scholarly journals Estimation of Different Performance Parameters of Slotted Microstrip Antennas with Air-Gap Using Neural Networks

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Taimoor Khan ◽  
Asok De
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Neural Model ◽  
Microstrip Antennas ◽  
Air Gap ◽  
Performance Parameters ◽  
Dual Frequency ◽  
The Past ◽  
Resonance Frequencies ◽  
Good Agreement

Over the past decade, artificial neural networks have emerged as fast computational medium for predicting different performance parameters of microstrip antennas due to their learning and generalization features. This paper illustrates a neural network model for instantly predicting the resonance frequencies, gains, directivities, antenna efficiencies, and radiation efficiencies for dual-frequency operation of slotted microstrip antennas with air-gap. The proposed neural model is valid for any arbitrary slot-dimensions and inserted air-gap within their specified ranges. A prototype is fabricated using Roger’s substrate and its performance is measured for validation. A very good agreement is achieved in simulated, predicted, and measured results.

scholarly journals Prediction of Slot Shape and Slot Size for Improving the Performance of Microstrip Antennas Using Knowledge-Based Neural Networks

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Taimoor Khan ◽  
Asok De
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prior Knowledge ◽  
Neural Model ◽  
Microstrip Antennas ◽  
Performance Parameters ◽  
Dual Frequency ◽  
Knowledge Based ◽  
Slot Size ◽  
Good Agreement

In the last decade, artificial neural networks have become very popular techniques for computing different performance parameters of microstrip antennas. The proposed work illustrates a knowledge-based neural networks model for predicting the appropriate shape and accurate size of the slot introduced on the radiating patch for achieving desired level of resonance, gain, directivity, antenna efficiency, and radiation efficiency for dual-frequency operation. By incorporating prior knowledge in neural model, the number of required training patterns is drastically reduced. Further, the neural model incorporated with prior knowledge can be used for predicting response in extrapolation region beyond the training patterns region. For validation, a prototype is also fabricated and its performance parameters are measured. A very good agreement is attained between measured, simulated, and predicted results.

Performance parameters prediction of slotted microstrip antennas with modified ground plane using support vector machine

2016 ◽  
Vol 9 (5) ◽  
pp. 1169-1177 ◽  
Author(s):  
Chandan Roy ◽  
Taimoor Khan ◽  
Binod Kumar Kanaujia
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Resonant Frequency ◽  
Ground Plane ◽  
Microstrip Antennas ◽  
Support Vector ◽  
Performance Parameters ◽  
Local Minima ◽  
Vector Machines ◽  
Good Agreement

Artificial neural networks (ANNs) have acquired enormous importance in computing of the performance parameters of microstrip antennas due to their generalized and adaptive features. However, recently the concept of support vector machines (SVMs) has become very much popular in performance parameters computation due to several attractive features over ANNs. Specifically, SVMs outreach ANNs noticeably in terms of execution time. Likewise, ANNs are having multiple local minima problem, whereas a global and unique solution is provided by SVMs. In this paper, several performance parameters like: resonant frequency, gain, directivity, and radiation efficiency of slotted microstrip antennas with modified ground plane are computed with the help of SVM formulation. Comparisons of different parameters of simulated and computed values are illustrated. The achieved radiation patterns at particular resonant frequency in different planes are included as well. A prototype of the optimized antenna is also fabricated and characterized. A good agreement is attained among the computed, simulated, and measured results.

scholarly journals A Neural Network Aided Real-Time Hospital Recommendation System

2020 ◽  
Vol 5 (2) ◽  
pp. 217-235
Author(s):  
Om Adideva Paranjay ◽  
V Rajeshkumar
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Time ◽  
Recommendation System ◽  
Healthcare Providers ◽  
Geographical Location ◽  
Neural Model ◽  
The Past ◽  
Trained Neural Network ◽  
The Right

