The Help Of Soft Computing Techniques Biology Essay

Published:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

Soft Computing is a branch of artificial computational intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to "learn" from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, computational intelligence is frequently used in cancer diagnosis and detection. More recently soft computing has been applied to cancer prophecy and prediction. A number of trends are there, including a increasing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on"older" technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable soft computing techniques. Among the better designed and validated studies it is clear that soft computing techniques can be used to substantially to improve the accuracy of predicting cancer susceptibility, recurrence and mortality.In addition to it provides a general idea for further improvement in this field.

1. Introduction:

Bioinformatics[28] is the application of computer science and information technology to the field of biology and medicine. Bioinformatics deals with algorithms, databases and information systems, web technologies, artificial intelligence and soft computing, information and computation theory, software engineering, data mining, image processing, modeling and simulation, signal processing, discrete mathematics, control and system theory, circuit theory, and statistics. Bioinformatics generates new knowledge as well as the computational tools to create that knowledge.

Cancer research is a field of bio-informatics, where we can use classification, clustering algorithmic methods and soft computing techniques for better prediction and understandability in a earlier stage.

In systems Biology[35] gene regulatory networks have an important role in advance prediction of cancer. By modeling understanding and analysis of these gene regulatory networks dynamics. It may shed light on the mechanism of diseases that

occur when these cellular processes are deregulated .Accurate prediction of the behaviour of gene regulatory networks will also speed up in developing personalized medicines and earlier diagnosis.

2. Soft Computing Methods:

Classification & clustering [29][30] is a method in which Objects are characterized by one or more features

Classification is a task which assign objects to classes or groups on the basis of measurements made on the objects

Have labels for some points

Want a "rule" that will accurately assign labels to new points

Supervised learning

Clustering is to group observations that are "similar" based on predefined criteria.

No labels

Group points into clusters based on how "near" they are to one another

Identify structure in data

Unsupervised learning

Table 1: Soft computing clustering and classification [40]

Various Important Clustering Methods

Various important Classifiers

Hierarchical Methods

Supervised Methods

Agglomerative hierarchical clustering

Divisive hierarchical clustering

Single-link clustering

Complete-link clustering

Average-link clustering

Naïve Bayes Classifier

J48 Decision Trees

Support Vector Machines

Partitioning Methods

Unsupervised method

Error Minimization Algorithms.

Graph-Theoretic Clustering

SenseClusters (an adaptation of the K-means clustering algorithm)

Density-based Methods

Model-based Clustering Methods

Instance-based learning

Decision Trees.

Neural Networks

Nearest neighbor classifier

Grid-based Methods

Perceptron-based techniques

Soft-computing Methods

Single layered perceptrons

Multilayered perceptrons

Radial Basis Function (RBF) networks

Fuzzy Clustering

Evolutionary Approaches for Clustering

Simulated Annealing for Clustering

Statistical learning algorithms

Naive Bayes classifiers

Bayesian Networks

Instance-based learning

Soft computing [31][32]is a branch of computer science capable of analyzing complex medical data. Advances in the area of microarray based expression analysis have led to the promise of cancer diagnosis using new molecular based approaches. Many studies and methodologies have come up which analyzes the gene expression data by using the techniques in data mining such as feature selection, classification, clustering etc. emboiding the soft computing methods for more accuracy.

The approach Soft Computing is helpful to be applied for classification, clustering and prediction of cancer as the data contains intangible parameters which are highly non linear and incomplete.

Table 2: Various soft computing techniques in diagnostics of diseases [36][37][38]

Sl. No.

SC Techniques used

Diseases cure/detection/recognition

1

Fuzzy logic

Neural system disorder

2

Medical imaging (bio inspired soft computing)

Cancer, arteriosclerosis, epilepsy, alzheimer, parkinson

3

Object-oriented expert system

Diagnosis of fungal diseases of date palm

4

Decision support systems

Diagnosis of disease states and corresponding herbal prescriptions

5

Neural networks,image processing

Oral cysts

6

Artificial neural network

Neonatal diseasediagnosis

7

Decision support system

Congenital heartdisease diagnosis based on signs and symptoms

8

Fuzzy knowledge base

Glaucoma monitoring

9

Clustering techniques

To distinguish the data set to twoprimary clusters i.e. diseased and disease free

10

Classification techniques

To classify a sample at first asdiseased or free from disease and subsequently if diseased then particular type of the disease

Table 3: Survey of computational intelligent learning methods used in cancer prediction showing the types of cancer, clinical endpoints, choice of algorithm, performance and type of training data.

