Single Kernel Research Articles

TOF-PET Image Reconstruction With Multiple Timing Kernels Applied on Cherenkov Radiation in BGO.

Today Time-of-Flight (TOF), in PET scanners, assumes a single, well-defined timing resolution for all events. However, recent BGO–Cherenkov detectors, combining prompt Cherenkov emission and the typical BGO scintillation, can sort events into multiple timing kernels, best described by the Gaussian mixture models. The number of Cherenkov photons detected per event impacts directly the detector time resolution and signal rise time, which can later be used to improve the coincidence timing resolution. This work presents a simulation toolkit which applies multiple timing spreads on the coincident events and an image reconstruction that incorporates this information. A full cylindrical BGO–Cherenkov PET model was compared, in terms of contrast recovery and contrast-to-noise ratio, against an LYSO model with a time resolution of 213 ps. Two reconstruction approaches for the mixture kernels were tested: 1) mixture Gaussian and 2) decomposed simple Gaussian kernels. The decomposed model used the exact mixture component applied during the simulation. Images reconstructed using mixture kernels provided similar mean value and less noise than the decomposed. However, typically, more iterations were needed. Similarly, the LYSO model, with a single TOF kernel, converged faster than the BGO–Cherenkov with multiple kernels. The results indicate that the model complexity slows down convergence. However, due to the higher sensitivity, the contrast-to-noise ratio was 26.4% better for the BGO model.

Examination of the Peleg and Normand equation during relaxation of wheat: The effect of holding time.

In this study, we analyzed the effect of the duration of relaxation experiments on the parameters of the model proposed by Peleg and Normand. The relaxation experiments were conducted for individual intact wheat kernels in compression. Single kernels were initially loaded with a force of 20 N, then maintained at a constant deformation over time of 300 s. For the following time intervals 0-10, 0-20, 0-30, 0-40, 0-50, 0-60, 0-120, 0-180, 0-240, and 0-300 s coefficients k1 , k2 and Y(t) were determined according to the Normand and Peleg equation. The effect of time was compared at variable wheat moisture ranging from 8 to 20%. For longer holding times, the relaxed force was higher and the decay parameter, Y(t), decreased. The coefficient k1 increased proportionally with increase in the time of relaxation from ~3.3 to 23.3 s. The values of coefficient k2 declined for longer experiments, and the decline was relatively quick for up to 60 s and then asymptotically diminished. The effect of time on the decay parameter Y(t) and coefficients k1 and k2 depended on the moisture of kernels. The accuracy of the models was significantly different for the studied holding times. The highest standard error of the estimate was evidenced for 10 s experiments, and its minimum was noted at times close to 120-180 s.

Multikernel Clustering via Non-Negative Matrix Factorization Tailored Graph Tensor Over Distributed Networks

Next-generation wireless networks are witnessing an increasing number of clustering applications, and produce a large amount of non-linear and unlabeled data. In some degree, single kernel methods face the challenging problem of kernel choice. To overcome this problem for non-linear data clustering, multiple kernel graph-based clustering (MKGC) has attracted intense attention in recent years. However, existing MKGC methods suffer from two common problems: (1) they mainly aim to learn a consensus kernel from multiple candidate kernels, slight affinity graph learning, such that cannot fully exploit the underlying graph structure of non-linear data; (2) they disregard the high-order correlations between all base kernels, which cannot fully capture the consistent and complementary information of all kernels. In this paper, we propose a novel non-negative matrix factorization (NMF) tailored graph tensor MKGC method for non-linear data clustering, namely TMKGC. Specifically, TMKGC integrates NMF and graph learning together in kernel space so as to learn multiple candidate affinity graphs. Afterwards, the high-order structure information of all candidate graphs is captured in a 3-order tensor kernel space by introducing tensor singular value decomposition based tensor nuclear norm, such that an optimal affinity graph can be obtained subsequently. Based on the alternating direction method of multipliers, the effective local and distributed solvers are elaborated to solve the proposed objective function. Extensive experiments have demonstrated the superiority of TMKGC compared to the state-of-the-art MKGC methods.

