Genetic Algorithm Based Potential Selection in Simultaneous Voltammetric Determination of Isoniazid and Hydrazine by Using Partial Least Squares (PLS) and Artificial Neural Networks (ANNs)

The voltammetric behavior of isoniazid and hydrazine at an overoxidized polypyrrole modified glassy carbon electrode has been investigated. The obtained cyclic voltammograms showed that their oxidation peaks were overlapped and it is difficult to determine them individually from a mixture without separation. To overcome this limitation, a procedure was proposed for resolution of overlapped voltammetric signals from mixtures of isoniazid and hydrazine. In this procedure, genetic algorithm was used for the selection of potentials for partial least squares. A feed forward artificial neural network with back propagation error algorithm was used to process the nonlinear relationship between currents and concentrations of hydrazine and isoniazid. The proposed method was suitable for determination of isoniazid in pharmaceutical tablets and detection of hydrazine impurities in the same samples.     

Attempt to Built 13—Hydroxy—9,15—cyclo GA Skeletons

An easy and mild way to construet 13-hydroxy-9,15-cyclo GA skeletons was reported and it could be used as a general protocol in the synthesis of GAs with this structure.     

Influence of the thickness of matching layers on narrow band transmitter ultrasonic airborne transducers with frequencies <100 kHz: Application of a genetic algorithm

The acoustic impedances of matching layers and their thicknesses are the most important and influential parameters in the performance of airborne ultrasonic transducers. In this paper, the optimum thicknesses of the matching layers of the narrow band transmitter ultrasonic transducer regarding transmission coefficient were determined by individual calculations using a genetic algorithm. The genetic algorithm was chosen because it is a powerful tool in the optimization domain. The results show that the permitted thickness variation is 0.0005% for one matching layer, and this value can be increased to 0.0031%, which corresponds to the permitted thickness variation for five matching layers. Approximately 55% enhancement in the transmission coefficient is theoretically possible, and 42% enhancement was observed experimentally when the genetic algorithm was applied to calculate the matching layer thicknesses in place of the quarter wavelength equation that is conventionally used for the determination of layer thickness. To verify our approach, the effect of the thickness variation on the transmission coefficient has been investigated experimentally for three, four and five matching layers. The experimental results displayed good agreement with the theoretical predictions.     

A novel approach to generate robust classification models to predict developmental toxicity from imbalanced datasets

Computational models to predict the developmental toxicity of compounds are built on imbalanced datasets wherein the toxicants outnumber the non-toxicants. Consequently, the results are biased towards the majority class (toxicants). To overcome this problem and to obtain sensitive but also accurate classifiers, we followed an integrated approach wherein (i) Synthetic Minority Over Sampling (SMOTE) is used for re-sampling, (ii) genetic algorithm (GA) is used for variable selection and (iii) support vector machines (SVM) is used for model development. The best model, M3, has (i) sensitivity (SE) = 85.54% and specificity (SP) = 85.62% in leave-one-out validation, (ii) classification accuracy of the training set = 99.67%, (iii) classification accuracy of the test set = 92.59%; and (iv) sensitivity = 92.68, specificity = 92.31 on the test set. Consensus prediction based on models M3–M5 improved these percentages by 5% over M3. From the analysis of results we infer that data imbalance in toxicity studies can be effectively addressed by the application of re-sampling techniques.     

Electrodetermination of Gallic Acid Using Multi-walled Carbon Nanotube Paste Electrodes and N-Octylpyridinium Hexafluorophosphate

In this work, the determination of gallic acid was performed using surface-renewable carbon paste electrodes fabricated with multi-walled carbon nanotubes (MWCNT) and a mixture of N-octylpyridinium hexafluorophosphate (OPyPF₆) ionic liquid with mineral oil (MO) as binder. This system shows remarkable amperometric sensor characteristics and promotes a better electronic transfer. An electroanalytical study of gallic acid shows a linear range from 4.98±0.25 to 74.1±2.2 μmol L⁻¹, with R²=0.9958 and an experiment a limit of detection of 2.70±0.08 μmol L⁻¹ (S/N=3), and a sensitivity of 0.029 μA μmol⁻¹ L.     