Sr. Nm

Cancer Type

Clinical Endpoint

Computational Intelligent Algorithm

Benchmark

Training Data

1

Bladder

Recurrence

Fuzzy Logic

Statistics

mixed

2

Bladder

Recurrence

ANN

N/A

Clinical

3

Bladder

Survivability

ANN

N/A

Clinical

4

Bladder

Recurrence

ANN

N/A

clinical

5

Brain

Survivability

ANN

Statistics

Genomic

6

Breast

Recurrence

Clustering

Statistics

Mixed

7

Breast

Survivability

Decision Tree

Statistics

Clinical

8

Breast

Susceptibility

SVM

Random

Genomic

9

Breast

Recurrence

ANN

N/A

Clinical

10

Breast

Recurrence

ANN

N/A

Mixed

11

Breast

Recurrence

ANN

Statistics

Clinical

12

Cervical

Survivability

ANN

N/A

Mixed

13

Colorectal

Recurrence

ANN

Statistics

Clinical

14

Colorectal

Survivability

ANN

Statistics

Clinical

15

Colorectal

Survivability

Clustering

N/A

Clinical

16

Esophageal

Treatment response

SVM

N/A

Proteomic

17

Esophageal

Survivability

ANN

Statistics

Clinical

18

Leukemia

Recurrence

Decision Tree

N/A

Proteomic

19

Liver

Recurrence

ANN

Statistics

Genomic

20

Liver

Recurrence

SVM

N/A

Genomic

21

Liver

Susceptibility

ANN

Statistics

Clinical

22

Liver

Survivability

ANN

N/A

Clinical

23

Lung

Survivability

ANN

N/A

Clinical

24

Lung

Survivability

ANN

Statistics

Mixed

The major broad areas of this paper is Soft Computing and Oncology( cancer Classification & Detection) which further embraces of following subjects/areas:

Cancer, its study, prediction, recognition techniques & analysis of its most common types:

Cancer is an abnormal cell-growth occurring in human body and may originate from any of the areas or organs. The disorder can be very dangerous, or even fatal, if ignored for long. It develops in the form of tumors that have a typical tendency to metastasize. Such tumors metastasize or spread to various parts of the body via bloodstream[1].

Cancer is characterized by out-of-control cell growth. [2,4]. Research requires detailed study of most common Cancer in men and women including Lung, Prostate, Breast and Oral Cancer and their recognition.

The below stated referred research works are classified as cancer detection methods and cancer classification methods. A comparative study is made between the detection methods and the classification methods separately.

Diagnosis[3][5] of any type of cancer in human being: Diagnosis is concerned with the development of algorithms and techniques that are able to determine whether the behavior of a system is correct. If the system is not functioning correctly, the algorithm should be able to determine, as accurately as possible, which part of the system is failing, and which kind of fault it is facing. The computation is based on observations, which provide information on the current behavior.

Table 4. Comparisons of various cancer detection methods [14]

S. No

Authors

Cancer Type

Technique

Algorithms used

Results

Future Enhancement

Limitations

1

A Banumathi,Praylin Mallika,S Raju

Oral Cysts

Neural networks,Image Processing

Contrast stretching,Radial Basis function

Severity of cysts is measured.For each dental Image accuracy is calculated for classification of Cysts

2

S murugavalli,V Rajamani

Brain Tumor

Neuro Fuzzy

Fuzzy c-means clustering algorithm

Detected brain tumour at an earlier stage

3

Ghassan Hamameh,Artur Chodorowski

Oral cancer

Image Processing

Active contour model(snakes)

Segmentation of oral lesion is obtained in single band images from true color images

To further automize and improve segmentation

User assiatance is required due to larger variability of objects

4

Varsha H Patil

,Vaishali S Pawar

Breast Cancer

CAD, Image processing

Super resolution technique

Detected cancer at very early stage

To simulate the system

5

H s Sheshadri,

A Kandasamy

Breast Cancer

Image processing

Watershed segmentation

Detected cancer tumors at an early stage

A new methodology to extract various parameters which helps to view automatically identifies the suspect lesions

