Tree-Based Mining for
Discovering Patterns of Human Interaction in Meetings
ABSTRACT:
Discovering semantic knowledge is
significant for understanding and interpreting how people interact in a meeting
discussion. In this paper, we propose a mining method to extract frequent
patterns of human interaction based on the captured content of face-to-face
meetings. Human interactions, such as proposing an idea, giving comments, and
expressing a positive opinion, indicate user intention toward a topic or role
in a discussion. Human interaction flow in a discussion session is represented
as a tree. Treebased interaction mining algorithms are designed to analyze the
structures of the trees and to extract interaction flow patterns. The experimental
results show that we can successfully extract several interesting patterns that
are useful for the interpretation of human behavior in meeting discussions,
such as determining frequent interactions, typical interaction flows, and
relationships between different types of interactions.
SCOPE
OF THE PROJECT:
Data mining, which is a
powerful method of discovering new knowledge, has been widely adopted in many
fields, such as bioinformatics, marketing, and security. In this study, we
investigate data mining techniques to detect and analyze frequent interaction patterns;
we hope to discover various types of new knowledge on interactions.
Human interaction flow
in a discussion session is represented as a tree. Inspired by tree-based
mining, we designed interaction tree pattern mining algorithms to analyze tree
structures and extract interaction flow patterns. An interaction flow that
appears frequently reveals relationships between different types of
interactions. Mining human interactions
is important for accessing and understanding meeting content.
First, the mining
results can be used for indexing meeting semantics, also existing meeting
capture systems could use this technique as a smarter indexing tool to search
and access particular semantics of the meetings.
Second, the extracted
patterns are useful for interpreting human interaction in meetings. Cognitive
science researchers could use them as domain knowledge for further analysis of
human interaction. Moreover, the discovered patterns can be utilized to
evaluate whether a meeting discussion is efficient and to compare two meeting
discussions using interaction flow as a key feature.
EXISTING
SYSTEM:
Existing meeting
capture systems could use this technique as a smarter indexing tool to search
and access only particular semantics of the meetings. This work focuses on only
lower level knowledge about human interaction. The process didn’t have any key
features. So it not compares two meeting discussions. The process only gets the
positive and negative comments from the users. So further process to be discussed
only by the admin. So complex of the topic should not be identified easily.
Sometimes this process not provides the semantic information and produces
redundant data.
DISADVANTAGES
OF EXISTING SYSTEM:
·
Complex to handle.
·
Identification of negative points in
topic is very tough.
·
It increases the repeated data.
PROPOSED
SYSTEM:
We propose a mining method to extract
frequent patterns of human interaction based on the captured content of
face-to-face meetings. The work focuses on discovering higher level knowledge
about human interaction. In our proposed system T-pattern technique is used to
discover hidden time patterns in human behavior. We conduct analysis on human
interaction in meetings and address the problem of discovering interaction
patterns from the perspective of data mining. It extracts simultaneously
occurring patterns of primitive actions such as gaze and speech. We discover
patterns of interaction flow from the perspective of tree-based mining rather
than using simple statistics of frequency. The main features of the process are
user can also provides the idea about the topic. So admin can easily solve the
problem based on users needed.
ADVANTAGES
OF PROPOSED SYSTEM:
·
Easy to handle.
·
It extracts data simultaneously.
·
Problems occurred in the process is
easily solved by the admin.
ALGORITHM:
Stochastic
Techniques: The visualization systems aim at
detecting and visualizing human interactions in meetings, while our work
focuses on discovering higher level knowledge about human interaction. There
have been several works done in discovering human behavior patterns by using
stochastic techniques. A Stochastic Techniques is a collection of random
variables; this is often used to represent the evolution of some random value,
or system, over time. This is the probabilistic counterpart to a deterministic
process. Instead of describing a process which can only evolve in one way, in a
stochastic or random process there is some indeterminacy: even if the initial
condition is known, there are several directions in which the process may
evolve.