Over the past few years, there have been an overwhelming number of healthcare providers, hospitals and clinics. In such a situation, finding the right hospital for the right ailment can be a considerable challenge. Inspired by this challenge, this work attempts to build a model that can automatically recommend hospitals based on user requirements. In the past there have been important works in physician recommendation.  Our proposed work aims to be more inclusive and provide an automated hospital recommendation system to patients based on neural networks driven classification. We suggest a model that considers several unique parameters, including geographical location. To optimize its usefulness, we design a system that recommends hospitals for general consultation, specialty hospitals, and in view of the pandemic, hospitals recommended for treatment of COVID-19. In this work, we adopt Neural Networks and undertake a comparative analysis between several different available supervised algorithms to identify one best suited neural architecture that can work best in the applied fields. Based on our results from the analysis, we train the selected neural network with context relevant data. In the image of the recommendation system, we develop a website that uses the trained neural network on its backend and displays the recommendation results in a manner interpretable by the end user. We highlight the process of choosing the right neural model for the backend of the website.  To facilitate the working of the website in real-time, we use real time databases hosted on Google Firebase and edge devices on hospital ends. Additionally, we suggest two hospital side data updation tools. These tools would ensure that hospitals can update the parameters which change quickly in the real world to their latest values so as to maintain the precision of the system. We test the website with test data and find that the website recommends hospitals with sufficient precision in the specified format. The model has been designed with the limited amount of data available in this field, but its performance and utility can be easily improved with better quality and more abundant data.

scholarly journals A Generalized ANN Model for Analyzing and Synthesizing Rectangular, Circular, and Triangular Microstrip Antennas

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Taimoor Khan ◽  
Asok De
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Microstrip Antennas ◽  
Computational Technique ◽  
Performance Parameters ◽  
Ann Model ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Good Agreement

Since last one decade, artificial neural network (ANN) models have been used as fast computational technique for different performance parameters of microstrip antennas. Recently, the concept of creating a generalized neural approach for different performance parameters has been motivated in microstrip antennas. This paper illustrates a generalized neural approach for analyzing and synthesizing the rectangular, circular, and triangular MSAs, simultaneously. Such approach is very much required for the antenna designers for getting instant answer for the required parameters. Here, total seven performance parameters of three different MSAs are computed using generalized neural approach as such a method is rarely available in the open literature even for computing more than three performance parameters, simultaneously. The results thus obtained are in very good agreement with the measured results available in the referenced literature for all seven cases.

scholarly journals Hardware Neural Networks Modeling for Computing Different Performance Parameters of Rectangular, Circular, and Triangular Microstrip Antennas

2014 ◽  
Vol 2014 ◽  
pp. 1-11
Author(s):  
Taimoor Khan ◽  
Asok De
Keyword(s):  
Neural Networks ◽  
Low Cost ◽  
Microstrip Antennas ◽  
Performance Parameters ◽  
Neural Models ◽  
Hardware Platform ◽  
Generalized Neural Networks ◽  
Field Programmable ◽  
The Neural Networks ◽  
Good Agreement

In the last one decade, neural networks-based modeling has been used for computing different performance parameters of microstrip antennas because of learning and generalization features. Most of the created neural models are based on software simulation. As the neural networks show massive parallelism inherently, a parallel hardware needs to be created for creating faster computing machine by taking the advantages of the parallelism of the neural networks. This paper demonstrates a generalized neural networks model created on field programmable gate array- (FPGA-) based reconfigurable hardware platform for computing different performance parameters of microstrip antennas. Thus, the proposed approach provides a platform for developing low-cost neural network-based FPGA simulators for microwave applications. Also, the results obtained by this approach are in very good agreement with the measured results available in the literature.

scholarly journals Semiotic Aggregation in Deep Learning

Entropy ◽  
2020 ◽  
Vol 22 (12) ◽  
pp. 1365
Author(s):  
Bogdan Muşat ◽  
Răzvan Andonie
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Decision Model ◽  
Deep Neural Networks ◽  
Neural Model ◽  
Network Layers ◽  
Saliency Maps ◽  
Spatial Entropy ◽  
Insight Into

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.

