最小角回归结合核极限学习机的近红外光谱对柑橘黄龙病的鉴别

传统的柑橘黄龙病检测方法存在准确度低、稳定性差等问题,该文提出了一种基于最小角回归结合核极限学习机(Leastangleregressioncombinedwithkernelextremelearningmachine,LAR-KELM(RBF))的近红外柑橘黄龙病鉴别方法。该方法将光谱数据通过小波变换进行预处理,然后用最小角回归(LAR)算法进行光谱波长的筛选,最后通过核极限学习机(KELM(RBF))实现样本的分类。实验采用柑橘叶片的近红外光谱数据,验证了LAR-KELM(RBF)算法的性能,其分类准确度最高为99.91%,标准偏差为011。不同规模训练集的实验结果表明,LAR-KELM(RBF)模型较极限学习机(ELM)、波形叠加极限学习机(SWELM)、反向传播神经网络(BP(2层))、KELM(RBF)和支持向量机(SVM)模型分类准确度高、稳定性强,能够广泛应用于柑橘黄龙病的检测鉴别。     

Partitioning of atomization energy

The present work provides a technique for partitioning the atomization energy of a molecule into diatomic contributions. The method is largely based on the redistribution of the kinetic energy term in Mayer's energy partitioning and uses free‐atom energies as a reference. The comparison of Mayer's original method, the alternative Ichikawa–Yoshida approach, and the new atomization energy partitioning (AEP) shows that the new approach has advantages in describing trends in diatomic energies in molecules with triple bonds, as well as for hydrogen bonds. The proposed AEP is a viable alternative to Mayer's energy partitioning method. © 2007 Wiley Periodicals, Inc. Int. J. Quantum Chem, 2008     

Evaluation of the bond energy terms for the various types of boron-nitrogen bonds

Summary We have determined a series of bond energy terms in compounds containing dative, single, double and/or triple boron-nitrogen bonds. We describe various interesting applications based on these bond energy terms namely the determination of enthalpies of atomization and stabilization energies. More particularly, the conventional ring strain energies of three- and four-membered small ring containing boron and nitrogen atoms could be determined and the aromaticity of borazine, reexamined.Dedicated to Professor Alberte Pullman     

Nonlinear semisupervised principal component regression for soft sensor modeling and its mixture form

Compared with daily recorded process variables that can be easily obtained through the distributed control system, acquirements of key quality variables are much more difficult. As a result, for soft sensor development, we may only have a small number of output data samples and have much more input data samples. In this case, it is important to incorporate more input data samples to improve the modeling performance of the soft sensor. On the basis of the semisupervised modeling method, this paper aims to extend the linear semisupervised soft sensor to the nonlinear one, with incorporation of the kernel learning algorithm. Under the probabilistic modeling framework, a mixture form of the nonlinear semisupervised soft sensor is developed in the present work. To evaluate the performance of the developed nonlinear semisupervised soft sensor, an industrial case study is provided. Copyright © 2014 John Wiley & Sons, Ltd.     

Quantum Monte Carlo calculations of bond dissociation energies for some nitro and amino molecules

Bond dissociation energies (BDEs) for some nitro or amino contained prototypical molecules in energetic materials are computed by fixed‐node diffusion quantum Monte Carlo method. The nodes are determined from a Slater determinant calculated within density functional theory at the B3LYP/6‐311G** level. The possible errors, the nodal error, and the cancellation of nodal errors in calculating BDE are discussed, and the accuracy is compared with other available ab initio computations and experimental results. © 2010 Wiley Periodicals, Inc. Int J Quantum Chem, 2010     

Quantitative Analysis of Solar Photovoltaic Panel Performance with Size-Varied Dust Pollutants Deposition Using Different Machine Learning Approaches

In this paper, the impact of dust deposition on solar photovoltaic (PV) panels was examined, using experimental and machine learning (ML) approaches for different sizes of dust pollutants. The experimental investigation was performed using five different sizes of dust pollutants with a deposition density of 33.48 g/m² on the panel surface. It has been noted that the zero-resistance current of the PV panel is reduced by up to 49.01% due to the presence of small-size particles and 15.68% for large-size (ranging from 600 µ to 850 µ). In addition, a significant reduction of nearly 40% in sunlight penetration into the PV panel surface was observed due to the deposition of a smaller size of dust pollutants compared to the larger size. Subsequently, different ML regression models, namely support vector machine (SVMR), multiple linear (MLR) and Gaussian (GR), were considered and compared to predict the output power of solar PV panels under the varied size of dust deposition. The outcomes of the ML approach showed that the SVMR algorithms provide optimal performance with MAE, MSE and R² values of 0.1589, 0.0328 and 0.9919, respectively; while GR had the worst performance. The predicted output power values are in good agreement with the experimental values, showing that the proposed ML approaches are suitable for predicting the output power in any harsh and dusty environment.     

