恢复方式和地形对晋西黄土区退耕林分物种多样性的影响

运用样带样方调查法,对比不同恢复方式和地形条件下退耕林分的物种多样性,以期为晋西黄土区植被恢复效果评价和经营管理提供参考.结果表明: 恢复方式对退耕林分物种多样性具有显著影响.自然恢复林物种数为刺槐人工林的 1.6倍,Shannon 指数大于刺槐人工林,Pielou 指数小于刺槐人工林.物种多样性受坡位影响显著,各指数均表现为沟底>沟坡>梁峁坡>梁峁顶;坡向对退耕林分物种多样性影响不显著,各指数均表现为阴坡>阳坡.物种多样性受地形和恢复方式综合作用影响显著,在自然恢复林阴坡沟底处最高,物种均匀度在刺槐人工林阴坡沟底处最高.从提高物种多样性角度,黄土区植被恢复在遵循适地适树原则的同时,应参照自然恢复林分,在不同地形部位采用不同的造林设计.     

Evolutionary optimization of RBF networks

One of the main obstacles to the widespread use of artificial neural networks is the difficulty of adequately defining values for their free parameters. This article discusses how Radial Basis Function (RBF) networks can have their parameters defined by genetic algorithms. For such, it presents an overall view of the problems involved and the different approaches used to genetically optimize RBF networks. A new strategy to optimize RBF networks using genetic algorithms is proposed, which includes new representation, crossover operator and the use of a multiobjective optimization criterion. Experiments using a benchmark problem are performed and the results achieved using this model are compared to those achieved by other approaches.     

A novel feature extraction approach for microarray data based on multi-algorithm fusion

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions.     

基于辅助环境变量的土壤有机碳空间插值——以黄土丘陵区小流域为例

利用普通克里格法(OK)、反距离加权法(IDW)、径向基函数法(RBF)、基于土地利用类型修正的普通克里格法(OK_LU)4种插值方法,对黄土丘陵羊圈沟小流域的土壤有机碳含量进行空间插值。预测结果的准确性通过Pearson相关系数(R),平均绝对误差(MAE),均方根误差(RMSE),准确度(AC)来评价。研究结果表明:(1)在前3种常规空间插值方法中,OK对刻画区域土壤有机碳的空间分布趋势效果最佳,其预测MAE值和RMSE值均为最小,Pearson相关系数(R)和准确度(AC)最大,说明其预测结果的准确性最好、预测的极端误差也最小;其次为RBF;IDW预测的效果最差。(2)OK_LU在空间特征表达方面能够更好地反映复杂地形区的局部变异,其插值结果的精度相比OK有一定程度的提高,其平均绝对误差(MAE)从0.900%降到了0.567%,均方根误差(RMSE)从1.101%降到了0.777%,Pearson相关系数(R)从0.4026提高到0.5589,准确度(AC)从0.9081提高到0.9505。综合比较,在黄土丘陵地区,OK_LU能使插值结果的精度有较大提高,是土壤有机碳空间制图的有效途径。     

An assessment of magnetic and geochemical indicators of weathering and pedogenesis at two contrasting sites on the Chinese Loess plateau

We present the results of high stratigraphic resolution measurements of magnetic and geochemical parameters sensitive to weathering and pedogenesis at two ～ 2500 ky loess–palaeosol sequences on the Chinese Loess Plateau. The two sites, Duanjiapo and Luochuan, are located on a strong modern climatic gradient and should have been subject to a significantly different degree of precipitation and temperature during the period of loess accumulation. Comparison of the magnetic and geochemical parameters indicates a complex and inconsistent relationship both within and between sites. In particular, a previously suggested coherency between the amplitude of variations in magnetic susceptibility and the Rb/Sr ratio is shown not to be the case over the entire length of the sequence. This finding indicates that quantitative climatic reconstructions for Chinese loess which are based on any single magnetic or geochemical parameter should be treated with caution. ‘Difference’ plots, obtained by calculating the difference between coeval magnetic or geochemical parameters between the two sites appear may offer a useful means of characterising latitudinal gradients in weathering and soil forming intensity, and indicate increases in the intensity of summer monsoon strength after about 1200 ka and 600 ka.     

