Spam emails pose a substantial cybersecurity danger, necessitating accurate classification to reduce unwanted messages and mitigate risks. This study focuses on enhancing spam email classification accuracy using stacking ensemble machine learning techniques. We trained and tested five classifiers: logistic regression, decision tree, K-nearest neighbors (KNN), Gaussian naive Bayes and AdaBoost. To address overfitting, two distinct datasets of spam emails were aggregated and balanced. Evaluating individual classifiers based on recall, precision and F1 score metrics revealed AdaBoost as the top performer. Considering evolving spam technology and new message types challenging traditional approaches, we propose a stacking method. By combining predictions from multiple base models, the stacking method aims to improve classification accuracy. The results demonstrate superior performance of the stacking method with the highest accuracy (98.8%), recall (98.8%) and F1 score (98.9%) among tested methods. Additional experiments validated our approach by varying dataset sizes and testing different classifier combinations. Our study presents an innovative combination of classifiers that significantly improves accuracy, contributing to the growing body of research on stacking techniques. Moreover, we compare classifier performances using a unique combination of two datasets, highlighting the potential of ensemble techniques, specifically stacking, in enhancing spam email classification accuracy. The implications extend beyond spam classification systems, offering insights applicable to other classification tasks. Continued research on emerging spam techniques is vital to ensure long-term effectiveness.

Natural scene classification, which has potential applications in precision agriculture, environmental monitoring, and disaster management, poses significant challenges due to variations in the spatial resolution, spectral resolution, texture, and size of remotely sensed images of natural scenes on Earth. For such challenging problems, deep-learning-based algorithms have demonstrated amazing performances in recent years. Among these methodologies, transfer learning is a useful technique which employs the learned features already extracted from the pre-trained models from large-scale datasets for the problem at hand, resulting in quicker and more accurate models. In this study, we deployed cross-domain transfer learning for the land-cover classification of remotely sensed images of natural scenes. We conducted extensive experiments to measure the performance of the proposed method and explored the factors that affect the performance of the models. Our findings suggest that fine-tuning the ResNet-50 model outperforms various other models in terms of the classification accuracy. The experimental results showed that the deployed cross-domain transfer-learning system achieved outstanding (99.5% and 99.1%) accurate performances compared to previous benchmarks on the NaSC-TG2 dataset with the final tuning of the whole structure and only the last three layers, respectively.

Object detection in maritime environments is a challenging problem because of the continuously changing background and moving objects resulting in shearing, occlusion, noise, etc. Unluckily, this problem is of critical importance since such failure may result in significant loss of human lives and economic loss. The available object detection methods rely on radar and sonar sensors. Even with the advances in electro-optical sensors, their employment in maritime object detection is rarely considered. The proposed research aims to employ both electro-optical and near-infrared sensors for effective maritime object detection. For this, dedicated deep learning detection models are trained on electro-optical and near-infrared (NIR) sensor datasets. For this, (ResNet-50, ResNet-101, and SSD MobileNet) are utilized in both electro-optical and near-infrared space. Then, dedicated ensemble classifications are constructed on each collection of base learners from electro-optical and near-infrared spaces. After this, decisions about object detection from these spaces are combined using logical-disjunction-based final ensemble classification. This strategy is utilized to reduce false negatives effectively. To evaluate the performance of the proposed methodology, the publicly available standard Singapore Maritime Dataset is used and the results show that the proposed methodology outperforms the contemporary maritime object detection techniques with a significantly improved mean average precision.

In many machine learning applications, there are many scenarios when performance is not satisfactory by single classifiers. In this case, an ensemble classification is constructed using several weak base learners to achieve satisfactory performance. Unluckily, the construction of the ensemble classification is empirical, i.e., to try an ensemble classification and if performance is not satisfactory then discard it. In this paper, a challenging analytical problem of the estimation of ensemble classification using the prediction performance of the base learners is considered. The proposed formulation is aimed at estimating the performance of ensemble classification without physically developing it, and it is derived from the perspective of probability theory by manipulating the decision probabilities of the base learners. For this purpose, the output of a base learner (which is either true positive, true negative, false positive, or false negative) is considered as a random variable. Then, the effects of logical disjunction-based and majority voting-based decision combination strategies are analyzed from the perspective of conditional joint probability. To evaluate the forecasted performance of ensemble classifier by the proposed methodology, publicly available standard datasets have been employed. The results show the effectiveness of the derived formulations to estimate the performance of ensemble classification. In addition to this, the theoretical and experimental results show that the logical disjunction-based decision outperforms majority voting in imbalanced datasets and cost-sensitive scenarios.