基于人工智能和互联网时代的化合物毒性预测综述

随着商品中所含各种化合物的不断使用,人们日益关注其对人类及生态环境的安全危害。在过去的几年里,通过计算方法预测化合物毒性已经显示出极大的潜力。在此,总结了常用的机器学习和深度学习算法在建立毒性预测模型上的优缺点,并系统回顾了近三年发表的可免费访问的毒性预测网络服务器。此外,还讨论了基于人工智能和互联网时代下毒性预测所面临的机遇和挑战。希望指导人们合理的选择算法和网络服务器进行建模及化合物毒性评估。     

Doubly excited3Se,3De and3Ge states of two-electron atomic systems

Summary Time-dependent perturbation theory has been applied to calculate the doubly excited triplet statesNsns:³S^e,Npnp:³D^e andNdnd:³G^e (N=2, 3, 4,n=N+1, ... ,5) for He, Li⁺, Be²⁺ and B³⁺. A time-dependent harmonic perturbation causes simulataneous excitation of both the electrons with a change of spin state. The doubly excited energy levels have been identified as the poles of an appropriately constructed linearized variational functional with respect to the driving frequency. In addition to the transition energies, effective quantum numbers of these doubly excited states have been calculated and analytic representations of their wave functions are obtained. These are utilized to estimate the Coulomb repulsion term for these states which checks the consistency of the wave functions. These wave functions may also be used for calculating other physical properties of the systems.     

Modeling Structure–Activity Relationship of AMPK Activation

The adenosine monophosphate activated protein kinase (AMPK) is critical in the regulation of important cellular functions such as lipid, glucose, and protein metabolism; mitochondrial biogenesis and autophagy; and cellular growth. In many diseases—such as metabolic syndrome, obesity, diabetes, and also cancer—activation of AMPK is beneficial. Therefore, there is growing interest in AMPK activators that act either by direct action on the enzyme itself or by indirect activation of upstream regulators. Many natural compounds have been described that activate AMPK indirectly. These compounds are usually contained in mixtures with a variety of structurally different other compounds, which in turn can also alter the activity of AMPK via one or more pathways. For these compounds, experiments are complicated, since the required pure substances are often not yet isolated and/or therefore not sufficiently available. Therefore, our goal was to develop a screening tool that could handle the profound heterogeneity in activation pathways of the AMPK. Since machine learning algorithms can model complex (unknown) relationships and patterns, some of these methods (random forest, support vector machines, stochastic gradient boosting, logistic regression, and deep neural network) were applied and validated using a database, comprising of 904 activating and 799 neutral or inhibiting compounds identified by extensive PubMed literature search and PubChem Bioassay database. All models showed unexpectedly high classification accuracy in training, but more importantly in predicting the unseen test data. These models are therefore suitable tools for rapid in silico screening of established substances or multicomponent mixtures and can be used to identify compounds of interest for further testing.     

Zincbindpredict—Prediction of Zinc Binding Sites in Proteins

Background: Zinc binding proteins make up a significant proportion of the proteomes of most organisms and, within those proteins, zinc performs rôles in catalysis and structure stabilisation. Identifying the ability to bind zinc in a novel protein can offer insights into its functions and the mechanism by which it carries out those functions. Computational means of doing so are faster than spectroscopic means, allowing for searching at much greater speeds and scales, and thereby guiding complimentary experimental approaches. Typically, computational models of zinc binding predict zinc binding for individual residues rather than as a single binding site, and typically do not distinguish between different classes of binding site—missing crucial properties indicative of zinc binding. Methods: Previously, we created ZincBindDB, a continuously updated database of known zinc binding sites, categorised by family (the set of liganding residues). Here, we use this dataset to create ZincBindPredict, a set of machine learning methods to predict the most common zinc binding site families for both structure and sequence. Results: The models all achieve an MCC ≥ 0.88, recall ≥ 0.93 and precision ≥ 0.91 for the structural models (mean MCC = 0.97), while the sequence models have MCC ≥ 0.64, recall ≥ 0.80 and precision ≥ 0.83 (mean MCC = 0.87), with the models for binding sites containing four liganding residues performing much better than this. Conclusions: The predictors outperform competing zinc binding site predictors and are available online via a web interface and a GraphQL API.