Two-dimensional Input Research Articles

Tunable optical matrix convolution of 20-Gbit/s QPSK 2-D data with a kernel using optical wave mixing.

Compared to its electronic counterpart, optically performed matrix convolution can accommodate phase-encoded data at high rates while avoiding optical-to-electronic-to-optical (OEO) conversions. We experimentally demonstrate a reconfigurable matrix convolution of quadrature phase-shift keying (QPSK)-encoded input data. The two-dimensional (2-D) input data is serialized, and its time-shifted replicas are generated. This 2-D data is convolved with a 1-D kernel with coefficients, which are applied by adjusting the relative phase and amplitude of the kernel pumps. Time-shifted data replicas (TSDRs) and kernel pumps are coherently mixed using nonlinear wave mixing in a periodically poled lithium niobate (PPLN) waveguide. To show the tunability and reconfigurability of this approach, we vary the kernel coefficients, kernel sizes (e.g., 2 × 1 or 3 × 1), and input data rates (e.g., 6-20 Gbit/s). The convolution results are verified to be error-free under an applied: (a) 2 × 1 kernel, resulting in a 16-quadrature amplitude modulation (QAM) output with an error vector magnitude (EVM) of ∼5.1-8.5%; and (b) 3 × 1 kernel, resulting in a 64-QAM output with an EVM of ∼4.9-5.5%.

A label-free battery state of health estimation method based on adversarial multi-domain adaptation network and relaxation voltage

The state of health (SOH) estimation of lithium-ion batteries is crucial for the operational reliability and safety of electric vehicles. However, traditional data-driven methods face problems of label shortage and domain discrepancy caused by diverse battery types and operating conditions. This paper proposes a label-free SOH estimation method based on adversarial multi-domain adaptation technique and relaxation voltage (RV). Firstly, the raw RV and integral voltage are proposed to construct the two-dimensional input sequence to ensure high adaptability across various target domains. Secondly, a two-dimensional convolutional neural network integrated with fully connected layers is developed to establish the feature extractor and SOH estimator, which paves the way for effective knowledge transfer. Furthermore, an adversarial multi-domain adaptation method with a domain discriminator is developed to optimize the extraction of domain-invariant features and enable accurate SOH estimation without SOH labels. Datasets of 50 batteries with different temperatures and materials are used for the validation. The proposed method shows outstanding performance, achieving the average RMSE and MAE of 0.0274 and 0.0240 across various working temperatures, and 0.0177 and 0.0148 across different battery types. It suggests that the proposed method can achieve robust adaptive battery SOH estimation across multiple target domains without using SOH labels.

Multi-Scale Spatial Attention-Based Multi-Channel 2D Convolutional Network for Soil Property Prediction.

Visible near-infrared spectroscopy (VNIR) is extensively researched for obtaining soil property information due to its rapid, cost-effective, and environmentally friendly advantages. Despite its widespread application and significant achievements in soil property analysis, current soil prediction models continue to suffer from low accuracy. To address this issue, we propose a convolutional neural network model that can achieve high-precision soil property prediction by creating 2D multi-channel inputs and applying a multi-scale spatial attention mechanism. Initially, we explored two-dimensional multi-channel inputs for seven soil properties in the public LUCAS spectral dataset using the Gramian Angular Field (GAF) method and various preprocessing techniques. Subsequently, we developed a convolutional neural network model with a multi-scale spatial attention mechanism to improve the network's extraction of relevant spatial contextual information. Our proposed model showed superior performance in a statistical comparison with current state-of-the-art techniques. The RMSE (R²) values for various soil properties were as follows: organic carbon content (OC) of 19.083 (0.955), calcium carbonate content (CaCO3) of 24.901 (0.961), nitrogen content (N) of 0.969 (0.933), cation exchange capacity (CEC) of 6.52 (0.803), pH in H2O of 0.366 (0.927), clay content of 4.845 (0.86), and sand content of 12.069 (0.789). Our proposed model can effectively extract features from visible near-infrared spectroscopy data, contributing to the precise detection of soil properties.

