Time filter

Source Type

Girdhar A.,Guru Nanak Institutions | Gupta S.,Panjab University | Bhullar J.,Malout Institute of Management and Information Technology
Journal of Medical Imaging and Health Informatics | Year: 2015

Medical ultrasound images suffer from multiplicative speckle noise that degrades the image quality, thus making automatic image analysis difficult. Many despeckling methods have been reported till date for ultrasound images, but most of them fail to enhance curved edges as these inhibit smoothing near the edges. In this paper, an adaptive technique for image denoising via thresholding of curvelet coefficients using a weighted window is proposed. The proposed scale adaptive threshold exploits the intra-band dependencies present in the curvelet coefficients using weighted variance for every pixel of the curvelet wedges except at the coarse scale. The weights of local window are proposed based on predominant directional correlations for reliable statistical dependencies in curvelet domain. In addition, a tuning parameter, image tuner is devised to assist the radiologists to control the degree of smoothness of the processed image. The proposed technique is evaluated on simulated as well as on real ultrasound images with the help of objective quality measures and clinical evaluations, respectively. Experimental results show that the proposed technique exhibits substantial improvement in terms of all quality metrics when compared with spatial filters, wavelet and curvelet based counterparts. Evaluations show that the proposed technique suppresses speckle effectively while preserving the fine details that are essential for better diagnosis and image analysis. Copyright © 2015 American Scientific Publishers

Girdhar A.,Guru Nanak Institutions | Gupta S.,Panjab University | Bhullar J.,Malout Institute of Management and Information Technology
Advanced Science Letters | Year: 2015

Medical ultrasound images are degraded due to multiplicative speckle noise, thus making automatic image analysis difficult. In most of the existing despeckling approaches, first logarithmic transform (homomorphic approach) is applied to transform the multiplicative speckle model to an additive one, and then wavelet or curvelet filtering is done on the log-transformed image, followed by an exponential transformation. Moreover, most of the despeckling techniques reported in literature inhibit smoothing near the edges and fail to enhance curved edges. However, these homomorphic approaches increases the computation time, complexity of the filtering method and it also leads to biased estimation of the signal. To address these limitations, an adaptive non-homomorphic technique for despeckling of medical ultrasound images via thresholding of curvelet coefficients is proposed. The proposed threshold is adaptive as it relies on standard deviation, mean and median of curvelet coefficients. This technique is evaluated qualitatively and quantitatively on simulated as well as on real ultrasound images. Experimental results depict that the proposed technique exhibits substantial improvement in terms of all quality metrics when compared with other spatial filters, wavelet and curvelet counterparts. Further, visual evaluations show that the proposed technique is effective in speckle reduction and retains the fine details that are necessary for better image analysis. © 2015 American Scientific Publishers. All rights reserved.

Singh R.,International Management Institute | Sandhu H.S.,CKD Institute of Management and Technology | Metri B.A.,International Management Institute | Kaur R.,Malout Institute of Management and Information Technology
International Journal of Information Systems and Supply Chain Management | Year: 2014

Supply chain is the process of continuous flow of products or services from source to the destination. Supply chain management has become an effective tool now a day to survive in this competitive world. Organizations do their best to harvest profits by adopting better supply chain management practices for competitive advantage and organizational performance. In this paper an attempt has been made to understand the relationship among supply chain practices, competitive advantage, and organizational performance using structural equation modelling. This research conceptualizes and develops five secondary dimensions of supply chain practices (Use of technology, SC speed, Customer satisfaction, SC integration, and Inventory management). The research also identifies four primary competitive advantage components (Inventory management, Customer satisfaction, Profitability, and Customer base identification) and six primary organizational performance components (Financial Performance, Market performance, SC competencies, Customer satisfaction, Stakeholder satisfaction, and Innovation and learning). The data for analysis was collected from top 10 non-livestock organized retail players operating in Punjab, Haryana, Chandigarh, New Delhi and, Gurgaon in India. The relationships in the proposed framework were tested using structural equation modelling. The results indicate that Indian retailers know that competitive advantage has high impact on SCP but they have less understanding in matching SCP and competitive advantage with organizational performance. Copyright © 2014, IGI Global.

Kumar G.,Malout Institute of Management and Information Technology | Kumar K.,Alagappa Chettiar College of Engineering And Technology
Security and Communication Networks | Year: 2012

Feature selection methods play a significant role during classification of data having high dimensions of features. The methods select most relevant subset of features that describe data appropriately. Mutual information (MI) based upon information theory is one of the metrics used for measuring relevance of features. This paper analyses various feature selection methods for (1) reduction in number of features; (2) performance of Naïve Bayes classification model trained on reduced set of features. Research gaps identified are: (1) computation of MI from the whole sample space instead of unclassified sample subspace; (2) consideration of relevance of features only or tradeoff between relevance and redundancy, but class conditional interaction of features is ignored. In this paper, we propose a general evaluation function using MI for feature selection. The proposed evaluation function is implemented which use dynamically computed MI values from unclassified instances. Effectiveness of the proposed feature selection method is done empirically by comparing classification results using KDD 1999 benchmarked dataset of intrusion detection. The results indicate practicability and effectiveness of the proposed method for applications concerned with high accuracy and stability of predictions. © 2011 John Wiley & Sons, Ltd.

Sharma J.,Malout Institute of Management and Information Technology | Sidhu B.S.,Punjab Technical University
Journal of Cleaner Production | Year: 2014

Millions of gallons of metal working fluids are used each day in industry for cutting, milling, drilling, stamping, and grinding. But Metal working fluids has been found causing very much damage to employee health and environmental pollution. High production volume, the large number of occupationally-exposed workers, and the lack of carcinogenicity and chronic toxicology data of metal working fluids demands a careful scrutiny. The aim of this research is to investigate the effects of dry and near dry machining (NDM) on AISI D2 steel by using an environmental friendly vegetable oil as a lubricant and to completely eliminate the mineral and petroleum based harmful lubricants from turning process. The high carbon high chromium AISI D2 steel was turned at various feed and speed combinations by using Tungsten carbide insert (CNMG12408). The results have been compared with dry machining and near dry machining. The experimental results indicate that near dry machining shows promising results over dry machining in terms of work-tool interface temperature and surface roughness. In order to obtain a good cutting performance by NDM, it is considered that at higher speeds better surface finish properties are obtained. Therefore, it is suggested that near dry machining, provides environment friendliness, cleaner production and can also help to improve the desirable machinability characteristics up to certain extent. © 2013 Elsevier Ltd. All rights reserved.

Discover hidden collaborations