This study attempts to optimize the prediction accuracy of the compressive strength of high-performance concrete (HPC) by comparing data-mining methods. Modeling the dynamics of HPC, which is a highly complex composite material, is extremely challenging. Concrete compressive strength is also a highly nonlinear function of ingredients. Several studies have independently shown that concrete strength is determined not only by the water-to-cement ratio but also by additive materials. The compressive strength of HPC is a function of all concrete content, including cement, fly ash, blast-furnace slag, water, superplasticizer, age, and coarse and fine aggregate. The quantitative analyses in this study were performed by using five different data-mining methods: two machine learning models (artificial neural networks and support vector machines), one statistical model (multiple regression), and two metaclassifier models (multiple additive regression trees and bagging regression trees). The methods were developed and tested against a data set derived from 17 concrete strength test laboratories. The cross-validation of unbiased estimates of the prediction models for performance comparison purposes indicated that multiple additive regression tree (MART) was superior in prediction accuracy, training time, and aversion to overfitting. Analytical results suggested that MART-based modeling is effective for predicting the compressive strength of varying HPC age.

The banking industry has been seeking novel ways to leverage database marketing efficiency. However, the nature of bank marketing data hindered the researchers in the process of finding a reliable analytical scheme. Various studies have attempted to improve the performance of Artificial Neural Networks in predicting clients’ intentions but did not resolve the issue of imbalanced data. This research aims at improving the performance of predicting the willingness of bank clients to apply for a term deposit in highly imbalanced datasets. It proposes enhanced Artificial Neural Network models (i.e., cost-sensitive) to mitigate the dramatic effects of highly imbalanced data, without distorting the original data samples. The generated models are evaluated, validated, and consequently compared to different machine-learning models. A real-world telemarketing dataset from a Portuguese bank is used in all the experiments. The best prediction model achieved 79% of geometric mean, and misclassification errors were minimized to 0.192, 0.229 of Type I & Type II Errors, respectively. In summary, an interesting Meta-Cost method improved the performance of the prediction model without imposing significant processing overhead or altering original data samples.

Recently, spam on online social networks has attracted attention in the research and business world. Twitter has become the preferred medium to spread spam content. Many research efforts attempted to encounter social networks spam. Twitter brought extra challenges represented by the feature space size, and imbalanced data distributions. Usually, the related research works focus on part of these main challenges or produce black-box models. In this paper, we propose a modified genetic algorithm for simultaneous dimensionality reduction and hyper parameter optimization over imbalanced datasets. The algorithm initialized an eXtreme Gradient Boosting classifier and reduced the features space of tweets dataset; to generate a spam prediction model. The model is validated using a 50 times repeated 10-fold stratified cross-validation, and analyzed using nonparametric statistical tests. The resulted prediction model attains on average 82.32% and 92.67% in terms of geometric mean and accuracy respectively, utilizing less than 10% of the total feature space. The empirical results show that the modified genetic algorithm outperforms Chi² and PCA feature selection methods. In addition, eXtreme Gradient Boosting outperforms many machine learning algorithms, including BERT-based deep learning model, in spam prediction. Furthermore, the proposed approach is applied to SMS spam modeling and compared to related works.

In recent years, the chaotic logistic map key (CLMK) has been widely used for image encryption due to its ability to generate random and unpredictable sequences of numbers. The CLMK algorithm uses the chaotic logistic map to generate a key stream, which is then used to encrypt the plaintext image. This study proposes an image encryption scheme based on CLMK, Collatz Conjecture, and indexing techniques; it uses a private key of a 15-digit size that is parsed in a novel way to generate a considerable keyspace reaches up to 297. The Collatz Conjecture generator is used to create variable length sequences that are used to generate the Chaotic parameters $r_{1}$ , $r_{2}$ , $x_{1}$ , and $x_{2}$ ; these parameters are used to create a 2D CLMK for encrypting each color channel and a 1D vector that is used for permeation, both confusion and diffusion are performed in four consecutive rounds to ensure the robustness of the proposed approach. The random sequences generated by the Collatz Conjecture were tested for randomness using the NIST benchmark randomness test suit, and they passed most tests. The proposed method is robust against all the well-known attacks, including differential attacks, white Gaussian noise attacks, Salt-and-pepper noise attacks, clipping attacks, occlusion attacks, and known plaintext attacks. Various experiments were conducted to evaluate the performance of the proposed method in terms of encryption time, throughput, and several image quality metrics. The results indicate that the proposed method is efficient regarding encryption time, and throughput enhancement can reach up to 3.34 times the state-of-the-art chaotic encryption methods.

This research paper presents a novel digital color image encryption approach that ensures high-level security while remaining simple and efficient. The proposed method utilizes a composite key r and x of 128-bits to create a small in-dimension private key (a chaotic map), which is then resized to match the color matrix dimension. The proposed method is uncomplicated and can be applied to any image without any modification. Image quality, sensitivity analysis, security analysis, correlation analysis, quality analysis, speed analysis, and attack robustness analysis are conducted to prove the efficiency and security aspects of the proposed method. The speed analysis shows that the proposed method improves the performance of image cryptography by minimizing encryption–decryption time and maximizing the throughput of the process of color cryptography. The results demonstrate that the proposed method provides better throughput than existing methods. Overall, this research paper provides a new approach to digital color image encryption that is highly secure, efficient, and applicable to various images.