基于GA参数整定的时变时滞系统灰色预测控制

针对一类数学模型未知且存在时变时滞的复杂系统,提出一种基于遗传算法参数整定的灰色预测控制方法。该方法采用BP神经网络对系统的时变时滞进行辨识,利用灰色预测算法对系统的输出进行预测,进而使用基于遗传算法整定PID控制器对系统进行输出反馈控制。该方法将灰色预测算法与遗传算法相结合,有效提高了控制器的自适应性。通过仿真实例,结果表明该方法能够对具有大时滞、大惯性、模型不确定等特点的复杂系统进行有效地控制。该方法是可行的、有效的。     

基于遗传神经网络的VAV空调系统预测模型

针对单纯的机理建模方法难以准确预测变风量空调系统（VAV）的参数,利用BP神经网络构建了变风量空调系统的预测模型,并将遗传算法与BP网络相结合,提出运用遗传算法对神经网络的权值和阈值进行遗传搜索,寻优后再进行BP运算,以克服BP算法收敛速度慢、易陷入局部解的缺点。通过实验平台采集了大量数据对所建模型进行训练和验证,结果表明,模型对空调送风参数以及房间温湿度的预测结果与实测数据能很好拟合,精确度高,泛化能力强。     

智能算法在晶体色散方程参量反演中的比较研究

为了研究智能优化算法在不同晶体材料色散方程参数反演中的迭代搜索性能问题,根据已测石英和方解石晶体的实验数据,分别采用遗传算法、模拟退火算法和遗传模拟退火算法应用于晶体色散方程的参数反演中,获得了晶体修正的塞耳迈耶尔方程的参量,同时比较了三种算法在迭代搜索性能、算法稳定性、计算时间和差方和等之间的差异,结果表明,三种算法在晶体色散方程参数反演时都可以得到满意的结果,但是,由于遗传模拟退火算法同时具备遗传算法的快速全局搜索性能和模拟退火算法的极强局部搜索性能,使得在晶体色散方程参数反演中的优化效果更优.因此在建立其它材料色散方程时建议采用遗传模拟退火算法,而且这一结果对研究混合智能算法的迭代搜索性能也是有帮助的.     

Development of enzyme-based bar code-style lateral-flow assay for hydrogen peroxide determination

A unique approach of developing a bar code version of lateral-flow enzymatic-based assay for the semi-quantification of hydrogen peroxide is described. The proposed assay system is mainly composed of a goat anti-mouse IgG-horseradish peroxidase conjugate (Gt anti-M IgG-HRP)-coated nitrocellulose (NC) membrane and a peroxidase substrate pad. Unlike the bar code immunochromatographic assay which depends on the stepwise capture of analyte, the principle of enzyme-based bar code lateral-flow assay is based on the different reaction time on successive lines due to the delay in 3,3′,5,5′-tetramethylbenzidine (TMB) release. Hydrogen peroxide (H₂O₂) acts as a limiting factor which controls the rate of the enzymatic conversion of TMB to blue color complex. The system expresses the concentration of H₂O₂ in micromole range as three distinct ladder bars in 9 min therefore without the need of any reading device. The major advantages of this assay are its easily readable result, and also its simplicity and low-cost in production offers a cheaper alternative for testing those expensive biosensors might not be available to the third world countries. By incorporating with H₂O₂-generating oxidoreductases, the assay can be further extended to detect a variety of analytes with clinical and environmental importance. Glucose was chosen to be the model analyte where the proposed system gave signal response at between 5 μM and 100 μM.     

Use of a novel Hill-climbing genetic algorithm in protein folding simulations

We have developed a novel Hill-climbing genetic algorithm (GA) for simulation of protein folding. The program (written in C) builds a set of Cartesian points to represent an unfolded polypeptide’s backbone. The dihedral angles determining the chain’s configuration are stored in an array of chromosome structures that is copied and then mutated. The fitness of the mutated chain’s configuration is determined by its radius of gyration.

A four-helix bundle was used to optimise simulation conditions, and the program was compared with other, larger, genetic algorithms on a variety of structures. The program ran 50% faster than other GA programs. Overall, tests on 100 non-redundant structures gave comparable results to other genetic algorithms, with the Hill-climbing program running from between 20 and 50% faster. Examples including crambin, cytochrome c, cytochrome B and hemerythrin gave good secondary structure fits with overall alpha carbon atom rms deviations of between 5 and 5.6 Å with an optimised hydrophobic term in the fitness function.