Algorithms
for Pattern Discovery: With the representation model and
annotated interaction Flows, we generate a tree for each interaction flow and
thus build a tree data set. For the purpose of pattern discovery, we first
provide the definitions of a pattern and support for determining patterns. In
developing our frequent sub tree discovery algorithm, we decided to follow the
structure of the algorithm for pattern discovery used for finding frequent item
sets, because it achieves the most effective pruning compared with other
algorithms.
Tree
pattern mining algorithms: To analyze tree structures and
extract interaction flow patterns. An interaction flow that appears frequently
reveals relationships between different types of interactions. Mining human
interactions is important for accessing and understanding meeting content. A
tree-based mining method is used for discovering frequent patterns of human
interaction in meeting discussions. The mining results would be useful for
summarization, indexing, and comparison of meeting records. They also can be
used for interpretation of human interaction in meetings.
MODULES:
·
Interaction Flow
Construction Module
·
Expressing Opinion
Module
·
Analysis Module
·
Session Tree Module
·
Graph Creation Module
·
Final Tree Module
MODULES
DESCRIPTION:
Interaction Flow Construction
This
is the first module, where we create an environment for interaction and flow
construction. Based on the interaction defined and recognized, we now describe the
notion of interaction flow and its construction. An interaction flow is a list
of all interactions in a discussion session with triggering relationship
between them. We create an application based on it. In the application we have
authentication process. For authentication process we build Login process,
which is used for enter the process and register the new users. This process is
produced for both users and admin process. All users details can be stored in
the database elements. So, unwanted users cannot easily access this Login
process. Homepage is used for the login. Registration process requires the
Name, Details, address, phone number and email id.
EXPRESSING OPINION MODULE
Comments display
process is the process of displaying the comments in the user and admin view.
But users view is different from the admin view. In user view, the user can view the comments
and also enter the comment elements. This comment display is classified by four
meeting display in our project are
·
Home page
·
PC Purchase
·
Trip Planning
·
Soccer
·
Job
These processes get the details about
the users and get the idea for the topics and also negative and positive
comments. Users can view the positive and negative comments of other users are
used. So currents users can get the knowledge about that particular topic and
also they correct the doubts in their topics.
ANALYSIS MODULE
Admin process is the
process that maintains the process and users details. The Main details of the
users can not viewed by users, that type of process is maintained by the admin
process. Admin process can view the process as tree based structure. So the
admin can easily identified by the human interactions. Human interaction
process can be viewed by admin by the following structure based elements are
various elements which are described in the following modules.
SESSION TREE MODULE:
Session
tree process is the process that is used to avoid the repeated data in session
database. And the process provides the tree based structure. So the admin
identified the main problem in the particular topic. All process such as PC
purchase, Trip planning, Soccer and job can be viewed by the admin process.
GRAPH CREATION MODULE:
Graph
is another process for the admin view. This process is also related to the
session tree concept. But is process only provides the separate graph view. So
the admin can easily maintain the process.
FINAL TREE MODULE:
Final Tree is the process that is fully related
to the session tree and graph. This process provides the full view of the user
interaction. So details of all users can be easily identified by the admin
process.
SYSTEM
REQUIREMENTS:
HARDWARE
REQUIREMENTS:
•
System : Pentium IV 2.4 GHz.
•
Hard
Disk : 40 GB.
•
Floppy
Drive : 1.44 Mb.
•
Monitor : 15 VGA Colour.
•
Mouse : Logitech.
•
Ram : 512 Mb.
SOFTWARE
REQUIREMENTS:
•
Operating system : - Windows XP.
•
Coding Language : ASP.NET, C#.Net.
•
Data Base : SQL Server 2008
REFERENCE:
Zhiwen Yu, Senior Member, IEEE, Zhiyong
Yu, Xingshe Zhou, Member, IEEE,
Christian Becker, Member, IEEE, and
Yuichi Nakamura, Member, IEEE, “Tree-Based Mining for Discovering Patterns of
Human Interaction in Meetings”, IEEE
TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 24, NO. 4, APRIL 2012.