Search or add a thesis

Advanced Search (Beta)
Home > A Framework to Predict the Student S Performance in Programing Courses

A Framework to Predict the Student S Performance in Programing Courses

Thesis Info

Access Option

External Link

Author

Waqar-Un-Nisa

Institute

Virtual University of Pakistan

Institute Type

Public

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Software Engineering

Language

English

Link

http://vspace.vu.edu.pk/detail.aspx?id=343

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676721028165

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Academic grades prediction is considered as one of the hot research areas since last decade, which comes under the domain of educational data mining. It has been observed that in undergraduate computer science programs, programming courses are considered challenging. This results in higher tendency of earning lower grades, failures or drop-outs than other computer science subjects. An early prediction of the students who have high probability of failure (known as at-risk students) will enable the instructors to intervene and provide extra guidance to learners. An accurate prediction of student?s grades can directly influence the overall quality of any degree program and the retention rate of the institution. This research presents a machine learning based classification model for undergraduate students grades prediction, enrolled in any programming course(s) in traditional education system. The proposed model is built after careful collection and pre-processing of data, appropriate feature selection, and model evaluation based on four metrics namely accuracy, precision, recall and F1-score. Six widely used supervised machine learning techniques including Random Forest, Artificial Neural Network, K-Nearest Neighbors, Na?ve Bayes, Ordinal Regression, and Support Vector Machine are used after tuning and optimization. The data used for this research is collected from a private sector university in Lahore. The collected data covers two major domains: student?s academic record and demographic data. The results show that Support Vector Machine and K-Nearest Neighbors give highest scores (ranging from 81% to 94%) for all the evaluation metrics and for all the seven programming courses considered for this study.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

44. Ad-Dukhan/The Smoky Haze

44. Ad-Dukhan/The Smoky Haze

I/We begin by the Blessed Name of Allah

The Immensely Merciful to all, The Infinitely Compassionate to everyone.

44:01
a. Ha. Mim.

44:02
a. By the Book of Divine Qur’an - clear in itself and clearly guiding to the truth.

44:03
a. WE sent it down during a night full of blessings.
b. Because with it WE had planned to warn people.

44:04
a. On that night every matter of wisdom was made distinct -

44:05
a. – by OUR Command.
b. Indeed, WE had decided to send OUR Messengers to these people for guidance -

44:06
a. - as a Mercy from your Rabb - The Lord to humankind.
b. Indeed, HE - HE is The All-Listening of their sayings, The All-Knowing of their actions.

44:07
a. Rabb - The Lord of the celestial realm and the terrestrial world and whatever is between them,
b. only if you were firm believers.

44:08
a. There is no entity of worship except HIM.
b. HE gives both life as well as death.
c. HE is your Rabb - The Lord and Rabb - The Lord of your forefathers.

44:09
a. Yet they are lost in their doubts.

44:10
a. Then be on the watch for the Time – The Last Hour - when the sky will exhale visible smoky haze -

44:11
a. – covering all people, causing them to cry out:
b. ‘This is an awful punishment!’

44:12
a. ‘O Our Rabb - The Lord!
b. Take this punishment away from...

حد الزاني البكر و المحصن

Islam is a complete code of life and it provides complete guidance in every field of life. Islamic law provides protection to the human wisdom, race and respect. Spiritual purity, sacred heart and environmental cleanliness, is one of the important persistence of Islamic sharia. Every act which leads us towards ignorance, contradiction, ambiguity and vulgarity is prohibiting in human societies. Zina has destroyed the spiritual values of individuals, families, societies and even nations. This ruthless deed is not only prohibited and sentenced in Islam, but also rather detested by other heavenly religions as well. Without discrimination of any religion, many scholars considered this hated act as the source of unrest and anarchy. Physically, ethically, medically, socially and even religiously zina has infinite hindrances in the society. Islam has provided various teachings and precautions to shun from this major sin for the protection of greatness and superiority of humanity. One of the important teachings is punishment for committing this sin, which is known as “Hadd” in Islamic sharia. In the current book, the punishments of married and unmarried (Fornicator) zani have been described in the light of Sunnah and Quran. The important purpose of Qisas and Hadd is the correction of societies, protection of life, respect and wealth, not the humiliation of people. To punish the criminals is the source of rectification for others.

Novel Hybrid Models Based on Hesitant Fuzzy Sets

Hesitant fuzzy set theory is an impressive tool, to express the vagueness and ambiguity derive from experts, to analyze the characteristics of objects, and to determine the membership functions for each criterion domain. Due to the unpredictability of real world problems, and the limitation of human’s observations, it is very challenging to apply only a particular or specific uncertainty method to deal with complex problems. One can approach to more impressive and effective models to handle decision-making problems, by relating or associating the advantages of several other distinct theories of uncertainty. Hesitant fuzzy sets and soft sets are considered more efficient to deal the uncertain conditions. By combining these theories with several other useful models, novel hybrid models can be developed for decision-making problems. The aim of this research is to construct novel hybrid models based on hesitant fuzzy sets, because the use of hesitant fuzzy computations makes the decision-makers assessments more feasible and significant in decision-making. The proposed hybrid models are named as, hesitant N-soft sets, hesitant fuzzy N-soft sets, interval-valued hesitant fuzzy N-soft sets, m−polar hesitant fuzzy sets and hesitant m−polar fuzzy sets. These models are obtained by the hybridization of hesitant fuzzy sets with N-soft sets and m−polar fuzzy sets, which are more flexible and expressive for modeling and processing of vague information under hesitancy. These models provide us information about the occurrence of ratings or grades and enable us to tackle multi-polar information with hesitancy. Various properties of hybrid models are investigated with different methods of their construction. Intrinsic operations are highlighted and explored with several new concepts including weak, top weak and bottom weak complements. The concept of decision-making methods named as choice value, L-choice value, TOPSIS and ELECTRE-I, is explored by applying them on proposed models. Potential applications related to real life situations are presented, that illustrate the procedure of the proposed decision-making methods. Efficient algorithms are developed to solve the decision-making problems based on hybrid models.