Novel neural network modeling method and applications

Neural networks play an important role for designing the parametric model of electromagnetic structures. The current neural network methods are unfit for a circuit model with many input variables because it is costly to extract a large number of the training data and test data to complete the highly nonlinear mapping approximation. This article proposes a new neural network modeling method—the multidimensional neural network model, which can be used to solve the issue of multivariable radiofrequency and microwave passive device modeling. The entire multidimensional neural network modeling problem is simplified into a set of neural network submodels through decomposition method. Then the submodels are combined into an equivalent model, and the final entire model is produced through the neural‐network mapping model developed with the submodels and equivalent model. A microstrip hairpin filter model is developed using the proposed method. The simulation results show the correctness and the effectivity of the proposed method. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:769–779, 2015.     

Design of a compact dual‐band folded‐waveguide bandpass filter using multilayer waveguide resonators

A novel compact dual‐band bandpass filter based on multilayer folded‐waveguide (FWG) structure is presented in this article.In this design, slots are used to realize direct coupling between adjacent resonators and apertures are adopted to implement cross coupling between non‐adjacent resonators.A new technique of external quality factor of FWG resonator and coupling coefficients between different resonators are studied using full‐wave simulator. In order to demonstrate the proposed technique, a four‐pole dual‐band bandpass filter is designed, fabricated and measured using vector network analyzer. Measurement results which are well agreed with simulation results are presented. Moreover, four‐pole substrate integrated folded waveguide SIFW dual‐band bandpass filter, using two layers of slotted folded waveguide resonators, is demonstrated. The proposed filter has a compact size and it is excellent candidate for the application of wireless communication systems. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:780–788, 2015.     

Novel ultra‐compact two‐dimensional waveguide‐based metasurface for electromagnetic coupling reduction of microstrip antenna array

A novel ultracompact two‐dimensional (2D) waveguide‐based metasurface is proposed herein and applied for the first time to reduce mutual coupling in antenna array for multiple‐input multiple‐output applications. The unit cell of the proposed 2D waveguide‐based metasurface is ultracompact (8.6 mm × 4.8 mm, equal to λ₀/14.2 × λ₀/25.5) mainly due to the symmetrical spiral lines etched on the ground. The metasurface exhibits a bandgap with two transmission zeros attributing to the negative permeability in the vicinity of magnetic resonance and the negative permittivity in the vicinity of electric resonance. Taking advantage of these two features, a microstrip antenna array is then designed, fabricated, and measured by embedding an 8 × 1 array of the well‐engineered 2D waveguide‐based metasurface elements between two closely spaced (9.2 mm, equal to λ₀/13.3) H‐plane coupled rectangular patches. There is good agreement between the simulated and measured results, indicating that the metasurface effectively reduces antenna mutual coupling by more than 11.18 dB and improves forward gain. The proposed compact structure has one of the highest reported decoupling efficiencies among similar periodic structures with comparable dimensions. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:789–794, 2015.     

Exploring the Relationship Between Green Consumption Value,Satisfaction, and Loyalty to Hybrid Car in Elderly Consumers

The study aimed to examine the relationship between green consumption value, satisfaction, and loyalty of driving hybrid cars among elderly consumers. Data were collected from a cross‐sectional survey of 314 elderly consumers who purchased hybrid cars in the United States. A partial least squares analysis revealed that elderly consumers’ social, price, and quality values positively influenced the satisfaction of their hybrid car experience, and their satisfaction significantly influenced their loyalty of hybrid car. The relationship between green consumption value, satisfaction, and loyalty toward driving hybrid cars among elderly consumers revealed insight into their value orientations toward the hybrid car. Special efforts are suggested in promoting hybrid car use to elderly consumer groups. Marketers should pay attention to changing beliefs and increasing perceived values of driving a hybrid car for consumers to encourage them to use green products.     

Recurrent neural network technique for behavioral modeling of power amplifier with memory effects

A new technique for behavioral modeling of power amplifier (PA) with short‐ and long‐term memory effects is presented here using recurrent neural networks (RNNs). RNN can be trained directly with only the input–output data without having to know the internal details of the circuit. The trained models can reflect the behavior of nonlinear circuits. In our proposed technique, we extract slow‐changing signals from the inputs and outputs of the PA and use these signals as extra inputs of RNN model to effectively represent long‐term memory effects. The methodology using the proposed RNN for modeling short‐term and long‐term memory effects is discussed. Examples of behavioral modeling of PAs with short‐ and long‐term memory using both the existing dynamic neural networks and the proposed RNNs techniques are shown. © 2014 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:289–298, 2015.     

Wide passband/stopband bandpass filter based on transversal signal interference concepts and modified branch‐line structure

A high selectivity wide passband filter with a broader stopband based on transversal signal‐interaction concepts and modified branch line structure (MBLS) is developed in this article. Two transmission paths, that is, one half‐wavelength transmission line and one MBLS, are used to realize signal transmission from Port 1 to Port 2. Then, two transmission zeros are introduced at both lower and upper sides of the passband, which are used to improve the passband selectivity greatly. The filter bandwidth can be easily controlled by reasonable adjusting the coupling coefficient of the coupled lines. Furthermore, with four stubs connected at the input/output ports, the stopband attenuation level is improved greatly. Finally, one prototype filter having 69.1% of 3 dB fractional bandwidth is fabricated with advantages of sharp selectivity and high out‐of‐band rejection. The EM simulated and measured results are presented, and an excellent agreement can be obtained. © 2014 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:330–336, 2015.     

Extracting Microfacet‐based BRDF Parameters from Arbitrary Materials with Power Iterations

We introduce a novel fitting procedure that takes as input an arbitrary material, possibly anisotropic, and automatically converts it to a microfacet BRDF. Our algorithm is based on the property that the distribution of microfacets may be retrieved by solving an eigenvector problem that is built solely from backscattering samples. We show that the eigenvector associated to the largest eigenvalue is always the only solution to this problem, and compute it using the power iteration method. This approach is straightforward to implement, much faster to compute, and considerably more robust than solutions based on nonlinear optimizations. In addition, we provide simple conversion procedures of our fits into both Beckmann and GGX roughness parameters, and discuss the advantages of microfacet slope space to make our fits editable. We apply our method to measured materials from two large databases that include anisotropic materials, and demonstrate the benefits of spatially varying roughness on texture mapped geometric models.     

Smooth Loops from Unconstrained Video

Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence‐based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch‐based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.