Two-dimensional Data Sets Research Articles

Frequency-spatial interaction network for gaze estimation

Gaze estimation is a fundamental task in the field of computer vision, which determines the direction a person is looking at. With advancements in Convolutional Neural Networks (CNNs) and the availability of large-scale datasets, appearance-based models have made significant progress. Nonetheless, CNNs exhibit limitations in extracting global information from features, resulting in a constraint on gaze estimation performance. Inspired by the properties of the Fourier transform in signal processing, we propose the Frequency-Spatial Interaction network for Gaze estimation (FSIGaze), which integrates residual modules and Frequency-Spatial Synergistic (FSS) modules. To be specific, its FSS module is a dual-branch structure with a spatial branch and a frequency branch. The frequency branch employs Fast Fourier Transformation to transfer a latent representation to the frequency domain and applies adaptive frequency filter to achieve an image-size receptive field. The spatial branch, on the other hand, can extract local detailed features. Acknowledging the synergistic benefits of global and local information in gaze estimation, we introduce a Dual-domain Interaction Block (DIB) to enhance the capability of the model. Furthermore, we implement a multi-task learning strategy, incorporating eye region detection as an auxiliary task to refine facial features. Extensive experiments demonstrate that our model surpasses other state-of-the-art gaze estimation models on three three-dimensional (3D) datasets and delivers competitive results on two two-dimensional (2D) datasets.

Electrical resistivity tomography inversion combining deep variational autoencoder and stochastic adaptive sampling

Geophysical methods, such as electrical resistivity tomography (ERT), can be used to imaging the near-surface electrical resistivity as field measurements depend on the subsurface porosity, water saturation and fluid salinity. ERT has been widely applied to investigate mineral and groundwater resources, and in archaeological, environmental, and engineering studies. The prediction of subsurface electrical conductivity from ERT data requires solving a geophysical inverse problem. For near-surface characterization studies, this is often accomplished with deterministic inverse methods. These methods linearize the problem around an initial solution, and their smoothness depends on an imposed a priori spatial regularization term. Depending on this parameterization, these methodologies might struggle to capture the natural variability of the subsurface. Moreover, deterministic solutions have limited capabilities for uncertainty assessment. On the contrary, stochastic inverse methods can assess uncertainties by predicting multiple model realizations that fit similarly the recorded ERT data. However, they are often more computationally expensive than deterministic solutions. Deep learning algorithms based on deep generative models have been used to re-parametrize model and data spaces into low-dimensional domains and efficiently solve geophysical inverse problems. However, within this context, uncertainty assessment is challenging. We propose a deep convolutional variational autoencoder (VAE) coupled with stochastic adaptive optimization to perform stochastic ERT inversion. Geostatistical simulations of electrical resistivity are used as training data set of the VAE. After training, the VAE generates electrical resistivity models that reproduce the statistics and spatial continuity patterns of the training data set. Then, the VAE latent space is iteratively perturbed and updated with adaptive stochastic sampling based on the misfit between observed and predicted ERT data. The proposed methodology is illustrated in two-dimensional synthetic and real data sets to illustrate the ability of the proposed method to predict reliable electrical resistivity models while generating multiple possible scenarios for uncertainty assessment.

Elucidation of AsANS controlling pigment biosynthesis in Angelica sinensis through hormonal and transcriptomic analysis.

Angelica sinensis, a traditional Chinese medicinal plant, has been primarily reported due to its nutritional value. Pigmentation in this plant is an important appearance trait that directly affects its commercial value. To understand the mechanism controlling purpleness in A. sinensis, hormonal and transcriptomic analyses were performed in three different tissues (leave, root and stem), using two cultivars with contrasting colors. The two-dimensional data set provides dynamic hormonal and gene expression networks underpinning purpleness in A. sinensis. We found abscisic acid as a crucial hormone modulating anthocyanin biosynthesis in A. sinensis. We further identified and validated 7 key genes involved in the anthocyanin biosynthesis pathway and found a specific module containing ANS as a hub gene in WGCNA. Overexpression of a candidate pigment regulatory gene, AsANS (AS08G02092), in transgenic calli of A. sinensis resulted in increased anthocyanin production and caused purpleness. Together, these analyses provide an important understanding of the molecular networks underlying A. sinensis anthocyanin production and its correlation with plant hormones, which can provide an important source for breeding.