A Security Domain Feature Pattern Recognition Method Based on Capsule Neural Network

Abstract In this paper, a security domain feature pattern recognition method based on capsule neural network is proposed. Firstly, Halton sampling is performed on the active output of all generators except for the balancing machine to obtain a uniform sample in the coverage space. Then, the support vector machine based recursive feature elimination (SVM-RFE) method is used to select the critical pre fault feature quantities of the system. Finally, based on the selected active features, one-dimensional data is converted into two-dimensional data and input into the capsule neural network. Dynamic security domain boundaries are constructed in both two-dimensional and three-dimensional spaces, which can divide the feature space into stable and unstable subspaces.

Two-dimensional LSTM soft sensor using noisy process data

Establishing a reliable data-based soft sensor still faces a series of challenges, particularly the presence of outliers and different kinds of noise which are non-negligible in process data. To address these challenges, a correntropy-based two-dimensional long short-term memory (TLSTM) model is developed to handle noisy process data. First, the multidimensional time series samples are reconstructed into numerous two-dimensional input matrices in the feature and time directions. Then, the convolution and pooling operations are used to extract useful information in the process variables related to the quality variable. Meanwhile, a gating mechanism is employed to learn the internal representation of time series. Finally, a correntropy-based strategy is utilized to assign relatively small weights to outliers automatically, enabling reliable prediction. Two cases illustrate the reliability and advantages of TLSTM in effectively extracting quality-related features for prediction.

An intelligent human-machine interaction-based longitudinal control strategy for autonomous vehicles

In the foreseeable future, the anticipation is that intelligent vehicles will transition to a mode where the intelligent driving system collaborates seamlessly with the human driver. This harmonious integration between the driver and the intelligent control system holds paramount significance for the successful execution of driving tasks, ultimately contributing to the development of more advanced and user-friendly automobiles. A pivotal element in advancing from assisted to autonomous driving lies in the establishment of a human-machine co-driving mode. This research delineates a longitudinal control strategy tailored for intelligent vehicles featuring human-machine interaction. The approach involves the creation of a personalized safe distance model for car-following by collecting driver characteristic parameters. Focused on the car-following methodology, this study formulates the kinematics state space equation, performance index function, and constraint conditions governing car-following dynamics. Subsequently, a car-following control strategy is devised based on model predictive control (MPC), which is addressed through rolling optimization techniques. Building upon this foundation, a human-machine driving control strategy is proposed to dynamically allocate driving authorities in real-time. This strategy takes into account speed and vehicle distance risk as two-dimensional inputs, employing a cooperative driving control strategy within the dual-drive dual-control system. The proposed method was validated in a simulated environment.

A Performance Comparison of Japanese Sign Language Recognition with ViT and CNN Using Angular Features

In recent years, developments in deep learning technology have driven significant advancements in research aimed at facilitating communication with individuals who have hearing impairments. The focus has been on enhancing automatic recognition and translation systems for sign language. This study proposes a novel approach using a vision transformer (ViT) for recognizing Japanese Sign Language. Our method employs a pose estimation library, MediaPipe, to extract the positional coordinates of each finger joint within video frames and generate one-dimensional angular feature data from these coordinates. Then, the code arranges these feature data in a temporal sequence to form a two-dimensional input vector for the ViT model. To determine the optimal configuration, this study evaluated recognition accuracy by manipulating the number of encoder layers within the ViT model and compared against traditional convolutional neural network (CNN) models to evaluate its effectiveness. The experimental results showed 99.7% accuracy for the method using the ViT model and 99.3% for the results using the CNN. We demonstrated the efficacy of our approach through real-time recognition experiments using Japanese sign language videos.

Pattern classification of interstitial lung diseases from computed tomography images using a ResNet-based network with a split-transform-merge strategy and split attention.

