Projection Algorithm Research Articles

基于高光谱成像的大豆籽粒含水率检测研究

Using hyperspectral imaging technology for rapid, non-destructive detection of soybean grain moisture content provides technical support for high-quality soybean harvesting. A total of 90 samples of soybean grains from different varieties were collected, with hyperspectral images acquired in the wavelength range of 900–1700 nm. The moisture content of each soybean grain sample was determined using the direct drying method as specified in GB 5009.3-2016. The samples were divided into a calibration set and a prediction set based on a 4:1 ratio using the sample partitioning method of Joint X-Y Distance. Eight preprocessing methods were applied to the raw spectral data, including baseline correction, moving average, Savitzky-Golay filtering, normalization, standard normal variate transformation, multiple scatter correction, first derivative, and deconvolution. Feature wavelengths were then extracted using the successive projections algorithm and the competitive adaptive reweighted sampling algorithm. Finally, a partial least squares regression model for predicting the moisture content of soybean grains was developed based on these feature wavelengths. The results show that the correlation coefficient and the root mean square error of the optimal model for the prediction set were 0.92 and 0.2371, respectively. The moisture spectrum inversion model can precisely and rapidly predict the moisture content of soybean grains non-destructively, thereby determining the timing of mechanical soybean harvesting and enhancing the quality of soybean harvesting, storage, and processing.

Physics-driven untrained neural network for vortex beam compensation in adaptive optics aided underwater wireless optical communications

Orbital angular momentum (OAM) multiplexing is emerging as a critical technique for achieving high data capacity in underwater wireless optical communications (UWOC). Nonetheless, wavefront distortions induced by underwater turbulence compromise the orthogonality of OAM modes. In this paper, we introduce a physics-driven untrained learning approach for adaptive optics that operates independently of extensive amplitude datasets. Without iterative processing and pre-trained datasets, the underwater turbulence characteristics can be retrieved accurately by only relying on a one-shot distorted probe beam and a priori known amplitude of the probe beam. By leveraging a single distorted diffraction pattern and a priori known amplitude of the probe beam, the characteristics of underwater turbulence can be accurately retrieved without iterative processing or pre-trained datasets. Furthermore, by implementing a hybrid input/output alternating projection algorithm with a square constraint area, the retrieved underwater turbulence phase screen beyond the [0, 2π] range aligns with the target pattern. This consistency indicates that the proposed wavefront recovery technology is validated across a broad range of turbulence strengths. As a demonstration of feasibility, numerical simulations, and optical experiments were conducted to validate the compensation of OAM beams. Furthermore, the theoretical bit error rate (BER) and channel capacity were inferred based on the purity of OAM modes and the level of crosstalk.

A Graph-Based Machine-Learning Approach Combined with Optical Measurements to Understand Beating Dynamics of Cardiomyocytes.

The development of computational models for the prediction of cardiac cellular dynamics remains a challenge due to the lack of first-principled mathematical models. We develop a novel machine-learning approach hybridizing physics simulation and graph networks to deliver robust predictions of cardiomyocyte dynamics. Embedded with inductive physical priors, the proposed constraint-based interaction neural projection (CINP) algorithm can uncover hidden physical constraints from sparse image data on a small set of beating cardiac cells and provide robust predictions for heterogenous large-scale cell sets. We also implement an in vitro culture and imaging platform for cellular motion and calcium transient analysis to validate the model. We showcase our model's efficacy by predicting complex organoid cellular behaviors in both in silico and in vitro settings.

