Bidirectional Deep Neural Network Research Articles

Customizable multifunctional metasurface absorber based on bidirectional deep neural networks covering the quasi-entire terahertz band

Customizable multifunctional metasurface absorber based on bidirectional deep neural networks covering the quasi-entire terahertz band

Evaluation and design of photothermal conversion performance for multiple “complex-morphology” nanofluids via bidirectional deep neural network

The optical absorption and scattering of plasmonic nanoparticles are crucial for optimizing photothermal conversion efficiency, which holds great potential in various applications. Evaluating the photothermal conversion performance of nanofluids with known geometry is a computationally expensive task. The design of nanofluids that exhibit optimal photothermal conversion performance poses a complex inverse problem. The necessity to explore a wide parameter space, which encompasses various factors such as the shape, size, and material of nanoparticles, contributes to this challenge. In this study, we employ a combination of machine learning with high-throughput radiative transfer calculations to conduct a comprehensive analysis of the entire photothermal conversion process for various nanofluids. The modulation of resonance absorption peaks and spectral absorption can be achieved by adjusting the shape, material constituents, and geometric parameters of nanoparticles. Meanwhile, we establish a design space dataset that encompasses 14,060 groups of nanofluids. Based on the dataset, we demonstrate as a proof of concept bidirectional deep neural network model that enables an efficient and reliable solution to both the forward and inverse problems. The results show that the absorptivity of SiO2@Au nanofluids is significantly influenced by the volume fraction, particularly when it falls within the range of 1 × 10−5 to 1 × 10−4. However, the impact is significantly reduced within the range of 1 × 10−4 to 1 × 10−3. Furthermore, the SiO2@Au nanofluids exhibit enhanced full spectral absorption characteristics at the core-shell ratio of 0.1. Our proposed model achieves a forward prediction of the solar absorption spectra with 99% accuracy and an inverse design of the geometric parameter with 93% accuracy. In comparison to the experimental results, the relative errors for the predicted and design efficiency are 0.42% and 0.82%, respectively. The design geometry parameters including the effective radius and volume fraction exhibit relative errors of 3.88% and 1.6%, respectively. This work provides a widely applicable and computationally efficient method for the evaluation and design of nanofluids in photothermal conversion.

A novel multifactor clustering integration paradigm based on two-stage feature engineering and improved bidirectional deep neural networks for exchange rate forecasting

Accurate exchange rate forecasting is of great importance for foreign exchange investment, hedging foreign exchange risk and international economic transactions. However, it is extremely challenging to make accurate forecasts for exchange rates because of their high volatility, nonlinearity, and non-stationarity. Based on this, this paper proposes a multifactor clustering integration paradigm for exchange rate prediction. From the classical theory of exchange rate determination, a comprehensive library of factors affecting the exchange rate is constructed. A two-stage feature engineering is constructed to capture the stable structure of features. In order to enable features to be learned adequately and to improve algorithmic efficiency and predictive performance, a novel clustering integration paradigm is constructed to improve the stability of the model. The framework builds different predictive sub-models for different data, and then embeds Bayesian optimization algorithms into the bidirectional deep neural networks. Finally, the output results of different sub-models are integrated using nonlinear integration techniques. In addition, the superiority of the proposed model is verified using eight comparative models. The results of the empirical analysis show that the average percentage error of our proposed model is the lowest among all the comparative models (0.412648 %, 0.515348 %, and 0.329892 % on the three datasets, respectively). Compared to the standard LSTM, the average percentage error is at least 88 % lower, proving the effectiveness of the proposed model. It can help investors to make better decisions in the international financial markets.

Exploiting bi-directional deep neural networks for multi-domain sentiment analysis using capsule network

Exploiting bi-directional deep neural networks for multi-domain sentiment analysis using capsule network

A Capability Fitting and Data Reconstruction Model Based on Particle Swarm Optimization-Bidirectional Deep Neural Network for Search and Rescue System of Systems

Search and rescue (SAR) is an important part of joint operations and a key support for combat effectiveness. Because of the complex composition of the SAR system of systems (SoS), sensitivity analysis method is usually used to carry out sensitivity analysis of SoS capability, so as to determine the main design indicators affecting SoS capability. Reliable sensitivity analysis results are often based on the analysis for sufficient data. However, the SAR SoS capability is affected by many factors and there are numerous design indicators. Even if a small number of design points are selected for each design indicator, tens of thousands of test schemes will be formed, and carrying out all simulation tests will bring huge workload and time cost. To solve this contradiction, this paper introduces a bidirectional deep neural network (BDNN), and takes advantage of its better self-learning and adaptive features and unique structure to train the existing test data, Through strong feature extraction ability of BDNN, the network model between the design indicator and capability indicator is formed, namely, the capability fitting and data reconstruction (CFDR) model, so that the implicit relationship between the two is fixed into the model. In the training process, the number of hidden layers and neurons in each hidden layer, and the amount of training data are explored according to the training effect, so as to obtain a better parameter combination. In order to avoid introducing large cumulative errors accumulated during BDNN pre-training into DNN, particle swarm optimization (PSO) was introduced to optimize weight parameters and avoid large training errors being transmitted to deep neural network (DNN). Meanwhile, three basic functions were used to verify the strong global optimization and convergence abilities of the BDNN after optimized by the PSO (PSO-BDNN). Finally, the new test scheme is applied to the CFDR model to obtain the SoS capability value. The reconstructed data obtained from the CFDR model based on BDNN and PSO-BDNN respectively were compared with the simulation test data.The results show that the reconstruction accuracy of the CFDR model based on the PSO-BDNN is greatly improved than that of the BDNN. And the feasibility of this model as a reconstruction data generation model and the effectiveness of this model as an analysis data extension method applied to the sensitivity analysis of insufficient data to obtain reliable analysis results are verified.