Design of a microstrip dual-frequency diplexer using microstrip cells analysis and coupled lines components

2017 ◽  
Vol 9 (7) ◽  
pp. 1467-1471 ◽  
Author(s):  
Leila Noori ◽  
Abbas Rezaei
Keyword(s):  
General Structure ◽  
Basic Information ◽  
Dual Frequency ◽  
Wireless Applications ◽  
Resonance Frequencies ◽  
Measurement Results ◽  
Coupled Lines ◽  
Lc Circuit ◽  
Insertion Losses ◽  
Good Agreement

In this paper, a microstrip diplexer composed of two similar resonators is designed. The proposed resonator is consisting of four microstrip cells, which are connected to a coupled lines structure. In order to select a suitable geometric structure, first, all cells are assumed as undefined structures where there is a lack of basic information about their geometry and dimensions. Then, an equivalent LC circuit of the coupled lines is introduced and analyzed to estimate the general structure of the resonator respect to a requested resonance frequency. The proposed diplexer is designed to operate at 2.36 and 4 GHz for wireless applications. The insertion losses (S21 and S31) are decreased significantly at the resonance frequencies, so that they are 0.2 and 0.4 dB at 2.36 and 4 GHz, respectively. The designed diplexer is fabricated and measured and the measurement results are in a good agreement with the simulations.

Efficiency testing of artificial neural networks in predicting the properties of carbon nanomaterials as potential systems for nervous tissue stimulation and regeneration

2017 ◽  
Vol 13 (1) ◽  
Author(s):  
Martyna Sasiada ◽  
Aneta Fraczek-Szczypta ◽  
Ryszard Tadeusiewicz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Nervous Tissue ◽  
Carbon Nanomaterials ◽  
Real Life ◽  
Neural Model ◽  
Carbon Nanomaterial ◽  
Neural Models ◽  
Predictive Learning ◽  
The Many

AbstractA new method of predicting the properties of carbon nanomaterials from carbon nanotubes and graphene oxide, using electrophoretic deposition (EPD) on a metal surface, was investigated. The main goal is to obtain the basis for nervous tissue stimulation and regeneration. Because of the many variations of the EPD method, costly and time-consuming experiments are necessary for optimization of the produced systems. To limit such costs and workload, we propose a neural network-based model that can predict the properties of selected carbon nanomaterial systems before they are produced. The choice of neural networks as predictive learning models is based on many studies in the literature that report neural models as good interpretations of real-life processes. The use of a neural network model can reduce experimentation with unpromising methods of systems processing and preparation. Instead, it allows a focus on experiments with these systems, which are promising according to the prediction given by the neural model. The performed tests showed that the proposed method of predictive learning of carbon nanomaterial properties is easy and effective. The experiments showed that the prediction results were consistent with those obtained in the real system.

scholarly journals The Use of Neural Networks in High-Energy Physics

1993 ◽  
Vol 5 (4) ◽  
pp. 505-549 ◽  
Author(s):  
Bruce Denby
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
High Energy Physics ◽  
High Energy ◽  
High Quality ◽  
Network Algorithms ◽  
The Past ◽  
The Neural Network ◽  
Energy Physics

In the past few years a wide variety of applications of neural networks to pattern recognition in experimental high-energy physics has appeared. The neural network solutions are in general of high quality, and, in a number of cases, are superior to those obtained using "traditional'' methods. But neural networks are of particular interest in high-energy physics for another reason as well: much of the pattern recognition must be performed online, that is, in a few microseconds or less. The inherent parallelism of neural network algorithms, and the ability to implement them as very fast hardware devices, may make them an ideal technology for this application.

Sign in / Sign up

Export Citation Format

Share Document