Clustering with empty clusters

Cluster analysis is widely used in various scientific and practical fields related to data analysis. It is an important tool for solving problems in such areas as machine learning, image processing, text recognition, etc. The absence of observations is not always the absence of information, therefore it is assumed that the presence of gaps in the data, the presence of “empty” clusters, also carries information about the object of study, as well as real observations. In this study, it is assumed that we do not observe not only a variable, but a whole set of objects forming a separate cluster. Thus, it is assumed that the missing in data is not the fact of the missing of a cluster of objects as such, but potentially existing objects that are absent from our selection. An algorithm is proposed to determine potential "empty" clusters for one-dimensional and two-dimensional data sets, taking into account their size and location in the feature space, depending on the initial distribution of samples. A method is implemented to fill in these gaps and estimate the displacement of the centroids of the initial clustering when taking into account an empty cluster. The application of this approach to rid the data of outliers is demonstrated.

Comprehensive application of AI algorithms with TCR NGS data for glioma diagnosis

T-cell receptor (TCR) detection can examine the extent of T-cell immune responses. Therefore, the article analyzed characteristic data of glioma obtained by DNA-based TCR high-throughput sequencing, to predict the disease with fewer biomarkers and higher accuracy. We downloaded data online and obtained six TCR-related diversity indices to establish a multidimensional classification system. By comparing actual presence of the 602 correlated sequences, we obtained two-dimensional and multidimensional datasets. Multiple classification methods were utilized for both datasets with the classification accuracy of multidimensional data slightly less to two-dimensional datasets. This study reduced the TCR β sequences through feature selection methods like RFECV (Recursive Feature Elimination with Cross-Validation). Consequently, using only the presence of these three sequences, the classification AUC value of 96.67% can be achieved. The combination of the three correlated TCR clones obtained at a source data threshold of 0.1 is: CASSLGGNTEAFF_TRBV12_TRBJ1-1, CASSYSDTGELFF_TRBV6_TRBJ2-2, and CASSLTGNTEAFF_TRBV12_TRBJ1-1. At 0.001, the combination is: CASSLGETQYF_TRBV12_TRBJ2-5, CASSLGGNQPQHF_TRBV12_TRBJ1-5, and CASSLSGNTIYF_TRBV12_TRBJ1-3. This method can serve as a potential diagnostic and therapeutic tool, facilitating diagnosis and treatment of glioma and other cancers.

Identifying and analyzing power-law scaling in two-dimensional image datasets.

Power-law distributions provide a general description of diverse natural phenomena in which events with a logarithmically increasing size occur with logarithmically decreasing probability. However, experimentally derived correlated two-dimensional information is often difficult to cleanly interpret as discrete events of defined size. Moreover, physical limitation of techniques such as those based on scanning probe microscopy, which can ideally be used to observe power-law behavior, reduce event number and thus render straightforward power-law fits even more challenging. Here we develop and compare different techniques to analyze event distributions from two-dimensional images. We show that tracking interface position allows the associated scaling parameters to be accurately extracted from both experimental and synthetic image-based datasets. We also show how these techniques can differentiate between power-law and non-power-law behavior by comparison of Hill, moments, and kernel estimators of this scaling parameter. We thus present computational tools to analyze power-law fits in two-dimensional datasets and identify the scaling parameters that best describe these distributions.

