Saif-Ur-Rehman Saif Abbasi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Saif-Ur-Rehman Saif Abbasi has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Nazneen Habib
Department of Sociology & Rural Development, University of Azad Jammu & Kashmir, Muzaffarabad, Pakistan
2 shared publications - Wajid Aziz
The University of Azad Jammu & Kashmir, Muzaffarabad, Azad Kashmir, Pakistan
2 shared publications - Lal Hussain
The University of Azad Jammu and Kashmir
1 shared publication - Majid Almaraashi
The University College in Aljamoum, Umm Al-Qura University, Makkah, Saudi Arabia
1 shared publication
Latest Publications
- 30 March 2021
- Published by Taylor & Francis in Waves in Random and Complex Media
- Vol. 34 (1) , 226-251
Machine learning-based lungs cancer detection using reconstruction independent component analysis and sparse filter features
In the present study, based on the multivariate nature of images from lung cancer, we extracted autoencoder, reconstruction independent component analysis (RICA) and sparse filters features along with traditional texture and morphological features. The machine learning techniques such as Support Vector Machine (SVM) with Gaussian, radial base function (RBF) and polynomial kernels, decision tree and Naïve Bayes were used classification purpose. The Jackknife 10-fold cross validation (CV) was used for training/testing data formulation and performance was evaluated in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), total accuracy (TA), false positive rate (FPR) and area under the receiving operating curve (AUC) to distinguish the small cell lung cancer (SCLC) from non-small cell lung cancer (NSCLC) images. The highest detection performance was obtained by extracting RICA and Sparse filters with 100% of sensitivity, specificity, PPV, NPV and TA using SVM with RBF, polynomial kernels and Naïve Bayes followed by Sparse filter with decision tree with TA (99.78%). The highest AUC of 1.00 was obtained by extracting RICA and Sparse filters using decision tree, SVM Gaussian, RBF and polynomial and Naïve Bayes. The results showed the good potential of these methods for lung cancer detection (LCD).
- 30 March 2021
- Published by Taylor & Francis in Waves in Random and Complex Media
- Vol. 34 (1) , 226-251
Machine learning-based lungs cancer detection using reconstruction independent component analysis and sparse filter features
In the present study, based on the multivariate nature of images from lung cancer, we extracted autoencoder, reconstruction independent component analysis (RICA) and sparse filters features along with traditional texture and morphological features. The machine learning techniques such as Support Vector Machine (SVM) with Gaussian, radial base function (RBF) and polynomial kernels, decision tree and Naïve Bayes were used classification purpose. The Jackknife 10-fold cross validation (CV) was used for training/testing data formulation and performance was evaluated in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), total accuracy (TA), false positive rate (FPR) and area under the receiving operating curve (AUC) to distinguish the small cell lung cancer (SCLC) from non-small cell lung cancer (NSCLC) images. The highest detection performance was obtained by extracting RICA and Sparse filters with 100% of sensitivity, specificity, PPV, NPV and TA using SVM with RBF, polynomial kernels and Naïve Bayes followed by Sparse filter with decision tree with TA (99.78%). The highest AUC of 1.00 was obtained by extracting RICA and Sparse filters using decision tree, SVM Gaussian, RBF and polynomial and Naïve Bayes. The results showed the good potential of these methods for lung cancer detection (LCD).
- Open Access
- 22 January 2020
- Published by Hindawi Limited in Anemia
- Vol. 2020, 1-9
An Analysis of Societal Determinant of Anemia among Adolescent Girls in Azad Jammu and Kashmir, Pakistan
Societal determinants of health are of recognized importance for understanding the causal association of society and health of an individual. Iron deficiency anemia (IDA) is a challenging public health problem across the globe instigating from a broader sociocultural background. It is more prevalent among pregnant women, children under the age of five years, and adolescent girls. Adolescent girls are vulnerable to develop IDA because of additional nutritional demand of the body needed for growth spurt, blood loss due to onset of menarche, malnourishment, and poor dietary iron intake. In this study, we explore the societal determinants of anemia among adolescent girls in Azad Jammu and Kashmir (AJK), Pakistan. A cross-sectional study was conducted in the Muzaffarabad division of AJK on randomly selected 626 adolescent girls. The data were collected using a pretested self-administered interview schedule comprising mainly closed-ended questions with a few open-ended questions. Descriptive statistics was computed for describing the data, and bivariate regression and logistic regression were used to determine the association of anemia with its societal determinants. Multiple linear regression is used to determine the relationship of different determinants (independent variables) with the hemoglobin level (dependent variable) of the respondents. The prevalence of anemia among adolescent girls is 47.9%, of which 47.7% have mild anemia, 51.7% have moderate anemia, and 5.7% have severe anemia, which reveals that anemia is a severe public health problem among adolescent girls in the study area. The findings aver that anemia occurrence was significantly associated with the respondent’s and her parental education, economic well-being, prevalence of communicable diseases, menstrual disorder, exercise habits, meals regularity, and type of sewerage system.
- 22 January 2020
- Published by Hindawi Limited in Anemia
- Vol. 2020, 1-9
Open AccessAn Analysis of Societal Determinant of Anemia among Adolescent Girls in Azad Jammu and Kashmir, Pakistan
Societal determinants of health are of recognized importance for understanding the causal association of society and health of an individual. Iron deficiency anemia (IDA) is a challenging public health problem across the globe instigating from a broader sociocultural background. It is more prevalent among pregnant women, children under the age of five years, and adolescent girls. Adolescent girls are vulnerable to develop IDA because of additional nutritional demand of the body needed for growth spurt, blood loss due to onset of menarche, malnourishment, and poor dietary iron intake. In this study, we explore the societal determinants of anemia among adolescent girls in Azad Jammu and Kashmir (AJK), Pakistan. A cross-sectional study was conducted in the Muzaffarabad division of AJK on randomly selected 626 adolescent girls. The data were collected using a pretested self-administered interview schedule comprising mainly closed-ended questions with a few open-ended questions. Descriptive statistics was computed for describing the data, and bivariate regression and logistic regression were used to determine the association of anemia with its societal determinants. Multiple linear regression is used to determine the relationship of different determinants (independent variables) with the hemoglobin level (dependent variable) of the respondents. The prevalence of anemia among adolescent girls is 47.9%, of which 47.7% have mild anemia, 51.7% have moderate anemia, and 5.7% have severe anemia, which reveals that anemia is a severe public health problem among adolescent girls in the study area. The findings aver that anemia occurrence was significantly associated with the respondent’s and her parental education, economic well-being, prevalence of communicable diseases, menstrual disorder, exercise habits, meals regularity, and type of sewerage system.