Ankur Choudhary

Prof. Dr. Ankur Choudhary

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 February 2021 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
PMPartha Sarathi Mangipudi
Partha Sarathi Mangipudi
HPHari Mohan Pandey
Hari Mohan Pandey
ACAnkur Choudhary
Ankur Choudhary
Glaucoma is an ailment causing permanent vision loss but can be prevented through the early detection. Optic disc to cup ratio is one of the key factors for glaucoma diagnosis. But accurate segmentation of disc and cup is still a challenge. To mitigate this challenge, an effective system for optic disc and cup segmentation using deep learning architecture is presented in this paper. Modified Groundtruth is utilized to train the proposed model. It works as fused segmentation marking by multiple experts that helps in improving the performance of the system. Extensive computer simulations are conducted to test the efficiency of the proposed system. For the implementation three standard benchmark datasets such as DRISHTI-GS, DRIONS-DB and RIM-ONE v3 are used. The performance of the proposed system is validated against the state-of-the-art methods. Results indicate an average overlapping score of 96.62%, 96.15% and 98.42% respectively for optic disc segmentation and an average overlapping score of 94.41% is achieved on DRISHTI-GS which is significant for optic cup segmentation.


14 March 2024
Verified
Conference Paper
Closed access
AKArshleen Kaur
Arshleen Kaur
VKVinay Kukreja
Vinay Kukreja
MKMukesh Kumar
Mukesh Kumar
ACAnkur Choudhary
Ankur Choudhary
RSRishabh Sharma
Rishabh Sharma
The detection of maize leaf disease is essential for food security and sustainable agriculture. Early maize leaf disease detection enables timely treatment, limiting crop losses and stopping the replication of diseases. Precise identification facilitates the application of focused interventions, maximizes the use of available resources, and guarantees a more robust yield of maize. In the end, this helps to sustain a steady supply of food and the livelihoods of those who depend on maize farming. This work investigates the use of a DenseNet model for maize leaf disease detection. The model has been supplied with different learning rate values as 0.1, 0.01, 0.001, and 0.0001. The optimizers during the implementation have been also changed to Adam and SGD. The highest accuracy has been achieved by the Adam optimizer at a learning rate of 0.01. The model performs best, demonstrating a 96.53% training accuracy and an even higher 97.43% testing accuracy. The loss of the model has been also analyzed as 0.1433, and 0.0948, during the training and testing phases. The results highlight denseNet’s effectiveness in precisely identifying diseases of the maize leaf, with promising implications for agricultural diagnostics. In the future, the model’s performance can be increased by expanding its identification of a wider variety of maize leaf diseases and combining the model with innovative agricultural technologies to monitor diseases in real-time and react quickly to new challenges associated with leaf diseases.

28 October 2016 in International Journal of System Assurance Engineering and Management
Verified
Journal Article
Closed access
PDF file
ACAnkur Choudhary
Ankur Choudhary
ABAnurag Singh Baghel
Anurag Singh Baghel
OSOm Prakash Sangwan
Om Prakash Sangwan

1 September 2014
Verified
Conference Paper
Closed access
JSJeelen Kumar Sarungbam
Jeelen Kumar Sarungbam
BKBhupendra Kumar
Bhupendra Kumar
ACAnkur Choudhary
Ankur Choudhary
India is a diverse country with various cultural and traditional differences. There are more than 12 distinguished different languages in the country, viz., Hindi, Bangla, Marathi, Oriya, Tamil, Telugu, Assamese, Manipuri, Gujarati, Kannada, Malayalam, Panjabi, Nepali, Tibetan, Urdu, etc. Optical Character Recognition (OCR) of Indian Languages needs to be designed in such a way that it automatically identifies the language of the input document for further processing. There are many techniques which are already implemented, but the problem lies in identifying and detecting the correct language as some of the languages uses the same or similar script. For example, the Bangla script is used to write - Bengali, Assamese and Manipuri languages. Though the scripts can be distinguished using global technique, the problem with languages having similar script still exist. To deal with this problem, a robust wavelet transform cumtemplate-matching invariant to rotation, scale and translation technique is deployed to identify the script and detect the language of the document automatically.

1 December 2017 in IET Software
Verified
Journal Article
Open access
PDF file
ACAnkur Choudhary
Ankur Choudhary
ABAnurag Singh Baghel
Anurag Singh Baghel
OSOm Prakash Sangwan
Om Prakash Sangwan
The primary challenge of software reliability growth model is to find the unknown model parameters that are used to validate on software failure dataset. Though, numerical estimation technique plays a vital role in parameter estimation of software reliability growth models, they are not optimal as they suffer from constraints sucha as sample size, biasing, and initialisation of parameters. In this study, a parameter estimation of software reliability growth model that utilises a variant of harmony search is proposed. Extensive experiments are conducted on seven different software datasets of varying complexity. A robust experimental setup is developed employing an orthogonal array and Taguchi method. Two‐fold performance comparisons are performed. First, the authors tested their proposed approach against Cuckoo search and numerical method (least square estimation) considering mean square error and Theil's statistics as a quality measure. Second, the authors applied statistical tests are performed that demonstrate the superiority of their approach over the others. The underlying motivation to conduct this study is to motivate researchers to utilise their approach for a better estimation of model parameters.