Background: Machine Learning (ML) is becoming increasingly popular in healthcare, particularly for improving the timing and accuracy of diagnosis. ML can provide disease prediction by analyzing vast amounts of healthcare data, thereby, empowering patients and healthcare providers with information to make informed decisions about disease prevention. Due to the rising cost of treatment, one of the most important topics in clinical data analysis is the prediction and prevention of cardiovascular disease. It is difficult to manually calculate the chances of developing heart disease due to a myriad of contributing factors. Objective: The aim of this paper is to develop and compare various intelligent systems built with ML algorithms for predicting whether a person is likely to develop heart disease using the publicly available Cleveland Heart Disease dataset. This paper describes an alternative multilayer perceptron (MLP) training technique that utilizes a particle swarm optimization (PSO) algorithm for heart disease detection. Methods: The proposed MLP-PSO hybrid algorithm and ten different ML algorithms are used in this study to predict heart disease. Various classification metrics are used to evaluate the performance of the algorithms. Results: The proposed MLP-PSO outperforms all other algorithms, obtaining an accuracy of 84.61%. Conclusions: According to our findings, the current MLP-PSO classifier enables practitioners to diagnose heart disease earlier, more accurately, and more effectively.

Although the multi-layer perceptron (MLP) neural networks provide a lot of flexibility and have proven useful and reliable in a wide range of classification and regression problems, they still have limitations. One of the most common is associated with the optimization algorithm used to train them. The most commonly used training method is stochastic gradient descent with backpropagation (or backpropagation for short) because it is mathematically tractable (given that the activation functions are differentiable). However, backpropagation is not guaranteed to find the globally optimal set of weights and biases. As a result, the MLP is often incapable of obtaining a desirable solution to the problem. Clonal selection algorithms (CSA) are optimization procedures that effectively explore a complex and large space to find values near the global optimum. Consequently, CSA can be used to solve the problem of training MLP networks. This paper presents a novel implementation of CSA for training MLP architectures to solve real-world problems such as breast cancer diagnosis, active sonar target classification, wheat classification, and flower classification. The CSA is used to find the optimal weights and biases that will significantly increase the classification accuracy of the MLP. The performance of our proposed approach is compared with other popular training methods: genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), Harris hawks optimization (HHO), moth-flame optimization (MFO), flower pollination algorithm (FPA), and backpropagation (BP). The comparison is benchmarked using five classification datasets: Iris Flower, Sonar, Wheat Seeds, Breast Cancer Wisconsin, and Haberman’s Survival. Comparative study results illustrate the improvements in MLP performance gained by using CSA over other training methods, and hence it can be considered a competitive approach to training MLP networks when solving real-world applications in various disciplines.

This paper aims to automatically design optimal LSTM topologies using the clonal selection algorithm (CSA) to solve text classification tasks such as sentiment analysis and SMS spam classification. Designing optimal topologies involves determining the best configuration of hyperparameters that will give the best performance. The current state-of-the-art LSTM topologies are often designed using trial and error approaches which are incredibly time-consuming and require domain experts. Our proposed method, referred to as CSA-LSTM, is evaluated using the Large Movie Review Dataset (IMDB). Furthermore, to verify the robustness of the hyperparameters discovered by CSA for the IMDB dataset, we have used them for the other datasets, viz. the Twitter US Airline Sentiment and the SMS Spam Collection. Additionally, the discovered hyperparameters for the LSTM are combined with pre-determined convolutional neural network (CNN) layers to achieve the same or better results to fast the training time and fewer trainable parameters. For further verification and evaluation of the generalization ability and effectiveness of the proposed approach, it is compared with four machine learning algorithms widely used for text classification tasks: (1) random forest (RF), (2) logistic regression (LR), (3) support vector machine (SVM), and (4) multinomial naive Bayes (NB). The results of our experiments show that the LSTM topologies automatically designed by our CSA method are less expensive, reusable and outperform the machine learning algorithms and other models in the literature evaluated on the same three datasets. Through our proposed method, LSTM’s best topology can be self-determined without any human intervention, making CSA-based algorithms a promising approach to automatically design optimal LSTM topologies that provide the best performance for a given task.

Clickbait headlines are misleading headiness designed to attract attention and entice users to click on the link. Links can host malware, trojans and phishing attacks. Clickbaiting is one of the more subtle methods used by hackers and scammers. For these reasons, clickbait is a serious issue that must be addressed. This paper presents a method for identifying clickbait headlines using semantic analysis and machine learning techniques. The method involves analyzing thirty unique semantic features and exploring six different machine learning classification algorithms individually and in ensemble forms. Results show that the top models have an accuracy of 98% in classifying clickbait headlines. The proposed models can serve as a template for developing practical applications to detect clickbait headlines automatically.

Background: Intracranial neoplasm, often referred to as a brain tumor, is an abnormal growth or mass of tissues in the brain. The complexity of the brain and the associated diagnostic delays cause significant stress for patients. This study aims to enhance the efficiency of MRI analysis for brain tumors using deep transfer learning. Methods: We developed and evaluated the performance of five pre-trained deep learning models—ResNet50, Xception, EfficientNetV2-S, ResNet152V2, and VGG16—using a publicly available MRI scan dataset to classify images as glioma, meningioma, pituitary, or no tumor. Various classification metrics were used for evaluation. Results: Our findings indicate that these models can improve the accuracy of MRI analysis for brain tumor classification, with the Xception model achieving the highest performance with a test F1 score of 0.9817, followed by EfficientNetV2-S with a test F1 score of 0.9629. Conclusions: Implementing pre-trained deep learning models can enhance MRI accuracy for detecting brain tumors.

Convolutional neural networks (CNN) have transformed the field of computer vision by enabling the automatic extraction of features, obviating the need for manual feature engineering. Despite their success, identifying an optimal architecture for a particular task can be a time-consuming and challenging process due to the vast space of possible network designs. To address this, we propose a novel neural architecture search (NAS) framework that utilizes the clonal selection algorithm (CSA) to automatically design high-quality CNN architectures for image classification problems. Our approach uses an integer vector representation to encode CNN architectures and hyperparameters, combined with a truncated Gaussian mutation scheme that enables efficient exploration of the search space. We evaluated the proposed method on six challenging EMNIST benchmark datasets for handwritten digit recognition, and our results demonstrate that it outperforms nearly all existing approaches. In addition, our approach produces state-of-the-art performance while having fewer trainable parameters than other methods, making it low-cost, simple, and reusable for application to multiple datasets.