Multiple Kernel Stein Spatial Patterns for the Multiclass Discrimination of Motor Imagery Tasks

Brain–computer interface (BCI) systems communicate the human brain and computers by converting electrical activity into commands to use external devices. Such kind of system has become an alternative for interaction with the environment for people suffering from motor disabilities through the motor imagery (MI) paradigm. Despite being the most widespread, electroencephalography (EEG)-based MI systems are highly sensitive to noise and artifacts. Further, spatially close brain activity sources and variability among subjects hampers the system performance. This work proposes a methodology for the classification of EEG signals, termed Multiple Kernel Stein Spatial Patterns (MKSSP) dealing with noise, raveled brain activity, and subject variability issues. Firstly, a bank of bandpass filters decomposes brain activity into spectrally independent multichannel signals. Then, Multi-Kernel Stein Spatial Patterns (MKSSP) maps each signal into low-dimensional covariance matrices preserving the nonlinear channel relationships. The Stein kernel provides a parameterized similarity metric for covariance matrices that belong to a Riemannian manifold. Lastly, the multiple kernel learning assembles the similarities from each spectral decomposition into a single kernel matrix that feeds the classifier. Experimental evaluations in the well-known four-class MI dataset 2a BCI competition IV proves that the methodology significantly improves state-of-the-art approaches. Further, the proposal is interpretable in terms of data distribution, spectral relevance, and spatial patterns. Such interpretability demonstrates that MKSSP encodes features from different spectral bands into a single representation improving the discrimination of mental tasks.

TOLERANCE MECHANISM AGAINST IMPACT OF HEAT STRESS ON WHEAT : A REVIEW

Wheat (Triticum aestivum) of the family Poaceae is an important cereal crop and is regarded as a basic source of calories and protein demands of the increasing population. With regards to change in global temperature, the impact of rising temperature on crop production is gaining concern worldwide. Among the various abiotic stresses observed in wheat, heat and drought are the major abiotic stresses. An increase in temperature results in the reduction of grain number, photosynthetic activity, chlorophyll content, and starch synthesis in the endosperm interrupting the important morphological, physiological, and biochemical processes of the plant causing considerable variation like reduction in grain weight per ear, single kernel weight, kernel number, grain size. Spikelet formation, seed size, etc. along with decreased plant size under morphological changes. Similarly, under physiological changes, water potential, photosynthesis, respiration, etc. are adversely affected due to heat stress in wheat. Content of starch, protein, and different types of amino acid present in wheat grain is also affected due to heat stress which comes under biochemical changes. Heat shock proteins (HSPs) and stay green are the mechanisms for the heat tolerance in wheat. The present review was carried out to summarize the various effects of heat stress on wheat at morpho-anatomical, physiological, and biochemical behavior with a brief discussion on suitable breeding strategies to improve the production of wheat crops.

Standardization of near infrared hyperspectral imaging for wheat single kernel sorting according to deoxynivalenol level

The spatial recognition feature of near infrared hyperspectral imaging (HSI-NIR) makes it potentially suitable for Fusarium and deoxynivalenol (DON) management in single kernels to break with heterogeneity of contamination in wheat batches to move towards individual kernel sorting and provide more quick, environmental-friendly and non-destructive analysis than wet-chemistry techniques. The aim of this study was to standardize HSI-NIR for individual kernel analysis of Fusarium damage and DON presence, to predict the level of contamination and classify grains according to the EU maximum limit (1250 µg/kg). Visual inspection on Fusarium infection symptoms and HPLC analysis for DON determination were used as reference methods. The kernels were scanned in both crease-up and crease-down position and for different image captures. The spectra were pretreated by Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV), 1st and 2nd derivatives and normalisation, and they were evaluated also by removing spectral tails. The best fitted predictive model was on SNV pretreated data (R2 0.88 and RMSECV 4.8 mg/kg) in which 7 characteristic wavelengths were used. Linear Discriminant Analysis (LDA), Naïve Bayes and K-nearest Neighbours models classified with 100% of accuracy 1st derivative and SNV pretreated spectra according to symptomatology and with 98.9 and 98.4% of correctness 1st derivative and SNV spectra, respectively. The starting point results are encouraging for future investigations on HSI-NIR technique application to Fusarium and DON management in single wheat kernels to overcome their contamination heterogeneity.

