ARTIFICIAL INTELLIGENCE.

BY

MOUNISHA R

SRUJANA K N… &

GUDIANCE OF

Mr. K R DASEGOWDA

DEFINITION

Artificial -It made or produced by human beings rather than occurring naturally, especially as a copy of something natural.

Intelligence- -It has been defined in many different ways

including logic, abstract thought, understanding, self-awareness, communication, learning, having emotional knowledge, retaining, planning, and problem solving.

DEFINITION

Artificial intelligence (AI) is technology and a branch of computer science that studies and develops intelligent machines and software.

Major AI researchers and textbooks define the field as "the study and design of intelligent agents",where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success.

John McCarthy, who coined the term in 1955,defines it as "the science and engineering of making intelligent machines"

APPLICATIONS OF AI..

Medical diagnosis Stock trading Robot control Hearing aids Remote sensing Scientific discovery Toys

BIOINFORMATICS

It is an interdisciplinary field that develops & IMPROVES ON METHODS FOR STORING,RETRIVING,ORGANIZING & ANALYSING BIOLOGICAL DATA.

AI & BIOINFORMATICS

During last decades methods and tools of AI have played a central role in research in bioinformatics and computational molecular biology.

Protein structure prediction Sequence analysis and alignment Motif and pattern discovery Gene expression analysis from microarray Genomics & Proteomics Data visualization Biological net work analysis.

Cancer -it is known medically as a malignant neoplasm.

It is a broad group of diseases involving unregulated cell growth.

Cells divide and grow uncontrollably, forming malignant tumors, and invading nearby parts of the body.

The cancer may also spread to more distant parts of the body through the lymphatic system or bloodstream.

There are over 200 different known cancers that affect humans.

Machine learning is not new to cancer research. Artificial neural networks (ANNs) and decision trees

(DTs) have been used in cancer detection and diagnosis for nearly 20 years (Simes 1985; Maclin et al.1991; Ciccheti 1992).

Today machine learning methods are being used in a wide range of applications ranging from detecting and classifying tumors via X-ray and CRT images (Petricoin and Liotta 2004;Bocchi et al. 2004) to the classification of malignancies from proteomic and genomic (microarray)assays (Zhou et al. 2004; Dettling 2004; Wang et al. 2005). According to the latest PubMed statistics,

more than 1500 papers have been published on the subject of machine learning and cancer.

CANCER DIAGNOSIS…MACHINE LEARNING…

WHAT IS MACHINE LEARNING???

Machine learning is a branch of artificial intelligence research that employs avariety of statistical, probabilistic and optimization tools to “learn” from past examples and to then use that prior training to classify new data, identify new patterns or predict novel trends (Mitchell 1997).

Machine learning, like statistics, is used to analyze and interpret data.

Unlike statistics,though, machine learning methods can employ Boolean logic (AND, OR, NOT), absolute conditionality (IF, THEN, ELSE), conditional probabilities (the probability of X given Y) and unconventional optimization strategies to model data or classify patterns.

TOOLS

Search and optimization -Many problems in AI can be solved in theory by intelligently searching through many possible solutions: Reasoning can be reduced to performing a search.

Logic -is used for knowledge representation and problem solving, but it can be applied to other problems as well.Eg.. non-monotonic logics

TOOLS…

Probabilistic methods for uncertain reasoning -Many problems in AI (in reasoning, planning, learning, perception and robotics) require the agent to operate with incomplete or uncertain information. AI researchers have devised a number of powerful tools to solve these problems using methods from probability theory and economics.

Eg.. Bayesian networks

TOOLS…

Neural networks -The study of artificial neural networks

began in the decade before the field AI research was founded, in the work of Walter Pitts and Warren McCullough. Other important early researchers were Frank Rosenblatt, who invented the perceptron and Paul Werbos who developed the backpropagation algorithm.[

TOOLS…

Hamiltonian path/TSP( Traveling Salesman Problem (TSP)) -The SBH problem can be approached as a TSP(Blasewicz,Formanowicz, Kasprzak, Markiewicz, & Welglarz, 1999) onian path/TSP.

EPP ( Eulerian path problem). -Pevzner (Pevzner, 1989) proposed a

different approach, which reduces the SBH problem to the EPP, leading to a simple linear-time algorithm for sequence reconstruction.

TOOLS…

Positional SBH (PSBH). enhancements of SBH based on adding location information to

the spectrum (Adleman, 1998; Broude, Sano, Smith, & Cantor, 1994;Gusfield, Karp, Wang, & Stelling, 1998; Hannenhalli, Pevzner,Lewis, & Skiena, 1996; Shamir & Tsur, 2001)

NOVEL METHOD PROCESSED TASK…

A. BIOINFORMATICS TECHNIQUES 1) FASTA: Compares a query string against a

single text string when searching the whole database for matching for given query, that comparing done by using the FASTA algorithm to every string in the database.

