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.

Do procedures really matter when rewards are more important? A Pakistani perspective on the effects of distributive and procedural justice on employee behaviors

Abstract: Introduction Researchers agree that procedural justice and distributive justice interact so that high procedural fairness reduces the negative consequences of distributive unfairness. Objectives Our objective was to test the hypothesis that employees in Pakistan (i.e., an underdeveloped economy) would be more focused on rewards than procedures. Therefore, procedural and distributive justice will not interact in predicting employee behaviors. Methods Using independent measures for organizational justice and job outcomes, we conducted two field surveys (n = 372 and n = 550 paired responses) in Pakistan to examine the direct and combined effects of procedural and distributive justice on job performance, citizenship behaviors, and creativity. Results In both studies, the results suggest that distributive justice is a more consistent and relatively stronger predictor of job outcomes as compared to procedural justice. The results also showed that procedural justice did not moderate the relationship between distributive justice and employee behaviors. Conclusion The findings suggest that workers in an underdeveloped economy like Pakistan may be more concerned with fairness in the distribution of rewards than procedural fairness. Therefore, in such context, procedures may be less likely to reduce negative consequences of unfair reward distribution.

Road Traffic Accident Analysis and Identification of Black Spot Locations on Highway

Abstract: Road safety is the main problem in developing countries. Every year, millions of people die in road traffic accidents, resulting in huge losses of humankind and the economy. This study focuses on the road traffic accident analysis and identification of black spots on the Lahore-Islamabad Highway M-2. Official data of road traffic accidents were collected from National Highway and Highway Police (NH & MP) Pakistan. The data was digitized on MS Excel and Origin Pro. The accident Point weightage (APW) method was employed to identify the black spots and rank of the top ten black spots. The analysis shows that the trend of road traffic accidents on M-2 was characterized by a high rate of fatal accidents of 35.3%. Human errors account for 66.8% as the major contributing factors in road traffic accidents, while vehicle errors (25.6%) and environmental factors (7.6%) were secondary and tertiary contributing factors. The main causes of road traffic accidents were the dozing on the wheel (27.9%), the careless driving (24.6%), tyre burst (11.7%), and the brakes failure (7.4%). Kallar Kahar (Salt Range) was identified as a black spot (223 km, 224 km, 225 km, 229 km, and 234 km) due to vehicle brake failure. The human error was a major contributory factor in road traffic accidents, therefore public awareness campaign on road safety is inevitable and use of the dozen alarm to overcome dozing on the wheel. Doi: 10.28991/cej-2020-03091629 Full Text: PDF

An Accurate Deep Learning Model for Clinical Entity Recognition From Clinical Notes

Abstract: The growing use of electronic health records in the medical domain results in generating a large amount of medical data that is stored in the form of clinical notes. These clinical notes are enriched with clinical entities like disease, treatment, tests, drugs, genes, and proteins. The extraction of clinical entities from clinical notes is a challenging task as clinical notes are written in the form of natural language. The extraction of clinical entities has many useful applications such as clinical notes analysis, medical data privacy, decision support systems, and disease analysis. Although various machine learning and deep learning models are developed to extract clinical entities from clinical notes, developing an accurate model is still challenging. This study presents a novel deep learning-based technique to extract the clinical entities from clinical notes. The proposed model uses local and global context to extract clinical entities in contrast to existing models that use only global context. The combination of CNN, Bi-LSTM, and CRF with non-complex embedding (proposed model) outperforms existing models by a margin of $4-10\%$ and $5-12\%$ in terms of F1-score on i2b2-2010 and i2b2-2012 data. The accurate detection of clinical entities can be helpful in the privacy preservation of medical data that increases the user's and medical organization's trust in sharing medical data.

An Invisible Text Watermarking Algorithm using Image Watermark

Abstract: Copyright protection of digital contents is very necessary in today’s digital world with efficient communication mediums as internet Text is the dominant part of the internet contents and there are very limited techniques available for text protection This paper presents a novel algorithm for protection of plain text, which embeds the logo image of the copyright owner in the text and this logo can be extracted from the text later to prove ownership The algorithm is robust against content-preserving modifications and at the same time, is capable of detecting malicious tampering Experimental results demonstrate the effectiveness of the algorithm against tampering attacks by calculating normalized hamming distances The results are also compared with a recent work in this domain