Dr. B. Khuntia - Academia.edu (original) (raw)

Papers by Dr. B. Khuntia

Research paper thumbnail of Initializing artificial neural networks by genetic algorithm to calculate the resonant frequency of single shorting post rectangular patch antenna

IEEE Antennas and Propagation Society International Symposium. Digest. Held in conjunction with: USNC/CNC/URSI North American Radio Sci. Meeting (Cat. No.03CH37450)

A simple and accurate method for calculating the resonant frequency of a rectangular microstrip p... more A simple and accurate method for calculating the resonant frequency of a rectangular microstrip patch antenna with a single shorting post by using the artificial neural networks is presented in this paper. Genetic algorithm is used to select the initial weights of artificial neural networks. The calculated resonant frequency is compared with experimental results. The results are in very good agreement with experimental results with decreased computational time.

Research paper thumbnail of Tunnel based artificial neural networks to calculate the radiation pattern of commercially available cell phone antenna in presence of human head

2002 IEEE International Conference on Personal Wireless Communications

ABSTRACT An efficient way to calculate the radiation pattern of a cellular telephone antenna in f... more ABSTRACT An efficient way to calculate the radiation pattern of a cellular telephone antenna in free space as well as in the presence of a human head is presented in this paper. A tunnel based artificial neural network has been used which takes less computational time compared to the backpropagation method while giving accurate results. The results obtained are in good agreement with experimental findings.

Research paper thumbnail of Inverted L-shaped and parasitically coupled inverted L-shaped microstrip patch antennas for wide bandwidth

Microwave and Optical Technology Letters, 2004

Coax-fed inverted L-shaped microstrip antennas and parasitically coupled inverted L-microstrip an... more Coax-fed inverted L-shaped microstrip antennas and parasitically coupled inverted L-microstrip antennas are presented. The inverted L-shaped microstrip antenna gives an impedance bandwidth of 30.6%, which is increased to 33.7% by parasitic coupling. The bandwidth has been achieved with a substrate thickness of 2 mm. Radiation patterns and gains are also studied and presented.

Research paper thumbnail of Genetic algorithm with artificial neural networks as its fitness function to design rectangular microstrip antenna on thick substrate

Microwave and Optical Technology Letters, 2004

Basic standard for the measurement of specific absorption rate related to human exposure to elect... more Basic standard for the measurement of specific absorption rate related to human exposure to electromagnetic fields from mobile phones (300 MHz-3 GHz), European standard, 2001.

Research paper thumbnail of A simple and efficient approach to train artificial neural networks using a genetic algorithm to calculate the resonant frequency of an RMA on thick substrate

Microwave and Optical Technology Letters, 2004

Both genetic algorithms (GAs) and artificial neural networks (ANNs) have been used in the field o... more Both genetic algorithms (GAs) and artificial neural networks (ANNs) have been used in the field of computational electromagnetics as the most powerful optimizing tools. In this paper, a simple and efficient method is presented to handle the problem of competing convention while training an ANN by using a GA. This technique is applied to calculate the resonant frequency of a thick-substrate rectangular microstrip antenna (RMA). The training time is less than that of a normal feed-forward backpropagation algorithm. The measured results are in very good agreement with experimental results.

Research paper thumbnail of Design of a wideband microstrip antenna and the use of artificial neural networks in parameter calculation

IEEE Antennas and Propagation Magazine, 2005

This paper deals with the design of a multi-slot hole-coupled microstrip antenna on a substrate o... more This paper deals with the design of a multi-slot hole-coupled microstrip antenna on a substrate of 2 mm thickness that gives mulMrequency (wideband) characteristics. The Method of Moments (MoM)-based IE3D software was used to simulate the results for return loss, VSWR, the Smith chart, and the radiation patterns. A tunnel-based artificial neural network (ANN) was also developed to calculate the radiation patterns of the antenna. The radiation patterns were measured experimentally at 10.5 GHz and 12 GHz. The experimental results were in good agreement with the simulated results from IE3D and those of the artificial neural network. A new method of using a genetic algorithm (GA) in an artificial neural network is also discussed. This new method was used to calculate the resonant frequency of a single-shorting-post microstrip antenna. The resonant frequency calculated using the genetic-algorithm-coupled artificial neural network was compared with the analytical and experimental results. The results obtained were in very good agreement with the experimental results.