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method.

Near-infrared (NIR) hyperspectroscopy becomes an emerging nondestructive sensing technology for inspection of crop seeds. A large spectral dataset of more than 140,000 wheat kernels in 30 varieties was prepared for classification. Feature selection is a critical segment in large spectral data analysis. A novel convolutional neural network-based feature selector (CNN-FS) was proposed to screen out deeply target-related spectral channels. A convolutional neural network with attention (CNN-ATT) framework was designed for one-dimension data classification. Popular machine learning models including support vector machine (SVM) and partial least square discrimination analysis were used as the benchmark classifiers. Features selected by conventional feature selection algorithms were considered for comparison. Results showed that the designed CNN-ATT produced a higher performance than the compared classifier. The proposed CNN-FS found a subset of features, which made a better representation of raw dataset than conventional selectors did. The CNN-ATT achieved an accuracy of 93.01% using the full spectra and keep its high precision (90.20%) by training on the 60-channel features obtained via the CNN-FS method. The proposed methods have great potential for handling the analyzing tasks on other large spectral datasets. The proposed feature selection structure can be extended to design other new model-based selectors. The combination of NIR hyperspectroscopic technology and the proposed models has great potential for automatic nondestructive classification of single wheat kernels.

Water‐use efficiency of maize may be increased by the plant growth regulator paclobutrazol

AbstractContradictory results of the paclobutrazol (PAC) effect on maize plants were obtained under semiarid compared to well‐watered conditions with grain yield improvements versus depressions, respectively. In addition, maize cultivars differed in their reactions to similar PAC dosages. Thus, in the present study PAC was applied in the appropriate dosage at growth stage V5 to six maize cultivars (Zea mays L. cvs. Amanova, Severeen, Hubble, Galactus, Fabregas, Pioneer 3906) grown in a container experiment under well‐watered conditions. PAC caused significant decreases in plant height, increases in culm diameter and reduced transpiration rates in comparison with the untreated control plants. At anthesis, start and duration of pollen production, start of silking and anthesis‐silking interval (ASI) were mostly unaffected by PAC application. Senescence of PAC‐treated plants was delayed by one week. Apart from cultivar Galactus, PAC treatment caused significant grain yield reductions between 9% and 20%, which were solely based on decreases in kernel number because higher single kernel weights were obtained. In all cultivars, reductions in straw yield of 28% to 49% were achieved with PAC application, which were responsible for significant improvements of the harvest index by 8%–36%. PAC‐treated plants showed reduced water consumption (11%–21%), resulting in significantly improved WUEgrain during the critical period of kernel setting of the cultivars Amanova, Severeen, Galactus and Fabregas. The results indicate that PAC treatment of maize plants bears several advantages such as reduced water demand and improved water‐use efficiency (WUE), higher mechanical strength of the stalk and an enhanced harvest index. Possible grain yield decreases per plant under well‐watered conditions could be counteracted by moderate increases in plant density, yet concurrently this might diminish some of the beneficial PAC effects.

Spark and flame kernel interaction with dual-pulse laser-induced spark ignition in a lean premixed methane–air flow

The growth rate of flame kernels from dual-pulse laser-induced spark (DPLIS) ignition was compared to that from single-pulse laser-induced spark (SPLIS) ignition in a flowing premixed methane–air mixture. The flow speed ranged from 3.75 m/s to 12.5 m/s with equivalence ratios of 0.57–0.67. The pulse energy ranged from 10 mJ to 30 mJ, with each DPLIS pulse having half of the SPLIS pulse energy. High-speed schlieren imaging captured ignition and flame propagation. Two regimes were identified depending on the location of the first laser-induced spark (LIS) kernel: direct interaction and flame combination. The direct interaction regime occurred when the second LIS immediately combined with the first LIS. In the direct interaction regime, DPLIS ignition had faster flame kernel growth rates than SPLIS ignition when the second LIS occurred near the boundary of the first LIS expansion prior to the first LIS igniting the fuel–air mixture. The flame combination regime occurred when each LIS separately ignited the fuel–air mixture and then combined into a single flame kernel. DPLIS ignition had faster flame kernel growth rates in the flame combination regime than did SPLIS ignition when each DPLIS had fully developed into a self-sustaining flame.