Discrimination of leaf diseases in Maize/Soybean intercropping system based on hyperspectral imaging

In order to achieve precise discrimination of leaf diseases in the Maize/Soybean intercropping system, i.e. leaf spot disease, rust disease, mixed leaf diseases, this study utilized hyperspectral imaging and deep learning algorithms for the classification of diseased leaves of maize and soybean. In the experiments, hyperspectral imaging equipment was used to collect hyperspectral images of leaves, and the regions of interest were extracted within the spectral range of 400 to 1000 nm. These regions included one or more infected areas on the leaves to obtain hyperspectral data. This approach aimed to enhance the accurate discrimination of different types of diseases, providing more effective technical support for the detection and control of crop diseases. The preprocessing of hyperspectral data involved four methods: Savitzky-Golay (SG), Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC) and 1st Derivative (1st Der). The 1st Der was found to be the optimal preprocessing method for hyperspectral data of maize and soybean diseases. Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA) and Principal Component Analysis (PCA) were employed for feature extraction on the optimal preprocessed data. The Support Vector Machines (SVM), Bidirectional Long Short-Term Memory Network (BiLSTM) and Dung Beetle Optimization-Bidirectional Long Short-Term Memory Network (DBO-BiLSTM) were established for the discrimination of maize and soybean diseases. Comparative analysis indicated that, in the classification of maize and soybean diseases, the DBO-BiLSTM model based on the CARS extraction method (1st Der-CARS-DBO-BiLSTM) demonstrated the highest classification rate, reaching 98.7% on the test set. The research findings suggest that integrating hyperspectral imaging with both traditional and deep learning methods is a viable and effective approach for classifying diseases in the intercropping model of maize and soybean. These results offer a novel method and a theoretical foundation for the non-invasive, precise, and efficient identification of diseases in the intercropping model of maize and soybean, carrying positive implications for agricultural production.

A modified projection algorithm for solving nonmonotone variational inequalities without Lipschitz continuity

ABSTRACT In this paper, we first present a modified double projection algorithm (MDPA for short) for solving variational inequality problems (VIP for short) without monotonicity. Compared with the algorithm of Ye and He [Comput Optim Appl. 2015;60(1):141–150], the next iterate point of MDPA is generated by projecting the current iterate point onto the intersection of the feasible set and only one half-space. Hence, MDPA can save the computational cost of computing the next iterate point. Moreover, we present a new MDPA (NMDPA for short) to decrease the total number of iterations of MDPA. The computational cost of NMDPA is the same as that of MDPA in each iteration. The global convergence of both MDPA and NMDPA is established under the same assumption that the underlying mapping is continuous and the solution set of its dual variational inequality is nonempty. Numerical experiments show that NMDPA can accelerate MDPA for solving nonmonotone VIP from the total number of iterative point of view and the CPU time point of view. Moreover, NMDPA is more efficient than Algorithm 1 of Dinh et al. [Numer Algorithms. 2022;90(4):1715–1734] from the CPU time point of view and the total number of iterations point of view.

Iterative methods for projection onto the ℓ p quasi-norm ball

In this paper, we focus on computing the projection onto the ℓ p quasi-norm ball. Motivated by the existing IRBP algorithm, which tackles ℓ p quasi-norm ball projection through projections onto a sequence of simple and tractable weighted ℓ 1 norm balls, we propose an innovative and effective iteratively reweighting approach for solving the projection problem. Specifically, our method centres on an ϵ -approximation that yields better approximation accuracy. We propose an innovative non-smooth, yet continuously differentiable approximation to the ℓ p quasi-norm function. Leveraging the concavity of our approximate model, we developed a novel variant of the iterative reweighted ℓ 1 norm ball projection algorithm. Through rigorous analysis, we demonstrated the global convergence properties of our proposed numerical approach. Numerical studies demonstrates the superior computational efficiency of our proposed algorithm. Moreover, our solution method can be further leveraged within current iterative algorithms designed to solve ℓ p quasi-norm ball constrained optimization problems, especially in scenarios where rapid convergence is of utmost importance.

Simulation on Image Reconstruction of Concrete with Rebars by Filtered Back Projection Algorithm using PHITS and MATLAB Program

This paper describes simulation on image reconstruction of concrete with rebars by filtered back projection algorithm using PHITS and MATLAB program. In PHITS simulation, a source of Cs-137 and NaI (Tl) detector were used. Concrete block with one rebar was carried out with PHITS simulation. The sample of another concrete block with two rebars with different diameters was also conducted. Linear attenuation coefficient values of the concrete were calculated. These phantoms were rotated with 2.8125 degree intervals over 0 to 180° in PHITS simulation. The objects were scanned with the parallel beam method and the projection data were obtained. The data was built into the image using filtered back projection (FBP) algorithm. The ‘spline’ interpolation and ‘Hamming’ filter functions were chosen for the clearest image in image reconstruction. The results indicated that the reconstructed images of the concrete containing one rebar and two rebars can be observed clearly in MATLAB.