Research paper thumbnail of Application of a genetic algorithm in an artificial neural network to calculate the resonant frequency of a tunable single-shorting-post rectangular-patch antenna

International Journal of RF and Microwave Computer-Aided Engineering, 2004

In this article, an efficient application of a genetic algorithm (GA) in an artificial neural net... more In this article, an efficient application of a genetic algorithm (GA) in an artificial neural network (ANN) to calculate the resonant frequency of a coaxially-fed tunable rectangular microstrip-patch antenna is presented. For a normal feed-forward back-propagation algorithm, with a compromise between time and accuracy, it is difficult to train the network to achieve an acceptable error tolerance. The selection of suitable parameters of ANNs in a feed-forward network leads to a high number of man-hours necessary to train a network efficiently. However, in the present method, the GA is used to reduce the man-hours while training a neural network using the feed forward-back-propagation algorithm. It is seen that the training time has also been reduced to a great extent while giving high accuracy. The results are in very good agreement with the experimental results.

Research paper thumbnail of Genetic algorithm with artificial neural networks as its fitness function to design rectangular microstrip antenna on thick substrate

Microwave and Optical Technology Letters, 2005

Over the years, genetic algorithms (GAs) have been applied in many applications. But the lack of ... more Over the years, genetic algorithms (GAs) have been applied in many applications. But the lack of a proper fitness function has been a hindrance to its widespread application in many cases. In this paper, a novel technique of using artificial neural networks (ANNs) as the fitness function of a genetic algorithm in order to calculate the design parameters of a thick substrate rectangular microstrip antenna is presented. A multilayer feed-forward neural network is used as the fitness function in a binary-coded genetic algorithm. The results obtained using this method are found to be closer to the experimental value, as compared to previous results obtained using the curve-fitting method. To validate this, the results are compared with the experimental values for five fabricated antennas. The results are in very good agreement with the experimental findings. © 2004 Wiley Periodicals, Inc. Microwave Opt Technol Lett 44: 144–146, 2005; Published online in Wiley InterScience (www.interscie...

Research paper thumbnail of Initializing artificial neural networks by genetic algorithm to calculate the resonant frequency of single shorting post rectangular patch antenna

IEEE Antennas and Propagation Society International Symposium. Digest. Held in conjunction with: USNC/CNC/URSI North American Radio Sci. Meeting (Cat. No.03CH37450)

A simple and accurate method for calculating the resonant frequency of a rectangular microstrip p... more A simple and accurate method for calculating the resonant frequency of a rectangular microstrip patch antenna with a single shorting post by using the artificial neural networks is presented in this paper. Genetic algorithm is used to select the initial weights of artificial neural networks. The calculated resonant frequency is compared with experimental results. The results are in very good agreement with experimental results with decreased computational time.

Research paper thumbnail of Tunnel based artificial neural networks to calculate the radiation pattern of commercially available cell phone antenna in presence of human head

2002 IEEE International Conference on Personal Wireless Communications

ABSTRACT An efficient way to calculate the radiation pattern of a cellular telephone antenna in f... more ABSTRACT An efficient way to calculate the radiation pattern of a cellular telephone antenna in free space as well as in the presence of a human head is presented in this paper. A tunnel based artificial neural network has been used which takes less computational time compared to the backpropagation method while giving accurate results. The results obtained are in good agreement with experimental findings.

Research paper thumbnail of Inverted L-shaped and parasitically coupled inverted L-shaped microstrip patch antennas for wide bandwidth

Microwave and Optical Technology Letters, 2004

Coax-fed inverted L-shaped microstrip antennas and parasitically coupled inverted L-microstrip an... more Coax-fed inverted L-shaped microstrip antennas and parasitically coupled inverted L-microstrip antennas are presented. The inverted L-shaped microstrip antenna gives an impedance bandwidth of 30.6%, which is increased to 33.7% by parasitic coupling. The bandwidth has been achieved with a substrate thickness of 2 mm. Radiation patterns and gains are also studied and presented.

