Institution
National Institute of Technology, Raipur
Education•Raipur, Chhattisgarh, India•
About: National Institute of Technology, Raipur is a education organization based out in Raipur, Chhattisgarh, India. It is known for research contribution in the topics: Computer science & Fault (power engineering). The organization has 1549 authors who have published 3229 publications receiving 25258 citations. The organization is also known as: NIT Raipur & Govt. College of Mining & Metallurgy.
Topics: Computer science, Fault (power engineering), Wireless sensor network, Fault detection and isolation, Support vector machine
Papers published on a yearly basis
Papers
More filters
••
36 citations
••
TL;DR: In this article, the authors discuss the parameters which are believed to be the primary factors that affect material wear rate and several mechanisms and equations suggested by various researchers for the prediction of wear of materials are also reviewed.
Abstract: Pipeline transportation of slurry is being carried out all over the world. Slurry pipeline wear is one of the major problems associated with it. The wear rate of the slurry pipeline depends upon factors such as slurry properties, slurry particle properties, flow properties, and pipeline wall properties. Any change in these properties results in change in pipeline wear rate. There is a need to study the effect of individual properties, for predicting the slurry pipeline life span and also to find the methods to minimize the wear rate. In this review paper, an attempt has been made to discuss the parameters which are believed to be the primary factors that affect material wear rate. Several mechanisms and equations suggested by various researchers for the prediction of wear of materials are also reviewed. Most of the models incorporate the effects of only few parameters involved during the wear process. These equations are specific and valid up to limited operating conditions. No general equation ha...
36 citations
••
TL;DR: In this article, the creep and stress relaxation properties of the VHB 4910 elastomer have been investigated and it has been shown that the material possesses strong time-dependent stress relaxation.
Abstract: Dielectric elastomers (DEs) are gaining acceptance as potential actuator materials because of their exhibition of a large amount of deformation when stimulated by electrostatic forces. However, time-dependent behaviour such as creep and stress relaxation still pose a great challenge for the design, modelling and control of the DE-based actuators. In this work, attempts are made for experimental estimation and modelling of creep and relaxation properties of one of the most widely used dielectric acrylic elastomers, VHB 4910. Experimental investigation shows that the material possesses strong time-dependent creep and stress relaxation. It has been shown that creep and stress relaxation characteristics vary with the holding stress and holding strain respectively. Creep and stress relaxation properties are also shown to depend on the number of cycles in the case of cyclic loading. Results also show that Findley's power law can successfully model the creep and stress relaxation behaviour of the VHB 4910 elastomer.
36 citations
••
01 Sep 2017TL;DR: It is observed that the SMOTE ENN method detects the fraud in a better way than other classifiers in the set of oversampling techniques considered, and TL works better on theSet of undersampled techniques taken.
Abstract: The number of online transactions has unraveled in large proportions with each passing day. Credit card transactions constitute a huge portion of these transactions. The financial losses have also increased analogously along with the credit card fraud transactions. Therefore, fraud detection systems have acquired great importance for banks and financial institutions. As the occurrence of fraud is unlikely in comparison to normally occurring transactions, we are posed with the class imbalance problem and to handle this imbalance problem we use resampling techniques in this paper. We applied oversampling (SMOTE, SMOTE ENN, SAFE SMOTE, ROS, SMOTE TL). On the resampled data, we applied cost sensitive (CSVM, C4.5) and ensemble classifier (Adaboost, Bagging) to evaluate the performances using sensitivity, specificity, G-mean, Area under ROC. We observed that the SMOTE ENN method detects the fraud in a better way than other classifiers in the set of oversampling techniques considered, and TL works better on the set of undersampling techniques taken.
36 citations
Authors
Showing all 1625 results
Name | H-index | Papers | Citations |
---|---|---|---|
Shyam Sundar | 86 | 614 | 30289 |
Arun Kumar | 81 | 384 | 26259 |
Yogesh Sharma | 59 | 261 | 12027 |
Anil Kumar | 44 | 1411 | 11378 |
Xiangliang Pan | 43 | 227 | 5699 |
Rajesh Kumar | 37 | 525 | 6193 |
Subhamoy Bhattacharya | 33 | 198 | 3469 |
Vinod Kumar Singh | 32 | 186 | 3797 |
Kamlesh Shrivas | 26 | 98 | 2120 |
Varun Bajaj | 26 | 132 | 2791 |
Manoranjan Dash | 24 | 72 | 7720 |
Awanish Kumar | 24 | 141 | 2064 |
Anup Sharma | 23 | 99 | 3301 |
Manish Mishra | 22 | 56 | 1275 |
Pradeep Kumar Singh | 22 | 234 | 1720 |