Predictive modeling of human operator cognitive state via sparse and robust support vector machines

The accurate prediction of the temporal variations in human operator cognitive state (HCS) is of great practical importance in many real-world safety-critical situations. However, since the relationship between the HCS and electrophysiological responses of the operator is basically unknown, complicated and uncertain, only data-based modeling method can be employed. This paper is aimed at constructing a data-driven computationally intelligent model, based on multiple psychophysiological and performance measures, to accurately estimate the HCS in the context of a safety-critical human–machine system. The advanced least squares support vector machines (LS-SVM), whose parameters are optimized by grid search and cross-validation techniques, are adopted for the purpose of predictive modeling of the HCS. The sparse and weighted LS-SVM (WLS-SVM) were proposed by Suykens et al. to overcome the deficiency of the standard LS-SVM in lacking sparseness and robustness. This paper adopted those two improved LS-SVM algorithms to model the HCS based solely on a set of physiological and operator performance data. The results showed that the sparse LS-SVM can obtain HCS models with sparseness with almost no loss of modeling accuracy, while the WLS-SVM leads to models which are robust in case of noisy training data. Both intelligent system modeling approaches are shown to be capable of capturing the temporal fluctuation trends of the HCS because of their superior generalization performance.     

Hydrologic and geologic factors that influenced spatial variations in loess deposition in China during the last interglacial-glacial cycle: results from proxy climate and GCM analyses

Results from climate proxy and General Circulation Model (GCM) analyses suggest that variations in soil moisture and desert expansion are key hydrologic and geologic factors, respectively, influencing temporal and spatial variations in loess texture and distribution in the Loess Plateau of China. During the last glacial period a reduction in soil moisture led to dune destabilization and a southward expansion of the desert (the source of loess) toward the Loess Plateau. Changes in soil moisture in East Asia may have been influenced by the size and extent of the Fennoscandian ice sheet, and the atmospheric circulation pattern that it induced downstream. These results suggest that both regional factors (i.e. changes in soil moisture and the position of the desert margin) and hemispherical factors (i.e. changes in the size and extent of the Eurasian ice sheets) have influenced loess deposition on the Loess Plateau of China.     

Bayesian LASSO for quantitative trait loci mapping

The mapping of quantitative trait loci (QTL) is to identify molecular markers or genomic loci that influence the variation of complex traits. The problem is complicated by the facts that QTL data usually contain a large number of markers across the entire genome and most of them have little or no effect on the phenotype. In this article, we propose several Bayesian hierarchical models for mapping multiple QTL that simultaneously fit and estimate all possible genetic effects associated with all markers. The proposed models use prior distributions for the genetic effects that are scale mixtures of normal distributions with mean zero and variances distributed to give each effect a high probability of being near zero. We consider two types of priors for the variances, exponential and scaled inverse-chi(2) distributions, which result in a Bayesian version of the popular least absolute shrinkage and selection operator (LASSO) model and the well-known Student's t model, respectively. Unlike most applications where fixed values are preset for hyperparameters in the priors, we treat all hyperparameters as unknowns and estimate them along with other parameters. Markov chain Monte Carlo (MCMC) algorithms are developed to simulate the parameters from the posteriors. The methods are illustrated using well-known barley data.     

