Novel neural network optimization approach for modeling scattering and noise parameters of microwave transistor

Şenel, Bilge; Şenel, Fatih Ahmet

doi:10.1002/jnm.2930

Cited by 11 publications

(5 citation statements)

References 36 publications

(117 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scattering parameters or the S‐parameters are crucial parameters for the analysis of any semiconductor devices as it does not only give insights into RF performance but also on other trappings, thermal and noise related behavior 39,50,75 . Figure 7A–C depicts the S‐parameter matching for sample A and Figure 7D–F shows the S‐parameter matching for sample B at different operating conditions.…”

Section: Resultsmentioning

confidence: 99%

“…Scattering parameters or the S-parameters are crucial parameters for the analysis of any semiconductor devices as it does not only give insights into RF performance but also on other trappings, thermal and noise related behavior. 39,50,75 Figure 8C shows the overall model time computational efficiency. As depicted in Figure 8C, the extremely low prediction time (in range of milliseconds) over training time (8-10 s) directs excellent computational and time capabilities of the proposed framework and its compatibility with the realtime events.…”

Section: S-parameter and Current Gain Estimationmentioning

confidence: 99%

“…The accuracy of parameter extraction procedural calls greatly depends on the optimization techniques and the consideration of various process-dependent parameters for which different optimization techniques have also been explored. [47][48][49] Senel et al 50 have presented artificial neural network (ANN) based generalized regression neural network (GRNN) and multilayer perceptron neural network (MLPNN) with four different optimization methods: whale optimization algorithm (WOA), artificial bee colony (ABC), particle swarm optimization (PSO), and ant-lion optimizer (ALO) algorithms. ANN is another widely used mathematical approach for RF and microwave device modeling.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Multilayer perceptron–random forest based hybrid machine learning–neural network model for GaN high electron mobility transistor's parameter estimations

Mishra

Raut

Sehra

et al. 2022

Int J RF Mic Comp-Aid Eng

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: S-parameter and Current Gain Estimationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Multilayer perceptron–random forest based hybrid machine learning–neural network model for GaN high electron mobility transistor's parameter estimations

Mishra

Raut

Sehra

et al. 2022

Int J RF Mic Comp-Aid Eng

View full text Add to dashboard Cite

“…These layers include the input layer, hidden layer, and output layer. It comprises several nested neurons that are processed by adding the input and weight products for the hidden layer [34]. Once the data is computed in the hidden layer with an activation function, it will be sent to the output layer, which has an activation function that depends on the type of prediction.…”

Section: Multi-layer Perceptron Neural Networkmentioning

confidence: 99%

Improving the Avoidant Personality Disorder Prediction for Higher Education Using SMOTE-ENN and Multi-Layer Perceptron Neural Network

Nuanmeesri

Poomhiran

2023

TEM Journal

View full text Add to dashboard Cite

Adolescents in higher education are more prone to Avoidant Personality Disorder (AVPD), which strongly affects academic achievement. The goal of this study was to create models for accurate prediction of the likelihood of Avoidant Personality Disorder among students in higher education. Information Gain, Gain Ratio, and Wrapper Approach are used as feature selection methods combined with data resampling techniques and machine learning, including Multi-Layer Perceptron Neural Network, Naïve Bayes, Decision Tree, Random Forest, and Support Vector Machine. The findings revealed that the Wrapper approach gave higher accuracy than Information Gain and Gain Ratio approach. Further, using the Gain Ratio approach gives the model a slightly higher efficiency than the Information Gain. Furthermore, when comparing feature selection and data resampling, it was found that the model using feature selection had more higher model efficiency than data resampling alone. Additionally, combining the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbor (SMOTE-ENN) considerably increased the model’s effectiveness. Finally, the model’s efficiency was at its maximum, with an accuracy of 95.52%, when the Wrapper approach was used in conjunction with the Synthetic Minority Over-sampling Technique, the Edited Nearest Neighbor algorithm, and the Multi-Layer Perceptron Neural Network.

show abstract

“…This includes a sufficient coverage of the input and output space of the model through appropriate sampling strategies, as well as the exclusion of samples from certain regions of the space 4 . For example, in modelling of microwave transistor for LNA designs, a designer might want to exclude training samples pertinent to higher DC currents, where the transistor would not act as an amplifier, or can only use a narrow range of frequency samples from the provided data, corresponding to the target application [22][23][24][25][26][27][28][29][30] . Such methods can significantly increase the performance of ANN models by reducing the complexity of the dataset, yet, might be detrimental for the versatility of the ANN-based modeling framework.…”

mentioning

confidence: 99%

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Çalık

Güneş

Kozieł

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Accurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning (DL), have been found suitable for this task by capitalizing on their flexibility and generality. Yet, rendering reliable transistor surrogates is hindered by a number of issues such as the need for finding good match between the input data and the network architecture and hyperparameters (number and sizes of layers, activation functions, data pre-processing methods), possible overtraining, etc. This work proposes a novel methodology, referred to as Fully Adaptive Regression Model (FARM), where all network components and processing functions are automatically determined through Tree Parzen Estimator. Our technique is comprehensively validated using three examples of microwave transistors and demonstrated to offer a competitive edge over the state-of-the-art methods in terms of modeling accuracy and handling the aforementioned issues pertinent to standard ANN-based surrogates.

show abstract

Novel neural network optimization approach for modeling scattering and noise parameters of microwave transistor

Cited by 11 publications

References 36 publications

Multilayer perceptron–random forest based hybrid machine learning–neural network model for GaN high electron mobility transistor's parameter estimations

Multilayer perceptron–random forest based hybrid machine learning–neural network model for GaN high electron mobility transistor's parameter estimations

Improving the Avoidant Personality Disorder Prediction for Higher Education Using SMOTE-ENN and Multi-Layer Perceptron Neural Network

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Contact Info

Product

Resources

About