A Mobile Learning by Decision Tree

tenderlaΛογισμικό & κατασκευή λογ/κού

13 Δεκ 2013 (πριν από 3 χρόνια και 3 μήνες)

64 εμφανίσεις

A
Mobile Learning by Decision Tree

for
Provisional Diagnosis on Smartphone


Presented by

Miss.
Rakwarinn

Wannasin

and
Mr.Krittachai

Boonsivanon

Outline

Background

Related
works


Objectives

Methodology


Result

Conclusion

(Traxler, 2005; Kukulska
-
Hulme & Shield, 2008)


ICT


(
Information and Communication Technology)

ICT


(
Information and Communication Technology)

(
Garrison

& Kanuka, 2004; Masie, 2006; Kumar, 2007

)


An innovation of teaching and learning.
(Soh, Park & Chang, 2009)


E
-
Learning


The students to search and retrieve the information through
the computer with low expenses.

(
Tissana

Kaemanee
, 2004)

E
-
Learning

(Eke, 2011)

The Limitations of E
-
Learning

Training Methodologies


Mobile phone


(Reuters, 2008)


Internet


(Miniwatts Marketing Group, 2008)


M
-
Learning or Mobile Learning


(Park, 2011)


The Advantages of M
-
Learning


(
Geddes, 2004)

Decision Tree

http://www.tuesdayconsultingllc.com/decision
-
tree
-
model
-
vs
-
effective
-
delegation/

http://sasdkmitl09.blogspot.com/2009/07/blog
-
post_23.html

The

application

of

decision

tree

inthe

research


of

anemia

among

rural

children

under

3
-
year
-
old







(
Zhonghua Yu Fang Yi Xue Za Zhi,

2009.
)

Ensemble decision tree classifier for breast cancer data.





(D.Lavanya & Dr.K.Usha Rani, 2012.)

(Oteuffel et al.,

2011)





(Lukas Tanner

et al.,

2008)

Cost effectiveness of outpatient treatment for febrile

neutropaenia

in adult cancer patients.

Decision tree algorithms predict the diagnosis and

outcome of dengue fever in the early phase of illness.

Related
works

Objectives


To develop and improve mobile learning to provisional
diagnose for basic Traditional Thai Medicine.


To study the result before and after studying
decision
-
tree via
smartphone

to provisional
diagnose 20 diseases.

Methodology

Group 1

Not yet
learning


20 persons

Group 2

General

class room

activities

20 persons


Group 3

M
-
Learning


45 persons



Experimental set
-
up


Sampling:


85 first
-
year Thai Traditional Medicine
students.





Methodology


Experimental set
-
up


Hardware and software:


Xcode

software ,
SQLite

and
iOS

Simulator


Running under Apple
iOS
,

iPhone

platform






Methodology


Implementation:


M
-
learning programming
: Java and Decision tree algorithm.


D
atabase
:
Xcode

and
SQLite


Contents based on:
10
-
012
-
203 Thai Traditional medicine

1


Title:

Provisional diagnosis
”.









Methodology

Pre
-
test

Group 1

Not yet
learning

Group2

General

Class room

activities

Group3

M
-
Learning

Pre
-
test

2.M
-
Learning

method

1.General
learning

method

Methodology

Group 1

Not yet
learning

Group2

General

Class room

activities

Group3

M
-
Learning

T
-
test was used to analyze the data and compare the student’s
learning achievement.

Post
-
test

Result of General Learning

Result of Learning M
-
Learning


24. 7%

Result of General Learning and M
-
Learning

General Learning


M
-
Learning

@

@

@

Represented
a
significant
different when
compared to the
control.


*

Represented a
significant
different when
compared to the
general learning.


*

Result of Learning M
-
Learning

Result of Learning M
-
Learning

Cholinergic pathway
-

ACh

ACh Choline


+ acetate

AChE

A
cetylcholinesterase inhibitors

Anticholinesterase

Discussion


Conclusion


The results of this study demonstrated that the learning
through mobile learning score could significantly
enhance ability provisional diagnose through
mobile learning by the decision
-
tree in the first year
Traditional Thai Medicine students.


Thank you for your attention

Miss.
Rakwarinn

Wannasin

Lecturer, Dept. Traditional Thai Medicine, Faculty of

Natural Resources,

Rajamangala

University of Technology
Isan

Sakonnakhon

Campus,
Thailand.

Tel:
087
-
4499332

Email:
rakwarinn@outlook.com




Mr.
Krittachai

Boonsivanon

Lecturer, Dept.
Computer Engineering,
Faculty of

Creative Industry,

Kalasin

Rajabhat

University,
Thailand
.

Tel:
087
-
4236374

Email:
krittachai@fci.ksu.ac.th