黄土高原生态分区及概况

黄土高原地域广阔,水土流失区域差异显著。为了有效治理水土流失,评估水土流失治理技术和模式及生态恢复建设工程的成效性,需要对黄土高原进行区域划分。依据自然条件、水土流失治理技术和模式的区域性特征及差异,基于国家基础地理信息系统数据的县级行政界,对其进行合并,进行生态分区的划分,并分别统计其气候、地形地貌、植被特征及水土流失现状,以期为黄土高原水土流失治理技术和模式的改良优化提供依据。主要结论如下:(1)黄土高原分为黄土高塬沟壑区,黄土丘陵沟壑区,沙地和农灌区,土石山区及河谷平原区。其中黄土高塬沟壑区和黄土丘陵沟壑区分别划分为两个副区。(2)黄土高原的气候、植被、水土流失具有明显的分区差异。降水和植被覆盖度自东南向西北递减,二者在空间分布上具有很好的一致性,降水量大的分区,植被覆盖度也高。在年际变化方面,丘陵沟壑区B2副区降水量呈增加趋势,其他分区呈减小趋势,变化均不显著。80年代以来,黄土高原和各生态分区的植被覆盖度均逐渐增加,黄土丘陵沟壑区的增加量最大。各分区的面平均气温均呈非显著增加趋势,90年代以来增温明显。(3)1970年以来,黄土高原侵蚀产沙强度减弱趋势显著,至2002—2015年,多年平均输沙模数在0.13—3924 t km~(-2) a~(-1)之间,侵蚀强度最大为中度侵蚀(2500—5000 t km~(-2) a~(-1)),但面积较小,主要分布于第二高塬沟壑区的泾河流域。     

黄土丘陵沟壑区坡面尺度土壤水分空间变异及影响因子

土壤水分空间分布特征及其影响因子是土壤前期含水量模拟和小流域产流机制研究的重要内容,也是半干旱地区进行生态建设的重要参考。通过对黄土高原典型坡面雨季前后100 cm深度内土壤含水量进行观测,分析地形、植被和雨季对土壤水分空间分布的影响。基本统计分析显示,土壤水分的空间异质性在上层(<20 cm)较小,在下层(>40 cm)较大。坡面尺度上,土壤含水量的空间差异主要表现在不同植被类型之间,而不是坡位之间。各覆被类型的土壤含水量相对大小为荒草地>8年生刺槐林>20年生刺槐林>沙棘林。即使沙棘林和刺槐林位于更利于获取土壤水分的地形条件下,其土壤含水量仍然明显低于荒草地。地形对土壤水分的影响被植被类型的影响所掩盖。上述规律在雨季前后都有明显表现。因此,完全基于地形指数的土壤水分预测模型在黄土高原应该慎用,植被类型应该作为土壤水分空间预测的一个重要参数。雨季使土壤含水量整体提高,但是土壤水分空间分布格局并没有根本改变,高处仍高,低处仍低,各样点处的土壤含水量在雨季前后达到显著相关水平,说明土壤水分空间格局并不是瞬时状态,而具有明显的时间稳定性。     

Initial guesses generation for fluorescence intensity distribution analysis

The growing number of applications of Fluorescence Intensity Distribution Analysis (FIDA) demands for new approaches in data processing, aiming at increased speed and robustness. Iterative algorithms of parameter estimation, although proven to be universal and accurate, require some initial guesses (IG) of the unknown parameters. An essential component of any data processing technology, IG become especially important in case of FIDA, since even with apparently reasonable, and physically admissible but randomly chosen IG, the iterative procedure may converge to situations where the FIDA model cannot be evaluated correctly. In the present work we introduce an approach for IG generation in FIDA experiments based on the method of moments. IG are generated for the sample parameters: brightness, concentration, and for the parameters related to experimental set-up: background, observation volume profile. A number of analytical simplifications were introduced in order to increase the accuracy and robustness of the numerical algorithms. The performance of the developed method has been tested on number of simulations and experimental data. Iterative fitting with generated IG proved to be more robust and at least five times faster than with an arbitrarily chosen IG. Applicability of the proposed method for quick estimation of brightness and concentrations is discussed.     