Hardware simulation of real-time wavelength corrected phase projection

We demonstrate the real-time signal processing operation of a dispersion-free phase projection algorithm intended for atmospheric correction of multi-aperture optical phased arrays. It uses interferometric phase measurements at multiple sensing wavelengths, offset by 50 GHz, to compute a phase correction at a third, remote wavelength. This is useful where phase sensing cannot be implemented at the wavelength of interest, enabling interferometric level control from wavelength offset targeting beacons or guidestars. The digital signal processing implementation we demonstrate has a residual temporal phase error of 4×10−4rad/Hz while being capable of 100 MHz throughput with 0.53 µs latency, making it a viable approach for either feedback or feed-forward atmospheric correction in segmented piston-phase control systems.

Dimensionally Aligned Signal Projection Algorithms Library

Dimensionally Aligned Signal Projection Algorithms Library

Enhancing Leaf Area Index Estimation in Southern Xinjiang Fruit Trees: A Competitive Adaptive Reweighted Sampling-Successive Projections Algorithm and Three-Band Index Approach with Fractional-Order Differentiation

The Leaf Area Index (LAI) is a key indicator for assessing fruit tree growth and productivity, and accurate estimation using hyperspectral technology is essential for monitoring plant health. This study aimed to improve LAI estimation accuracy in apricot, jujube, and walnut trees in Xinjiang, China. Canopy hyperspectral data were processed using fractional-order differentiation (FOD) from 0 to 2.0 orders to extract spectral features. Three feature selection methods—Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA), and their combination (CARS-SPA)—were applied to identify sensitive spectral bands. Various band combinations were used to construct three-band indices (TBIs) for optimal LAI estimation. Random forest (RF) models were developed and validated for LAI prediction. The results showed that (1) the reflectance spectra of jujube and walnut trees were similar, while apricot spectra differed. (2) The correlation between fractional-order differential spectra and LAI was highest at orders 1.4 and 1.7, outperforming integer-order spectra. (3) The CARS-SPA selected a smaller set of feature bands in the 1100~2500 nm, reducing collinearity and improving spectral index construction. (4) The RF model using TBI4 demonstrated high R², low RMSE, and an RPD value > 2, indicating optimal prediction accuracy. This approach holds promise for hyperspectral LAI monitoring in fruit trees.

Nondestructive detection of multiple qualities of dried jujube in different storage periods based on hyperspectral imaging combined with deep learning

Moisture content and sugar content are characteristic substances that determine the quality of dried jujubes. In this study, we collected visible/near-infrared and near-infrared hyperspectral data (Vis-NIR and NIR) from three dried jujubes samples with different storage periods, and established recognition models for different storage periods of jujubes using Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Deep Learning Methods (LeNet, ResNet, DenseNet, MobileNet and EfficientNet). Then, we constructed a dried jujubes storage period classification model based on feature bands using Successive projections algorithm (SPA) and Principal component analysis (PCA) methods, the results showed that the classification results based on Vis-NIR were better than those based on NIR, and the classification model based on SPA method was more accurate. In addition, the internal quality attributes of moisture content and total sugar during a single storage period of jujube were also predicted, and a quality prediction model for multiple storage periods was established based on NIR. This study provides a fast and non-destructive method for detecting the storage and quality components of jujube, in order to control the quality of jujube at different storage periods.

