Wyniki wyszukiwania - BazTech

1

An intelligible deep convolution neural network based approach for classification of diabetic retinopathy

Sharma S., Maheshwari S., Shukla A.

Bio-Algorithms and Med-Systems

|

2018

|

Vol. 14, no. 2

art. no. 20180011

EN

Deep convolution neural networks (CNNs) have demonstrated their capabilities in modern-day medical image classification and analysis. The vital edge of deep CNN over other techniques is their ability to train without expert knowledge. Time bound detection is very beneficial for the early cure of disease. In this paper, a deep CNN architecture is proposed to classify nondiabetic retinopathy and diabetic retinopathy fundus eye images. Kaggle 2015 diabetic retinopathy competition dataset and messier experiment dataset are used in this study. The proposed deep CNN algorithm produces significant results with 93% area under the curve (AUC) for the Kaggle dataset and 91% AUC for the Messidor dataset. The sensitivity and specificity for the Kaggle dataset are 90.22% and 85.13%, respectively; the corresponding values of the Messidor dataset are 91.07% and 80.23%, respectively. The results outperformed many existing studies. The present architecture is a promising tool for diabetic retinopathy image classification.

2

State of the Art of Ex-Situ Aluminium Matrix Composite Fabrication through Friction Stir Processing

Gangil N., Siddiquee A. N., Maheshwari S., Al-Ahmari A. M., Abidi M. H.

Archives of Metallurgy and Materials

|

2018

|

Vol. 63, iss. 2

719--738

EN

Aluminium metal matrix composites (AMMCs) are the fastest developing materials for structural applications. Friction Stir Processing (FSP) has evolved as a promising surface composite fabrication technique mainly because it is an eco-friendly and solid-state process. A spurt in the interest of research community and a resulting huge research output makes it difficult to find relevant information to further the research with objectivity. To facilitate this, the present article addresses the current state of the art and development in surface metal matrix fabrication through FSP with a specific focus on ex-situ routes. The available literature has been carefully read and categorized to present effects of particle size, morphology and elemental composition. The effect of various reinforcements on development of different functional characteristics is also discussed. Effect of main FSP parameters on various responses is presented with objectivity. Based on the studied literature concluding summary is presented in a manner in which the literature becomes useful to the researchers working on this important technology.

3

Some new results on information transmission over noisy channels

Maheshwari S., Srivastava A.

Demonstratio Mathematica

|

2015

|

Vol. 48, nr 3

462--472

EN

Information transmission over communication channels has been characterized by weighted information schemes involving probabilities and weights. Binary erasure channel has been used as an example for determination of constants in the proposed measure.