A graphic approach to evaluate algorithms of secondary structure prediction

Algorithms of secondary structure prediction have undergone the developments of nearly 30 years. However, the problem of how to appropriately evaluate and compare algorithms has not yet completely solved. A graphic method to evaluate algorithms of secondary structure prediction has been proposed here. Traditionally, the performance of an algorithm is evaluated by a number, i.e., accuracy of various definitions. Instead of a number, we use a graph to completely evaluate an algorithm, in which the mapping points are distributed in a three-dimensional space. Each point represents the predictive result of the secondary structure of a protein. Because the distribution of mapping points in the 3D space generally contains more information than a number or a set of numbers, it is expected that algorithms may be evaluated and compared by the proposed graphic method more objectively. Based on the point distribution, six evaluation parameters are proposed, which describe the overall performance of the algorithm evaluated. Furthermore, the graphic method is simple and intuitive. As an example of application, two advanced algorithms, i.e., the PHD and NNpredict methods, are evaluated and compared. It is shown that there is still much room for further improvement for both algorithms. It is pointed out that the accuracy for predicting either the alpha-helix or beta-strand in proteins with higher alpha-helix or beta-strand content, respectively, should be greatly improved for both algorithms.     

Timing and Spatial Distribution of Loess in Xinjiang,NW China

Central Asia is one of the most significant loess regions on Earth, with an important role in understanding Quaternary climate and environmental change. However, in contrast to the widely investigated loess deposits in the Chinese Loess Plateau, the Central Asian loess–paleosol sequences are still insufficiently known and poorly understood. Through field investigation and review of the previous literature, the authors have investigated the distribution, thickness and age of the Xinjiang loess, and analyzed factors that control these parameters in the Xinjiang in northwest China, Central Asia. The loess sediments cover river terraces, low uplands, the margins of deserts and the slopes of the Tianshan Mountains and Kunlun Mountains and are also present in the Ili Basin. The thickness of the Xinjiang loess deposits varies from several meters to 670 m. The variation trend of the sand fraction (>63 μm) grain-size contour can indicate the local major wind directions, so we conclude that the NW and NE winds are the main wind directions in the North and South Xinjiang, and the westerly wind mainly transport dust into the Ili basin. We consider persistent drying, adequate regional wind energy and well-developed river terraces to be the main factors controlling the distribution, thickness and formation age of the Xinjiang loess. The well-outcropped loess sections have mainly developed since the middle Pleistocene in Xinjiang, reflecting the appearance of the persistent drying and the present air circulation system. However, the oldest loess deposits are as old as the beginning of the Pliocene in the Tarim Basin, which suggests that earlier aridification occurred in the Tarim Basin rather than in the Ili Basin and the Junggar Basin.     

Individualized performance prediction of sleep-deprived individuals with the two-process model.

We present a new method for developing individualized biomathematical models that predict performance impairment for individuals restricted to total sleep loss. The underlying formulation is based on the two-process model of sleep regulation, which has been extensively used to develop group-average models. However, in the proposed method, the parameters of the two-process model are systematically adjusted to account for an individual's uncertain initial state and unknown trait characteristics, resulting in individual-specific performance prediction models. The method establishes the initial estimates of the model parameters using a set of past performance observations, after which the parameters are adjusted as each new observation becomes available. Moreover, by transforming the nonlinear optimization problem of finding the best estimates of the two-process model parameters into a set of linear optimization problems, the proposed method yields unique parameter estimates. Two distinct data sets are used to evaluate the proposed method. Results of simulated data (with superimposed noise) show that the model parameters asymptotically converge to their true values and the model prediction accuracy improves as the number of performance observations increases and the amount of noise in the data decreases. Results of a laboratory study (82 h of total sleep loss), for three sleep-loss phenotypes, suggest that individualized models are consistently more accurate than group-average models, yielding as much as a threefold reduction in prediction errors. In addition, we show that the two-process model of sleep regulation is capable of representing performance data only when the proposed individualized model is used.     

