Optimization of neural network for ionic conductivity of nanocomposite solid polymer electrolyte system (PEO-LiPF6-EC-CNT)

In this study, the ionic conductivity of a nanocomposite polymer electrolyte system (PEO-LiPF₆-EC-CNT), which has been produced using solution cast technique, is obtained using artificial neural networks approach. Several results have been recorded from experiments in preparation for the training and testing of the network. In the experiments, polyethylene oxide (PEO), lithium hexafluorophosphate (LiPF₆), ethylene carbonate (EC) and carbon nanotubes (CNT) are mixed at various ratios to obtain the highest ionic conductivity. The effects of chemical composition and temperature on the ionic conductivity of the polymer electrolyte system are investigated. Electrical tests reveal that the ionic conductivity of the polymer electrolyte system varies with different chemical compositions and temperatures. In neural networks training, different chemical compositions and temperatures are used as inputs and the ionic conductivities of the resultant polymer electrolytes are used as outputs. The experimental data is used to check the system’s accuracy following the training process. The neural network is found to be successful for the prediction of ionic conductivity of nanocomposite polymer electrolyte system.     

On a problem of Hornik

In 1991,Hornik proved that the collection of single hidden layer feedforward neural networks(SLFNs)with continuous,bounded,and non-constant activation functionσis dense in C(K)where K is a compact set in R~s(see Neural Networks,4(2),251-257(1991)).Meanwhile,he pointed out"Whether or not the continuity assumption can entirely be dropped is still an open quite challenging problem".This paper replies in the affirmative to the problem and proves that for bounded and continuous almost everywhere(a.e.)activation functionσon R,the collection of SLFNs is dense in C(K)if and only ifσis un-constant a.e..     

基于布谷鸟算法与BP神经网络的煤灰变形温度预测

以120种煤样为数据基础,采用布谷鸟算法(CS)优化BP(Back Propagation)神经网络,建立了CSBP模型对单煤、煤掺添加剂和配煤等3类样本的煤灰变形温度(DT)样本进行预测。模型以煤灰化学成分及其组合参数等13个变量作为输入量,以变形温度(DT)作为输出量。CSBP模型预测结果与BP神经网络模型预测结果进行对比发现,无论是单煤、煤掺添加剂还是配煤,CSBP模型较BP模型对煤灰变形温度(DT)的预测都更加精准,平均相对误差分别达到了3.11%、4.08%和4.22%。另外,对比3类样本预测结果发现,无论是CSBP模型还是BP模型,相比单煤预测而言,煤掺添加剂及配煤的预测误差都有明显的增加。     

Process prediction of Ni–SiC coatings based on RBF-BP model

The preparation of Ni–SiC coatings using magnetic field-assisted jet electrodeposition under various plating settings is described in this study. A RBF-BP composite neural network with 4 × 4 × 4 × 7 × 10 × 1 was used to predict the corrosion resistance of Ni–SiC coatings prepared by employing different plating parameters. The results show that the fitting degree between the expected value and the actual value of the RBF-BP composite neural network is 0.97497. Moreover, the hybrid neural network can accurately predict the corrosion resistance of Ni–SiC coatings prepared under different process parameters. The corrosion weight loss of the coating is the lowest at the current density of 4 A/dm², a jet rate of 3 m/s, a SiC particle concentration of 8 g/L, and at a magnetic field intensity of 0.8 T, demonstrating its corrosion resistance under these conditions. According to the coating characterization analysis, the coating's grain size was significantly refined, and the surface was smoother with a high amount of uniformly sized SiC nanoparticles.     

Exploring artificial neural networks to model interatomic and intermolecular potential energy surfaces

We demonstrate how a back-propagation artificial neural network can be trained to represent a potential energy surface (PES) in a formless manner with limited data points and exploited to predict interaction energies for configurations not included in the training set. A similar exercise is undertaken for predicting the eigenvalues and eigenvectors of a model Hamiltonian matrix that delicately depends on parameters and exhibits crossing of eigen values.     

Year Discrimination of Mild Aroma Chinese Liquors Using Three-Dimensional Fluorescence Spectroscopy Combined with Parallel Factor and Neural NetworkSCIEI北大核心CSCD

Three-dimensional fluorescence spectroscopy coupled with parallel factor analysis and neural network was applied to the year discrimination of mild aroma Chinese liquors. The excitation-emission fluorescence matrices (EEMs) of 120 samples with various years were measured by FLS920 fluorescence spectrometer. The trilinear decomposition of the data array was performed and the loading scores of and the excitation-emission profiles of four components were also obtained. The scores were employed as the inputs of the BP neural networks and the PARAFAC-BP identification model was constructed. 10 samples were collected from 10, 20 and 30 years of liquors respectively, and 30 samples were selected as the test sets. The remaining 90 samples were used as the training sets to build the training model. The year prediction of unknown samples was also carried out, and the prediction accuracy was 90%, 100% and 100%, respectively. Meanwhile, the discrimination analysis method and the multi way partial least squares discriminant analysis were compared, namely PARAFAC-BP and NPLS-DA. The results indicated that parallel factor combined with the neural network (PARAFAC-BP) has higher prediction accuracy. The proposed method can effectively extract the spectral characteristics, and also reduce the dimension of the input variables of neural network. A good year discrimination result was finally achieved.     