An optimal kernel-based multivariate U-statistic to test for associations with multiple phenotypes.

Set-based analysis that jointly considers multiple predictors in a group has been broadly conducted for association tests. However, their power can be sensitive to the distribution of phenotypes, and the underlying relationships between predictors and outcomes. Moreover, most of the set-based methods are designed for single-trait analysis, making it hard to explore the pleiotropic effect and borrow information when multiple phenotypes are available. Here, we propose a kernel-based multivariate U-statistics (KMU) that is robust and powerful in testing the association between a set of predictors and multiple outcomes. We employed a rank-based kernel function for the outcomes, which makes our method robust to various outcome distributions. Rather than selecting a single kernel, our test statistics is built based on multiple kernels selected in a data-driven manner, and thus is capable of capturing various complex relationships between predictors and outcomes. The asymptotic properties of our test statistics have been developed. Through simulations, we have demonstrated that KMU has controlled type I error and higher power than its counterparts. We further showed its practical utility by analyzing a whole genome sequencing data from Alzheimer's Disease Neuroimaging Initiative study, where novel genes have been detected to be associated with imaging phenotypes.

Rapid high-throughput determination of major components and amino acids in a single peanut kernel based on portable near-infrared spectroscopy combined with chemometrics

The quality traits of peanuts (Arachis hypogaea L.) are fundamental to the whole peanut industry. However, many common analyses require the sample to be brought to the laboratory. Therefore, this research explores the feasibility of portable near-infrared spectroscopy combined with a single detection accessory to analyse the composition of peanuts in a single seed level quantitatively. The single detection accessory was specifically designed for spectral data collection considering the internal and external characteristics of single peanuts. Confocal laser scanning microscopy revealed that the oil body and protein body were randomly distributed at cell of single peanuts. The external characteristics of single peanuts were also determined and considered length (11.32–24.25 mm) and width (7.49–12.25 mm). The chemical compositional data (i.e. fat, sucrose, protein, and 16 amino acids) were determined by conventional wet-chemical methods and showed large variation. Principal component analysis on the compositional data showed that peanuts with higher fat contents usually have higher hydrophobic amino acids contents, lower sucrose contents, and lower protein contents. The composition prediction models of single peanuts were estimated using partial least squares regression models that were integrated with different spectral pre-treatments and validated by external sets. The results showed that the prediction models have good performance with a correlation coefficient above 0.88 (calibration) and 0.83 (prediction) and a residual prediction deviation above 1.5 except for a few indicators. Overall, the portable near-infrared spectroscopy offered reliable methods to assess the major components and amino acids quantitatively in a single peanut, which will improve the raw material quality in the peanut industry through the simultaneous and short-term determination of multiple indicators.

Structured and Consistent Multi-Layer Multi-Kernel Subtask Correction Filter Tracker

Some multi-task correlation filter trackers achieve the top-ranked performance in terms of accuracy and robustness. However, they directly fuse multiple types of features into a single kernel space. This operation fails to fully explore the discriminative strength and diversity of different features, and also ignores the structured correspondence of different tasks. To solve these issues, we propose a structured multi-kernel subtask correlation filter tracker with temporal-spatial consistency, which enjoys the merits of both layered multi-kernel subtask learning and structured correlation filter. Specifically, we firstly assign one kernel space to each channel feature. Multi-channel features correspond to multi-kernel spaces to boost their powerful discriminability. And then, we divide the target into multi-layer patches with different sizes, and regard the correlation filter trace of each patch with one channel feature as a subtask. In the following, we incorporate globally and locally structured correlation filters into a unified multi-kernel subtask particle tracking framework. The global and local subtasks complement and enhance each other with similar motion model. The proposed tracker not only exploits the cooperation and complementarity of layered multi-kernel subtask correlation filters, but also mines the underlying geometric structure of global subtasks, and the inner spatial locality correspondences of local subtasks inside the target. This operation is achieved by dual group sparsity regularized terms with mixed-norm l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p,q</sub> , which decomposes the multi-kernel subtask filter matrix into two collaborative components. They correspond to the adaptive filter feature selection and outlier subtask detection, respectively. Besides, the developed tracking model maintains the temporal coherence and spatial consistency of multi-layer subtask filters via the smooth regularizer. Finally, the tracking formulation is optimized by the accelerated proximal gradient approach (APG). Encouraging analyses on six benchmark datasets, verify the favorable effectiveness and robustness of our method against state-of-the-art trackers.

