AGGRESSIVE ADVENT FOR CONSTITUTING DECISION TREES WITH VARIOUS

CLASSIFICATION

Abstract:

Classification techniques have been used extensively by many businesses and

organizations to retrieve valuable information from large databases and develop

effective knowledge-based decision models. This is one of the most common tasks in data

mining, which involves developing procedures for assigning objects to a predefined set of

classes. Main classification methods existing today include decision trees, neural

networks, logistic regression, and nearest neighbors.

Most decision tree classifiers are designed to classify the data with categorical

or Boolean class labels. Unfortunately, many practical classification problems concern

data with class labels that are naturally organized as a hierarchical structure, such as

test scores. In the hierarchy, the ranges in the upper levels are less specific but easier

to predict, while the ranges in the lower levels are more specific but harder to predict.

To build a decision tree from this kind of data, we must consider how to classify data so

that the class label can be as specific as possible while also ensuring the highest possible

accuracy of the prediction. To the best of our knowledge, no previous research has

considered the induction of decision trees from data with hierarchical class labels. This

paper proposes a novel classification algorithm for learning decision tree classifiers from

data with hierarchical class labels. Empirical results show that the proposed method is

efficient and effective in both prediction accuracy and prediction specificity.

Modules:

 Authentication
 Create Training Set for Gun Source
 Insert
 Update
 Delete

 Classifying Training Set for Gun Source

 Classifying Training Set for other Database

 Models by Category

 Purchase
Modules Description:

 Authentication

Authentication is the act of establishing or confirming something (or

someone) as authentic, that is, that claims made by or about the subject are true.

This might involve confirming the identity of a person, tracing the origins of an

artifact, ensuring that a product is what it’s packaging and labeling claims to be,

or assuring that a computer program is a trusted one. One familiar use of

authentication and authorization is access control. A computer system supposed

to be used only by those authorized must attempt to detect and exclude the

unauthorized. Access to it is therefore usually controlled by insisting on an

authentication procedure to establish with some established degree of confidence

the identity of the user, thence granting those privileges as may be authorized to

that identity.

In computer security, a login or logon (also called logging in or on and

signing in or on) is the process by which individual access to a computer system is

controlled by identification of the user using credentials provided by the user. A

user can log in to a system to obtain access and can then log out or log off

(perform a logout / logoff) when the access is no longer needed. To log out is to

close off one's access to a computer system after having previously logged in.
  User Authentication:

User Login:
In the default setup login block is always displayed unless a user is logged

in. This may not always be desirable. Login (logging or signing in, also log on) is the

process by which individual access to a computer system is controlled by

identification of the user using credentials provided by the user. A user can log in

to a system to obtain access, and then log out when the access is no longer

needed.

Registration:

User Registration is a one-time identification procedure that enables us to

obtain information necessary for sending remittances for persons or

organizations that do not maintain an account with gun source. This procedure has

been formulated to counter terrorism and money laundering risks. Once a person

or organization is registered, a remitter number (called User Registration

Identity (URI)) is assigned that is required to be quoted by the remitter for all

remittances. Persons or organizations to which URI has been allotted are called

Registered Users (of Remittance Services of New York branch)

 Create Training Set for Gun Source

created in the backend. This gun source training set is categorized into

groups, name, country, rate, firing range, load capacity, manufacturing date.

 Insert
Insertion is used to further inclusion of data into the gun source with the

corresponding groups.
  Update
After insertion the update module is used to alter the incorrect data

which is inserted into the training set.

 Delete
Deletion module is used to remove the unwanted data from the training set

with respect to their category.

 Classifying Training Set for Gun Source

 Label Based Classification

Continuous data discretization, another area related to this project, has

recently received much research attention. The simplest discretization

method, equal width, merely divides the range of observed values into a pre-

specified number of equal, non overlapped intervals. This method is vulnerable

to outliers that may drastically skew the results. Another simple method,

equal depth, divides the range of the data into a pre-specified number of

intervals, which contains roughly the same number of cases. Another well-

known method, MCCs, divides the range of the data into k intervals by finding

the partition boundaries that produce the greatest contrast according to a

given contrast function. The clustering method or the entropy method can be

used to perform the same task. These popular data discretization methods

have been commonly used in the preprocessing phase when constructing DTs

with continuous labels and have also been applied in various areas, such as data

stream software engineering Web application detection and others. As

discussed in Section 1, the weakness of the preprocessing approach using a

discretization method is that it is inherently a static approach, which

essentially ignores the likelihood that the data distributions could be

dynamically discretizes data at each node in the tree induction process. As

shown in the last section, the proposed algorithm outperforms the

preprocessing approach, the regression tree approach, and several non tree-

based algorithms.

 Analyzing Mean, Median, Mode and Range

This classification can also produce the mean, median, and other statistics

for each leaf node as part of its output. In other words, the proposed method is

also capable of producing numerical predictions as a regression tree algorithm

does.

 Purchase
A quotation is a purchase order in a ‘Draft’ state. Then the order has to be confirmed by
the user, the state switch to ‘Confirmed’. Then the supplier must confirm the order to
change the state to ‘Approved’. When the purchase order is paid and received, the state
becomes ‘Done’. If a cancel action occurs in the invoice or in the reception of goods, the
state becomes in exception.

Database Design

Table:1

Gun Data:
Name Type
Sno int
Groups varchar
Name varchar
Country varchar
Rate int
Firing_Range int
Load_Capacity int
Mfg-Date Date
 Table:2

User:
Name Type
Name varchar
Password varchar

Data Flow Diagram

Architectural Diagram:
 Admin

User/Admin
Registration Purchase

Classification

Database

Other DB