The Effect of Chemical Representation on Active Machine Learning Towards Closed-Loop Optimization

Multivariate chemical reaction optimization involving catalytic systems is a non-trivial task due to the high number of tuneable parameters and discrete choices. Closed-loop optimization featuring active Machine Learning (ML) represents a powerful strategy for automating reaction optimization. However, the translation of chemical reaction conditions into a machine-readable format comes with the challenge of finding highly informative features which accurately capture the factors for reaction success and allow the model to learn efficiently. Herein, we compare the efficacy of different calculated chemical descriptors for a high throughput generated dataset to determine the impact on a supervised ML model when predicting reaction yield. Then, the effect of featurization and size of the initial dataset within a closed-loop reaction optimization was examined. Finally, the balance between descriptor complexity and dataset size was considered. Ultimately, tailored descriptors did not outperform simple generic representations, however, a larger initial dataset accelerated reaction optimization.

Nature-Inspired Algorithm Applied to a Renewable Energy-Integrating Hydro-Thermal Power Plant

Due to the rising requirement on energy sources and the global doubts for using fossil fuel because of its consequences on the climate changes and the global warming caused by hazardous gases, the scientific research has shifted to the renewable energy. To minimize the usage of thermal power generation plants and to meet the rising load demand, a thermal-integrated wind-hydro-system is taking an important role in renewable power systems. A proficient nature-inspired optimization is proposed for solving economic and emission dispatch for the hydro-thermal-wind (HTW) scheduling problem. Further, the opposition-based learning have been incorporated with the chemical reaction optimization for improving the performance of the algorithm. To investigate the performance of oppositional chemical reaction optimization algorithm, the algorithm is tested on two different cases. Along with this, some statistical tests have also been performed. The results obtained by the OCRO algorithm are compared with other recently proposed methods to establish its robustness.

Adsorption Of Methylene Blue By Imperata Cylindrica: Reaction Optimization By Response Surface Methodology (RSM)

Imperata Cylindrica (IC) is a solid waste that is readily available throughout the year known as one of the most important weed in the world and frequently causes major disposal issues. As a result, using IC as a low-cost adsorbent is beneficial from both, economic and environmental standpoint to remove colors from wastewater of textile industry. This work studies the reaction optimization of methylene blue (MB) removal using IC by response surface methodology (RSM). The RSM experiments were designed with 4 independent variables (initial adsorbent dosage, initial pH, initial dye concentration, and initial temperature) and 1 response variable (percent removal of MB). According to the pareto figure, the initial pH demonstrated the greatest impact on the percent removal of MB. The RSM data predicted the optimum condition of MB removal up to 86.61% using IC, by utilizing adsorbent dosage of 1.458 g/L, at 42 oC, initial pH of 6.8 and MB concentration of 235 ppm. The chacterization analysis revealed the physicochemical properties of IC in the adsoprtion process.

Model for Refactoring a Software Using Feature Oriented Dependency (FOD)

Refactoring is the process of improving the code of the software without affecting the external behavior of the code only by reconstruct the internal structure . It makes code cleaner, clearer, simpler or in other words, clean up the code. It also improves the quality of code then it became more reliable and easy to maintain through lifecycle of software. Refactoring has become renowned concept in software development process. The IDE (Integrated Development Environment) highly prefer this technique. Researches on refactoring technique have improved now a day. Beyond that, this particular technique is used to improve different functions of application software. It mainly speed up the function and helps to get the output much faster. In this proposed work Feature Oriented Dependency (FOD) tool is created used for refactoring process established on a chemical reaction optimization meta heuristic approach to discover the appropriate refactoring resolutions.