In patients with interstitial lung disease (ILD), accurate pattern assessment from their computed tomography (CT) images could help track lung abnormalities and evaluate treatment efficacy. Based on excellent image classification performance, convolutional neural networks (CNNs) have been massively investigated for classifying and labeling pathological patterns in the CT images of ILD patients. However, previous studies rarely considered the three-dimensional (3D) structure of the pathological patterns of ILD and used two-dimensional network input. In addition, ResNet-based networks such as SE-ResNet and ResNeXt with high classification performance have not been used for pattern classification of ILD. This study proposed a SE-ResNeXt-SA-18 for classifying pathological patterns of ILD. The SE-ResNeXt-SA-18 integrated the multipath design of the ResNeXt and the feature weighting of the squeeze-and-excitation network with split attention. The classification performance of the SE-ResNeXt-SA-18 was compared with the ResNet-18 and SE-ResNeXt-18. The influence of the input patch size on classification performance was also evaluated. Results show that the classification accuracy was increased with the increase of the patch size. With a 32 × 32 × 16 input, the SE-ResNeXt-SA-18 presented the highest performance with average accuracy, sensitivity, and specificity of 0.991, 0.979, and 0.994. High-weight regions in the class activation maps of the SE-ResNeXt-SA-18 also matched the specific pattern features. In comparison, the performance of the SE-ResNeXt-SA-18 is superior to the previously reported CNNs in classifying the ILD patterns. We concluded that the SE-ResNeXt-SA-18 could help track or monitor the progress of ILD through accuracy pattern classification.

Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy.

Advanced process control in the biopharmaceutical industry often lacks real-time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real-time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two-dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed-batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real-time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs.

TransQA: deep hybrid transformer network for measurement-guided volumetric dose prediction of pre-treatment patient-specific quality assurance

Objective. Performing pre-treatment patient-specific quality assurance (prePSQA) is considered an essential, time-consuming, and resource-intensive task for volumetric modulated arc radiotherapy (VMAT) which confirms the dose accuracy and ensure patient safety. Most current machine learning and deep learning approaches stack excessive convolutional/pooling operations (CPs) to predict prePSQA with two-dimensional or one-dimensional information input. However, these models generally present limitations in explicitly modeling long-range dependency for volumetric dose prediction due to the loss of spatial dose features and the inherent locality of CPs. The purpose of this work is to construct a deep hybrid network by combining the self-attention mechanism-based Transformer with modified U-Net for predicting measurement-guided volumetric dose (MDose) of prePSQA. Approach. The enrolled 307 cancer patients underwent VMAT were randomly divided into 246 and 61 cases for training and testing the model. The input data included computed tomography images, radiotherapy dose images exported from the treatment planning system, as well as the MDose distribution from the verification system. The output was the predicted high-quality voxel-wise prePSQA dose distribution. Main results: qualitative and quantitative experimental results show that the proposed prediction method could achieve comparable or better performance on MDose prediction over other approaches in terms of spatial dose distribution, dose–volume histogram metrics, gamma passing rates, mean absolute error, root mean square error, and structural similarity. Significance. The preliminary results on multiple cancer sites show that our approach can be taken as a clinical guidance tool and help medical physicists to reduce the measurement work of prePSQA.

Key technologies research on of soil-structure interaction base story isolated structure response in 3D seismic zone

The development of karst in Karst area leads to poor stability of stratum. If earthquake occurs, the area will produce destructive disaster. In order to improve the stability capacity of the grassroots in the region, this study investigates the seismic response of inter-story isolation structures considering soil-structure interaction (SSI) in three-dimensional earthquakes. A model of the inter-story isolation structure incorporating SSI was developed, and one-dimensional, two-dimensional, and three-dimensional ground motions were applied to compare the seismic response under different input conditions. A three-dimensional isolation system was introduced and compared with traditional horizontal isolation structures to address excessive tensile and compressive stresses on the isolation structure during three-dimensional ground motion. The results demonstrate that the seismic response to three-dimensional earthquakes surpasses one-dimensional and two-dimensional inputs. Furthermore, adding a three-dimensional isolation structure effectively isolates vertical ground motion and reduces structural seismic response. Moreover, it minimizes soil stresses on the foundation compared to traditional horizontal isolation structure, enhancing foundation stability. This study will provide theoretical value and practical guidance for the research on key technology of SSI base story isolation structure response in Karst Plateau 3D Seismic zone.