6

Sibastian Steger,

Marius Eddt,

Gianfranco

Oral Cancer

Image Processing

Supervised segmentation,image

Feature extraction

Oral cancer reoccurrence is predicted automatically

Incorporation of other source modalities like PET

7

Ranjan Rashmi

Paul et al

Oral cancer

Wavelet,neural networks

Multilayered feed forward neural network

The feature vectore are extracted from each contiguous 64*64 blocks by wavelet decomposition

8

M Muthuramakrishan,

Chandan Chakroborty,

Oral cancer

Wavelet,Data mining,neural network

Bayesian classification,support vector machines

48 gabor wavelet features& 9 wavelet features are extracted

Improvement in accuracy 76.83% accuracyachievedBayesian classification

Expert diagnosis

The expert diagnosis (or diagnosis by expert system) is based on experience with the system. Using this experience, a mapping is built that efficiently

associates the observations to the corresponding diagnoses.Model-based diagnosis is an example of abductive reasoning using a model of the system.

3. Microarray Technology and Soft Computing In Cancer Biology

DNA microarray[41] technology has emerged as a boon to the scientific community in understanding the growth and development of life as well as in widening their knowledge in exploring the genetic causes of anomalies occurring in the working of the human body. microarray technology makes biologists be capable of monitoring expression of thousands of genes in a single experiment on a small chip. Extracting useful knowledge and info from these microarray has attracted the attention of many biologists and computer scientists. Soft computing is a branch of computer science capable of analyzing complex medical data. Advances in the area of microarray -based expression analysis have led to the promise of cancer diagnosis using new molecular based approaches. Many studies and methodologies have come up which analyses the gene expression data by using the techniques in data mining such as feature selection, classification, clustering etc. embedding the soft computing methods for more accuracy.

DNA Microarray Technology:

One intense area of microarray[41] research at the NIH is the study of cancer.In the past, scientists have classified different types of cancer based on the organs in which the tumors develop. With the help of microarray technology, however, they will be able to further classify these types of cancer based on the patterns of gene activity in the tumor cells and will then be able to design treatment strategies targeted directly to each specific type of cancer. Additionally, by examining the differences in gene activity between untreated and treated-radiated or oxygen -starved, for example-tumor cells, scientists can better understand how different types of cancer therapies affect tumors and can develop more effective treatments.

DNA microarrays[33] are also generally known as gene-chip or DNA chip.In which it is a group of microscopic DNA spots attached to a solid surface. Scientists utilize DNA microarrays to determine the expression levels of huge numbers of genes concurrently. Significant information can be extracted from these data by the use of data analysis techniques.

In short the usefulness of dna technology can be listed as

Can follow the activity of MANY genes at the same time.

Can get a lot of results fast

Can COMPARE the activity of many genes in diseased and healthy cells

Can categorize diseases into subgroups.

Table 5: Use Of Microarray Technology With Soft Computing Cancer Research

Techniques

Main-objctives

Developers

2-way Clustering

Both genes & tumors were clustered

H. Midelfart, A. Lægreid, and J. Komorowski, Classification of Gene Expression Data in an Ontology, vol. 2199. Lecture Notes in Computer Science, Berlin, Germany: Springer-Verlag, 2001, pp. 186-194

Hirarchical clustering

Found different groups of Breast cancer

M. Banerjee, S. Mitra, and H. Banka, "Evolutionary-rough feature selection in gene expression data," IEEE Trans. Syst., Man, Cybern. C, Appl.

Nearest Shrunken centroid

method (PAM)

Limit on the number of genes necessary to prediction.

-

ANN & DCT

Very high success rate for classification of tumor and non tumors

Ahmad M. Sarhan, "Cancer Classification Based on Micro array Gene Expression Data Using DCT and ANN", Journal of Theoretical and Applied Information Technology, Vol. 6, No. 2, pp. 208-216, 2009

Supervised machine learning

High accuracy with only two genes

Bharathi and Natarajan, "Cancer Classification of Bioinformatics data using ANOVA", International Journal of Computer Theory and Engineering, Vol. 2, No. 3, pp. 369-373, June 2010

Manifold learning method

Efficient discriminant feature extraction and gene expression data classification.

Bo Li, Chun-Hou Zheng, De-Shuang Huang, Lei Zhang and Kyungsook Han, ""Gene expression data classification using locally linear discriminant embedding", Computers in Biology and Medicine, Vol. 40, pp. 802-810, 2010

Rough sets ,feature selection

Superior in applicability and robustness.

