Neural Network Intelligence In Medical Application Gene Prediction

CONTENTS
Introduction
Rioinformatie's
Rielogical Rackground
DNA
Concept of Gene
Computer Science and Gene
Soft Computing Methods
Soft Computing Techniques for Gene Prediction
Soft Computing in Cancer Biology
Microarray Technology
Principal Component Analysis
Neural Network
Neural Network Architecture
Objectives of the Research Work
Outline of the Report
LITERATURE SURVEY
Introduction
Review on Classification of Gene Prediction Techniques
SVM Classifier for miRNA Gene Prediction
SVM based Bayesian protein-protein interaction
Computational method for prediction of genomes
Hidden Markov Model (HMM) used in DNA sequence
Web Server programs on prediction of genes
Computational Methodologies
Gene Prediction algorithm based on Machine Learning Techniques
Gene Prediction using Digital Signal Processing
Phenotypic Gene Prediction
Experimental Technique for Gene Prediction
ab initio model for Gene Prediction
ORS
Neural Network
Other Gene Prediction Methodology
Supplementary Research Conducted
Support Vector Mochote
Gene Ontology
Homology
Hidden Markov Model (IMM)
Different Software programs for Gene Prediction
Other Training Methodologies
Other Machine Learning Techniques
Digital Signal Processing
Other techniques
Conclusion
ANN GENE CLASSIFIER: PPCA-EP TECHNIQUE
Introduction
Background Information
Cancer Classification and the Challenges
The Challenges
Public Repository of Gene Expression Data
ANN and Gene Classification
Classification Technique for Microarray Gene Expression Data
Dimensionality Reduction using PPCA
Enhancement of Feed Forward ANNs
Gene Expession Data Classification
Classification of Microarray Gene Expression Data using Enhanced Classifier
Training Phase: Minimization of Error by BF algorithm
Testing Phase: Classification of Microarray Gem Sequence
Conclusion
4. DOMINANT GENE PREDICTOR: GA-ANN TECHNIQUE
Introduction
Genetic Algorithm
Dominant gene prediction using Genetic algorithm
Preprocess for dominant gene prediction
Generation of Training Data
Selection of Optimal Solution
Dimensionality reduction by PPCA
Draming phase Training through Feed Forward ANN
Mromization of Eve by BP algorithm
Tin Phave Geners Algorithm Based domemsant gew prediction of AML ALL
Clevation of Promotomes
Crecemeer and Morton
Conclusion
CANCER PREDICTION: ANN CLASSIFIER-DOMINANT
GENE PREDICTOR
Introduction
Dominant Gene prediction using PPCA and GA-ANN Classifier
Preprocess for dominant gene prediction
Training through Feed Forward ANN
Minimization of Error by BP algorithm
Genetic Algorithm based dominant gene prediction of cancer diagnosis
Conclusion
RESULTS AND DISCUSSION
Introduction
Results of the proposed classification technique on ALL/AML dataset
Results of the proposed gene prediction technique on ALL/AML dataset
Cancer Prediction in CNS tumor, Colon tumor, Lung tumor and Diffuse Large B-Cell datasets
Lymphoma
Discussion and Conclusion
CONCLUSION
Introduction
Shortcomings of Existing Methods
Advantages of New Method
Future Research Direction and Suggestions