Identification of SSR Markers for Differentiating Rice (Oryza sativa L.) Varieties Marketed in Turkey

This study was carried out to identify SSR markers for the differentiation and identification of rice cultivars marketed in Turkey between 2016 and 2017. In this study 60 registered or production permitted, some local and foreign rice varieties were used as a material. DNA was isolated from single polished rice kernels for PCR amplification and rice cultivars were genotyped by 50 SSR markers. We found that 45 out of 50 SSR markers produced reproducible and polymorphic alleles. Thirty-six rice varieties had variety specific alleles among 60 rice varieties analysed in the study. This variety specific alleles belong to only one variety and they can be used to identify rice variety among 60 rice varieties studied. Osmancık-97, Cammeo, Ronaldo and Baldo are the most import 4 varieties in Turkish rice production and milled rice market. In this study, it was found that RM152, RM144, RM259 and RM118 SSR markers can be used to differentiate and identify these most important four varieties with different combinations. Collectively, this study provided some variety specific SSR markers that can be used to differentiate and identify rice varieties sold in Turkey.

Whole-body voxel-based internal dosimetry using deep learning

PurposeIn the era of precision medicine, patient-specific dose calculation using Monte Carlo (MC) simulations is deemed the gold standard technique for risk-benefit analysis of radiation hazards and correlation with patient outcome. Hence, we propose a novel method to perform whole-body personalized organ-level dosimetry taking into account the heterogeneity of activity distribution, non-uniformity of surrounding medium, and patient-specific anatomy using deep learning algorithms.MethodsWe extended the voxel-scale MIRD approach from single S-value kernel to specific S-value kernels corresponding to patient-specific anatomy to construct 3D dose maps using hybrid emission/transmission image sets. In this context, we employed a Deep Neural Network (DNN) to predict the distribution of deposited energy, representing specific S-values, from a single source in the center of a 3D kernel composed of human body geometry. The training dataset consists of density maps obtained from CT images and the reference voxelwise S-values generated using Monte Carlo simulations. Accordingly, specific S-value kernels are inferred from the trained model and whole-body dose maps constructed in a manner analogous to the voxel-based MIRD formalism, i.e., convolving specific voxel S-values with the activity map. The dose map predicted using the DNN was compared with the reference generated using MC simulations and two MIRD-based methods, including Single and Multiple S-Values (SSV and MSV) and Olinda/EXM software package.ResultsThe predicted specific voxel S-value kernels exhibited good agreement with the MC-based kernels serving as reference with a mean relative absolute error (MRAE) of 4.5 ± 1.8 (%). Bland and Altman analysis showed the lowest dose bias (2.6%) and smallest variance (CI: − 6.6, + 1.3) for DNN. The MRAE of estimated absorbed dose between DNN, MSV, and SSV with respect to the MC simulation reference were 2.6%, 3%, and 49%, respectively. In organ-level dosimetry, the MRAE between the proposed method and MSV, SSV, and Olinda/EXM were 5.1%, 21.8%, and 23.5%, respectively.ConclusionThe proposed DNN-based WB internal dosimetry exhibited comparable performance to the direct Monte Carlo approach while overcoming the limitations of conventional dosimetry techniques in nuclear medicine.

An experimental investigation on pre-ignition phenomena: Emphasis on the role of turbulence

