Aftab Akram

Aftab Akram

Auto-generated profile, based on publicly available information

Aftab Akram

School of Computer Science, South China Normal University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 July 2019 in IEEE Access
Verified
Journal Article
Open access
AAAftab Akram
Aftab Akram
CFChengzhou Fu
Chengzhou Fu
YLYuyao Li
Yuyao Li
MJMuhammad Yaqoob Javed
Muhammad Yaqoob Javed
RLRonghua Lin
Ronghua Lin
YTYong Tang
Yong Tang
Academic procrastination has been reported affecting students' performance in computer-supported learning environments. Studies have shown that students who demonstrate higher procrastination tendencies achieve less than the students with lower procrastination tendencies. It is important for a teacher to be aware of the students' behaviors especially their procrastination trends. EDM techniques can be used to analyze data collected through computer-supported learning environments and to predict students' behaviors. In this paper, we present an algorithm called students' academic performance enhancement through homework late/non-submission detection (SAPE) for predicting students' academic performance. This algorithm is designed to predict students with learning difficulties through their homework submission behaviors. First, students are labeled as procrastinators or non-procrastinators using k-means clustering algorithm. Then, different classification methods are used to classify students using homework submission feature vectors. We use ten classification methods, i.e., ZeroR, OneR, ID3, J48, random forest, decision stump, JRip, PART, NBTree, and Prism. A detailed analysis is presented regarding performance of different classification methods for different number of classes. The analysis reveals that in general the prediction accuracy of all methods decreases with increase in the number of classes. However, different methods perform best or worst for different number of classes.

28 November 2019 in Computer Applications in Engineering Education
Verified
Journal Article
Closed access
PDF file
IJIqra Jawaid
Iqra Jawaid
MJMuhammad Yaqoob JAVED
Muhammad Yaqoob JAVED
MJMujtaba H. Jaffery
Mujtaba H. Jaffery
AAAftab Akram
Aftab Akram
USUmair Safder
Umair Safder
SHSarmad Hassan
Sarmad Hassan

3 January 2020 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
SWShahbaz Hassan Wasti
Shahbaz Hassan Wasti
MHMuhammad Jawad Hussain
Muhammad Jawad Hussain
GHGuangjian Huang
Guangjian Huang
AAAftab Akram
Aftab Akram
YJYuncheng Jiang
Yuncheng Jiang
YTYong Tang
Yong Tang

15 September 2016
Verified
Conference Paper
Closed access
AAAftab Akram
Aftab Akram
CFChengzhou Fu
Chengzhou Fu
YTYong Tang
Yong Tang
YJYuncheng Jiang
Yuncheng Jiang
XLXueqin Lin
Xueqin Lin
The data stored in E-Learning and academic social networking system databases can reveal useful insight into the behavior of the users of these systems. The statistical analysis and machine learning techniques can be used to make meaningful inferences from this data. Moreover, Education Data Mining (EDM) and Learning Analytics (LA) practices can help educators and administrators to take educated decisions related to the wellbeing of learners and the learning system overall. In this paper, we present descriptive statistical analysis of SCHOLAT E-Learning data to expose interesting information about the behavior of learners and the data gathering practices. The data was fetched from SCHOLAT Courses module database, and then univariate and bivariate analysis was performed to get an insight. This data represents the activities of students when they were undergoing a blended learning course. The analysis revealed that students' interest lies in activities which are related to improve their grades, e.g. submitting homework on time where mean value approaches the maximum value. However, they do not show the same enthusiasm in other activities. Moreover, a loophole was also discovered in data gathering practices as a result of analysis. The analysis lays a foundation for more complicated analysis in future and improving the system's data gathering practices.

31 July 2017 in International Journal of Intelligent Systems
Verified
Journal Article
Closed access
PDF file
PLPu Li
Pu Li
BXBao Xiao
Bao Xiao
AAAftab Akram
Aftab Akram
YJYuncheng Jiang
Yuncheng Jiang
ZZZhifeng Zhang
Zhifeng Zhang

1 December 2011
Verified
Conference Paper
Closed access
AAAftab Akram
Aftab Akram
MAMuhammad Aslam
Muhammad Aslam
AMA. M. Martinez-Enriquez
A. M. Martinez-Enriquez
ZQZia Ul Qayyum
Zia Ul Qayyum
ASAfraz Z. Syed
Afraz Z. Syed
One of the most important challenges in traditional learning environments is coping with the learning pace of naturally varying skilled learners. Not all learners have same learning tendency. They suffer if a proper way is not devised to cope with this challenge. In such a heterogeneous learning environment, they should be provided with personalized instructions based on their own perception skills to give them opportunity to learn on their own pace. Also, they can collaborate and interact with other peers to enhance then-learning. Definitely providing these features in a learning environment is not a simple and easy task. Although traditional computer based learning management systems can provide users with these facilities to some extent. However, there is a room for improvement. In this paper, we propose an agent based e-learning management system architecture to provide personalized, self-paced, and collaborative learning opportunities to its learners. We test our system in a university environment. The results of the experimentation show that we achieve the state of the art performance in learning.