基于形态特征提取的急性下壁心肌梗死BiLSTM网络辅助诊断算法

急性下壁心肌梗死是一种病发急、进展快、致死率高的心脏疾病,该文提出一种新颖的基于形态特征提取的BiLSTM神经网络分类的急性下壁心肌梗死辅助诊断算法,可大幅度提高医生对急性下壁心肌梗死疾病的诊断效率并有助于及时确诊.算法包括:对胸痛中心数据库心拍信号进行降噪及心拍分割;根据临床心内科医学诊断指南提取了12导联波形距离特征和分导联波形幅值特征;依据提取的特征搭建LSTM与BiLSTM神经网络进行心拍的分类识别;使用PTB公开数据库和胸痛中心数据库多临床中心进行交叉验证.实验结果表明,加入胸痛中心真实临床数据后,基于形态特征提取BiLSTM神经网络的急性下壁心肌梗死辅助诊断算法准确率达到99.72％,精度达到99.53％,灵敏度达到100.00％,同时F1-Score达到99.76.该算法比其他现有算法准确率提高至少1％,该项研究具有非常重要的临床应用价值.     

Technological and sensorial properties of liquid nitrogen ice cream enriched with protein from brewing waste (trub)

Debittered trub (brewing waste) is an important source of protein source (70.26%). Trub and whey protein were used for 5% protein enrichment of ice cream frozen by liquid nitrogen. Three formulations were elaborated: ice cream standard (ICS), ice cream with whey protein (ICW) and ice cream with trub (ICT). Chemical composition, rheological properties, texture, overrun, melting rate, scanning electron microscopy and a sensorial test were performed. Results showed that ICT presented a higher viscosity, obtained on the upward curve up to 6.76 Pa s⁻¹, consistency index (22.96 (Pa s⁻¹)ⁿ), hysteresis area (140.40 mPa s⁻¹) and hardness (31113.33 g) but a lower melting rate (0.38 g min⁻¹), overrun (13.92%) and sensorial acceptability than the other formulations. The addition of trub debittered for protein enrichment improved ice cream properties and demonstrated that it could be used as a food ingredient.     

Adaptive backstepping repetitive learning control design for nonlinear discrete‐time systems with periodic uncertainties

This paper addresses a tracking problem for uncertain nonlinear discrete‐time systems in which the uncertainties, including parametric uncertainty and external disturbance, are periodic with known periodicity. Repetitive learning control (RLC) is an effective tool to deal with periodic unknown components. By using the backstepping procedures, an adaptive RLC law with periodic parameter estimation is designed. The overparameterization problem is overcome by postponing the parameter estimation to the last backstepping step, which could not be easily solved in robust adaptive control. It is shown that the proposed adaptive RLC law without overparameterization can guarantee the perfect tracking and boundedness of the states of the whole closed‐loop systems in presence of periodic uncertainties. In addition, the effectiveness of the developed controller is demonstrated by an implementation example on a single‐link flexible‐joint robot. Copyright © 2014 John Wiley & Sons, Ltd.     

Correlation between instrumental texture and colour quality attributes with sensory analysis of selected cheeses as affected by fat contents

This study evaluated several physical and sensory parameters of different types of cheese available in the Polish market. The measurements of textural properties were conducted in an Instron universal testing machine, while the colour properties of cheeses were measured using a Minolta chromameter. The chemical composition was determined by means of the near‐infrared spectroscopy (NIRs). Moreover, a trained sensory panel was invited to assess the cheese texture‐related properties. Generally, cheeses with reduced fat content were characterised by higher hardness, adhesiveness, cohesiveness and elasticity. Texture‐related parameters of cheese with canola oil were comparable to that of most of full‐fat cheeses. The correlation analysis between physical and sensory attributes related to cheese textural properties indicated the potential applications of TPA, shear and penetration tests (r = 0.766, r = 0.75 and r = 0.765, respectively) for the evaluation of sensory properties related to the hardness. Meanwhile, the elasticity of cheese obtained from sensory evaluation was strongly correlated with the elasticity determined from the shear test (r = 0.722) and moderately correlated with the elasticity from penetration test (r = 0.588), indicating a need to refine the method of penetration test. In addition, cheeses exhibited higher meltability during convection heating at 230 °C than microwave heating. The values of meltability for cheese with reduced fat content were lower than those of full‐fat cheese.     

Properties and applications of β‐glycosidase from Bacteroides thetaiotaomicron that specifically hydrolyses isoflavone glycosides

To modify the glycan part of glycosides, the gene encoding β‐glycosidase was cloned from Bacteroides thetaiotaomicron VPI‐5482. The cloned gene, bt_1780, was expressed in Escherichia coli MC1061 and the expressed enzyme was purified using Ni‐NTA affinity chromatography. The purified enzyme, BTBG, showed optimal activity at 50 °C and pH 5.5. Interestingly, this enzyme did not have any hydrolysing activity on ordinary β‐linkage–containing substrates such as xylobiose, lactose and cello‐oligosaccharide, but specifically hydrolysed isoflavone glycosides such as daidzin, genistin and glycitin. Compared to a commercial beta glucosidase, BTBG selectively hydrolysed isoflavone glycosides in soybean extract mixture solution. These results suggest that BTBG may be a specialized enzyme for the hydrolysis of glycosides and that the substrate specificity of BTBG is applicable for the bioconversion of isoflavone glycosides in the food industry.     

Catalytic Hydrocracking of a Bitumen‐Derived Asphaltene over NiMo/γ‐Al2O3 at Various Temperatures

Hydrocracking of a bitumen‐derived asphaltene over NiMo/γ‐Al₂O₃ was investigated in a microbatch reactor at varying temperatures. The molar kinetics of asphaltene cracking reaction was examined by fitting the experimental data. Below a defined temperature, the molar reaction showed the first‐order kinetic feature while at higher temperatures secondary reactions such as coke formation became significant, causing deviation of the reaction behavior from the proposed first‐order kinetic model. Selectivity analysis proved that dominant products varied from gases to liquids to gases with increasing temperature, shifting the dominant reaction from C–S bonds cleavage to C–C bonds cleavage.     

一种基于Spark的不确定数据集频繁模式挖掘算法

如何在海量不确定数据集中提高频繁模式挖掘性能是目前研究的热点.传统算法大多是以期望、概率或者权重等单一指标为数据项集支持度，在大数据背景下，同时考虑概率和权重支持度的算法难以兼顾其执行效率.为此，本文提出一种基于Spark的不确定数据集频繁模式挖掘算法（UWEFP），首先，为了同时兼顾数据项的概率和权重，计算一项集的最大概率权重值并进行剪枝；然后，为了减少对数据集的多次扫描，结合Spark框架的优点，设计了一种具有FP-tree特征的新颖的UWEFP-tree结构进行模式树的构建及挖掘；最后在Spark环境下，以UCI数据集进行实验验证.实验结果表明本文的方法在保证挖掘结果的同时，提高了效率.