Data dimension reduction
-
Upload
pawan-kurmi -
Category
Data & Analytics
-
view
23 -
download
0
Transcript of Data dimension reduction
DIMENSION REDUCTION USING ROUGH SET IN PATIENT CARE
SYSTEM
Guide By
Dr. Neelu Khare Pawan Kumar Kurmi14MCA0103
INTRODUCTION The study of Web-based support systems (WSS) aims at developing and transforming
existing systems to support and extend various human activities onto the Web. The
motivation of WSS research came from the realization of the Web as a common
platform, medium, and interface in supporting and assisting activities like managing,
planning, searching, and decision making in different fields. An important area of
WSS is Web-based decision support systems (WDSS) that provide assistance for
decision making in various. The WMDSS have become a valuable aid for medical
practitioners in making effective decisions for selecting a course of action in medical
diagnosis and treatment. Komkhao et al.view the WMDSS from the viewpoint of a
recommender system where suitable decision recommendations are being made by the
system. In any case, the WMDSS serve as a platform for integrating evidence-based
medicine into effective and efficient care delivery. There are challenges in designing,
developing, and deploying WMDSS.
.
SCOPE OF THE PROJECT
In this project , the game-theoretic rough set (GTRS) model is a recent development
in rough sets that can be used to determine the three rough set regions in the
probabilistic rough sets framework by determining pair of thresholds. The three
regions are used to obtain three-way decision rules in the form of acceptance,
rejection, and deferment rules. In this paper we extend the GTRS model to analyze
uncertainty involved in medical decision making. Experimental results with a
GTRS-based approach on different health care datasets suggest that the approach
may improve the overall quality of decision making in the medical field, as well as
other fields. It is hoped that the incorporation of a GTRS component in WMDSS
will enrich and enhance its decision-making capabilities.
PROBLEM STATEMENT
In this existing system correct decisions are confidently made for majority of the
objects. i.e., no additional information and forced two ways certain decisions, the
average accuracies are 94.89% and 94.72% for the PID datasets, respectively. These
results are dynamically changed promising when compared with some of the
proposed results. For instance, an information gain-based approach and Fuzzy C-
Means were reported to have accuracies of 95.9% and83.7%, respectively, for the
dataset.
EXISTING SYSTEM
Existing System
These results are dynamically changed promising when compared with some of the
proposed results. For instance, an information gain-based approach and Fuzzy C-
Means were reported to have accuracies of 95.9% and83.7%, respectively, for the
TD dataset.
PROJECT IMPLEMENTATION
Modules:
User
•User Authentication
•Patient Uploading Details
•View Medical Report
Admin
•Admin Authentication
•View Details
Doctor
•Admin Authentication
•View Details
•Decision making
MODULE DESCRIPTION & DIAGRAMS
USER
Authentication
Registration
If you are the new user going to login into the application then you have to
register first by providing necessary details. After successful completion of sign up
process, the user has to login into the application by providing username and exact
password.
User
Provide Details to Register
DB
Login
The user has to provide exact username and password which was provided at the
time of registration, if login success means it will take up to main page else it will
remain in the login page itself.
LOGIN
CHECK
STATUS
Proceed To next stage
Hierarchy
DB
Patient Uploading Details
After complete the login, Patient uploading the medical details and report to the
doctor .Doctor will update the corresponding details to patient.
Patient
Upload details
Database
Send to doctor
View Medical Report
After complete the uploading process, patient login and get the medical report from
the doctor. Patient report stored in database.
DatabaseDoctor updating the patient report
Patient view the patient report
ADMIN
Authentication
The user has to provide exact username and password which was provided at the
time
of registration, if login success means it will take up to main page else it will
remain
in the login page itself.
LOGIN
CHECK
STATUS
Proceed to next stage
Hierarchy
DB
Admin view the reportDatabase
Admin Allocate the Doctor to patient
View Details After complete the Admin login, Admin view all the medical report from the database. And also allocating the doctor to patient.
Doctor:
Authentication
The user has to provide exact username and password which was provided at
the time of registration, if login success means it will take up to main page else it
will remain in the login page itself.
LOGIN
CHECK
STATUS
Proceed to next stage
Hierarchy
DB
View Details After complete the Admin login, Admin view all the medical report from the database. And also allocating the doctor to patient.
Admin view the reportDatabase
Admin Allocate the Doctor to patient
Decision making
Patient details or medical report generate the decision making process .
In this process calculate the report as positive, negative and pending and
stored in database.
Patient
Generate the decision making
process
Database
Patient Details
GIVEN INPUT AND EXPECTED OUTPUT:
1. USER
Authentication
Input: Provide username and password to get permission for access.
Output: Became authenticated person to request and process the request.
Patient Uploading Details
Input: patient uploading the report
Output: Doctor view the patient details
View Medical Report
Input: patient view the updated details
Output: it will display the patient medical details
2. ADMIN
Authentication
Input: Provide username and password to get permission for access.
Output: Became authenticated person to request and process the request.
View Details
Input: Admin allocate the doctor to patient
Output: Doctor gets the message
3. DOCTOR
Admin Authentication
Input: Provide username and password to get permission for access.
Output: Became authenticated person to request and process the request.
View Details
Input: Doctor view the details
Output: it will display the patient details
Decision making
Input: Check the patient details
Output: it will display the positive, negative and pending details
TECHNIQUE USED OR ALGORITHM USED:
Three way decision making methods
In this paper, we extend the GTRS model to analyze uncertainty
involved in medical decision making. Experimental results with a GTRS-based
approach on different health care datasets suggest that the approach may improve the
overall quality of decision making in the medical field, as well as other fields.