Automatic Object Detection in Radargrams of Multi-Antenna GPR Systems Based on Simulation Data for Railway Infrastructure Analysis

Ground-penetrating radar (GPR) is a non-invasive technology that uses electromagnetic pulses for subsurface exploration. In the railroad sector, it is crucial to assessing soil layers and infrastructure, offering insights into soil stratification and geological features and aiding in identifying subsurface hazards. However, the automation of radargram analysis is impeded by the lack of ground truth—accurate real-world data used to validate machine learning models—thus affecting the deployment of advanced algorithms. This study focuses on generating high-quality simulated data to address the shortage of real-world data in the context of object detection along railroad tracks and presents a fully automated pipeline that includes data generation, algorithm training, and validation using real-world data. By doing so, it paves the way for significantly easing the future task of object detection algorithms in the railway sector. A simulation environment, including the digital twin of a GPR antenna, was developed for artificial data generation. The process involves pre- and post-processing techniques to transform the three-dimensional data from the multichannel GPR system into two-dimensional datasets. This ensures minimal information loss and suitability for established two-dimensional object detection algorithms like the well-known YOLO (You Only Look Once) framework. Validation involved real-world measurements on a track with predefined buried objects. The entire pipeline, encompassing data generation, processing, training, and application, was automated for efficient algorithm testing and implementation. Artificial data show promise for better performance with increased training. Future AI and sensor advancements will enhance subsurface exploration, contributing to safer and more reliable railroad operations.

SimpleNMR: An interactive graph network approach to aid constitutional isomer verification using standard 1D and 2D NMR experiments.

Despite progress in computer automated solutions, constitutional isomer verification by NMR using one- and two-dimensional data sets is still, in the main, a manual, user-intensive activity that is challenging for a number of reasons. These include the problem of simultaneously keeping track of the information from a number of separate NMR experiments and the difficulty of another researcher subsequently verifying the assignments made without having to independently repeat the whole analysis. This paper describes a graphical interactive approach that overcomes some of these problems. By using concepts used to visualise graph networks, we have been able to represent the NMR data in a manner that highlights directly the link between the different NMR experiments and the molecule of interest. Furthermore, by making the graph networks interactive, a user can easily validate and correct the assignment and understand the decisions made in arriving at the solution. We have developed a usable proof-of-concept computer program, 'simpleNMR', written in Python to illustrate the ideas and approach.

Fault diagnosis of brushless DC motor based on Stack Sparse Autoencoder

Because of their simple structure, long service life, high efficiency, etc., brushless DC (BLDC) motors have been widely applied in many fields. In some applications, high requirements for BLDC continuous use of motors, so often to BLDC running state monitoring of motors, realizes the early fault diagnosis, to improve the reliability, safety, and prolonged use. To solve this problem, a BLDC fault diagnosis method based on Fast Fourier Transform (FFT), Stacked Sparse Auto-encoder (SSAE), and soft classifier was proposed. In the laboratory, a BLDC model R-3525 was used as the experimental equipment, and the data of 9 kinds of fault conditions such as bearing damage, cage damage, inner and outer ring damage, and the normal condition of the motor were collected. The collected data are transformed into 28 × 28 two-dimensional data sets by FFT. The feature expressions of various faults are adaptively learned from many data, and the intelligent diagnosis of the motor is realized by the feature function expression. The experimental results demonstrate that, in comparison to the single neural network approach, the stacked method can significantly enhance the precision of fault classification and achieve fault diagnosis for brushless DC motors. This method carries valuable implications for other varieties of BLDC motors.

Using geometric wing morphometrics to distinguish Aedes japonicus japonicus and Aedes koreicus

BackgroundAedes japonicus japonicus (Theobald, 1901) and Aedes koreicus (Edwards, 1917) have rapidly spread in Europe over the last decades. Both species are very closely related and occur in sympatry. Females and males are difficult to distinguish. However, the accurate species discrimination is important as both species may differ in their vectorial capacity and spreading behaviour. In this study, we assessed the potential of geometric wing morphometrics as alternative to distinguish the two species.MethodsA total of 147 Ae. j. japonicus specimens (77 females and 70 males) and 124 Ae. koreicus specimens (67 females and 57 males) were collected in southwest Germany. The left wing of each specimen was removed, mounted and photographed. The coordinates of 18 landmarks on the vein crosses were digitalised by a single observer. The resulting two-dimensional dataset was used to analyse the differences in the wing size (i.e. centroid size) and wing shape between Ae. j. japonicus and Ae. koreicus using geometric morphometrics. To analyse the reproducibility of the analysis, the landmark collection was repeated for 20 specimens per sex and species by two additional observers.ResultsThe wing size in female Ae. koreicus was significantly greater than in Ae. j. japonicus but did not differ significantly for males. However, the strong overlap in wing size also for the females would not allow to discriminate the two species. In contrast, the wing shape clustering was species specific and a leave-one-out validation resulted in a reclassification accuracy of 96.5% for the females and 91.3% for the males. The data collected by different observers resulted in a similar accuracy, indicating a low observer bias for the landmark collection.ConclusionsGeometric wing morphometrics provide a reliable and robust tool to distinguish female and male specimens of Ae. j. japonicus and Ae. koreicus.Graphical

