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.

Automation and monitoring of greenhouse

Abstract: Recent era has brought upon a major global food shortage due to the climatic changes in the world. So in order to deal with this issue of global food shortage households must need to grow a reasonable deal of vegetables and other crops using artificial greenhouses. An artificially controlled greenhouse yields more crops per square meter compared to open field cultivation since the microclimatic parameters that determine crop yield are continuously examined and controlled to ensure that an optimum environment is created. This research paper addresses and tries to resolve a few issues that are faced by plants caretakers using the engineering approach so that he/she could remain satisfied even when he/she is physically away for a long duration of time because the automated system will take care of everything in the absence. This automated system works using sensors and actuators, which are controlled by a microcontroller and monitor and manage every environmental parameter required for the good growth of plants.

An adaptive training based on classification system for patterns in facial expressions using SURF descriptor templates

Abstract: Most facial expression recognition (FER) systems used facial expression data created during a short period of time and this data is used for learning/training of FER systems. There are many facial expression patterns (i.e. a particular expression can be represented in many different patterns) which cannot be generated and used as learning/training data in a short time. Therefore, in order to maintain its high accuracy and robustness for a long time of a facial expression recognition system, the classifier should be evolved adaptively over time and space. We proposed a facial expression recognition system that has the aptitude of incrementally learning and thus can learn all possible patterns of expressions that may be generated in feature. After extraction of region of interest (face), the system extracts Speeded-Up Robust Features (SURF). A novel SURF descriptor template based nearest neighbor classifier is proposed for classification. This classifier is used as base/weak classifier for incremental learning algorithm Learn++. A vast range of experimentation is performed on five different databases that demonstrate the incremental learning capability of the proposed system. The experiments using the incrementally learning classification demonstrate promising results.

Attribution in cyberspace: techniques and legal implications

Abstract: Attribution of cybercrimes is significant in limiting the rate of crime as well as in preparing the required level of response. Motivated by this significance, we introduce a level-based approach for achieving attribution. In our proposed approach, attribution consists of three steps: 1 identification of the cyberweapon used; 2 determination of the origin of the attack; and 3 identification of the actual attacker. We conduct an in-depth analysis of recently proposed attribution techniques. Our analysis reveals that indirect methods of attribution are particularly effective when attributing cybercrimes; many of them remain unattributed. We also discuss some of the legal issues pertaining to attribution, and we argue that well-defined international laws for cyberspace along with strong cooperation among governments are needed to track down and punish cybercriminals. Copyright © 2016 John Wiley & Sons, Ltd.

Domain Specific Emotion Lexicon Expansion

Abstract: Emotion Classification using lexicons has vast number of applications ranging from social media analysis to pervasive computing. Lexicons are usually hand-crafted and cost a lot of time and effort to generate. The major research challenge in this area is the creation of a generalized lexicon which serves well for every domain. This work focuses on automatic expansion of emotion lexicons to ease the process of domain adaption. Our proposed approach — CB-Lex — relies on a seed lexicon and an unlabeled corpus from the target domain. In experimental results, our expanded lexicons show an improvement of over 6% in F-Measure.

Classifier ensemble optimization for gender classification using Genetic Algorithm

Abstract: Gender classification problem is an active area of research; recently it had attracted many researchers. This study presents an efficient gender classification technique. Weighted Majority Voting (WMV) is the most popular technique used to combine individual classifiers in an ensemble based classification. Genetic Algorithm (GA) is a global optimization technique and is being widely used by the researchers in the last four decades. In this paper the optimized combination of individual classifiers is obtained using Genetic Algorithm for the problem of gender classification. The proposed method is tested on the Stanford university medical student (SUMS) frontal facial images database. The experimental results on the SUMS face database indicate that the proposed approach achieves higher accuracy then previous methods.