Study on bionics-based swarm intelligence optimization algorithms for wavelength selection in near-infrared spectroscopy

Wavelength selection is one of the most important steps in the modeling of near-infrared spectroscopy (NIRS), which is of great significance to reduce model complexity and improve model performance. In this paper, a total of ten bionics-based swarm intelligence optimization algorithms (BSIOAs) inspired by natural creatures, such as Harris Hawks Optimization (HHO), Butterfly Optimization Algorithm (BOA), Whale Optimization Algorithm (WOA), Monarch Butterfly Optimization (MBO), Grey Wolf Optimization (GWO), Fruit Fly Optimization Algorithm (FOA), Bat Algorithm (BA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) were studied on application to wavelength selection in the NIRS modeling. Three benchmark NIRS datasets were used to evaluate the algorithms by calculating the indicators, including coefficients of determination, root mean square error, and residual predictive deviation in calibration and prediction. The results obtained showed that these BSIOAs can significantly reduce the number of wavelengths (retaining half or fewer). Compared with the full-spectrum models, the present models not only simplified the model structures but improved the model performances. The performances were generally better than the ones by some popular and classic wavelength selection algorithms, such as competitive adaptive reweighted sampling, Monte Carlo uninformative variable elimination, variable importance in projection, interval partial least-squares, and successive projections algorithm.

Identification of the CD8+ T-cell exhaustion signature of hepatocellular carcinoma for the prediction of prognosis and immune microenvironment by integrated analysis of bulk- and single-cell RNA sequencing data.

Hepatocellular carcinoma (HCC) is a prevalent type of cancer with high incidence and mortality rates. It is the third most common cause of cancer-related deaths. CD8+ T cell exhaustion (TEX) is a progressive decline in T cell function due to sustained T cell receptor stimulation from continuous antigen exposure. Studies have shown that CD8+ TEX plays an important role in the anti-tumor immune process and is significantly correlated with patient prognosis. The aim of the research is to establish a reliable CD8+ TEX-based signature using single-cell RNA sequencing (scRNA-seq) and high-throughput RNA sequencing (RNA-seq), providing a new approach to evaluate HCC patient prognosis and immune microenvironment. The RNA-seq data of HCC patients were download from three different databases: The Cancer Genome Atlas (TCGA), the Gene Expression Omnibus (GEO), and the International Cancer Genome Consortium (ICGC). HCC's 10× scRNA data were acquired from GSE149614. Based on single-cell sequencing data, CD8+ TEX-related genes were identified using uniform manifold approximation and projection (UMAP) algorithm, singleR, and marker gene methods. Afterwards, we proceeded to construct CD8+ TEX signature using differential gene analysis, univariate Cox regression analysis, least absolute shrinkage and selection operator (LASSO) regression, and multivariate Cox regression analysis. We also validated the CD8+ TEX signature in GEO and ICGC external cohorts and investigated clinical characteristics, chemotherapy sensitivity, mutation landscape, functional analysis, and immune cell infiltration in different risk groups. The CD8+ TEX signature, consisting of 13 genes (HSPD1, UBB, DNAJB4, CALM1, LGALS3, BATF, COMMD3, IL7R, FDPS, DRAP1, RPS27L, PAPOLA, GPR171), was found to have a strong predictive effect on the prognosis of HCC. The Kaplan-Meier (KM) analysis showed that the overall survival (OS) rate of patients in the low-risk group was higher than that of patients in the high-risk group across different datasets and specific populations. The research findings suggested that the risk score was an independent predictor of HCC prognosis. The model based on clinical features and risk score has a strong predictive effect. We observed significant differences among various risk groups in terms of clinical characteristics, functional analysis, mutation landscape, chemotherapy sensitivity, and immune cell infiltration. We constructed a CD8+ TEX signature to predict the survival probability of patients with HCC. We also found that the model could predict the sensitivity of targeted drugs and immune cell infiltration, and the risk score was negatively correlated with CD8+ T cell infiltration. In summary, the CD8+ TEX signature of HCC was constructed for the prediction of prognosis and immune microenvironment by integrated analysis of bulk and scRNA-seq data.