Research paper thumbnail of Genetic algorithm with artificial neural networks as its fitness function to design rectangular microstrip antenna on thick substrate

Microwave and Optical Technology Letters, 2004

Basic standard for the measurement of specific absorption rate related to human exposure to elect... more Basic standard for the measurement of specific absorption rate related to human exposure to electromagnetic fields from mobile phones (300 MHz-3 GHz), European standard, 2001.

Research paper thumbnail of A simple and efficient approach to train artificial neural networks using a genetic algorithm to calculate the resonant frequency of an RMA on thick substrate

Microwave and Optical Technology Letters, 2004

Both genetic algorithms (GAs) and artificial neural networks (ANNs) have been used in the field o... more Both genetic algorithms (GAs) and artificial neural networks (ANNs) have been used in the field of computational electromagnetics as the most powerful optimizing tools. In this paper, a simple and efficient method is presented to handle the problem of competing convention while training an ANN by using a GA. This technique is applied to calculate the resonant frequency of a thick-substrate rectangular microstrip antenna (RMA). The training time is less than that of a normal feed-forward backpropagation algorithm. The measured results are in very good agreement with experimental results.

Research paper thumbnail of Design of a wideband microstrip antenna and the use of artificial neural networks in parameter calculation

IEEE Antennas and Propagation Magazine, 2005

This paper deals with the design of a multi-slot hole-coupled microstrip antenna on a substrate o... more This paper deals with the design of a multi-slot hole-coupled microstrip antenna on a substrate of 2 mm thickness that gives mulMrequency (wideband) characteristics. The Method of Moments (MoM)-based IE3D software was used to simulate the results for return loss, VSWR, the Smith chart, and the radiation patterns. A tunnel-based artificial neural network (ANN) was also developed to calculate the radiation patterns of the antenna. The radiation patterns were measured experimentally at 10.5 GHz and 12 GHz. The experimental results were in good agreement with the simulated results from IE3D and those of the artificial neural network. A new method of using a genetic algorithm (GA) in an artificial neural network is also discussed. This new method was used to calculate the resonant frequency of a single-shorting-post microstrip antenna. The resonant frequency calculated using the genetic-algorithm-coupled artificial neural network was compared with the analytical and experimental results. The results obtained were in very good agreement with the experimental results.

Research paper thumbnail of Application of a genetic algorithm in an artificial neural network to calculate the resonant frequency of a tunable single-shorting-post rectangular-patch antenna

International Journal of RF and Microwave Computer-Aided Engineering, 2004

In this article, an efficient application of a genetic algorithm (GA) in an artificial neural net... more In this article, an efficient application of a genetic algorithm (GA) in an artificial neural network (ANN) to calculate the resonant frequency of a coaxially-fed tunable rectangular microstrip-patch antenna is presented. For a normal feed-forward back-propagation algorithm, with a compromise between time and accuracy, it is difficult to train the network to achieve an acceptable error tolerance. The selection of suitable parameters of ANNs in a feed-forward network leads to a high number of man-hours necessary to train a network efficiently. However, in the present method, the GA is used to reduce the man-hours while training a neural network using the feed forward-back-propagation algorithm. It is seen that the training time has also been reduced to a great extent while giving high accuracy. The results are in very good agreement with the experimental results.

Research paper thumbnail of Genetic algorithm with artificial neural networks as its fitness function to design rectangular microstrip antenna on thick substrate

Microwave and Optical Technology Letters, 2005

Over the years, genetic algorithms (GAs) have been applied in many applications. But the lack of ... more Over the years, genetic algorithms (GAs) have been applied in many applications. But the lack of a proper fitness function has been a hindrance to its widespread application in many cases. In this paper, a novel technique of using artificial neural networks (ANNs) as the fitness function of a genetic algorithm in order to calculate the design parameters of a thick substrate rectangular microstrip antenna is presented. A multilayer feed-forward neural network is used as the fitness function in a binary-coded genetic algorithm. The results obtained using this method are found to be closer to the experimental value, as compared to previous results obtained using the curve-fitting method. To validate this, the results are compared with the experimental values for five fabricated antennas. The results are in very good agreement with the experimental findings. © 2004 Wiley Periodicals, Inc. Microwave Opt Technol Lett 44: 144–146, 2005; Published online in Wiley InterScience (www.interscie...