Metasurfaces designed by a bidirectional deep neural network and iterative algorithm for generating quantitative field distributions

Metasurfaces designed by a bidirectional deep neural network and iterative algorithm for generating quantitative field distributions

Multi-User Joint Detection Using Bi-Directional Deep Neural Network Framework in NOMA-OFDM System.

Non-orthogonal multiple access (NOMA) has great potential to implement the fifth-generation (5G) requirements of wireless communication. For a NOMA traditional detection method, successive interference cancellation (SIC) plays a vital role at the receiver side for both uplink and downlink transmission. Due to the complex multipath channel environment and prorogation of error problems, the traditional SIC method has a limited performance. To overcome the limitation of traditional detection methods, the deep-learning method has an advantage for the highly efficient tool. In this paper, a deep neural network which has bi-directional long short-term memory (Bi-LSTM) for multiuser uplink channel estimation (CE) and signal detection of the originally transmitted signal is proposed. Unlike the traditional CE schemes, the proposed Bi-LSTM model can directly recover multiuser transmission signals suffering from channel distortion. In the offline training stage, the Bi-LTSM model is trained using simulation data based on channel statistics. Then, the trained model is used to recover the transmitted symbols in the online deployment stage. In the simulation results, the performance of the proposed model is compared with the convolutional neural network model and traditional CE schemes such as MMSE and LS. It is shown that the proposed method provides feasible improvements in performance in terms of symbol-error rate and signal-to-noise ratio, making it suitable for 5G wireless communication and beyond.

Evaluation and Design of Colored Silicon Nanoparticle Systems Using a Bidirectional Deep Neural Network.

Silicon nanoparticles (SiNPs) with lowest-order Mie resonance produce non-iridescent and non-fading vivid structural colors in the visible range. However, the strong wavelength dependence of the radiation pattern and dielectric function makes it very difficult to design nanoparticle systems with the desired colors. Most existing studies focus on monodisperse nanoparticle systems, which are unsuitable for practical applications. This study combined the Lorentz–Mie theory, Monte Carlo, and deep neural networks to evaluate and design colored SiNP systems. The effects of the host medium and particle size distribution on the optical and color properties of the SiNP systems were investigated. A bidirectional deep neural network achieved accurate prediction and inverse design of structural colors. The results demonstrated that the particle size distribution flattened the Mie resonance peak and influenced the reflectance and brightness of the SiNP system. The SiNPs generated vivid colors in all three of the host media. Meanwhile, our proposed neural network model achieved a near-perfect prediction of colors with high accuracy of the designed geometric parameters. This work accurately and efficiently evaluates and designs the optical and color properties of SiNP systems, thus accelerating the design process and contributing to the practical production design of color inks, decoration, and printing.

Multi-Parameter Inversion of AIEM by Using Bi-Directional Deep Neural Network

A novel multi-parameter inversion method is proposed for the Advanced Integral Equation Model (AIEM) by using bi-directional deep neural network. There is a very complex nonlinear relationship between the surface parameters (dielectric constant and roughness) and radar backscattering coefficient. The traditional inverse neural network, which is constructed by using the backscattering coefficients as the input and the surface parameters as the output, leads to bad convergence and wrong results. This is because many sets of surface parameters can get the same backscattering coefficient. Therefore, the proposed bi-directional deep neural network starts with building an AIEM-based forward deep neural network (AIEM-FDNN), whose inputs are the surface parameters and outputs are the backscattering coefficients. In this way, the weights and biases of the forward deep neural network can be optimized and predicted, which can be used for the backward deep neural network (AIEM-BDNN). Then, the multi-parameters are updated by minimizing the loss between the output backscattering coefficients with the measured ones. By inserting a sigmoid function between the input and the first hidden layer, the input multi-parameters can be efficiently approximated and continuously updated. As a result, both the forward and backward deep neural networks can be built with these weights and biases. By sharing the weights and biases of the forward network, the training of the inverse network is avoided. The bi-directional deep neural network can not only predict the backscattering coefficient but can also inverse the surface parameters. Numerical results are given to demonstrate that the RMSE of the backscattering coefficients calculated by the proposed bi-directional neural network can be reduced to 0.1%. The accuracy of the inversion parameters, including the real and imaginary parts of the dielectric constant, the root mean square height and the correlation length, can be improved to 97.56%, 91.14%, 99.04% and 98.45%, respectively. At the same time, the bi-directional neural network also has good accuracy for the inversion of the POLARSCAT measured data.

Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancer.

Aims: This study presents a survival stratification model based on multi-omics integration using bidirectional deep neural networks (BiDNNs) in gastric cancer. Methods: Based on the survival-related representation features yielded by BiDNNs through integrating transcriptomics and epigenomics data, K-means clustering analysis was performed to cluster tumor samples into different survival subgroups. The BiDNNs-based model was validated using tenfold cross-validation and in two independent confirmation cohorts. Results: Using the BiDNNs-based survival stratification model, patients were grouped into two survival subgroups with log-rank p-value=9.05E-05. The subgroups classification was robustly validated in tenfold cross-validation (C-index=0.65±0.02) and in two confirmation cohorts (E-GEOD-26253, C-index=0.609; E-GEOD-62254, C-index=0.706). Conclusion: We propose and validate a robust and stable BiDNN-based survival stratification model in gastric cancer.

Bidirectional deep neural networks to integrate RNA and DNA data for predicting outcome forpatients withhepatocellular carcinoma.

Aims: Individualized patient profiling is instrumental for personalized management in hepatocellular carcinoma (HCC). This study built a model based on bidirectional deep neural networks (BiDNNs), an unsupervised machine-learning approach, to integrate multi-omics data and predict survival in HCC. Methods: DNA methylation and mRNA expression data for HCC samples from the The Cancer Genome Atlas database were integrated using BiDNNs. With optimal clusters as labels, a support vector machinemodel was developed to predict survival. Results: Using the BiDNN-based model, samples were clustered into two survival subgroups. The survival subgroup classification was an independent prognostic factor. BiDNNs were superior to multimodal autoencoders. Conclusion:Thisstudy constructed and validated a BiDNN-based model for predicting prognosis in HCC, withimplications for individualized therapies in HCC.

Deep Neural Networks: A Bidirectional Deep Neural Network for Accurate Silicon Color Design (Adv. Mater. 51/2019)

Deep Neural Networks: A Bidirectional Deep Neural Network for Accurate Silicon Color Design (Adv. Mater. 51/2019)

A Bidirectional Deep Neural Network for Accurate Silicon Color Design.

Silicon nanostructure color has achieved unprecedented high printing resolution and larger color gamut than sRGB. The exact color is determined by localized magnetic and electric dipole resonance of nanostructures, which are sensitive to their geometric changes. Usually, the design of specific colors and iterative optimization of geometric parameters are computationally costly, and obtaining millions of different structural colors is challenging. Here, a deep neural network is trained, which can accurately predict the color generated by random silicon nanostructures in the forward modeling process and solve the nonuniqueness problem in the inverse design process that can accurately output the device geometries for at least one million different colors. The key results suggest deep learning is a powerful tool to minimize the computation cost and maximize the design efficiency for nanophotonics, which can guide silicon color manufacturing with high accuracy.

A Crossmodal Approach to Multimodal Fusion in Video Hyperlinking

With the recent resurgence of neural networks and the proliferation of massive amounts of unlabeled multimodal data, recommendation systems and multimodal retrieval systems based on continuous representation spaces and deep learning methods are becoming of great interest. Multimodal representations are typically obtained with autoencoders that reconstruct multimodal data. In this article, we describe an alternative method to perform high-level multimodal fusion that leverages crossmodal translation by means of symmetrical encoders cast into a bidirectional deep neural network (BiDNN). Using the lessons learned from multimodal retrieval, we present a BiDNN-based system that performs video hyperlinking and recommends interesting video segments to a viewer. Results established using TRECVIDs 2016 video hyperlinking benchmarking initiative show that our method obtained the best score, thus defining the state of the art.

Joint trajectory tracking and recognition based on bi-directional nonlinear learning

Motion trajectory is one of the most important cues for tracking and behavior recognition and can be widely applied to numerous fields. However, it is a difficult problem to directly model the spatio-temporal variations of trajectories due to their high dimensionality and nonlinearity. In this paper, we propose a joint trajectory tracking and recognition algorithm by combining a generative model derived from a bi-directional deep neural network (called “autoencoder”) into a Bayesian estimation framework. The “autoencoder” network embeds high-dimensional trajectories into a two-dimensional plane based on a peculiar training rule and learns a trajectory generative model by its inverse mapping. A set of plausible trajectories can be generated by the trajectory generative model. In the tracking process, the samples from the plausible trajectory set are weighted by a mixed likelihood and are resampled to obtain the target state estimation at each time step in spirit of the particle filtering. The trajectory identity is inferred by evaluating the improved Hausdorff distance between the estimated trajectory up to now and the truncated reference trajectories. Moreover, the trajectory recognition results are also used to guide the trajectory tracking for the next time. The experiments on tracking and recognizing handwritten digits show that the proposed approach can achieve both robust tracking and exact recognition in background clutter and partial occlusion.