The Prediction of Consumer Behavior from Social Media Activities.

Consumer behavior variants are evolving by utilizing advanced packing models. These models can make consumer behavior detection considerably problematic. New techniques that are superior to customary models to be utilized to efficiently observe consumer behaviors. Machine learning models are no longer efficient in identifying complex consumer behavior variants. Deep learning models can be a capable solution for detecting all consumer behavior variants. In this paper, we are proposing a new deep learning model to classify consumer behavior variants using an ensemble architecture. The new model incorporates two pretrained learning algorithms in an optimized fashion. This model has four main phases, namely, data gathering, deep neural modeling, model training, and deep learning model evaluation. The ensemble model is tested on Facemg BIG-D15 and TwitD databases. The experiment results depict that the ensemble model can efficiently classify consumer behavior with high precision that outperforms recent models in the literature. The ensemble model achieved 98.78% accuracy on the Facemg database, which is higher than most machine learning consumer behavior detection models by more than 8%.

An Ensemble of Transfer Learning Models for the Prediction of Skin Cancers with Conditional Generative Adversarial Networks.

Skin cancer is one of the most severe forms of the disease, and it can spread to other parts of the body if not detected early. Therefore, diagnosing and treating skin cancer patients at an early stage is crucial. Since a manual skin cancer diagnosis is both time-consuming and expensive, an incorrect diagnosis is made due to the high similarity between the various skin cancers. Improved categorization of multiclass skin cancers requires the development of automated diagnostic systems. Herein, we propose a fully automatic method for classifying several skin cancers by fine-tuning the deep learning models VGG16, ResNet50, and ResNet101. Prior to model creation, the training dataset should undergo data augmentation using traditional image transformation techniques and Generative Adversarial Networks (GANs) to prevent class imbalance issues that may lead to model overfitting. In this study, we investigate the feasibility of creating dermoscopic images that have a realistic appearance using Conditional Generative Adversarial Network (CGAN) techniques. Thereafter, the traditional augmentation methods are used to augment our existing training set to improve the performance of pre-trained deep models on the skin cancer classification task. This improved performance is then compared to the models developed using the unbalanced dataset. In addition, we formed an ensemble of finely tuned transfer learning models, which we trained on balanced and unbalanced datasets. These models were used to make predictions about the data. With appropriate data augmentation, the proposed models attained an accuracy of 92% for VGG16, 92% for ResNet50, and 92.25% for ResNet101, respectively. The ensemble of these models increased the accuracy to 93.5%. A comprehensive discussion on the performance of the models concluded that using this method possibly leads to enhanced performance in skin cancer categorization compared to the efforts made in the past.