2) CLUSTALW: it is first technique for checkup whether the patient has malignant mutation for cancer or no.

CLUSTALW help in detection the gene mutation which increasing probability of cancer according to number of genes that are related with cancer (such as brca1 , brca2 which cause the breast cancer), in CLUSTALW must be knowing the normal sequence of each gene.

B. BACK-PROPAGATION ALGORITHM

The results which obtained in previous approach (bioinformatics technique), shows there is malignant mutations or benign (normal) in the patient's genes, when there is malignant mutations must diagnosing those mutations related to a certain disease.

The classifying of mutations (e.g. which are related to breast cancer) needs another approach focus on training back-propagation, which most commonly used in medical research.

mutations are related with gene of BRCA1 or BRCA2, so will use MATLAB R2010a on PC type Core i3 for neural network toolbox because it contains various functions can use for implementing feed forward neural networks.

ANN can be trained for tasks such as function approximation (regression) or pattern recognition (discriminate analysis).

The novel method will be used a feed forward back-propagation network as popular model in neural network,which hasn't feedback connections but the errors are back propagated during training.

Training the feed forward BP algorithm used to create the best neural network model, this algorithm is divided into three main parts which are feed forward, error calculation and the last part is updating the weight, training algorithm presented below

1) Each input unit (Xi, i = 1, 2, 3 …, n) receive input

signal xi, and sent the signal to all unit in their above layer (hidden units).

2) Each hidden layer unit (Zj, j = 1, 2, 3 …, p) sum the input weight signal,

Zinj=V0j+X(i-1-n) X1 Vij (1) with using its activation function to get

output signal value Zj=f(z-inj) (2)and sent that signal to all units at its above

layer(output units).

3) Each unit output (Yk, k = 1, 2, 3 …, m) sum input weight signal,

y_in(k)=W0k+x(j=1)-(p) ZjWjK (3) with using its activation function to get

output signal value, y(k)=f(y-in(k)) (4) Feed forward process is the first part in back-

propagation algorithm, which is used to send input signal into above layer and the next step is to do error calculation.

4) Each output unit (yk, k = 1, 2, 3 …, m) accept one pair target pattern with input training pattern, count an error,

delta(k)=(t(k)-(y(k))f ‘(y-in(k)) (5) count weight correction (used in update

weight wjk), diff(Wjk)=adelta(k)zj (6) count bias correction (used in update bias

value w0,k) diff(W0k)=adeltaK (7) and sent to unit below it.

5) Each hidden unit (Zj , j = 1, 2, 3 …, p) sum delta input (from its above layer units),

Delta_inj=X((k=1)_(m))delta(k)Wjk (8) multiply with activation output to count an

error,Delta(j)=delta_injf ‘(z-inj) (9) count weight error (used for update vij); deltha(Vij)=adelta(j)X(i) (10) and count its bias correction (used for update

v0j); deltaV0j=a delta(j) (11)

EXPERIMENTAL RESULTS..A) FRIST APPROACH.

B)

B. SECOND APPROACH

Shows training result of BP algorithm onto the list of genes mutations (BRCA1 & BRCA2) which caused breast cancer

reveals plots of the important three elements of this training

(A) shows performance.

B) reveals training state.

C) shows regression.

(A) the result of test BP algorithm when there aren't mutations,

while (B) when there is certain mutation

CONCLUSIONS

1.The proposed novel method is first prediction method gives strong results, because it not only based on malignant mutations of genes which caused the disease, but also base on their proteins.

2. This novel method suggested a general prediction method based on mutational in genes caused the disease, i.e. can implement this novel method for any disease when the mutations of its gene which caused the disease are known.

3. Offers an automatic, cost effective and friendly diagnosis system for detecting malignant mutation of breast cancer as shown in Table 1, i.e. can use by any researcher or patient who needed to test malignant mutations at genes which caused breast cancer.

4. The model of classification malignant mutations for breast cancer was developed successfully using feedforward back-propagation neural network which has only mean square error 0.0000001.

REFERENCES [1] Ir CATH Tee and Ali H. Gazala, A Novel

Breast Cancer Prediction System. © IEEE 978-1-61284-922-5/11 (2011), 621-625.

[2] Shweta Kharya, USING DATA MINING TECHNIQUES FOR DIAGNOSIS AND PROGNOSIS OF CANCER DISEASE. IJCSEIT Vol.2, No.2 (2012), 55-66.

[3] Fabio Vandin, Eli Upfal, and Benjamin J. Raphael, Algorithms and Genome Sequencing: Identifying Driver Pathways in Cancer, © IEEE,0018-9162/12 (2012), 39-46.

[4] Jean-Michel Claverie and Cedric Notredame., Bioinformatics for Dummies 2nd Editition. Wiley publishing Inc, (2007).

THANK YOU….