Pre-ignition is an undesirable ignition event that affects chemical kinetic measurements in chemical reactors. Meanwhile, it appears randomly in engineering systems and is highly relevant to the soft knock or much stronger and detrimental super-knock in modern downsized engines. Currently its origins are still not fully understood. In this study, the role of turbulence in pre-ignition phenomena was experimentally investigated using a novel rapid compression machine. Different turbulent flow fields were achieved through calibrated orifice plates. Stoichiometric isooctane/air mixtures were tested under engine-relevant conditions in a target pressure range of 15–50 bar and a temperature range of 720–860 K. Useful insights into pre-ignition mechanism were obtained by combining instantaneous pressure acquisition with simultaneously recorded high-speed imaging. The experimental results demonstrate that owning to turbulent mixing with colder boundary layers, ignition timing is delayed when compared to ideal homogeneous compression ignition scenarios. However, pre-ignition phenomena can still be observed and become pronounced at lower target pressures with longer ignition delays. Moreover, pre-ignition formation can be characterized by single or multiple spherical flame kernels, distributed discretely inside core mixture or at near-wall regions. Different from the auto-ignition scenarios dominated by the chemical reactivity of test mixture, these pre-ignition flame kernels feature standard deflagration propagation. Finally, a dimensionless scaling analysis shows that pre-ignition formation is closely associated with turbulent length scale and laminar flame thickness.

Determination of starch content in single kernel using near-infrared hyperspectral images from two sides of corn seeds

Rapid, non-destructive and reliable detection of starch content in single seed is significant to facilitate the breeding of high-starch corn but difficult for a traditional method of seed composition analysis. This study investigated the possibility of using near-infrared (NIR) hyperspectral imaging technology to determine the starch content in a single kernel corn seed. The hyperspectral images including embryo-up and embryo-down orientations of a corn seed were acquired with a range of 930–2500 nm. The characteristic spectrum of each corn seed was calculated by averaging the two sides’ spectra. All spectra were preprocessed by the smoothing and derivative algorithm, and then, the characteristic wavelengths were selected by competitive adaptive reweighted sampling (CARS) method. The selected wavelengths were used as the inputs to develop partial least squares regression (PLSR) and nonlinear statistical data models with artificial neural networks (ANN) algorithm. The results indicated that the ANN prediction model based on Levenberg-Marquardt algorithm (LMA) was the optimal for starch content determination with correlation coefficient (Rp) of 0.96 and root mean square error of prediction (RMSEP) of 0.98 in prediction sets. Therefore, NIR hyperspectral imaging technology combined with appropriate chemometric analysis can be considered as a useful tool for starch content determination in corn seed at a kernel level. These results can provide a useful reference for rapid and non-destructive detection of other chemical composition in single corn seed.

Efficient parallel implementations to compute the diameter of a graph

SummaryThe Floyd‐Warshall algorithm is a well‐known algorithm to compute the distance of all pairs of nodes of a graph. The Blocked Floyd‐Warshall algorithm, a variant of the Floyd‐Warshall has been proposed to accelerate the Floyd‐Warshall algorithm by means of a graphics processing unit (GPU) architecture. The previously published GPU implementations for the Blocked Floyd‐Warshall algorithm perform many separated kernel calls for costly barrier synchronization. The main contribution of this article is to present efficient implementations of the Blocked Floyd‐Warshall algorithm, which performs no barrier synchronization and invokes only one kernel call. Experimental results using NVIDIA Tesla V100 show that our implementation runs 1.05‐1.31 times faster than the previously published one. Our implementation with SIMD functions also runs 1.00‐1.28 times faster than it. Second, we propose efficient GPU implementations to execute the Blocked Floyd‐Warshall algorithm for many graphs at the same time. From the experimental results, our single kernel implementation runs 1.03‐1.60 times faster than multiple kernel one. In terms of implementations with SIMD functions, our single kernel implementation runs 1.01‐1.89 times faster than it. We also propose the low‐latency implementations for many graphs. Finally, we implemented the parallel Floyd‐Warshall algorithm on the multicore processors.

Spike formation and seed setting of the main stem and tillers under post‐jointing drought in winter wheat