Numerical and empirical modeling of peak deceleration and stress analysis of polyurethane elastomer under impact loading test

In this work, we present the modeling of the peak deceleration (PD) using data of the experimental drop test. Specimens with different thicknesses and areas tested in the drop test device which has adaptable height and weight. In the empirical modeling of the PD, the thickness, area, drop mass and drop height considered as separable functions. An analytical model and Neural Network (NN) was used as the empirical models. Further, the stress on the material was calculated using differential equations and the Finite Element Method (FEM). The Obtained PD from the experimental test, analytical and NN models was converted to the stress on the material using a derived differential equation. Finally, the best model for analyzing the PD and Stress on the material was presented.     

The physicochemical properties role of a functionalized alkyl-peptide in nanofibre formation and neural progenitor cells viability and survival

Amphiphilic alkyl-peptides as novel biomaterials form 3D scaffolds that are applicable in tissue engineering. Here, the nanofibre formation capability of a distinct alkyl-peptide was investigated using coarse-grained molecular dynamics simulation (CGMD) and experimental methods. The alkyl-peptide (Ace-FAQRVPPEEEGGGAAAAK-Nhe(C16)) was functionalized with a peptide epitope (FAQRVPPP) which can help to maintenance and differentiation of neural stem cells. Two alkyl-peptide systems were investigated: the all-functionalized system (with only bioactive alkyl-peptides) and the distributed system (a combination of bioactive and non-bioactive alkyl-peptides with ratio 1:2). The CGMD and TEM results confirm elongated nanofibres for all-functionalized system and cylindrical nanofibres for the distributed one. Furthermore, PC12 cells show a reliable growth on both 2D alkyl-peptides coated surfaces. Because of the nanofibres negative surface charges, the cell morphologies show clustered form in the distributed system and rounded shape in the all-functionalized one. Since the stem cell state preserves in cluster form, the physicochemical property of these nanofibres allows a potential advantage in stem cell long-time maintains.     

基于上转换纳米粒子的低损伤神经界面技术

Optogenetics is a neuromodulation technology that combines light control technology with genetic technology, thus allowing the selective activation and inhibition of the electrical activity in specific types of neurons with millisecond time resolution. Over the past several years, optogenetics has become a powerful tool for understanding the organization and functions of neural circuits, and it holds great promise to treat neurological disorders. To date, the excitation wavelengths of commonly employed opsins in optogenetics are located in the visible spectrum. This poses a serious limitation for neural activity regulation because the intense absorption and scattering of visible light by tissues lead to the loss of excitation light energy and also cause tissue heating. To regulate the activity of neurons in deep brain regions, it is necessary to implant optical fibers or optoelectronic devices into target brain areas, which however can induce severe tissue damage. Non- or minimally-invasive remote control technologies that can manipulate neural activity have been highly desirable in neuroscience research. Upconversion nanoparticles (UCNPs) can emit light with a short wavelength and high frequency upon excitation by light with a long wavelength and low frequency. Therefore, UCNPs can convert low-frequency near-infrared (NIR) light into high-frequency visible light for the activation of light-sensitive proteins, thus indirectly realizing the NIR optogenetic system. Because NIR light has a large tissue penetration depth, UCNP-mediated optogenetics has attracted significant interest for deep-tissue neuromodulation. However, in UCNP-mediated in vivo optogenetic experiments, as the up-conversion efficiency of UCNPs is low, it is generally necessary to apply high-power NIR light to obtain up-converted fluorescence with energy high enough to activate a photosensitive protein. High-power NIR light can cause thermal damage to tissues, which seriously restricts the applications of UCNPs in optogenetic technology. Therefore, the exploration of strategies to increase the up-conversion efficiency, fluorescence intensity, and biocompatibility of UCNPs is of great significance to their wide applications in optogenetic systems. This review summarizes recent developments and challenges in UCNP-mediated optogenetics for deep-brain neuromodulation. We firstly discuss the correspondence between the parameters of UCNPs and employed opsins in optogenetic experiments, which mainly include excitation wavelengths, emission wavelengths, and luminescent lifetimes. Thereafter, we introduce the methods to enhance the conversion efficiency of UCNPs, including optimizing the structure of UCNPs and modifying the organic dyes in UCNPs. In addition, we also discuss the future opportunities in combining UCNP-mediated optogenetics with flexible microelectrode technology for the long-term detection and regulation of neural activity in the case of minimal injury.