Keyur Mahant

Dr. Keyur Mahant

CHARUSAT University
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 September 2022 in Alexandria Engineering Journal
Verified
Journal Article
Open access
Amit PatelAmit Patel
Amit Patel
Arpan DesaiArpan Desai
Arpan Desai
Issa ElferganiIssa Elfergani
Issa Elfergani
AVAlpesh Vala
Alpesh Vala
Hiren K MewadaHiren K Mewada
Hiren K Mewada
Esraa Mousa AliEsraa Mousa Ali
Esraa Mousa Ali

22 August 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Hiren K MewadaHiren K Mewada
Hiren K Mewada
Amit PatelAmit Patel
Amit Patel
Mahmoud HassaballahMahmoud Hassaballah
Mahmoud Hassaballah
MAMonagi Alkinani
Monagi Alkinani
Keyur MahantKeyur Mahant
Keyur Mahant
Cancer identification and classification from histopathological images of the breast depends greatly on experts, and computer-aided diagnosis can play an important role in disagreement of experts. This automatic process has increased the accuracy of the classification at a reduced cost. The advancement in Convolution Neural Network (CNN) structure has outperformed the traditional approaches in biomedical imaging applications. One of the limiting factors of CNN is it uses spatial image features only for classification. The spectral features from the transform domain have equivalent importance in the complex image classification algorithm. This paper proposes a new CNN structure to classify the histopathological cancer images based on integrating the spectral features obtained using a multi-resolution wavelet transform with the spatial features of CNN. In addition, batch normalization process is used after every layer in the convolution network to improve the poor convergence problem of CNN and the deep layers of CNN are trained with spectral–spatial features. The proposed structure is tested on malignant histology images of the breast for both binary and multi-class classification of tissue using the BreaKHis Dataset and the Breast Cancer Classification Challenge 2015 Datasest. Experimental results show that the combination of spectral–spatial features improves classification accuracy of the CNN network and requires less training parameters in comparison with the well known models (i.e., VGG16 and ALEXNET). The proposed structure achieves an average accuracy of 97.58% and 97.45% with 7.6 million training parameters on both datasets, respectively.

26 April 2022 in Electronics
Verified
Journal Article
Open access
PDF file
Amit PatelAmit Patel
Amit Patel
AVAlpesh Vala
Alpesh Vala
Arpan DesaiArpan Desai
Arpan Desai
Issa ElferganiIssa Elfergani
Issa Elfergani
Hiren K MewadaHiren K Mewada
Hiren K Mewada
JRJonathan Rodriguez
Jonathan Rodriguez
Interconnected three-element and four-element wideband MIMO antennas have been proposed for millimeter-wave 5G applications by performing numerical computations and carrying out experimental measurements. The antenna structure is realized using Rogers 5880 substrate (εr = 2.2, tan δ = 0.0009), where the radiating element has the shape of an inverted L with a partial ground. The unit element is carefully designed and positioned (by orthogonally rotating the elements) to form three-element (case 1) and four-element (case 2) MIMO antennas. The interconnected ground for both cases is ascertained to increase the practical utilization of the resonator. The proposed MIMO antenna size is (0.95λ × 3λ) for case 1 and (2.01λ × 1.95λ) for case 2 (at the lowest functional frequency). Both the designs give an impedance bandwidth of approximately 26–40 GHz (43%). Moreover, they achieve greater than 15 dB isolation and more than 6 dBi gain with an ECC value lower than 0.02, which meets the MIMO diversity performance thus making the three-element and four-element MIMO antennas the best choice for millimeter-wave 5G applications.

6 May 2018 in Journal of Electromagnetic Waves and Applications
Verified
Journal Article
Closed access
Amit PatelAmit Patel
Amit Patel
RGRiddhi Goswami
Riddhi Goswami
AVAlpesh Vala
Alpesh Vala
Keyur MahantKeyur Mahant
Keyur Mahant
Hiren K MewadaHiren K Mewada
Hiren K Mewada
SKS. V. Kulkarni
S. V. Kulkarni
The paper presents overmoded circular waveguide mode converters (TE01 into HE11 with TE11 as an intermediate mode) used in a 42 ± 0.2 GHz, 200 kW gyrotron transmission line system for plasma heating in electron cyclotron resonance heating application. To convert mode from TE01 to TE11, we have used wriggle converter method with a deformation in the converter axis and for TE11 to HE11 mode converter the depth of corrugation decreases gradually from to . Both the converters are optimized in terms of design parameters using mode field matching technique. The TE01 to TE11 mode converter showed a conversion efficiency of 95% (predicted 99%) for a length of 1205 mm, while TE11 to HE11 mode converter gave conversion efficiency of 99% (predicted 99.98%) for a diameter of 32 mm. Cross-polarization isolation of 31.7 dB is obtained in TE11 to HE11 mode converter. Convergence of the theoretical values and the simulated results indicates that the converters meet the system requirements.

19 October 2015 in International Journal of Microwave Science and Technology
Verified
Journal Article
Open access
PDF file
JKJahnavi Kachhia
Jahnavi Kachhia
Amit PatelAmit Patel
Amit Patel
AVAlpesh Vala
Alpesh Vala
RPRomil Patel
Romil Patel
Keyur MahantKeyur Mahant
Keyur Mahant
This paper represents new generation of slotted antennas for satellite application where the loss can be compensated in terms of power or gain of antenna. First option is very crucial because it totally depends on size of satellite so we have proposed the high gain antenna creating number of rectangular, trapezoidal, and I shape slots in logarithm size in Substrate Integrated Waveguide (SIW) structure. The structure consists of an array of various shape slots antenna designed to operate in C and X band applications. The basic structures have been designed over a RT duroid substrate with dielectric constant of 2.2 and with a thickness of 0.508 mm. Multiple slots array and shape of slot effects have been studied and analyzed using HFSS (High Frequency Structure Simulator). The designs have been supported with its return loss, gain plot, VSWR, and radiation pattern characteristics to validate multiband operation. All the proposed antennas give gain more than 9 dB and return loss better than −10 dB. However, the proposed structures have been very sensitive to their physical dimensions.

27 March 2017 in Microwave and Optical Technology Letters
Verified
Journal Article
Closed access
PDF file
AVAlpesh Vala
Alpesh Vala
Amit PatelAmit Patel
Amit Patel
RGRiddhi Goswami
Riddhi Goswami
Keyur MahantKeyur Mahant
Keyur Mahant