Xiaosheng Wang and Osamu Gotoh, "A Robust Gene Selection Method for Micro array-based Cancer Classification", Journal of Cancer Informatics, Vol. 9, pp. 15-30, 2010

Gene ranking and gene subset ranking

Improved classification performance

Mallika and Saravanan, "An SVM based Classification Method for Cancer Data using Minimum Micro array Gene Expressions", World Academy of Science, Engineering and Technology, Vol. 62, No. 99, pp. 543-547, 2010

ANN,classification

Simultaneous pattern extraction,Leukemia classification

S. B. Cho and J. Ryu, "Classifying gene expression data of cancer using classifier ensemble with mutually exclusive features," Proc. IEEE, vol. 90, no. 11, pp. 1744-1753, Nov. 2002.

S. Bicciato,M. Pandin, G. Didon`e, andC.DiBello, "Pattern identification and classification in gene expression data using an autoassociative neural network model," Biotechnol. Bioeng., vol. 81, pp. 594-606, 2003.

GA,classification

reliable and accurate classification based on their expression levels,minimization of gene subset size

K. Deb and A. Raji Reddy, "Reliable classification of two-class cancer data using evolutionary algorithms," BioSystems, vol. 72, pp. 111-129, 2003.

NF,feature selection

Feature selection

K. Deb and A. Raji Reddy, "Reliable classification of two-class cancer data using evolutionary algorithms," BioSystems, vol. 72, pp. 111-129, 2003.

Fuzzy NN(dynamic structure growing),feature selection, ANN,classifiers

Colon classification,Classification of acute leukemia, having highly similar appearance in gene expression data

S. Bicciato,M. Pandin, G. Didon`e, andC.DiBello, "Pattern identification and classification in gene expression data using an autoassociative neural network model," Biotechnol. Bioeng., vol. 81, pp. 594-606, 2003.

K. Deb and A. Raji Reddy, "Reliable classification of two-class cancer data using evolutionary algorithms," BioSystems, vol. 72, pp. 111-129, 2003.

RS+GA,clustering

effectiveness of the algorithm is demonstrated on three cancer datasets, viz., colon, lymphoma, and leukemia.

S. Mitra, "An evolutionary rough partitive clustering," Pattern Recognit. Lett., vol. 25, pp. 1439- 1449, 2004

4. Comparative Study on Cancer (Image Diagnosis) using Soft Computing Techniques Using Neural Network And Fuzzy Techniques

Computer-aided diagnosis system (CAD) can be very helpful for radiologist in detection and diagnosing abnormalities earlier and faster than traditional screening programs. CAD as such employs several techniques to accomplish this task. Here is a comparative study of two classification methods: One in which we utilize the texture features extracted from the images by directly feeding to the Neural Network based classifier stage to classify the images into benign or malign and in the other hybrid method, those texture features are made to undergo fuzzy discretization before feeding to the Neural Network classifier for the classification. The studies so far conducted using both the systems show that the hybrid system is far superior to the first method in its accuracy. Backward Propagation Network (BPN) algorithm is used in the training stage[42].

The field of medicine has its own computer aided, manual as well as automated, tools for various activities.Though diagnosis is easy and simple for many diseases there are few diseases that includes cancer which requires much caution because, the fatal diseases are required to be detected and confirmed in real time or at very early stages, since the available treatment methods call for it. Computer Aided Diagnosis is an automated system, which utilizes techniques available in the areas of data mining, digital image processing and radiology..

Image classifiers established using neural network architecture achieved accuracy to a great extent. A Back Propagation Feed forward network is an interconnected network in which computing elements are arranged in multilayer. The weight associated with each connection modifies the input before they are fed into threshold element. In training the neural network structure, weights are adjusted using the Back Propagation algorithm. Once the learning phase is over, the network is used to perform the image classification. The proposed neural network classifiers make use of spatial information of the image known as features for input.

Fuzzy logic deals with uncertainty and impreciseness in various domains. A hybrid neuro-fuzzy system improves the accuracy and speed of the system. When fuzzified data set is given to neural structure the classification accuracy is improved. Fuzzy discretization is a process that characterizes sub ranges of a continuous variable. Fuzzy version of the crisp data set is defined by the degree of membership of crisp attribute to a fuzzy set by a membership function. In the proposed work trapezoidal membership function is used for fuzzifying the feature data set of images before classifying.

Table 6: Comparison of Relative Works

Sr Nm

Author Name

Soft Computing Technique Used

Description

1

Jesmin Nahar

Combining Microarray and Image Data

how image data classification plays a vital role in detecting cancer

2

Haralick

classification of images using texture features

Texture feature shows the difference in the intensity level which could easily identify the cancer images.