Classification of Chinese hickory with different aging times using two-dimensional correlation spectral (2DCOS) images combined with transfer learning

The Chinese hickory (Carya cathayensis Sarg.), highly valued in eastern China for its culinary appeal and nutritional value, is prone to rancidity during storage due to its high content of polyunsaturated fatty acids. This research introduces an innovative method for categorizing Chinese hickory nuts according to their aging durations by integrating two-dimensional correlation spectroscopy (2DCOS) with transfer learning, using hyperspectral imaging technology (HSI). The study captured hyperspectral images of 1,200 hickory kernels at various aging stages, extracting spectral data within the 900–––1670 nm range. Using this spectral data, synchronous, asynchronous, and integrative 2DCOS images were generated. The analytical framework comprised five spectral preprocessing methods:first derivative (FD), second derivative (SD), multiplicative scatter correction (MSC), standard normal variate (SNV), and detrend (DET); four wavelength selection techniques:successive projections algorithm (SPA), iteratively retaining information variables (IRIV), variable combination population analysis (VCPA), and iteratively variable subset optimization (IVSO); five transfer learning models:DarkNet19, DarkNet53, ResNet50, InceptionV3 and Xception; along with two traditional approaches: support vector machine (SVM) and linear discriminant analysis (LDA). This thorough strategy was designed to accurately classify the nuts on the basis of their aging time. The findings revealed that synchronous 2DCOS significantly outperformed asynchronous and integrative forms in classifying aged hickory kernels. The FD-IVSO-2DCOS-DarkNet19 model, employing 292 (62.80 %) wavelength variables, reached an impressive accuracy of 98.75 % in the test set, surpassing the SD-SPA-2DCOS-DarkNet53 model, which used only 40 (8.6 %) wavelength variables and achieved an accuracy of 97.92 %. These models excelled over other 2DCOS approaches that utilized the full wavelength range and significantly outdid the conventional one-dimensional spectral LDA and SVM models, regardless of wavelength scope. The study underscores that synchronous 2DCOS images, when combined with suitable transfer learning techniques, provide robust discriminative power, suggesting their potential utility in the classification aged hickory nuts.

Hybrid dark-field and attenuation contrast retrieval for laboratory-based X-ray tomography

X-ray dark-field imaging highlights sample structures through contrast generated by sub-resolution features within the inspected volume. Quantifying dark-field signals generally involves multiple exposures for phase retrieval, separating contributions from scattering, refraction, and attenuation. Here, we introduce an approach for non-interferometric X-ray dark-field imaging that presents a single-parameter representation of the sample. This fuses attenuation and dark-field signals, enabling the reconstruction of a unified three-dimensional volume. Notably, our method can obtain dark-field contrast from a single exposure and employs conventional back projection algorithms for reconstruction. Our approach is based on the assumption of a macroscopically homogeneous material, which we validate through experiments on phantoms and on biological tissue samples. The methodology is implemented on a laboratory-based, rotating anode X-ray tube system without the need for coherent radiation or a high-resolution detector. Utilizing this system with streamlined data acquisition enables expedited scanning while maximizing dose efficiency. These attributes are crucial in time- and dose-sensitive medical imaging applications and unlock the ability of dark-field contrast with high-throughput lab-based tomography. We believe that the proposed approach can be extended across X-ray dark-field imaging implementations beyond tomography, spanning fast radiography, directional dark-field imaging, and compatibility with pulsed X-ray sources.

Maturity Classification and Quality Determination of Cherry Using VNIR Hyperspectral Images and Comprehensive Chemometrics

ABSTRACT Sweetness and acidity are the two most important indicators to evaluate cherry quality. In this research, hyperspectral imaging (380–1030 nm) technology was applied to visually detect the sweetness and acidity of cherry. To improve the imaging performance, two spectral pretreatment methods (wavelet transform, standard normal variable transformation and detrend), three feature selection methods (successive projection algorithm, genetic algorithm, and shuffled frog leaping algorithm), and four regression modeling methods (principal components regression, partial least squares regression, least square-support vector regression, convolutional neural network) were employed and compared. After the chemometrics related to hyperspectral imaging had been examined, the least square-support vector regression models based on the feature bands, which were selected by the shuffled frog leaping algorithm, showed the best performance, and the determination coefficients of prediction (R2 P) for cherry sugar content and acidity reached 0.976 and 0.906, respectively. Based on the spectral principal components, three classifiers were built to classify the maturity level: support vector machine, backpropagation neural network, and radial basis function neural network. Excellent results with a classification accuracy of 100% were obtained. This research provides a complete and useful scheme to evaluate the quality and classify the maturity of cherry.

