In this work, we developed a QSAR model using the K-Nearest Neighbor (KNN) algorithm to predict the corrosion inhibition performance of the inhibitor compound. To overcome the small dataset problems, virtual samples are generated and added to the training set using a Virtual Sample Generation (VSG) method. The generalizability of the proposed KNN + VSG model is verified by using six small datasets from references and comparing their prediction performances. The research shows that for the six datasets, the proposed model is able to make predictions with the best accuracy. Adding virtual samples to the training data helps the algorithm recognize feature-target relationship patterns, and therefore increases the number of chemical quantum parameters correlated with corrosion inhibition efficiency. This proposed method strengthens the prospect of ML for developing material designs, especially in the case of small datasets.

Historically, the exploration of corrosion inhibitor technology has relied extensively on experimental methodologies, which are inherently associated with substantial costs, prolonged durations, and significant resource utilization. However, the emergence of ML approaches has recently garnered attention as a promising avenue for investigating potential materials with corrosion inhibition properties. This study endeavors to enhance the predictive capacity of ML models by leveraging polynomial functions. Specifically, the investigation focuses on assessing the effectiveness of pyridinequinoline compounds in mitigating corrosion. Diverse ML models were systematically evaluated, integrating polynomial functions to augment their predictive capabilities. The integration of polynomial functions notably amplifies the predictive accuracy across all tested models. Notably, the SVR model emerges as the most adept, exhibiting R² of 0.936 and RMSE of 0.093. The outcomes of this inquiry underscore a significant enhancement in predictive accuracy facilitated by the incorporation of polynomial functions within ML models. The proposed SVR model stands out as a robust tool for prognosticating the corrosion inhibition potential of pyridine-quinoline compounds. This pioneering approach contributes invaluable insights into advancing machine learning methodologies geared toward designing and engineering materials with promising corrosion inhibition properties. Keywords: machine learning, polynomial, corrosion inhibition, pyridine-quinoline

The existence of a trade-off between embedding capacity and imperceptibility is a challenge to improve the quality of steganographic images. This research proposes to cross diagonal embedding Pixel Value Differencing (PVD) and Modulus Function (MF) techniques using edge area patterns to improve embedding capacity and imperceptibility simultaneously. At the same time still, maintain a good quality of security. By implementing them into 14 public datasets, the proposed techniques are proven to increase both capacity and imperceptibility. The cross diagonal embedding PVD is responsible for increasing the embedding capacity reaching an average value of 3.18 bits per pixel (bpp), and at the same time, the implementation of edge area block patterns-based embedding is a solution of improving imperceptibility toward an average value of PSNR above 40 dB and that of SSIM above 0.98. Aside from its success in increasing the embedding capacity and the imperceptibility, the proposed techniques remain resistant to RS attacks.