A skin lesion is a portion of skin that observes abnormal growth compared to other areas of the skin. The ISIC 2018 lesion dataset has seven classes. A miniature dataset version of it is also available with only two classes: malignant and benign. Malignant tumors are tumors that are cancerous, and benign tumors are non-cancerous. Malignant tumors have the ability to multiply and spread throughout the body at a much faster rate. The early detection of the cancerous skin lesion is crucial for the survival of the patient. Deep learning models and machine learning models play an essential role in the detection of skin lesions. Still, due to image occlusions and imbalanced datasets, the accuracies have been compromised so far. In this paper, we introduce an interpretable method for the non-invasive diagnosis of melanoma skin cancer using deep learning and ensemble stacking of machine learning models. The dataset used to train the classifier models contains balanced images of benign and malignant skin moles. Hand-crafted features are used to train the base models (logistic regression, SVM, random forest, KNN, and gradient boosting machine) of machine learning. The prediction of these base models was used to train level one model stacking using cross-validation on the training set. Deep learning models (MobileNet, Xception, ResNet50, ResNet50V2, and DenseNet121) were used for transfer learning, and were already pre-trained on ImageNet data. The classifier was evaluated for each model. The deep learning models were then ensembled with different combinations of models and assessed. Furthermore, shapely adaptive explanations are used to construct an interpretability approach that generates heatmaps to identify the parts of an image that are most suggestive of the illness. This allows dermatologists to understand the results of our model in a way that makes sense to them. For evaluation, we calculated the accuracy, F1-score, Cohen’s kappa, confusion matrix, and ROC curves and identified the best model for classifying skin lesions.
Money laundering refers to activities that disguise money receive through illegal operations and make them become legitimate. It leaves serious consequence that may lead to economy corruption. Extensive research has been conducted to investigate proper solution for suspicious transactions detection. In the realm of clustering approaches, traditional research only concentrate on k-means as the best technique so far. On the other hand, although belongs to the same class, there is a lack of studies conducted in employing Expectation Maximization (EM) for Anti-Money Laundering (AML). The objective of this study is to exploit the advantages of EM for suspicious transaction detection. Data used in this study was obtained through a local bank in Malaysia. Subsets of crucial attributes were selected using genetic search and best first search algorithm. Results indicate that critical fields required for clustering phase include amount, number of credit & debit as well as its sum. The outcome of this study shows that EM overwhelmed traditional clustering method k-means for AML in terms of detecting correct suspicious and normal transactions. This lays the groundwork of employing EM in this field. However, further research is needed using different dataset of other banks in order to clarify the effectiveness of EM in AML.
Facial expression recognition (FER) is the task of determining a person's current emotion. It plays an important role in healthcare, marketing, and counselling. With the advancement in deep learning algorithms like Convolutional Neural Network (CNN), the system's accuracy is improving. A hybrid CNN and k-Nearest Neighbour (KNN) model can improve FER's accuracy. This paper presents a hybrid CNN-KNN model for FER on the Raspberry Pi 4, where we use CNN for feature extraction. Subsequently, the KNN performs expression recognition. We use the transfer learning technique to build our system with an EfficientNet-Lite model. The hybrid model we propose replaces the Softmax layer in the EfficientNet with the KNN. We train our model using the FER-2013 dataset and compare its performance with different architectures trained on the same dataset. We perform optimization on the Fully Connected layer, loss function, loss optimizer, optimizer learning rate, class weights, and KNN distance function with the k-value. Despite running on the Raspberry Pi hardware with very limited processing power, low memory capacity, and small storage capacity, our proposed model achieves a similar accuracy of 75.26% (with a slight improvement of 0.06%) to the state-of-the-art's Ensemble of 8 CNN model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.