Fine-Gained Recurrence Graph: Graphical Modeling of Vibration Signal for Fault Diagnosis of Wind Turbine

Benefiting from the recent successes of convolutional neural networks (CNNs), many studies have modeled the vibration signal of energy system into a two-dimensional (2D) input graph to amplify and highlight fault features. However, most works seldomly consider the system dynamic characteristics, which may affect the knowledge discovery and diagnosis quality. To address this issue, this paper proposes a novel graphical modeling approach, termed as fine-gained recurrence graph (FRG), to capture dynamic characteristics of vibration signals from the view of nonlinear dynamics. FRG focuses on modeling the temporal correlations and tendencies between state vectors in phase space and then visualizes the characteristics to represent intrinsic dynamic changes of the vibration signals into 2D graphs. The information representation capability of the proposed FRG is verified using different dynamic signals. Based on this finding, an ensemble fault diagnosis model is proposed fusing FRG with deep CNNs. Meanwhile, transfer learning is accompanied to deal with the training difficulties of deep CNNs. Finally, case studies on experimental data and real wind turbine data illustrate its effectiveness and feasibility. Comparisons with four state-of-the-art approaches have confirmed the preferable information representation and diagnosis performance of the proposed approach.

Extending orbital angular momentum multiplexing to radially high orders for massive mode channels in fiber transmission.

Orbital angular momentum (OAM) beams with different angular indices l have the potential to greatly increase communication capacity. However, the finite aperture of optical systems limits the value of the angular index. In order to fully use the orthogonal mode channels supported in the fiber for high-capacity communications, we propose extending the radial indices p of OAM modes as an additional multiplexing dimension. In this paper, we introduce spatially discrete multiple phase planes to multiplex the angular and radial OAM modes simultaneously. Due to the orthogonal property of the central symmetric OAM modes, a two-dimensional (2D) input Gaussian beams array can be converted to coaxial OAM modes through Cartesian to log-polar coordinate transformation by inverse design. For a proof-of-concept demonstration, a 10-mode multiplexer for high-order radial OAM modes was designed using five phase planes. The fabricated multiplexer generated high-quality multiplexed OAM modes with a loss of less than 5.4 dB. The multiplexed OAM modes were coupled into a specially designed ring-core fiber by mode-field matching, achieving stable mode transmission in 2 km fiber. The approach provides a scalable technology to increase the number of transmission channels and could lead to the practical applications of OAM multiplexing in communication.

Coupling Dilated Encoder–Decoder Network for Multi-Channel Airborne LiDAR Bathymetry Full-Waveform Denoising

Multi-channel airborne full-waveform LiDAR is widely used for high-precision underwater depth measurement. However, the signal quality of full-waveform data is unstable due to the influence of background light, dark current noise, and the complex transmission process. Therefore, we propose a nonlocal encoder block (NLEB) based on spatial dilated convolution to optimize the feature extraction of adjacent frames. On this basis, a coupled denoising encoder–decoder network is proposed that takes advantage of the echo correlation in deep-water and shallow-water channels. Firstly, full waveforms from different channels are stacked together to form a two-dimensional tensor and input into the proposed network. Then, NLEB is used to extract local and nonlocal features from the 2D tensor. After fusing the features of the two channels, the reconstructed denoised data can be obtained by upsampling with a fully connected layer and deconvolution layer. Based on the measured data set, we constructed a noise–noisier data set, on which several denoising algorithms were compared. The results show that the proposed method improves the stability of denoising by using the inter-channel and multi-frame data correlation.

