A comparison between the clustering results obtained from this method and the classical k-means clustering algorithm shows positive practical features of the Complete Gradient Clustering Algorithm.

X-Işını tekniği dedikleri bir metodla çektikleri görüntüler üzerinden çıkardıkları özniteliklerle, "Complete Gradient Clustering Algorithm"kullanılarak sınıflandırma çalışması yapılmış.

Biz bu çalışmanın veri setine The UCI Machine Learning Repository den ulaştık.

http://archive.ics.uci.edu/ml/datasets/seeds

Veri setininin tanıtımı şöyle yapılmış ;


The examined group comprised kernels belonging to three different varieties of wheat: Kama, Rosa and Canadian, 70 elements each, randomly selected for the experiment. High quality visualization of the internal kernel structure was detected using a soft X-ray technique. It is non-destructive and considerably cheaper than other more sophisticated imaging techniques like scanning microscopy or laser technology. The images were recorded on 13x18 cm X-ray KODAK plates. 

Studies were conducted using combine harvested wheat grain originating from experimental fields, explored at the Institute of Agrophysics of the Polish Academy of Sciences in Lublin.

The data set can be used for the tasks of classification and cluster analysis.

Attribute Information:

To construct the data, seven geometric parameters of wheat kernels were measured:
1. area A,
2. perimeter P,
3. compactness C = 4*pi*A/P^2,
4. length of kernel,
5. width of kernel,
6. asymmetry coefficient
7. length of kernel groove.
All of these parameters were real-valued continuous.

Bu veri setini FannTool'u kullanarak YSA ile sınıflandırmayı deneyeceğiz.

Öncelikle Veri setini inceliyoruz

 http://archive.ics.uci.edu/ml/machine-learning-databases/00236/seeds_dataset.txt

Veri setimiz 7 giriş ve 1 çıkış dan oluşuyor

1 çıkış değerimiz 3 buğday türü için bir sınıflandırma içerdiğinden
biz o bir sutunu her bir sınıf için bir sutun haline getiriyoruz yani

Kama için 1 0 0 
Rosa  için  0 1 0
Canadian   0 0 1

Sonuçda 7 giriş 3 çıkışlı bir veri setimiz oluyor

bu verileri bir text dosyasına kaydedip, FannTool'un DataProcessing kısmıyla açıyoruz

7 giriş 3 çıkış üzere ayarlayıp
sonrasında oluşan dosyalarımız

seed-scale.txt : Ölçeklendirme bilgilerini tutan dosya
seed-train.dat  :  Eğtim verileri
seed-test.dat   :   Test  Verileri

Artık yapmamız gereken şey Eğitim ve test verilerini yükleyip. YSA için değişik yapılarda ve değişik eğitim algoritmaları ve paramtereleri ile denemeler yapmak.

Sonuç :  

Yapılan pek çok denemenin ardından oldukça başarılı Sınıflandırma başarılarına ulaşıldı

Eğitim Verisi için %  99,32 ( 146 verinin 145 adedi doğru sınıflandırıldı )
Test Verisi için  %  96,88  ( 64 verinin 62 adedi doğru sınıflandırıldı )

Read More

Efficient Segmentation and Classification of Hyper Spectral Cubes

Efficient Segmentation and Classification of Hyper Spectral Cubes

Papagrigoriou Stylianos
Technical University of Crete

Abstract:

Hyper Spectral Imaging is a powerful analytical tool, which has been used in a wide area of applications, from Satellite Imaging to Biomedical Diagnosis. Spectral imagery of either macroscopic or microscopic origin is usually depicted in a spectral cube, a registered set of images, featuring one spectral and two spatial dimensions as pixel coordinates. From each pixel, associated with a spectrum -instead of an RGB value-, one is able to extract information about the nature of the material, by studying its spectral signature on the Spectral Cube.
This technique offers a non-destructive and non-invasive way (one does not have to extract part of the material and bring it to the lab) of examining materials, suitable for medical purposes. In the hereby thesis the computational capabilities of spectral imaging methods are examined and attempted to be improved, in order to provide real time pixel classification. Specifically, a successful attempt is made to create a hyper spectral classifier with real-time performance for cubes acquired from a cervix biopsy. Various techniques are tested for efficient segmentation of the Cube, in order to generate a golden standard for the training process. The classification is performed using Neural Networks while the final result is a GPU implementation, the main reason behind the speed up of the application.
Although this study was based on specific medical data, it is possible to be generalized on any aspect of Hyper Spectral Imaging, and shows that real-time Hyper Spectral Processing for classification purposes is feasible.

FannTool ;

...
FANN library, provides a really fast and powerful tool -FannTool- for training neural networks with many different algorithms and automatic mechanisms for identifying the best activation function and training algorithm. FANN library was used exactly for these two purposes (finding the best activation function and training algorithm) and train the Network
...

Read More

A Back Propagation Artificial Neural Networks Approach to Automatic Customer Record Classification

Maastricht University / Department of Quantitative Economics
Master Thesis
A Back Propagation Artificial Neural Networks Approach to Automatic Customer Record Classification.
Author: Camilo Gaviria

Introduction :

In this thesis I address the problem of finding the correct customer to account (AMID)
assignment based on several variables called customer attributes. These customer at-
tributes contain information that provide a partial description of the customer, i.e. cus-
tomer name, customer address, etc. As each customer record carries many attributes,
and there are many possible accounts or classes to which it can belong, this is in itself
a combinatorial optimization problem which is hard to solve. I will call the problem
of minimizing the number of incorrect class (AMID) assignments from now on, the
customer alignment problem.
...

In the literature, many approach to address similar problems are discussed,
one of these, which I have chosen to explore, is the utilization of neural network based
classi cation approaches that are commonly used in the classi cation of natural language
documents as patents, articles, books. In this thesis I will approach the customer record
alignment problem using an adaptation of the methodology used by to classify
patent documents.

FannTool ;

...
Another advantage of using this pre-compiled library, is the availability of a series of
open source graphical user interfaces. By using one of these GUI's, the development
efort is significantly reduced, and the number of additional tests and configurations
that can be easily performed is much larger. Taking into account that there are several
parameters for which there is no one setup rule (number of neurons per layer, number of layer, type of training algorithm, etc.) being able to easily change the configuration
of the ANN is an highly valued feature. The GUI of choice was FANNTool 1.3 an
open source GUI developed specifically for FANN and portable to several OS. This GUI
allows for direct instance scaling, data manipulation as well as real time monitoring of
the learning process.

...

Read More

ANN for Gesture Recognition using Accelerometer Data

Procedia Technology 3 ( 2012 ) 109 – 120
The 2012 Iberoamerican Conference on Electronics Engineering and Computer Science

ANN for Gesture Recognition using Accelerometer Data
Blanca Miriam Lee-Cosio, Carlos Delgado-Mata, Jesus Ibanez

Abstract

This paper presents the application of Artificial Neural Networks to recognise among gestures trajectory patterns in a Euclidean space. The data was filtered and normalised by the Fast Fourier Transform. The k-means algorithm was used to parametrise the optimized data as input of the ANN by creating 15 clusters of data. Using the FANN tool , the ANN was modeled trained and tested so that the output of the ANN is the recognised gesture . The raw data comes from a set of 8 trajectories representing gestures captured by a device based on accelerometers like the Nintendo Wii remote.

Read More