A co-kurtosis PCA based dimensionality reduction with nonlinear reconstruction using neural networks

For turbulent reacting flow systems, identification of low-dimensional representations of the thermo-chemical state space is vitally important, primarily to significantly reduce the computational cost of device-scale simulations. Principal component analysis (PCA), and its variants, are a widely employed class of methods. Recently, an alternative technique that focuses on higher-order statistical interactions, co-kurtosis PCA (CoK-PCA), has been shown to effectively provide a low-dimensional representation by capturing the stiff chemical dynamics associated with spatiotemporally localized reaction zones. While its effectiveness has only been demonstrated based on a priori analyses with linear reconstruction, in this work, we employ nonlinear techniques to reconstruct the full thermo-chemical state and evaluate the efficacy of CoK-PCA compared to PCA. Specifically, we combine a CoK-PCA-/PCA-based dimensionality reduction (encoding) with an artificial neural network (ANN) based reconstruction (decoding) and examine, a priori, the reconstruction errors of the thermo-chemical state. In addition, we evaluate the errors in species production rates and heat release rates, which are nonlinear functions of the reconstructed state, as a measure of the overall accuracy of the dimensionality reduction technique. We employ four datasets to assess CoK-PCA/PCA coupled with ANN-based reconstruction: zero-dimensional (homogeneous) reactor for autoignition of an ethylene/air mixture that has conventional single-stage ignition kinetics, a dimethyl ether (DME)/air mixture which has two-stage (low and high temperature) ignition kinetics, a one-dimensional freely propagating premixed ethylene/air laminar flame, and a two-dimensional dataset representing turbulent autoignition of ethanol in a homogeneous charge compression ignition (HCCI) engine. Results from the analyses demonstrate the robustness of the CoK-PCA based low-dimensional manifold with ANN reconstruction in accurately capturing the data, specifically from the reaction zones.

Graded diagnosis of Helicobacter pylori infection using hyperspectral images of gastric juice.

Helicobacter pylori is a potential underlying cause of many diseases. Although the Carbon 13 breath test is considered the gold standard for detection, it is high cost and low public accessibility in certain areas limit its widespread use. In this study, we sought to use machine learning and deep learning algorithm models to classify and diagnose H. pylori infection status. We used hyperspectral imaging system to gather gastric juice images and then retrieved spectral feature information between 400 and 1000 nm. Two different data processing methods were employed, resulting in the establishment of one-dimensional (1D) and two-dimensional (2D) datasets. In the binary classification task, the random forest model achieved a prediction accuracy of 83.27% when learning features from 1D data, with a specificity of 84.56% and a sensitivity of 92.31%. In the ternary classification task, the ResNet model learned from 2D data and achieved a classification accuracy of 91.48%.

