Time filter

Source Type

Sita Road, Pakistan

Bahria University , is a public research university primarily located in Islamabad, Pakistan. The university maintains campuses in Karachi and Lahore.Established by the Pakistan Navy in 2000, its status is granted as civilian. It offers programmes in undergraduate, post-graduate, and doctoral studies. Its research is directed towards the development of engineering, philosophy, natural, social, and medical science. The university is one of the top institution of higher learning in the country and secured its ranking in among country's top ten and most notable universities in "general category" by the HEC, as of 2013. The university is a member of the Association of Commonwealth Universities of the United Kingdom.The university research institutes offer scientific research in the development of medical, environmental, natural science as well as in the engineering and philosophy. Wikipedia.

Akram M.U.,National University of Sciences and Technology | Khalid S.,Bahria University | Khan S.A.,National University of Sciences and Technology
Pattern Recognition | Year: 2013

Diabetic retinopathy is a progressive eye disease which may cause blindness if not detected and treated in time. The early detection and diagnosis of diabetic retinopathy is important to protect the patients vision. The accurate detection of microaneurysms (MAs) is a critical step for early detection of diabetic retinopathy because they appear as the first sign of disease. In this paper, we propose a three-stage system for early detection of MAs using filter banks. In the first stage, the system extracts all possible candidate regions for MAs present in retinal image. In order to classify a candidate region as MA or non-MA, the system formulates a feature vector for each region depending upon certain properties, i.e. shape, color, intensity and statistics. We present a hybrid classifier which combines the Gaussian mixture model (GMM), support vector machine (SVM) and an extension of multimodel mediod based modeling approach in an ensemble to improve the accuracy of classification. The proposed system is evaluated using publicly available retinal image databases and achieved higher accuracy which is better than previously published methods. © 2012 Elsevier Ltd All rights reserved. Source

Hamid Z.,National University of Sciences and Technology | Hussain F.B.,Bahria University
Wireless Personal Communications | Year: 2014

The emergence of wireless multimedia sensor networks (WMSN) has given birth to several civilian as well as defense applications. Some of the interesting applications employing low cost sensor nodes to manipulate rich multimedia content include traffic monitoring, border surveillance, smart homes, environment and habitat monitoring. Unlike the traditional sensor networks which are aimed at maximizing network lifetime by decreasing energy utilization, the main objective of WMSNs is optimized delivery of multimedia content along with energy efficiency. Multimedia communications in WMSNs, has stringent delay and high bandwidth requirement as compared to scalar data transfer in WSNs. Fulfilling these constraints in resource and energy constrained WMSNs is a huge challenge. In WMSNs, each layer of the protocol stack is responsible and fully involved in providing QoS guarantees. There is a need for new schemes at each layer of the protocol stack- from advanced coding techniques that reduce encoder complexity and achieve maximum compression to dynamic routing and MAC protocols that provide service differentiation and reduce end-to-end latency. In wireless sensor networks, where all layers have dependency on each other, QoS guarantees are possible through the cross layer interaction of different layers. This paper gives an overview of the different existing layered schemes in WMSNs, followed by a discussion on the significance and efficiency gains that can be achieved from cross layer interactions in WMSNs along with the review of the existing cross layer approaches. Finally, we identify the open research issues which have not been adequately addressed so far. © 2013 Springer Science+Business Media New York. Source

Khalid S.,Bahria University | Razzaq S.,National University of Sciences and Technology
Pattern Recognition | Year: 2012

This paper presents an extension of m-mediods based modeling technique to cater for multimodal distributions of sample within a pattern. The classification of new samples and anomaly detection is performed using a novel classification algorithm which can handle patterns with underlying multivariate probability distributions. We have proposed two frameworks, namely MMC-ES and MMC-GFS, to enable our proposed multivarite m-mediods based modeling and classification approach workable for any feature space with a computable distance metric. MMC-ES framework is specialized for finite dimensional features in Euclidean space whereas MMC-GFS works on any feature space with a computable distance metric. Experimental results using simulated and complex real life dataset show that multivariate m-mediods based frameworks are effective and give superior performance than competitive modeling and classification techniques especially when the patterns exhibit multivariate probability density functions. © 2011 Elsevier Ltd. All rights reserved. Source

Zaman K.,COMSATS Institute of Information Technology | Mushtaq Khan M.,COMSATS Institute of Information Technology | Ahmad M.,Bahria University
Renewable and Sustainable Energy Reviews | Year: 2013

The purpose of this study is to identify major macroeconomic factors that enhance energy consumption for Pakistan through the cointegration, error correction model and Granger causality tests over a 32-year time period, i.e., between 1980 and 2011. The study employed the bivariate cointegration technique to estimate the long-run relationship between the variables; an error correction model was used to determine the short-run dynamics of the system, while Granger causality test was used to find the directions between these variables. The study investigates the relation between four energy consumption variables (i.e., oil/petroleum consumption, gas consumption, electricity consumption and coal consumption) and four macroeconomic factors which have further sub-classifications, i.e., balance of payment (BOP) factors (i.e., exports, imports, trade deficit, worker's remittances and current account balance), fuel factors (i.e., carbon dioxide emissions, natural resource depletion and net forest depletion), agricultural crops yield per hectare (i.e., wheat, rice, sugarcane, maize and cotton) and industrial production items (i.e., beverages, cigarettes, motor tyres, motor tubes, cycle tyres and cycle tubes) in order to manage robust data analysis. The result confirms the long-run relationship between total commercial energy consumption and macroeconomic factors in Pakistan, as oil/petroleum consumption increases exports, fuel factors, agricultural crops yield per hectare and industrial items; however, the intensity of these factors are different in nature. Carbon dioxide emissions, net forest depletion, beverages, motor tyres and motor tubes are more elastic with oil/petroleum consumption. However, oil/petroleum consumption decreases trade deficit and workers' remittances in Pakistan. Gas, electricity and coal consumption increases agricultural crops yield per hectare and industrial production which shows that as agriculture and industry modernizes, energy demand increases. Energizing the food production chain is an essential feature of agricultural development which is a prime factor in helping to achieve food security in Pakistan. The empirical results only moderately support the conventional view that energy consumption has significant long-run casual effect on macroeconomic variables in Pakistan. The present study finds evident of unidirectional causality between the commercial energy consumption factors and macroeconomic factors in Pakistan. However, there is some bidirectional causality exist which is running between electricity consumption (EC) and exports, EC to imports, EC to carbon emissions, EC to natural resource depletion (NRD) and EC to wheat. The results conclude that macroeconomic variables tend to positively respond to total primary energy consumption. This indicates that increasing total commercial energy consumption may cause growth variables which show that Pakistan is an input-driven economy. © 2012 Elsevier Ltd. Source

Akram M.U.,Bahria University | Khan S.A.,National University of Sciences and Technology
Engineering with Computers | Year: 2013

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results. © 2012 Springer-Verlag London Limited. Source

Discover hidden collaborations