Mustansar Ali Ghazanfar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mustansar Ali Ghazanfar has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Ali Javed
Department of Software Engineering, University of Engineering and Technology, Taxila, Pakistan
1 shared publication Anam Mustaqeem
1 shared publication- Asma Sattar
Dipartimento di Informatica, Università di Pisa, Pisa, Italy
1 shared publication Asmeen Fahad Aldhafiri
1 shared publication- Ayesha Raana
Faculty of Telecom and Information Engineering, University of Engineering & Technology Taxila, Pakistan
1 shared publication - Farhan Aadil
Department of Computer Engineering, Sivas University of Science and Technology, Sivas 58140, Turkey
1 shared publication
Latest Publications
- Open Access
- 15 October 2018
- Published by MDPI AG in Sustainability
- Vol. 10 (10) , 3702
A Robust Regression-Based Stock Exchange Forecasting and Determination of Correlation between Stock Markets
Knowledge-based decision support systems for financial management are an important part of investment plans. Investors are avoiding investing in traditional investment areas such as banks due to low return on investment. The stock exchange is one of the major areas for investment presently. Various non-linear and complex factors affect the stock exchange. A robust stock exchange forecasting system remains an important need. From this line of research, we evaluate the performance of a regression-based model to check the robustness over large datasets. We also evaluate the effect of top stock exchange markets on each other. We evaluate our proposed model on the top 4 stock exchanges—New York, London, NASDAQ and Karachi stock exchange. We also evaluate our model on the top 3 companies—Apple, Microsoft, and Google. A huge (Big Data) historical data is gathered from Yahoo finance consisting of 20 years. Such huge data creates a Big Data problem. The performance of our system is evaluated on a 1-step, 6-step, and 12-step forecast. The experiments show that the proposed system produces excellent results. The results are presented in terms of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).
- 15 October 2018
- Published by MDPI AG in Sustainability
- Vol. 10 (10) , 3702
Open AccessA Robust Regression-Based Stock Exchange Forecasting and Determination of Correlation between Stock Markets
Knowledge-based decision support systems for financial management are an important part of investment plans. Investors are avoiding investing in traditional investment areas such as banks due to low return on investment. The stock exchange is one of the major areas for investment presently. Various non-linear and complex factors affect the stock exchange. A robust stock exchange forecasting system remains an important need. From this line of research, we evaluate the performance of a regression-based model to check the robustness over large datasets. We also evaluate the effect of top stock exchange markets on each other. We evaluate our proposed model on the top 4 stock exchanges—New York, London, NASDAQ and Karachi stock exchange. We also evaluate our model on the top 3 companies—Apple, Microsoft, and Google. A huge (Big Data) historical data is gathered from Yahoo finance consisting of 20 years. Such huge data creates a Big Data problem. The performance of our system is evaluated on a 1-step, 6-step, and 12-step forecast. The experiments show that the proposed system produces excellent results. The results are presented in terms of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).
- Open Access
- 30 June 2017
- Published by Pakistan Atomic Energy Commission in The Nucleus
- Vol. 54 (2) , 114-120
A Comparative Study of Classifier Based Mispronunciation Detection System for Confusing
Pronunciation training systems detect mispronunciations from language learner’s speech and provide useful feedback. Mispronunciation detection systems can either be developed using Confidence Measures (CM) or using classifiers with Acoustic Phonetic Features (APF). This paper presents an APF based computer assisted pronunciation training (CAPT) system for most confusing Arabic phoneme pairs (/ ? / vs/ ?/)and (/ ? / vs / ? / or / ? /) developed for subjects of Pakistani origin. A super-vector is formed based on APF consisting of Mel-frequency cepstral coefficients (MFCCs) along with its first and second derivative, energy, zero-cross, spectral features and pitch. A large dataset has been recorded from 200 speakers of Pakistani origin learning Arabic as their second language. Four different machine learning classifiers; Random Forest, Naïve Bayes, Ada-boost and K-NN have been used for mispronunciation detection. A comparison has been conducted between these classifiers and standard Goodness of Pronunciation (GOP) method. The results show that Random Forest outperforms all other methods by a significant margin.