(Invited) Advanced Carbon Nanotube Fluorescence Spectrometry for Novel Applications

Instrumental advances in near-IR fluorescence spectroscopy are enabling new types of measurements involving single-wall carbon nanotubes (SWCNTs). Two unique systems will be described. The first is a two-dimensional fluorescence-detected circular dichroism (FDCD) spectrometer. In this, SWCNT samples are excited by a spectrally selected supercontinuum laser beam that is switched between left- and right-circular polarization in an electro-optic modulator. Near-infrared sample fluorescence emitted in the backward direction is captured and directed to a scanning monochromator with a cooled InGaAs single-channel detector. After amplification and high precision digitization, the modulated signal component is extracted by computer-based phase sensitive detection. The system can measure a sample’s E22 circular dichroism in four spectral modes: 1) conventional FDCD, with scanned visible excitation wavelength and spectrally integrated (zero-order grating) emission detection; 2) Emission-specific FDCD, with scanned visible excitation wavelengths and selected emission wavelength; 3) Emission-scanned FDCD, with selected visible excitation wavelength and scanned emission wavelengths; 4) Excitation-Emission FDCD, with excitation and emission wavelengths both scanned to give two-dimensional data sets. This instrument can spectroscopically resolve enantiomer signals from a single (n,m) species in a racemic SWCNT sample.In a parallel project, developments in SWCNT fluorescence spectrometry are advancing nanotube-based strain measurement technology toward commercialization. Because SWCNT emission wavelengths vary systematically with axial strain, nanotubes in a thin coating on a specimen can serve as optically interrogated strain gauges. We apply this effect to measure strain maps through hyperspectral imaging of SWCNT fluorescence. A rotated band pass filter is used to capture a set of images in multiple spectral slices, from which a custom computer program deduces strain at each of ~105 image pixels and compiles strain maps. We will describe how this apparatus has evolved from a lab prototype into a compact portable system that can make measurements in industrial settings.

In vivo magnetic resonance spectroscopy by transverse relaxation encoding with narrowband decoupling

Cell pathology in neuropsychiatric disorders has mainly been accessible by analyzing postmortem tissue samples. Although molecular transverse relaxation informs local cellular microenvironment via molecule-environment interactions, precise determination of the transverse relaxation times of molecules with scalar couplings (J), such as glutamate and glutamine, has been difficult using in vivo magnetic resonance spectroscopy (MRS) technologies, whose approach to measuring transverse relaxation has not changed for decades. We introduce an in vivo MRS technique that utilizes frequency-selective editing pulses to achieve homonuclear decoupled chemical shift encoding in each column of the acquired two-dimensional dataset, freeing up the entire row dimension for transverse relaxation encoding with J-refocusing. This results in increased spectral resolution, minimized background signals, and markedly broadened dynamic range for transverse relaxation encoding. The in vivo within-subject coefficients of variation for the transverse relaxation times of glutamate and glutamine, measured using the proposed method in the human brain at 7 T, were found to be approximately 4%. Since glutamate predominantly resides in glutamatergic neurons and glutamine in glia in the brain, this noninvasive technique provides a way to probe cellular pathophysiology in neuropsychiatric disorders for characterizing disease progression and monitoring treatment response in a cell type-specific manner in vivo.

First-order spatial dependent count integer-valued autoregressive (Sp-DCINAR(1,1)) process

In this article, we propose a new model to model the spatial count data on a two-dimensional regular grid using binomial thinning operator with dependent Bernoulli counting series. The model is called “first-order spatial dependent count integer-valued autoregressive (Sp-DCINAR(1,1)) model.” Some of its properties have been derived and the estimation of the parameters of the model are obtained by the Yule-Walker method, conditional least squares method and conditional maximum likelihood method. Finally, numerical results are presented together with an application to a two-dimensional practical data set.

Mesoscale standing wave imaging.

Standing wave (SW) microscopy is a method that uses an interference pattern to excite fluorescence from labelled cellular structures and produces high-resolution images of three-dimensional objects in a two-dimensional dataset. SW microscopy is performed with high-magnification, high-numerical aperture objective lenses, and while this results in high-resolution images, the field of view is very small. Here we report upscaling of this interference imaging method from the microscale to the mesoscale using the Mesolens, which has the unusual combination of a low-magnification and high-numerical aperture. With this method, we produce SW images within a field of view of 4.4mm × 3.0mm that can readily accommodate over 16,000 cells in a single dataset. We demonstrate the method using both single-wavelength excitation and the multi-wavelength SW method TartanSW. We show application of the method for imaging of fixed and living cells specimens, with the first application of SW imaging to study cells under flow conditions.

