Search

Prediction of trust and distrust in nodes in signed network analysis is an important task with diverse applications. However, the presence of imbalanced and incomplete rankings in signed networks makes prediction of node-level trust values using machine learning (ML) methods a very challenging task. To overcome these challenges, we introduce DATIS, an innovative approach employing generative adversarial networks (GANs) for data augmentation in node-level trust prediction tasks in signed networks. DATIS addresses imbalances in both sign and value of rankings, handling missing rankings by training on nodes' local and global network features without explicit information on edge rankings assigned to nodes. Unlike existing methods, we consider the trust prediction problem as a regression task to imply the strength of trust a node gained in a network. Our experimental evaluation shows that DATIS can significantly improve the accuracy of node-level trust intensity prediction on real-world datasets. [ABSTRACT FROM AUTHOR]

In response to the problem of low prediction accuracy in ultra short-term prediction of photovoltaic power, this study combines Hungarian clustering analysis and particle swarm optimization variational mode decomposition algorithm to construct a photovoltaic power ultra short-term forecasting model, to analyze data in depth and improve prediction accuracy. The experiment outcomes show that the Hungarian algorithm performs well in integrating single clustering results and effectively improves the problem of atypical classification. In addition, the clustering ensemble model shows significant improvement compared to other models on the Calinski-Harabasz index, and effectively reduces the overlap between clusters on the Davies-Bouldin index, improving the overall quality of clustering. Under different weather conditions, the convergence accuracy and speed of the multiverse optimization support vector machine, multiverse optimization support vector machine, and particle swarm optimization variational mode decomposition algorithms each have their own advantages, but the particle swarm optimization variational mode decomposition algorithm performs better. In addition, the Hungarian clustering model has high stability in predicting errors, with average absolute error and average relative error lower than BP and RBF models. The maximum absolute error and maximum relative error are reduced, indicating the effectiveness and predictive advantage of the proposed Hungarian clustering ensemble model in predicting photovoltaic power. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD), a progressive neurodegenerative condition, notably impacts cognitive functions and daily activity. One method of detecting dementia involves a task where participants describe a given picture, and extensive research has been conducted using the participants' speech and transcribed text. However, very few studies have explored the modality of the image itself. In this work, we propose a method that predicts dementia automatically by representing the relationship between images and texts as a graph. First, we transcribe the participants' speech into text using an automatic speech recognition system. Then, we employ a vision language model to represent the relationship between the parts of the image and the corresponding descriptive sentences as a bipartite graph. Finally, we use a graph convolutional network (GCN), considering each subject as an individual graph, to classify AD patients through a graph-level classification task. In experiments conducted on the ADReSSo Challenge datasets, our model surpassed the existing state-of-the-art performance by achieving an accuracy of 88.73%. Additionally, ablation studies that removed the relationship between images and texts demonstrated the critical role of graphs in improving performance. Furthermore, by utilizing the sentence representations learned through the GCN, we identified the sentences and keywords critical for AD classification. [ABSTRACT FROM AUTHOR]

Healthcare insurance fraud imposes a significant financial burden on healthcare systems worldwide, with annual losses reaching billions of dollars. This study aims to improve fraud detection accuracy using machine learning techniques. Our approach consists of three key stages: data preprocessing, model training and integration, and result analysis with feature interpretation. Initially, we examined the dataset's characteristics and employed embedded and permutation methods to test the performance and runtime of single models under different feature sets, selecting the minimal number of features that could still achieve high performance. We then applied ensemble techniques, including Voting, Weighted, and Stacking methods, to combine different models and compare their performances. Feature interpretation was achieved through partial dependence plots (PDP), SHAP, and LIME, allowing us to understand each feature's impact on the predictions. Finally, we benchmarked our approach against existing studies to evaluate its advantages and limitations. The findings demonstrate improved fraud detection accuracy and offer insights into the interpretability of machine learning models in this context. [ABSTRACT FROM AUTHOR]