- 30 June 2017
- Published by Pakistan Atomic Energy Commission in The Nucleus
- Vol. 54 (2) , 114-120
Open AccessA Comparative Study of Classifier Based Mispronunciation Detection System for Confusing
Pronunciation training systems detect mispronunciations from language learner’s speech and provide useful feedback. Mispronunciation detection systems can either be developed using Confidence Measures (CM) or using classifiers with Acoustic Phonetic Features (APF). This paper presents an APF based computer assisted pronunciation training (CAPT) system for most confusing Arabic phoneme pairs (/ ? / vs/ ?/)and (/ ? / vs / ? / or / ? /) developed for subjects of Pakistani origin. A super-vector is formed based on APF consisting of Mel-frequency cepstral coefficients (MFCCs) along with its first and second derivative, energy, zero-cross, spectral features and pitch. A large dataset has been recorded from 200 speakers of Pakistani origin learning Arabic as their second language. Four different machine learning classifiers; Random Forest, Naïve Bayes, Ada-boost and K-NN have been used for mispronunciation detection. A comparison has been conducted between these classifiers and standard Goodness of Pronunciation (GOP) method. The results show that Random Forest outperforms all other methods by a significant margin.
- 1 April 2017
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 7 (2) , 24-29
Using Machine Learning Classifiers to Predict Stock Exchange Index
- 1 April 2017
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 7 (2) , 24-29
Using Machine Learning Classifiers to Predict Stock Exchange Index
- 9 February 2017
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 42 (8) , 3229-3247
Building Accurate and Practical Recommender System Algorithms Using Machine Learning Classifier and Collaborative Filtering
- 9 February 2017
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 42 (8) , 3229-3247
Building Accurate and Practical Recommender System Algorithms Using Machine Learning Classifier and Collaborative Filtering
- Open Access
- 8 March 2016
- Published by Pakistan Atomic Energy Commission in The Nucleus
- Vol. 53 (1) , 56-63
C++ BUG CUB: Logical Bug Detection for C++ Code
Quality is seen as one of the key aspects for efficient and robust Software development. One of the ways to ensure quality is to ensure that developed software systems’ code istotally free of syntax, real time and logical bugs. Despite careful development process, there is always room for these bugs to stay in developed system. Many of the syntax and logical bugs escape from detection in testing phase, which has great impact on the quality and reliability of system and business value as well. These are usually Logical Bugs, which can be difficult to find and which can lead to frustration for the development team. To alleviate the overhead of static analysis of code performed by the developer to detect logical bugs, a system is proposed to detect these bugs in C++ code. The system has been engineered using tokenization concept -prerequisite for bug detection- followed by rule-based algorithm that is designed for logical bugs’ detection. A decision tree based approach has also been applied in order to classify the detected bugs. The system is also able to extract dependency among all the methods/functions written in the input code. Both tasks; bug(s) detection and function dependency are performed in one pass which makes the system efficient.
- 8 March 2016
- Published by Pakistan Atomic Energy Commission in The Nucleus
- Vol. 53 (1) , 56-63
Open AccessC++ BUG CUB: Logical Bug Detection for C++ Code
Quality is seen as one of the key aspects for efficient and robust Software development. One of the ways to ensure quality is to ensure that developed software systems’ code istotally free of syntax, real time and logical bugs. Despite careful development process, there is always room for these bugs to stay in developed system. Many of the syntax and logical bugs escape from detection in testing phase, which has great impact on the quality and reliability of system and business value as well. These are usually Logical Bugs, which can be difficult to find and which can lead to frustration for the development team. To alleviate the overhead of static analysis of code performed by the developer to detect logical bugs, a system is proposed to detect these bugs in C++ code. The system has been engineered using tokenization concept -prerequisite for bug detection- followed by rule-based algorithm that is designed for logical bugs’ detection. A decision tree based approach has also been applied in order to classify the detected bugs. The system is also able to extract dependency among all the methods/functions written in the input code. Both tasks; bug(s) detection and function dependency are performed in one pass which makes the system efficient.
- 1 July 2015
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 19 (4) , 845-877
Experimenting switching hybrid recommender systems
Recommender systems employ machine learning and data mining techniques for filtering unseen information and can predict whether a user would like a given resource. To date a number of recommendation algorithms have been proposed, where collaborative
- 1 July 2015
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 19 (4) , 845-877
Experimenting switching hybrid recommender systems
Recommender systems employ machine learning and data mining techniques for filtering unseen information and can predict whether a user would like a given resource. To date a number of recommendation algorithms have been proposed, where collaborative