Quantitative Analysis of Steel Alloy Elements Based on LIBS and Deep Learning of Multi-Perspective Features

The Si and Mn contents in steel alloys are important characteristic indexes that influence the plasticity and welding properties of these alloys. In this work, the quantitative analysis methods for trace elements under complex alloy matrices by laser-induced breakdown spectroscopy (LIBS) are studied, which provide a foundation for utilizing LIBS technology in the rapid online detection of steel alloy properties. To improve the quantitative analysis accuracy of LIBS, deep learning algorithm methods are introduced. Given the characteristics of LIBS spectra, we explore multi-perspective feature extraction and backward differential methods to extract the spatio-temporal characteristics of LIBS spectra. The Text Convolutional Neural Network (TextCNN) model, combined with multi-perspective feature extraction, displays good stability and lower average relative errors (6.988% for Si, 6.280% for Mn) in the test set compared to the traditional quantitative analysis method and deep neural network (DNN) model. Finally, the backward differential method is employed to optimize the two-dimensional LIBS spectral input matrix, and the results indicate that the average relative errors of Si and Mn elements in the test set decrease to 5.139% and 3.939%, respectively. The method proposed in this work establishes a theoretical basis and technical support for precise prediction and online quality monitoring.

Learning Picture Languages Using Dimensional Reduction

One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of their two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate the problem of learning formal two-dimensional picture languages by applying learning methods for one-dimensional (string) languages. We formalize the transcription process from a two-dimensional input picture into a string and propose a few adaptations to it. These proposals are then tested in a series of experiments, and their outcomes are compared. Finally, these methods are applied to a practical problem and an automaton for recognizing a part of the MNIST dataset is learned. The obtained results show improvements in the topic and the potential to use the learning of automata in fitting problems.

A research of the respiratory status detection method measured by abdominal rise and fall

Respiratory activity is the most important basic life activity of human body, respiratory state detection is of great practical significance. Based on the characteristic of high correlation between the change of tidal volume and the change of abdominal displacement, a method of detecting respiratory status through abdominal displacement data is proposed. The method uses a gas pressure sensor to collect the tidal volume in the steady state of the subject once, which is used as the baseline data. The abdominal displacement data of the subject in the three breathing states of slow breathing, steady breathing and rapid breathing were collected with an acceleration sensor. The warp path distance between the lung and abdominal data in the three different states was calculated, this warp path distance together with the period extracted from the abdominal data is used as a two-dimensional feature and input to the support vector machine classifier. The experiments show that the accuracy of the classification results reaches 90.23%. The method only needs to measure the lung data once in smooth breathing state, and the subsequent continuous detection is achieved by measuring the displacement of the abdomen only. This method has the advantages of stable and reliable acquisition results, low implementation cost and simplified wearing method, and has high practicality.

Improved neural distinguishers with multi-round and multi-splicing construction

In CRYPTO 2019, Gohr successfully applied deep learning to differential cryptanalysis against the NSA block cipher Speck32/64, achieving higher accuracy than traditional differential distinguishers. Until now, the improvement of neural differential distinguishers is a mainstream research direction in neural-aided cryptanalysis. But the current development of training data formats for neural distinguishers forms barriers: (1) The source of data features is limited to linear combinations of ciphertexts, which does not provide more learnable features to the training samples for improving the neural distinguishers. (2) Lacking breakthroughs in constructing data format for network training from the deep learning perspective. In this paper, considering both the domain knowledge about deep learning and information on differential cryptanalysis, we use the output features of the penultimate round to proposing a two-dimensional and non-realistic input data generation method of neural differential distinguishers. Then, we validate that the proposed new input data format has excellent features through experiments and theoretical analysis. Moreover, combining the idea of multiple ciphertext pairs, we generate two specific models for data input construction: MRMSP(Multiple Rounds Multiple Splicing Pairs) and MRMSD(Multiple Rounds Multiple Splicing Differences) and then build new neural distinguishers against Speck and Simon family, which effectively improve the performance compared with the previous works. To the best of our knowledge, our neural distinguishers achieve the longest rounds and the higher accuracy for NSA block ciphers Speck and Simon.