U-YOLOv7: A network for underwater organism detection

Detecting and monitoring underwater organisms is very important for sea aquaculture. The human eye struggles to quickly distinguish between aquatic species due to their variety and dense dispersion. In this paper, a deep learning object detection algorithm based on YOLOv7 is used to design a new network, called Underwater-YOLOv7 (U-YOLOv7), for underwater organism detection. This model satisfies the requirements with regards to both speed and accuracy. First, a network combining CrossConv and an efficient squeeze-excitation module is created. This network increases the extraction of channel information while reducing parameters and enhancing the feature fusion of the network. Second, a lightweight Content-Aware ReAssembly of FEatures (CARAFE) operator is used to obtain more semantic information about underwater images before feature fusion. A 3D attention mechanism is incorporated to improve the anti-interference ability of the model in underwater recognition. Finally, a decoupling head using hybrid convolution is designed to accelerate convergence and improve the accuracy of underwater detection. The results show that the network proposed in this paper obtains an improvement of 3.2% in accuracy, 2.3% in recall, and 2.8% in the mean average precision value and runs at up to 179 fps, far outperforming other advanced networks. Moreover, it has a higher estimation accuracy than the YOLOv7 network.     

Integrating Artificial and Human Intelligence into Tablet Production Process

We developed a new machine learning-based method in order to facilitate the manufacturing processes of pharmaceutical products, such as tablets, in accordance with the Process Analytical Technology (PAT) and Quality by Design (QbD) initiatives. Our approach combines the data, available from prior production runs, with machine learning algorithms that are assisted by a human operator with expert knowledge of the production process. The process parameters encompass those that relate to the attributes of the precursor raw materials and those that relate to the manufacturing process itself. During manufacturing, our method allows production operator to inspect the impacts of various settings of process parameters within their proven acceptable range with the purpose of choosing the most promising values in advance of the actual batch manufacture. The interaction between the human operator and the artificial intelligence system provides improved performance and quality. We successfully implemented the method on data provided by a pharmaceutical company for a particular product, a tablet, under development. We tested the accuracy of the method in comparison with some other machine learning approaches. The method is especially suitable for analyzing manufacturing processes characterized by a limited amount of data.KEY WORDS: artificial intelligence, machine learning, process analytical technology, process optimization, tablet manufacture     

Grain size of loess, palaeosol and Red Clay deposits on the Chinese Loess Plateau: Significance for understanding pedogenic alteration and palaeomonsoon evolution

To assess pedogenic modification to grain size distributions of loess, palaeosol and Red Clay deposits on the Chinese Loess Plateau and to understand long-term evolution of the East Asian palaeomonsoon since the late Miocene, we investigate a continuous loess-palaeosol-Red Clay sequence at Lingtai (south Chinese Loess Plateau) and another parallel Red Clay sequence at Zhaojiachuan (central Chinese Loess Plateau). By analyzing the grain size distributions of bulk samples and chemically isolated quartz samples, the relative intensity of pedogenic alteration of the loess, palaeosol and Red Clay deposits can be quantified. Comparisons of the grain size distributions and contents of different grain size fractions between the bulk and the quartz samples suggest that pedogenic alteration is apparently stronger in the Red Clay sequence than in the overlying loess-palaeosol deposits. Furthermore, grain size parameters derived from the bulk and the quartz samples, such as mean grain size, coarse fraction content and U-ratio, exhibit similar variations in the loess-palaeosol sequence (Quaternary, 0-2.6 Ma), whereas these grain size parameters of quartz samples show different variability from those of bulk samples in the Red Clay sequence (late Miocene to Pliocene, 2.6-7 Ma). Grain size of quartz from the loess-palaeosol and Red Clay deposits exhibits distinct and persistent oscillations from the late Miocene to the Pleistocene, implying that significant fluctuations of the palaeomonsoon climate in East Asia might have occurred at least since late Miocene time.     

