National University of Computer and Emerging Sciences

About: National University of Computer and Emerging Sciences is a education organization based out in Islamabad, Pakistan. It is known for research contribution in the topics: Computer science & The Internet. The organization has 1506 authors who have published 2438 publications receiving 26786 citations.

Survey of various feature extraction and classification techniques for facial expression recognition

Abstract: The purpose of this paper is to present a comprehensive study of latest and most famous facial features extraction techniques and as well as classification techniques. We studied these techniques in two different perspectives; one is spatial domain and other is frequency domain. We found many advantages and disadvantages of each technique inside one domain and as well in between different domains. We observed that Local Binary Pattern is a new technique and now it is becoming very famous technique in spatial domain. LBP simply knows about micro patterns using the comparison with neighbour pixel grey scale values. Lot of work on LBP has yielded its different extensions which have optimized the base concept of LBP operator. Frequency domain covers the techniques which transform images into frequency domain and use either cosine or sine waves to extract the facial features. This method is a very strong and precise that only two to three features have the ability to describe the facial expressions. We have also studied different classification techniques in domain of facial expressions classification. In most of the solutions classification is done through KNN classifier. K Nearest Neighbour is a successful and non-parametric technique of machine learning in supervised learning techniques.

Group Counseling Optimization for multi-objective functions

Abstract: Group Counseling Optimizer (GCO) is a new heuristic inspired by human behavior in problem solving during counseling within a group GCO has been found to be successful in case of single-objective optimization problems, but so far it has not been extended to deal with multi-objective optimization problems In this paper, a Pareto dominance based GCO technique is presented in order to allow this approach to handle multi-objective optimization problems In order to compute change in decision for each individual, we also incorporate a selfbelief counseling probability operator in the original GCO algorithm that enriches the exploratory capabilities of our algorithm The proposed Multi-objective Group Counseling Optimizer (MOGCO) is tested using several standard benchmark functions and metrics taken from the literature for multiobjective optimization The results of our experiments indicate that the approach is highly competitive and can be considered as a viable alternative to solve multi-objective optimization problems

Scope management in agile versus traditional software development methods

Abstract: Scope management is among one of the most important knowledge areas of software project management which if not managed carefully can lead the projects towards failure. A well defined and well managed scope is very important for a qualitative, cost effective and timely completion of the project. In this paper we discussed the role and impact of the scope on two very broadly accepted methodologies for software development. The two methodologies adopt different techniques for the development of software. How they are different from each other and how they adopt and manage the scope in there development process are discussed. Moreover, the replacement of traditional software development methods by agile software development methods in terms of cost, resources and time are also a part of this work.

On Super Edge-Antimagic Total Labeling Of Subdivided Stars

Abstract: Labeling is an interesting technique to assign labels to vertices and edges of a graph under certain conditions. There are many types of labeling, for example magic, antimagic, graceful, odd graceful, cordial, radio, sum and mean labeling. This paper deals with different results related to $(a,d)$-edge-antimagic total and super $(a,d)$-edge-antimagic total labelings of a subclass of subdivided stars denoted by $T(n,n+2,n+5,2n+7,n_5,...,n_r)$, where $n\equiv 1\hphantom{a}(\mbox{mod}\hphantom{a}2)$, $n_m=2^{m-3}(n+3)+1$ and $5\leq m\leq r$.

Transfer Learning and Semisupervised Adversarial Detection and Classification of COVID-19 in CT Images

Abstract: The ongoing coronavirus 2019 (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in a severe ramification on the global healthcare system, principally because of its easy transmission and the extended period of the virus survival on contaminated surfaces. With the advances in computer-aided diagnosis and artificial intelligence, this paper presents the application of deep learning and adversarial network for the automatic identification of COVID-19 pneumonia in computed tomography (CT) scans of the lungs. The complexity and time limitation of the reverse transcription-polymerase chain reaction (RT-PCR) swab test makes it disadvantageous to depend solely on as COVID-19’s central diagnostic mechanism. Since CT imaging systems are of low cost and widely available, we demonstrate that the drawback of the RT-PCR can be alleviated with a faster, automated, and reduced contact diagnostic process via the use of a neural network model for the classification of infected and noninfected CT scans. In our proposed model, we explore the benefit of transfer learning as a means of resolving the problem of inadequate dataset and the importance of semisupervised generative adversarial network for the extraction of well-mapped features and generation of image data. Our experimental evaluation indicates that the proposed semisupervised model achieves reliable classification, taking advantage of the reflective loss distance between the real data sample space and the generated data.