3

M.Vasantha

decision tree ID3 algorithm

Since the feature set was not discretized it may affect the accuracy of the classifier. BPN based classifier can provide more accuracy than decision tree algorithm.

4

Qurat-ul-ain

ANN Classification

Features are directly used for classification that leads to inaccuracy. Number of features may increase the computation complexity and minimizes prediction accuracy.

5

Jenn- Lung Su

BPN

compared various data analysis techniques and discussed that BPN network classify the images with high accuracy.

6

Brijesh Verma and John Zakos

Neural network + fuzzy techniques

Classifier is tested with different set of features for accuracy. With all features only 72.2% of accuracy is obtained. Number of iterations needed in training phase is also large. Fuzzification could improve the accuracy and reduce the number of iterations.

5. Predicting and classification of cancer in digital mammography using soft- computing techniques.

Here propose an automatic procedure for digital mammography based on soft-computing technique, for image interpretation, with increased accuracy and a feature subset selection algorithm that selects the most important features, used by Multilayer

Perceptron neural networks to classify the digital mammography. In order that the structure of the system can be automatically modified, and evolutionary algorithm is introduced.

What is mammogram: [44]

A mammogram is an x-ray picture of the breast. Screening mammograms are used to check for breast cancer in women who have no signs or symptoms of the disease. Diagnostic mammograms are used to check for breast cancer after

a lump or other sign or symptom of the disease has been found.

Results from randomized clinical trials and other studies show that screening mammography can help reduce the number of deaths from breast cancer among women ages 40 to 74.

Main Points:

Breast cancer is a malignant tumor that develops when cells in the breast tissue divide and grow without the normal controls on cell death and cell division.

Although scientists do not know the exact causes of most breast cancer, they do know some of the risk factors that increase the likelihood of a woman developing breast cancer.

Treatments for breast cancer are separated into two main types, local and systematic. Surgery and radiation are examples of local treatments whereas chemotherapy and hormone therapy are examples of systematic therapies.

The main goal of breast cancer detection methods is the best possible selection of patients at risk, this means, the selection of the smallest group with the highest risk developing breast cancer.

Recent advances in multimedia and image processing techniques can be utilized to assist pathologists in this respect propose an automatic procedure for digital mammography based on soft-computing technique, for image interpretation, with increased accuracy.

Fig: Flowchart of the working procedure

In the above stated figure all the processing steps according to the research paper have been summarized.The last step should be furtherly modified into Proposed algorithm,Solution representation,Selection function and Fitness function. In the experimented result The Classification step occurs after feature extraction and selection have been applied. In our experiments the MIAS MiniMammographic Database was used. Each acquired image has a spatial resolution of 1024x1024 pixels. The various types of breast abnormalities, which are visible in mammograms, include calcification, well-defined/circumscribed masses, spiculated masses, ill-defined masses, architectural distortion and asymmetry. Masses and clustered microcalcification often characterize early breast cancer. In the MIAS database there is also a column indicating the severity of abnormality: Benign or Malignant.

6. Modelling Biological Networks Using Soft Computing Techniques

In systems Biology gene regulatory networks have an important role in advance prediction of cancer. By modelling understanding and analysis of these gene regulatory networks dynamics. We may shed light on the mechanism of diseases that occur when these cellular processes are deregulated .Accurate prediction of the behaviour of gene regulatory networks will also speed up in developing personalized medicines.

Motivation for modeling GRN:

To present a synthetic network view of the currently available biological knowledge and to structure it in such a way that it brings to sight relevant properties which may remain hidden without the appropriate model.

To predict dynamic behaviour of the network. These predictions are compared with experimental results. It may allow either confirmation of the model's accuracy or recommend correction of the model.

The complexity of molecular and cellular interactions requires modeling tools that can be used to properly design and interpret biological experiments.

Soft Computing Techniques:

Fuzzy logic

artificial neural networks

evolutionary algorithms (genetic algorithm, genetic programming and evolutionary strategies)

simulated annealing

swarm optimization and probabilistic reasoning are fundamental computing constituents of soft computing

Among the various soft computing constituents, fuzzy logic (FL), artificial neural networks (ANNs) and evolutionary algorithms (EAs) are considered as the core methodologies of soft computing.

