Evaluation model of green supply chain cooperation credit based on BP neural network

Neural Computing and Applications - More and more enterprises hope to achieve cooperation and win–win. However, many companies often have problems such as insufficient partner credit, which...     

Predicting visual similarity between colour palettes

This work is concerned with the prediction of visual colour difference between pairs of palettes. In this study, the palettes contained five colours arranged in a horizontal row. A total of 95 pairs of palettes were rated for visual difference by 20 participants. The colour difference between the palettes was predicted using two algorithms, each based on one of six colour-difference formulae. The best performance (r² = 0.86 and STRESS = 16.9) was obtained using the minimum colour-difference algorithm (MICDM) using the CIEDE2000 equation with a lightness weighing of 2. There was some evidence that the order (or arrangement) of the colours in the palettes was a factor affecting the visual colour differences although the MICDM algorithm does not take order into account. Application of this algorithm is intended for digital design workflows where colour palettes are generated automatically using machine learning and for comparing palettes obtained from psychophysical studies to explore, for example, the effect of culture, age, or gender on colour associations.     

Comparative studies on thermal and toughness properties of polybenzoxazine composites with two functionalized graphene oxides

Abstract

Graphene oxide (GO) was functionalized by polyether amine (PEA) via two methods which were one-pot modification in acetone (GON) and two steps with the intermediate product of GOCO-Cl generated (GONS). There were more PEA successfully grafted onto GO for GONS than GON. The onset polymerization temperatures of the benzoxazine (Bz) composites decreased by the inclusion of 1?wt% of GO, GON or GONS. Thermal stability of the polybenzoxazine (PBz) composites was significantly improved indicated from the increase of weight loss temperature. T₁₀, T₂₀ and T₅₀ values of the composites with GONS were higher than that of the others. Toughness of PBzs may be enhanced by the incorporation of nanofillers, and GONS had stronger interfacial interaction with PBz matrix than GON.     

Functionalized graphene oxide nanosheets with unique three-inone properties for efficient and tunable antibacterial applications

Developing antibiotics-independent antibacterial agents is of great importance since antibiotic therapy faces great challenges from drug resistance.Graphene oxide(GO)is a promising agent due to its natural antibacterial mechanisms,such as sharp edgemediated cutting effect.However,the antibacterial activity of GO is limited by its negative charge and low photothermal effect.Herein,the amino-functionalized GO nanosheets(AGO)with unique three-in-one properties were synthesized.Three essential properties(positive charge,strong photothermal effect,and natural cutting effect)were integrated into AGO.The positive charge(30 mV)rendered AGO a strong interaction force with model pathogen Streptococcus mutans(330 nN).The natural cutting effect of 100 ng·mL^-1AGO caused 27%loss of bacterial viability after incubation for 30 min.Most importantly,upon the near-infrared irradiation for just 5 min,the three-in-one properties of AGO caused 98%viability loss.In conclusion,the short irradiation period and the tunable antibacterial activity confer the three-in-one AGO a great potential for clinical use.     

水文序列相依变异识别的RIC定阶准则——以自回归模型为例

水文过程相依性是水文变异的主要表现形式之一,应用自回归模型对其进行拟合时合理确定模型阶数是一个难点问题。本文在分析AIC和BIC准则的基础上,提出了一种以原序列与其相依成分的相关系数作为拟合度指标,同时借用信息熵形式的函数式,作为模型不确定性度量指标的自回归模型定阶准则(简称RIC准则)。以AR(1)、AR(2)、AR(3)和AR(4)模型为例进行统计试验,将不同序列长度下该准则的定阶准确率与其他定阶准则进行比较,试验结果表明,RIC准则对于上述模型均具有较好的适应性,且定阶准确率远高于AIC准则,其中对于前三阶模型RIC准则优于BIC准则,但四阶模型略低于BIC准则。RIC准则的优势是可以同时满足模型定阶、相依程度分级与模型检验的需求,将其应用于实测水文序列分析,结果显示,该准则能较准确地识别自回归模型的阶数,且符合提出的"相依有变异而残差无变异的最小阶数"的检验标准。     

基于近红外光谱技术的马铃薯叶片含水率高效预测

提出了运用近红外光谱技术检测新鲜马铃薯叶片中含水量的方法，并通过预测结果和运算量的对比得出一种高效率的预测方法。采集了900～2100 nm波段范围内110个新鲜马铃薯叶片的光谱反射率信息，经SG（Savitzky-Golay）平滑、多元散射校正（MSC）和标准正态变量变换（SNV）3种预处理后，分别建立偏最小二乘回归（PLSR）模型和BP神经网络模型，再运用回归系数（regression coefficients, RC）法在全波段光谱中提取特征波长，同样经3种预处理后分别建立预测模型。结果表明：在运用光谱全波段信息构建的模型中，经多元散射校正（MSC）预处理建立的BP神经网络模型预测效果最好，预测集决定系数R²为0.9791，均方根误差RMSE为0.3723；在基于特征波长构建的模型中，经SG平滑预处理建立的神经网络模型预测效果最优，预测集决定系数R²为0.9658，均方根误差RMSE为0.4759；验证了特征波段结合BP神经网络建立的模型与全波段建立的模型预测结果相差不大，因而能够极大地减少运算量，提高预测效率。     

煤化工酸水汽提装置运行存在问题及解决方法

本文简述了酸水汽提工艺的发展概况和技术进展,详细介绍了煤化工酸水汽提装置实际运行中存在的几类主要问题,并提出切实可行的解决措施,具有一定的借鉴意义。     

基于CVSD编码的无线语音系统方案的设计

简要介绍了连续可变斜率增量(CVSD)调制的原理。与目前应用较为广泛的其它语音编码方式相比较,CVSD拥有更优的数字特性。着重介绍了由CML公司研制开发的基于CVSD的语音编码芯片———CMX649的特点及相关的应用方式。CMX649能够成功地应用在广泛的语音编码系统中,尤其适合无线语音系统应用。在此基础上,给出了一种实用性很强的低成本、低功耗无线语音系统的设计与应用方案。该方案可提供清晰可靠的语音传输,可广泛应用于农村地区,具有广阔的市场空间。     

再生水水源水质问题及对策

以郑州市五龙口污水处理厂为例,论述了城市污水处理厂二级出水中活性微生物、藻类和NO_3~-对再生水生产设施造成的不利影响,同时提出了应对措施。对聚氯化铝和聚氯化铝铁除磷效果进行了试验,结果表明,聚氯化铝除磷效果优于聚氯化铝铁。