A modified PRP-type derivative-free projection algorithm for constrained nonlinear equations with applications

A modified PRP-type derivative-free projection algorithm for constrained nonlinear equations with applications

Dealing with Missing Angular Sections in NanoCT Reconstructions of Low Contrast Polymeric Samples Employing a Mechanical In Situ Loading Stage.

While in situ experiments are gaining importance for the (mechanical) assessment of metamaterials or materials with complex microstructures, imaging conditions in such experiments are often challenging. The lab-based computed tomography system Xradia 810 Ultra allows for the in situ (time-lapsed) mechanical testing of samples. However, the in situ loading setup of this system limits the image acquisition angle to 140°. For low contrast polymeric materials, this limited acquisition angle leads to regions of low information gain, thus preventing an accurate reconstruction of the data using a filtered back projection algorithm resulting in erroneous microstructures. Here, we demonstrate how the information gain can be improved by selecting an appropriate position of the sample. A low contrast polymeric tetrahedral microlattice sample and a structured sample with specific markers, both scanned over 140° and 180°, demonstrate that the missing structural details in the 140° reconstruction are limited to an angular wedge of about 20°. Depending on the sample geometry and microstructure, applying simple strategies for the in situ experiments allows accurate reconstruction of the data. For the tetrahedral microlattice, a simple rotation of the sample by 90° rotates all relevant surfaces by about 30° to the original illumination direction, creating a more even X-ray illumination for all the projections, thus providing enough X-ray absorption for an accurate reconstruction of the geometry.

Identification and crude protein prediction of porcini mushrooms via deep learning-assisted FTIR fingerprinting

Wild edible mushrooms are natural, green, and sustainable foods, and the key to their post-harvest safety and quality control lies in species identification, geographic traceability, and quality assessment. This study analyses the validity of partial least squares discriminant analysis (PLS-DA) model with residual convolutional neural network (ResNet) model based on Fourier transform infrared (FTIR) spectroscopy and two-dimensional correlation spectroscopy (2DCOS) for identifying species and geographic origin of porcini mushrooms. Exploring the feasibility of the partial least squares regression (PLSR) model and long short-term memory network (LSTM) model for predicting the crude protein content of porcini mushrooms. The results show that the ResNet model outperforms PLS-DA with 1.00 and 0.98 prediction results and 1.00 and 0.92 prediction accuracy for new samples, respectively. The LSTM model was more effective than the PLSR model in estimating crude protein content. Among them, LSTM model with first order derivative-multiple scattering correction-Savitzky-Golay (1D-MSC-SG) preprocessing combination was optimal with a prediction set RPD = 2.7, Sig. = 0.418. Besides, the sequential projection algorithm (SPA) feature extraction improves the prediction ability of the LSTM model. Its residual prediction deviation (RPD) was 2.9, Sig. = 0.627. The study provides a new reference for quality evaluation of edible mushrooms and other food products in the market.

Synthetizing Virtual Construction Images to Strengthen Real Data Volume and Variety in Real-world Application Scenarios

Despite the potential of synthetic construction images, it remains unknown whether they can strengthen real-data volume and variety in real-world scenarios, wherein a given, real training dataset is small and biased, or large but biased. To address this, we synthetize artificial images in a computer environment to strengthen a real training dataset and test its supplementary effects in both scenarios. Specifically, we simulate a worker’s physical behaviors, capture 2D synthetic images, and annotate its bounding box using a 3D-2D projection algorithm. After combining these synthetic images with a real dataset, we train a vision-based worker detection model and evaluate its performance in each scenario. Results show that the model’s performance is improved by up to 59.1% and 12.8% in each scenario, respectively, comparing to only adopting real images. This indicates that synthetic images can enrich the restricted volume and variety of a given, real training dataset in field application scenarios.