TFRegNCI: Interpretable Noncovalent Interaction Correction Multimodal Based on Transformer Encoder Fusion.

The interpretability is an important issue for end-to-end learning models. Motivated by computer vision algorithms, an interpretable noncovalent interaction (NCI) correction multimodal (TFRegNCI) is proposed for NCI prediction. TFRegNCI is based on RegNet feature extraction and a transformer encoder fusion strategy. RegNet is a network design paradigm that mainly focuses on local features. Meanwhile, the Vision Transformer is also leveraged for feature extraction, because it can capture global features better than RegNet while lowering the computational cost. Using a transformer encoder as the fusion strategy rather than multilayer perceptron can enhance model performance, due to its emphasis on important features with less parameters. Therefore, the proposed TFRegNCI achieved high accurate prediction (mean absolute error of ∼0.1 kcal/mol) comparing with the coupled cluster single double (triple) (CCSD(T)) benchmark. To further improve the model efficiency, TFRegNCI applies two-dimensional (2D) inputs transformed from three-dimensional (3D) electron density cubes, which saves time (30%), while the model accuracy remains. To improve model interpretability, a visualization module, Gradient-weighted Regression Activation Mapping (Grad-RAM) has been embedded. Grad-RAM is promoted from the classification algorithm, Gradient-weighted Class Activation Mapping, to perform feature visualization for the regression task. With Grad-RAM, the visual location map for features in deep learning models can be displayed. The feature map visualizations suggest that the 2D model has the similar performance as the 3D model, because of equally effective feature extractions from electron density. Moreover, the valid feature region on the location map by the 3D model is consistent with the NCIPLOT NCI isosurface. It is confirmed that the model does extract significant features related to the NCI interaction. The interpretable analyses are carried out through molecular orbital contribution on effective features. Thereby, the proposed model is likely to be a promising tool to reveal some essential information on NCIs, with regard to the level of electronic theory.

Surrogate models for plasma displacement and current in 3D perturbed magnetohydrodynamic equilibria in tokamaks

A numerical database of over one thousand perturbed three-dimensional (3D) equilibria has been generated, constructed based on the MARS-F (Liu et al 2000 Phys. Plasmas 7 3681) computed plasma response to the externally applied 3D field sources in multiple tokamak devices. Perturbed 3D equilibria with the n = 1–4 (n is the toroidal mode number) toroidal periodicity are computed. Surrogate models are created for the computed perturbed 3D equilibrium utilizing model order reduction (MOR) techniques. In particular, retaining the first few eigenstates from the singular value decomposition (SVD) of the data is found to produce reasonably accurate MOR-representations for the key perturbed quantities, such as the perturbed parallel plasma current density and the plasma radial displacement. SVD also helps to reveal the core versus edge plasma response to the applied 3D field. For the database covering the conventional aspect ratio devices, about 95% of data can be represented by the truncated SVD-series with inclusion of only the first five eigenstates, achieving a relative error (RE) below 20%. The MOR-data is further utilized to train neural networks (NNs) to enable fast reconstruction of perturbed 3D equilibria, based on the two-dimensional equilibrium input and the 3D source field. The best NN-training is achieved for the MOR-data obtained with a global SVD approach, where the full set of samples used for NN training and testing are stretched and form a large matrix which is then subject to SVD. The fully connected multi-layer perceptron, with one or two hidden layers, can be trained to predict the MOR-data with less than 10% RE. As a key insight, a better strategy is to train separate NNs for the plasma response fields with different toroidal mode numbers. It is also better to apply MOR and to subsequently train NNs separately for conventional and low aspect ratio devices, due to enhanced toroidal coupling of Fourier spectra in the plasma response in the latter case.