The purpose of this study is to use quantitative structure-property relationship (QSPR)-based machine learning (ML) to examine the corrosion inhibition capabilities of benzimidazole compounds. The primary difficulty in ML development is creating a model with a high degree of precision so that the predictions are correct and pertinent to the material's actual attributes. We assess the comparison between the extra trees regressor (EXT) as an ensemble model and the decision tree regressor (DT) as a basic model. It was discovered that the EXT model had better predictive performance in predicting the corrosion inhibition performance of benzimidazole compounds based on the coefficient of determination (R2) and root mean square error (RMSE) metrics compared DT model. This method provides a fresh viewpoint on the capacity of ML models to forecast potent corrosion inhibitors.

This study investigates machine learning-based quantitative structure-property relationship (QSPR) models for predicting the thermal stability of zinc metal-organic frameworks (Zn-MOF). Utilizing a dataset comprising 151 Zn-MOF compounds with relevant molecular descriptors, ridge (R) and kernel ridge (KR) regression models were developed and evaluated. The results demonstrate that the R model outperforms the KR model in terms of prediction accuracy, with the R model exhibiting exceptional performance (R² = 0.999, RMSE = 0.0022). While achieving high accuracy, opportunities for further improvement exist through hyperparameter optimization and exploration of polynomial functions. This research underscores the potential of ML-based QSPR models in predicting the thermal stability of Zn-MOF compounds and highlights avenues for future investigation to enhance model accuracy and applicability in materials science.

The application of Computational Thinking (CT) in the “Kurikulum Merdeka” is one way to strengthen fundamental competencies and holistic understanding in education. CT skills can be taught through Unplugged Programming Activities (UPA), which is an approach to teaching CT skills without using computer tools. This approach is appropriate for schools that do not have adequate technological infrastructure and for the “little ones”, namely students under 9 years of age. This service aims to provide UPA method training for teachers at Gaussian Kamil School (GKS) so that it can be applied to the Merdeka Curriculum at GKS. The UPA activity materials used were the games "Bee-bot" and "My Robotic Friends Activity". It is hoped that this material can provide knowledge and skills regarding CT to training participants at GKS. The results of the pre-test and post-test evaluation showed an increase in scores before and after the training process for the participants. So it can be said that the results of this service show that the UPA method is suitable for use to teach CT skills in schools that do not have adequate technological infrastructure.

This research proposes a combination of Quantum Key Distribution (QKD) based on the BB84 protocol with Improved Logistic Map (ILM) to improve data transmission security. This method integrates quantum key formation from BB84 with ILM encryption. This combination creates an additional layer of security, where by default, the operation on BB84 is only XOR-substitution, with the addition of ILM creating a permutation operation on quantum keys. Experiments are measured with several quantum measurements such as Quantum Bit Error Rate (QBER), Polarization Error Rate (PER), Quantum Fidelity (QF), Eavesdropping Detection (ED), and Entanglement-based detection (EDB), as well as classical cryptographic analysis such as Bit Error Ratio (BER), Entropy, Histogram Analysis, and Normalized Pixel Change Rate (NPCR) and Unified Average Changing Intensity (UACI). As a result, the proposed method obtained satisfactory results, especially perfect QF and BER, and EBD, which reached 0.999.

Penelitian ini merupakan studi eksperimen untuk melakukan penyelidikan inhibitor korosi oleh senyawa Benzimidazole dengan melakukan pendekatan machine learning (ML). Karena korosi menyebabkan banyak kerugian yang timbul karena kehilangan material konstruksi, keselamatan kerja dan pencemaran lingkungan akibat produk korosi dalam bentuk senyawa yang mencemarkan lingkungan. Melakukan pendekatan ML adalah untuk mendapatkan model akurasi yang terbaik sehingga dapat digunakan untuk memprediksi dengan relevan dan akurat terhadap suatu material. Dalam penelitian ini, kami mengevaluasi algoritma ML dengan metode linear dan nonlinear dengan menggunakan metode k-fold cross-validation untuk membantu dalam mengukur performa model ML. Mengacu pada metrik coefficient of determination (R2) dan root mean square error (RMSE), kami menyimpulkan bahwa model AdaBoost regressor (ADA) merupakan model dengan performa prediksi terbaik dari eksperimen yang kami lakukan dari literatur untuk dataset senyawa benzimidazole. Keberhasilan model penelitian ini menawarkan perspektif baru tentang kemampuan model ML untuk memprediksi penghambat korosi yang efektif.  

This study explores Quantum Convolutional Neural Network (QCNN) starting from foundational quantum operations, such as the Rx gate for encoding MNIST image data into quantum states. We implemented quantum convolutional and pooling layers using one_unitary and two_unitary circuits, enabling effective feature extraction and dimensionality reduction while preserving critical information. Expressibility analysis revealed varying capabilities across different one_unitary circuits, with Rx, Ry, and Rz combinations demonstrating promising results akin to Haar random states. The proposed QCNN model exhibited robust performance metrics (accuracy: 95.98%, precision: 94.44%, recall: 96.59%, F1-score: 0.9551, AUC: 0.9604) in classification tasks, supported by efficient convergence during optimization. Future directions include expanding QCNN applications to handle more complex datasets and optimizing architectures to enhance quantum machine learning capabilities, particularly in image processing. This study underscores the potential of QCNNs in advancing quantum computing applications in neural network architectures.
 
Keywords: MNIST, classification, CNN, expressibility

This study explores the use of Broad Learning Systems (BLS) to predict the corrosion inhibition efficiency (CIE) of heterocyclic compounds, addressing limitations of deep neural networks (DNNs) such as vanishing gradients and computational inefficiency. BLS prioritizes network width over depth, enabling faster learning and improved generalization. Trained on quantum chemical properties (QCPs) of 192 heterocyclic compounds, BLS outperformed multilayer perceptron neural networks (MLPNN) and random forest (RF) models, achieving lower mean absolute error (MAE: 1.41), root mean square error (RMSE: 1.79), and higher R² (0.993). Predicted CIE values for quinoxaline derivatives (95.39% and 94.05%) aligned closely with experimental data. This study demonstrates the potential of BLS as an efficient, accurate, and scalable approach for predicting corrosion inhibition capabilities, contributing to advancements in corrosion science and environmentally friendly solutions.
 
Keywords - machine learning, broad learning system, neural network, corrosion.