scispace - formally typeset
Search or ask a question
Institution

National Institute of Technology, Silchar

EducationSilchar, Assam, India
About: National Institute of Technology, Silchar is a education organization based out in Silchar, Assam, India. It is known for research contribution in the topics: Control theory & Electric power system. The organization has 1934 authors who have published 4219 publications receiving 41149 citations. The organization is also known as: NIT Silchar.


Papers
More filters
Journal ArticleDOI
01 Dec 2017
TL;DR: The class imbalance problem of network pruning is overcome to improve the accuracy of the hybrid CBR, which adopts a cost-sensitive back-propagation neural network (BPNN) in network pruned to find feature weights.
Abstract: Case-based reasoning (CBR) is an artificial intelligent approach to learning and problem-solving, which solves a target problem by relating past similar solved problems. But it faces the challenge of weights assignment to features to measure similarity between cases. There are many methods to overcome this feature weighting problem of CBR. However, neural network’s pruning is one of the powerful and useful methods to overcome this feature weighting problem, which extracts feature weights from trained neural network without losing the generality of training set by four popular mechanisms: sensitivity, activity, saliency and relevance. It is habitually assumed that the training sets used for learning are balanced. However, this hypothesis is not always true in real-world applications, and hence, the tendency is to yield classification models that are biased toward the overrepresented class. Therefore, a hybrid CBR system is proposed in this paper to overcome this problem, which adopts a cost-sensitive back-propagation neural network (BPNN) in network pruning to find feature weights. These weights are used in CBR. A single cost parameter is used by the cost-sensitive BPNN to distinguish the importance of class errors. A balanced decision boundary is generated by the cost parameter using prior information. Thus, the class imbalance problem of network pruning is overcome to improve the accuracy of the hybrid CBR. From the empirical results, it is observed that the performance of the proposed hybrid CBR system is better than the hybrid CBR by standard neural network. The performance of the proposed hybrid system is validated with seven datasets.

26 citations

Journal ArticleDOI
TL;DR: In this article, a non-uniform channel with double-material source and compressed drain TFET structure is introduced, and the simulation results show that the proposed structure has a minimum point SS of 9mV/decade and an average SS of 22mV /decade for a wide range of gate voltages.
Abstract: Tunnel FET is the well-built candidate in the field of low-power ICs mainly because of its lower subthreshold swing (SS). But its ON current is relatively small and ambipolar current is high. The advantage of having a lower SS does not hold for higher gate voltages, which leads to higher average SS. In this paper, for the first time, a non-uniform channel with double-material source and compressed drain TFET structure is introduced. The simulation results show that the proposed structure has a minimum point SS of 9 mV/decade and an average SS of 22 mV/decade for a wide range of gate voltages. In addition, the ambipolar current, ON current, and OFF current are obtained to be 10−14 A/μm, 10−5 A/μm, and 10−16 A/μm, respectively, which lead to a remarkable value of the ON–OFF current ratio of about 1011. The effects of trap charge at oxide/semiconductor interface for different trap charge distributions have been investigated. Finally, it is observed that as compared to uniform distribution traps, Gaussian distribution traps degrade the characteristics in terms of ON–OFF current ratio and SS.

26 citations

Journal ArticleDOI
TL;DR: An excellent efficiency of the recommended DPD is confirmed over the state-of-the-art algorithms and suitable mutation strategies for both DE and PSO are investigated over a set of existing 8 popular mutation strategies which results 64 variants of DPD.

26 citations

Journal ArticleDOI
01 May 2015-Energy
TL;DR: In this paper, the authors established an analytical method for predicting the performance of a fully wet constructal T-shaped fin assembly under dehumidifying conditions, where temperature and humidity ratio differences are the driving forces for heat and mass transfer, respectively.

26 citations


Authors

Showing all 2010 results

Network Information
Related Institutions (5)
Indian Institute of Technology Roorkee
21.4K papers, 419.9K citations

94% related

Indian Institutes of Technology
40.1K papers, 652.9K citations

92% related

Indian Institute of Technology Delhi
26.9K papers, 503.8K citations

92% related

Indian Institute of Technology Kharagpur
38.6K papers, 714.5K citations

91% related

Indian Institute of Technology Madras
36.4K papers, 590.4K citations

91% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202335
2022149
2021947
2020742
2019596
2018451