Extended Smoothing Methods for Sparse Test Data Based on Zero-Padding

Aiming at the problem of sparse measurement points due to test conditions in engineering, a smoothing method based on zero-padding in the wavenumber domain is proposed to increase data density. Firstly, the principle of data extension and smoothing is introduced. The core idea of this principle is to extend the discrete data series by zero-padding in the wavenumber domain. The conversion between the spatial and wavenumber domains is achieved using the Discrete Fourier Transform (DFT) and the Inverse Discrete Fourier Transform (IDFT). Then, two sets of two-dimensional discrete random data are extended and smoothed, respectively, and the results verify the effectiveness and feasibility of the algorithm. The method can effectively increase the density of test data in engineering tests, achieve smoothing and extend the application to areas related to data processing.

Holistic Variability Analysis in Resistive Switching Memories Using a Two-Dimensional Variability Coefficient.

We present a new methodology to quantify the variability of resistive switching memories. Instead of statistically analyzing few data points extracted from current versus voltage (I-V) plots, such as switching voltages or state resistances, we take into account the whole I-V curve measured in each RS cycle. This means going from a one-dimensional data set to a two-dimensional data set, in which every point of each I-V curve measured is included in the variability calculation. We introduce a new coefficient (named two-dimensional variability coefficient, 2DVC) that reveals additional variability information to which traditional one-dimensional analytical methods (such as the coefficient of variation) are blind. This novel approach provides a holistic variability metric for a better understanding of the functioning of resistive switching memories.

Spatial Data Analytics-Assisted Subsurface Modeling: A Duvernay Case Study

Data analytics facilitate the examination of spatial data sets by using multiple techniques to find and understand patterns to guide decision making. However, standard data analysis tools assume that the data are independent and identically distributed, an assumption that spatial data sets usually do not fulfill. Furthermore, the usual methods neglect spatial continuity and the inherent data paucity that should be considered in the data analytics workflow. We present a new approach that combines data analytics, geostatistics, and optimization techniques to provide an end-to-end workflow to analyze two-dimensional (2D) data sets. The proposed workflow identifies outliers based on their spatial location or distribution, models geological trends using a Gaussian kernel, models the semivariogram, and performs sequential Gaussian simulation applying kriging or cokriging for cosimulation. Moreover, it provides metrics and diagnostic plots to evaluate the goodness of the results at each step. It is also semiautomatic because it leverages the user’s judgment for subsequent operations. For optimization, the workflow uses Bayesian optimization and evolutionary algorithms. We demonstrate the use of the workflow by analyzing 1,152 wells over the Duvernay Formation in Canada. The examples include the simulation of density-porosity as the secondary feature and the cosimulation of total organic content constrained by the former. The proposed workflow helps focus more on interpreting the results than the modeling parameters, reducing workforce time and subjective errors. Moreover, the spatial simulation includes multiple realizations to assess uncertainty and support decision making in data paucity scenarios. Overall, the proposed workflow is a valuable and complementary tool for evaluating uncertainty in mature geospatial data.

Two-Path Conventional Neural Network Based Signal-to-Noise Ratio Evaluation for UAV Communication Link

With the development of information technology, unmanned aerial vehicles (UAVs) have become an indispensable and important part of daily life and they have brought great convenience to life. Evaluating the signal-to-noise ratio (SNR) of UAV communication link is vital to improve the communication performance between UAV and the user. The classical SNR evaluation schemes of UAV communication link are limited in terms of performance, while deep learning (DL) based schemes are always at the expense of computation complexity. To solve the issues mentioned above, a two-path convolution neural network (TP-CNN) is proposed therein to evaluate the SNR of UAV communication link. Firstly, a two-dimensional dataset of UAV control signal is built and expanded thereafter. Then the TP-CNN model is designed and modified by feature fusion of input samples. Finally, the simulations are conducted, and the simulation results indicate that the performance of our proposed model is superior to that of the baseline model in terms of mean absolute error (MAE) and mean relative error (MRE).