AbstractTo clarify the influence of post‐jointing drought on the ear‐bearing and seed‐setting characteristics of the main stem and tillers of winter wheat (Triticum aestivumL.), a pot experiment was conducted with cultivars “Shannong 29” (SN29) and “Heng 0628” (H0628), and five water regimes: mild drought (WR1) and severe drought (WR2) for 0–5 days after jointing, mild drought (WR3) and severe drought (WR4) for 0–10 days after jointing and adequate water supply as a control (CK). The present study focused on primary tillers (appear in the axils of main stem leaves: T1, T2, T3, T4, etc.), as well as on secondary tillers (appear from the bud in the axil of the prophyll: T10 and T20; appear in the axil of the first leaf of the primary tiller T1: T11). The yield components of tillers showed a downward trend with increasing tiller position and drought degree and duration, and the kernels per spike, single kernels weight and grain yield per spike of tillers T2, T3, T10 and T4 decreased more than those of the other tillers. These outcomes may be related to the spike developmental stages at the time of the drought period. Severe drought during the period from when the stamen primordium is first present (Waddington’s stage 4) to when the carpel extends around the three sides of the ovule (Waddington’s stage 5) significantly decreased the seed set of tillers, but short‐term (5 days) mild drought during this period and even a short‐term severe drought before Waddington’s stage 4 had little effect on the seed set of tillers. The ear‐bearing capacity of tillers was determined not only by the spike developmental stage, but also by the gap from the main stem and the competition of nutrition and space between tillers. Although the ear‐bearing rate of tillers T3 and T10 decreased rapidly after the short‐term mild drought, the increase in the ear‐bearing rate of tillers T20 and T11 effectively compensated for the loss of the number of spikes per plant. Therefore, the short‐term mild drought at the jointing stage had no significant effect on the grain yield of the two cultivars. The tillers T2, T3, T10 and T4 were sensitive to soil moisture in the jointing stage and had high plasticity. During this period, if timely irrigation improves soil moisture, it is expected to increase the ear‐bearing rate and seed set of these tillers, thereby increasing grain yield.

Fracture identification in tight reservoirs by multiple kernel Fisher discriminant analysis using conventional logs

Kernel Fisher discriminant analysis (KFD) can map well-log data into a nonlinear feature space to make a linear nonseparable problem of fracture identification into a linear separable one. Commonly, KFD uses one kernel. However, the prediction capacity of KFD based on one kernel is limited to some extent, especially for a complex classification problem, such as fracture identification in tight sandstone reservoirs. To alleviate this problem, we have used a multiple kernel Fisher discriminant analysis (MKFD) method to recognize fracture zones. MKFD uses multiscaled Gaussian kernel functions instead of a single kernel to realize optimal nonlinear mapping. To assess the effectiveness of MKFD in fracture identification for complex reservoirs, we chose a data set from tight sandstone reservoirs in China to implement comparison experiments. In the experiments, we used the MKFD with 20 Gaussian kernels to map the original well logs into nonlinear feature spaces so that we could obtain appropriate features for fracture identification. The comparison results demonstrated that the accuracy of fracture identification by MKFD improved about 13.4% over KFD and that MKFD also outperformed KFD in the blind well test, although the improvement of the generalization ability of MKFD was not very obvious. Overall, MKFD can provide an accurate means for the identification of fracture zones in tight reservoirs. We also evaluate the problems for fracture identification by MKFD.

A new multikernel relevance vector machine based on the HPSOGWO algorithm for predicting and controlling blast-induced ground vibration

The relevance vector machine (RVM) is considered a robust machine learning method and its superior performance has been confirmed through many successful engineering applications. To improve the performance of the RVM model, three single kernel functions, and three multikernel functions, including two newly proposed multikernel functions, tenfold cross-validation, and the hybrid particle swarm optimization with grey wolf optimizer (HPSOGWO) algorithm were combined to develop an artificial intelligence (AI) model framework. Afterwards, a new application of the RVM method was used and introduced for two different datasets of the blast-induced ground vibration. In addition, an artificial neural network (ANN) model and seven empirical equations were also developed for comparison purposes, and their prediction performances were evaluated considering three performance metrics, i.e., root mean square error (RMSE), correlation coefficient (R2), and mean absolute error (MAE). The obtained results showed that the multikernel RVM model can provide better performance capacity than the single-kernel RVM model. As a result, the AI models were found to be more applicable than the empirical equations in estimating blast-induced ground vibration. The prediction performance results of these models confirmed that the selected database has a great impact on the prediction capacity. Therefore, it is a common act to compare the performance of various models based on the selected database before selecting an optimal predictive model. The proposed model in this study provides new theoretical and practical support for the prediction of blast-induced ground vibration and can be utilized by other researchers in similar fields.