Table 7: Hybradized models for Modeling GRNs [43]

Modeling Techniques

Results Obtained

Referrences

Neuro Fuzzy

Reconstruction of partial GRN of yeast

Liu et. Al,2011

Neuro Fuzzy

Extract regulatory relationship & construct GRN

Vineetha et. Al,2010

RNN+Fuzzy

Extracted GRN from Yeast

Maraziotis,et. Al.,2010

Clustering+PSO+RNN

Inferred GRN

Zhang,et.al.,2009

RNN+Fuzzy

Determine regulatory interaction from genes

Datta et. Al.,2009

RNN+GA

Extracted GRN modules

Chiang & chao,2007

Neuro Fuzzy

Reconstructed GRN from microarray data

Jung & Cho,2007

RNN+PSO

Extracted GRN from gene expression profiles

Xu Rui et. Al. 2007

7. Conclusion and Future Enhancement:

Cancer classification,prediction and diagnosis is an emerging research area in the field of Bio-informatics.In this survey various soft-computing methods,data-mining and machine learning based algorithms for gene selection and cancer classification were discussed in detail.And also we have attemted to explain compare and performing of soft-computing methods which are using of cancer classification , prediction and prognosis to detect it in a earlier stage. specifically in a personalized way we identified a number of trends with respect to the types of computational intelligent methods being used and the types of training data being incorporated ,the kinds of endpoint predictions being made ,the types of cancers being studied,and the overall performance of these methods to predict cancer.

In future better neural network techniques can be incorporated with the present research work for less complexity and better learning adaptability.More over ,better neuro fuzzy techniques could also be used to improve the classification rate and accuracy.Better microaaray techniques can also be adapted as well as multiobjective ant-colony approach and genetic algorithmic approach for better prediction of cancer and to enhance the previous techniques.

8. Referrences

http://www.cancer8.com/

http://www.wcrf.org/cancer_facts/5-most-common-cancers.php

http://www.cancer.gov/cancertopics/cancerlibrary/what-is-cancer

http://www.medicalnewstoday.com/info/cancer-oncology/

http://www.wcrf.org/cancer_facts/5-most-common-cancers.php

http://www.scribd.com/doc/9522057/an-overview-of-soft-computing-with-its-techniques-and-application

http://dl.acm.org/citation.cfm?id=1539227

http://www.iconip2012.org/s02.pdf

http://www.biomedcentral.com/1471-2105/6/148

http://news.harvard.edu/gazette/tag/cluster-of-cancer-cells/

http://www.healthcommunities.com/cancer-treatment-and-care/cancer-staging.shtml

http://en.wikipedia.org/wiki/Oncology#Progress_and_research

http://www.cancer.net/patient/All+About+Cancer/Cancer.Net+Feature+Articles/Treatments%2C+Tests%2C+and+Procedures/Understanding+Cancer+Research+Studies%2C+Part+II

K. Anuradha and K.Sankaranarayanan "International Journal of Advances in Engineering & Technology, March 2012" Vol. 3, Issue 1, pp. 84-91

M. E. Futschik, A. Reeve, and N. Kasabov, "Evolving connectionist systems for knowledge discovery from gene expression data of cancer tissue," Artif. Intell. Med., vol. 28, pp. 165-189, 2003

H. Midelfart, A. Lægreid, and J. Komorowski, Classification of Gene Expression Data in an Ontology, vol. 2199. Lecture Notes in Computer Science, Berlin, Germany: Springer-Verlag, 2001, pp. 186-194

M. Banerjee, S. Mitra, and H. Banka, "Evolutionary-rough feature selection in gene expression data," IEEE Trans. Syst., Man, Cybern. C, Appl.

Ahmad M. Sarhan, "Cancer Classification Based on Micro array Gene Expression Data Using DCT and ANN", Journal of Theoretical and Applied Information Technology, Vol. 6, No. 2, pp. 208-216, 2009

Bharathi and Natarajan, "Cancer Classification of Bioinformatics data using ANOVA", International Journal of Computer Theory and Engineering, Vol. 2, No. 3, pp. 369-373, June 2010

Bo Li, Chun-Hou Zheng, De-Shuang Huang, Lei Zhang and Kyungsook Han, ""Gene expression data classification using locally linear discriminant embedding", Computers in Biology and Medicine, Vol. 40, pp. 802-810, 2010

Xiaosheng Wang and Osamu Gotoh, "A Robust Gene Selection Method for Micro array-based Cancer Classification", Journal of Cancer Informatics, Vol. 9, pp. 15-30, 2010

Mallika and Saravanan, "An SVM based Classification Method for Cancer Data using Minimum Micro array Gene Expressions", World Academy of Science, Engineering and Technology, Vol. 62, No. 99, pp. 543-547, 2010

K. Deb and A. Raji Reddy, "Reliable classification of two-class cancer data using evolutionary algorithms," BioSystems, vol. 72, pp. 111-129, 2003.