The Algorithm
The Algorithm Steps
In the Three way decision making methods process is as follows:
Step 1: Upload Patient Details (usually at random)
Step 2: Until "done“
Knowledge Management
Knowledge Discovery
Control Facilities
Three way rule database
Step 3: Repeat
SYSTEM ARCHITECTURE:
Architecture diagram shows the relationship between different components
of system. This diagram is very important to understand the overall concept of
system. Architecture diagram is a diagram of a system, in which the principal parts or
functions are represented by blocks connected by lines that show the relationships of
the blocks. They are heavily used in the engineering world in hardware
design, electronic design, software design, and process flow diagrams.
USER UPLOAD
THE DETAILSADMIN ALLOCATE THE DOCTOR
DOCTOR VIEW THE REPORT
DECISION MAKING
DATABASE
USER RETRIW
THE REPORT
FUTURE ENHANCEMENT
Description
Particularly, the option of deferment decisions is added in this approach that
provides the flexibility to further examine and investigate the uncertain and
doubtful cases. The game-theoretic rough set (GTRS) model is a recent
development in rough sets that can be used to determine the three rough set regions
in the probabilistic rough sets framework by determining pair of thresholds. The
three regions are used to obtain three-way decision rules in the form of acceptance,
rejection, and deferment rules.
USER UPLODING DETAILS
ALLOCATE
DOCTOR
ADMIN VERIFICATION
DOCTOR DECISION MAKING
DATABASE
Module Diagram:
GIVEN INPUT AND EXPECTED OUTPUT
Input: Admin allocate the doctor to patient.
Output: It will give the exact decision report.
ADVANTANGES
Which is used to send exact doctor and secure purpose.
We can give clear output.
APPLICATIONS
Online web based Medical Application
CONCLUSION
The uncertainty analysis of decision making sets up the motivation for analyzing
different decision-making aspects with GTRS, such as, the risks, errors, costs, and
benefits associated with medical decision making. Different competitive or
cooperative games may be setup to determine cost effective and balanced thresholds
based on these aspects.
REFERENCES OR BIBLIOGRAPHY:
[1] S. Al-Harbi and V. Rayward-Smith, “Adapting k-means for supervisedclustering,” Appl. Intell., vol. 24,
no. 3, pp. 219–226, 2006.
[2] F. Amasyali and S. Albayrak, “Fuzzy c-means clustering on medicaldiagnostic systems,” in Proc. 12th
Int. Turkish Symp. Artif. Intell.Neural Netw., 2003. [online] Availible at
http://www.ce.yildiz.edu.tr/mygetfile.php?id=269.
[3] N. Azam and J. T. Yao, “Multiple criteria decision analysis with gametheoreticrough sets,” in Proc. 7th
Int. Conf. Rough Sets Knowl. Techonol.,2012, pp. 399–408.
[4] N. Azam and J. T. Yao, “Game-theoretic rough sets for feature selection,”in Rough Sets and Intelligent
Systems—Professor Zdzislaw Pawlak inMemoriam, vol. 44. Berlin, Germany: Springer, 2013, pp. 61–78.
[5] N. Azam and J. T. Yao, “Analyzing uncertainties of probabilistic roughset regions with game-theoretic
rough sets,” Int. J. Approx. Reason.,vol. 55, no. 1, pp. 142–155, 2014.
[6] K. Bache and M. Lichman. (2013). UCI machine learning repository.[Online]. Available:
http://archive.ics.uci.edu/ml
[7] Y. Baram, “Partial classification: The benefit of deferred decision,” IEEETrans. Pattern Anal. Mach.
Intell., vol. 20, no. 8, pp. 769–776, Aug. 1998.
[8] E. S. Berner and J. J. McGowan, “Use of diagnostic decision supportsystems in medical education,”
Methods Inform. Med., vol. 49, no. 4,pp. 412–417, 2012.
[9] H. K. Bhargava, D. J. Power, and D. Sun, “Progress in web-based decisionsupport
technologies,” Decision Support Syst., vol. 43, no. 4, pp. 1083–1095, 2007.
[10] Z. Bisoffi, H. Tinto, B. S. Sirima, F. Gobbi, A. Angheben, D. Buonfrate,and J. Van den
Ende, “Should malaria treatment be guided by a pointof care rapid test? A threshold approach to
malaria management in ruralBurkina Faso,” PLoS One, vol. 8, p. e58019, 2013.
[11] B. Chandra and V. Paul, “A robust algorithm for classification using decisiontrees,” in Proc.
IEEE Conf. Cybern. Intell. Syst., 2006, pp. 1–5.
[12] P. C. Chang, C. Y. Fan, and W. Y. Dzan, “A CBR-based fuzzy decisiontree approach for
database classification,” Expert Syst. Appl., vol. 37, no.1, pp. 214–225, 2010.
[13] X. F. Deng and Y. Y. Yao, “An information-theoretic interpretation ofthresholds in
probabilistic rough sets,” in Proc. Rough Sets Current TrendsComput., Lecture Notes Comput.
Sci., 2012, pp. 232–241.
[14] X. F. Deng andY.Y.Yao, “Mean-value-based decision-theoretic shadowedsets,” in Proc.
Joint 9th IFSA World Congr. NAFIPS Annu. Meet., 2013,pp. 1382–1387.