A Comparative Approach for MI-Based EEG Signals Classification Using Energy,Power and Entropy

ObjectiveThe initial principal task of a Brain-Computer Interfacing (BCI) research is to extract the best feature set from a raw EEG (Electroencephalogram) signal so that it can be used for the classification of two or multiple different events. The main goal of the paper is to develop a comparative analysis among different feature extraction techniques and classification algorithms.Materials and methodsIn this present investigation, four different methodologies have been adopted to classify the recorded MI (motor imagery) EEG signal, and their comparative study has been reported. Haar Wavelet Energy (HWE), Band Power, Cross-correlation, and Spectral Entropy (SE) based Cross-correlation feature extraction techniques have been considered to obtain the necessary features set from the raw EEG signals. Four different machine learning algorithms, viz. LDA (Linear Discriminant Analysis), QDA (Quadratic Discriminant Analysis), Naïve Bayes, and Decision Tree, have been used to classify the features.ResultsThe best average classification accuracies are 92.50%, 93.12%, 72.26%, and 98.71% using the four methods. Further, these results have been compared with some recent existing methods.ConclusionThe comparative results indicate a significant accuracy level performance improvement of the proposed methods with respect to the existing one. Hence, this presented work can guide to select the best feature extraction method and the classifier algorithm for MI-based EEG signals.     

Optimized lightweight CA-transformer: Using transformer for fine-grained visual categorization

As a rapidly developing research direction in computer vision (CV), related algorithms such as image classification and object detection have achieved inevitable research progress. Improving the accuracy and efficiency of algorithms for fine-grained identification of plant diseases and birds in agriculture is essential to the dynamic monitoring of agricultural environments. In this study, based on the computer vision detection and classification algorithm, combined with the architecture and ideas of the CNN model, the mainstream Transformer model was optimized, and then the CA-Transformer (Transformer Combined with Channel Attention) model was proposed to improve the ability to identify and classify critical areas. The main work is as follows: (1) The C-Attention mechanism is proposed to strengthen the feature information extraction within the patch and the communication between feature information so that the entire network can be fully attentive while reducing the computational overhead; (2) The weight-sharing method is proposed to transfer parameters between different layers, improve the reusability of model data, and at the same time increase the knowledge distillation link to reduce problems such as excessive parameters and overfitting; (3) Token Labeling is proposed to generate score labels according to the position of each Token, and the total loss function of this study is proposed according to the CA-Transformer model structure. The performance of the CA-Transformer model proposed in this study is compared with the current mainstream models on datasets of different scales, and ablation experiments are performed. The results show that the accuracy and mIoU of the CA-Transformer proposed in this study reach 82.89% and 53.17MS, respectively, and have good transfer learning ability, indicating that the model has good performance in fine-grained visual categorization tasks and can be used in ecological information. In the context of more diverse ecological information, this study can provide reference and inspiration for the practical application of information.     

High-resolution multi-proxy climate records from Chinese loess: evidence for rapid climatic changes over the last 75 kyr

The loess/paleosol sequence in loess layer L1 (Malan Loess) is investigated in three regions of the Western Chinese Loess Plateau. Nine pedogenic layers are found in L1 and three proxy climate indices, magnetic susceptibility (MS), grain size (GS) and CaCO₃ content, are measured at intervals of 0.2 kyr in order to recover records of monsoon climate variations. Time series of MS, GS and CaCO₃ content document the high resolution history of summer and winter monsoon climate variations over the last 75 kyr. The records show a high degree of similarity to the warm interstadials recorded in ice cores from Greenland and the Antarctic, and with Heinrich events in the North Atlantic, during the last glacial cycle. Bond cycles are also recorded by the Chinese loess records. Overall, our results indicate that numerous rapid changes in climate occurred in China during the last glacial cycle, but that the range of climate variations was smaller than recorded in Greenland.