H. Midelfart, J. Komorowski, K. Nørsett, F. Yadetie, A. K. Sandvik,and A. Lægreid, "Learning rough set classifiers from gene expression and clinical data," Fundamenta Inf., vol. 53, pp. 155- 183, 2002.

F. Chu, W. Xie, and L. Wang, "Gene selection and cancer classification using a fuzzy neural network," in Proc. 2004 Annu. Meet. North Amer. Fuzzy Information Processing Soc. (NAFIPS), vol. 2, pp. 555-559

S. Mitra, "An evolutionary rough partitive clustering," Pattern Recognit. Lett., vol. 25, pp. 1439- 1449, 2004

S. Bicciato,M. Pandin, G. Didon`e, andC.DiBello, "Pattern identification and classification in gene expression data using an autoassociative neural network model," Biotechnol. Bioeng., vol. 81, pp. 594-606, 2003.

http://en.wikipedia.org/wiki/Bioinformatics

www.broadinstitute.org/...2006/.../Classification_and_Clustering.ppt

http://www.ims.nus.edu.sg/Programs/microarray/files/SingDiscV2.pdf

http://cscjournals.org/csc/manuscript/Journals/IJBB/volume5/Issue4/IJBB-133.pdf

An Extensive Survey on Artificial Neural. Network Based Cancer Prediction Using. SOFTCOMPUTING Approach. Manaswini Pradhan, Dr. Ranjit Kumar Sahu

http://ijcta.com/documents/volumes/vol2issue5/ijcta2011020550.pdf

http://www.iula.upf.edu/materials/040701wanner.pdf

Sami Halawani and Rafat Parveen,International Journal of Research and Reviews in Computer Science (IJRRCS), Vol. 3, No. 1, February 2012, ISSN: 2079-2557

http://www.softcomputing.es/metaspace/portal/7/274

http://www.medwelljournals.com/abstract/?doi=ijscomp.2009.201.207

http://www.scribd.com/chris_cao_11/d/82513248-A-Proposed-Model-of-SoftComputing-in-Diagnosing-Diseases-and-Prescribing-Herbal-Prescriptions-by-Oriental-Medicine

www.la-press.com/redirect_file.php?...Soft-Computing-Cancer-Classification

Megha Gupta,Naveen Agarwal "Classification Techniques Analysis", NCCI 2010 -National Conference on Computational Instrumentation

http://www.mrc-lmb.cam.ac.uk/genomes/madanm/microarray/chapter-final.pdf

http://www.ijcaonline.org/volume19/number5/pxc3873087.pdf

www.sciacademypublisher.com/journals/index.php/IJRRCS/.../581

http://metronu.ulb.ac.be/imacs/papers/T3-I-114-0597.pdf

Writing Services

Essay Writing
Service

Find out how the very best essay writing service can help you accomplish more and achieve higher marks today.

Assignment Writing Service

From complicated assignments to tricky tasks, our experts can tackle virtually any question thrown at them.

Dissertation Writing Service

A dissertation (also known as a thesis or research project) is probably the most important piece of work for any student! From full dissertations to individual chapters, we’re on hand to support you.

Coursework Writing Service

Our expert qualified writers can help you get your coursework right first time, every time.

Dissertation Proposal Service

The first step to completing a dissertation is to create a proposal that talks about what you wish to do. Our experts can design suitable methodologies - perfect to help you get started with a dissertation.

Report Writing
Service

Reports for any audience. Perfectly structured, professionally written, and tailored to suit your exact requirements.

Essay Skeleton Answer Service

If you’re just looking for some help to get started on an essay, our outline service provides you with a perfect essay plan.

Marking & Proofreading Service

Not sure if your work is hitting the mark? Struggling to get feedback from your lecturer? Our premium marking service was created just for you - get the feedback you deserve now.

Exam Revision
Service

Exams can be one of the most stressful experiences you’ll ever have! Revision is key, and we’re here to help. With custom created revision notes and exam answers, you’ll never feel underprepared again.