Krishnan Rangarajan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Krishnan Rangarajan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Abhinandan H. Patil
BITS Pilani,Goa, Zuari Nagar, Goa, India
1 shared publication Mukunda K Das
Dayananda Sagar College of Engineering, Bengaluru, India
1 shared publication- Neena Goveas
Birla Institute of Technology and Science, Pilani 333031, India
1 shared publication - Prashanth C. Ravoor
PES University
1 shared publication Ramesh Babu D.R.
Computer Science and Engineering Department, Dayananda Sagar College of Engineering, Bengaluru
1 shared publication- Tekal Subramanyam Babu Sudarshan
PES University
1 shared publication
Latest Publications
- 26 March 2021
- Published by Springer Nature
- p. 186-200
Digital Borders: Design of an Animal Intrusion Detection System Based on Deep Learning
- 26 March 2021
- Published by Springer Nature
- p. 186-200
Digital Borders: Design of an Animal Intrusion Detection System Based on Deep Learning
- 14 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 37-40
Performance Monitoring of Industrial Rotary Equipment using AI/ML Techniques
Industrial AI is the application of Artificial Intelligence and Machine Learning techniques to optimise production, increase safety and reliability of industrial equipment and manufacturing plants. The purpose of this paper is to document and compare different AI/ML techniques and their efficacy when used with data in the industrial manufacturing context. These techniques have been compared with each other in their performance on datasets recorded from select mechanical equipment used in the factories. The paper details the use of methods such as ANN and LSTM and their applicability to this domain. The comparison of results and discussion will enable the reader to choose the appropriate method for a given scenario.
- 14 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 37-40
Performance Monitoring of Industrial Rotary Equipment using AI/ML Techniques
Industrial AI is the application of Artificial Intelligence and Machine Learning techniques to optimise production, increase safety and reliability of industrial equipment and manufacturing plants. The purpose of this paper is to document and compare different AI/ML techniques and their efficacy when used with data in the industrial manufacturing context. These techniques have been compared with each other in their performance on datasets recorded from select mechanical equipment used in the factories. The paper details the use of methods such as ANN and LSTM and their applicability to this domain. The comparison of results and discussion will enable the reader to choose the appropriate method for a given scenario.
- Open Access
- 23 March 2016
- Published by Defence Scientific Information and Documentation Centre in Defence Science Journal
- Vol. 66 (2) , 122-129
Multi-object Tracking in Aerial Image Sequences using Aerial Tracking Learning and Detection Algorithm
Vison based tracking in aerial images has its own significance in the areas of both civil and defense applications. A novel algorithm called aerial tracking learning detection which works on the basis of the popular tracking learning detection algorithm to effectively track single and multiple objects in aerial images is proposed in this study. Tracking learning detection (TLD) considers both appearance and motion features for tracking. It can handle occlusion to certain extent, and can work well on long duration video sequences. However, when objects are tracked in aerial images taken from platforms like unmanned air vehicle, the problems of frequent pose change, scale and illumination variations arise adding to low resolution, noise and jitter introduced by motion of the camera. The proposed algorithm incorporates compensation for the camera movement, algorithmic modifications in combining appearance and motion cues for detection and tracking of multiple objects and enhancements in the form of inter object distance measure for improved performance of the tracker when there are many identical objects in proximity. This algorithm has been tested on a large number of aerial sequences including benchmark videos, TLD dataset and many classified unmanned air vehicle sequences and has shown better performance in comparison to TLD.
- 23 March 2016
- Published by Defence Scientific Information and Documentation Centre in Defence Science Journal
- Vol. 66 (2) , 122-129
Open AccessMulti-object Tracking in Aerial Image Sequences using Aerial Tracking Learning and Detection Algorithm
Vison based tracking in aerial images has its own significance in the areas of both civil and defense applications. A novel algorithm called aerial tracking learning detection which works on the basis of the popular tracking learning detection algorithm to effectively track single and multiple objects in aerial images is proposed in this study. Tracking learning detection (TLD) considers both appearance and motion features for tracking. It can handle occlusion to certain extent, and can work well on long duration video sequences. However, when objects are tracked in aerial images taken from platforms like unmanned air vehicle, the problems of frequent pose change, scale and illumination variations arise adding to low resolution, noise and jitter introduced by motion of the camera. The proposed algorithm incorporates compensation for the camera movement, algorithmic modifications in combining appearance and motion cues for detection and tracking of multiple objects and enhancements in the form of inter object distance measure for improved performance of the tracker when there are many identical objects in proximity. This algorithm has been tested on a large number of aerial sequences including benchmark videos, TLD dataset and many classified unmanned air vehicle sequences and has shown better performance in comparison to TLD.
- Open Access
- 3 April 2015
- Published by Association for Computing Machinery (ACM) in ACM SIGSOFT Software Engineering Notes
- Vol. 40 (2) , 1-3
Re-architecture of Contiki and Cooja Regression Test Suites using Combinatorial Testing Approach
In this paper, we describe how combinatorial testing can be applied to re-architecture Contiki and Cooja regression test suites. Contiki is the popular and widely accepted internet of things operating system. Combinatorial testing was pioneered by National Institute of Standards and Technology. National Institute of Standards and Technology offers a set of tools to public. One such tool is Automated Combinatorial Testing for Software. We describe how Automated Combinatorial Testing for Software can be used to generate a complete test suite for Contiki and Cooja. Coverage of base test suite is gathered using CodeCover, a code coverage tool for Java. The low percentage of coverage in Cooja indicated the need for a redesign of test suite. Once the base regression test suite is modified using Combinatorial Testing approach, it can be the new base regression test suite.
- 3 April 2015
- Published by Association for Computing Machinery (ACM) in ACM SIGSOFT Software Engineering Notes
- Vol. 40 (2) , 1-3
Open AccessRe-architecture of Contiki and Cooja Regression Test Suites using Combinatorial Testing Approach
In this paper, we describe how combinatorial testing can be applied to re-architecture Contiki and Cooja regression test suites. Contiki is the popular and widely accepted internet of things operating system. Combinatorial testing was pioneered by National Institute of Standards and Technology. National Institute of Standards and Technology offers a set of tools to public. One such tool is Automated Combinatorial Testing for Software. We describe how Automated Combinatorial Testing for Software can be used to generate a complete test suite for Contiki and Cooja. Coverage of base test suite is gathered using CodeCover, a code coverage tool for Java. The low percentage of coverage in Cooja indicated the need for a redesign of test suite. Once the base regression test suite is modified using Combinatorial Testing approach, it can be the new base regression test suite.