Imbalanced data classification based on diverse sample generation and classifier fusion

Prediction of Cholecystokinin-Secretory Peptides Using Bidirectional Long Short-term Memory Model Based on Transfer Learning and Hierarchical Attention Network Mechanism

Cholecystokinin (CCK) can make the human body feel full and has neurotrophic and anti-inflammatory effects. It is beneficial in treating obesity, Parkinson's disease, pancreatic cancer, and cholangiocarcinoma. Traditional biological experiments are costly and time-consuming when it comes to finding and identifying novel CCK-secretory peptides, and there is an urgent need to develop a new computational method to predict new CCK-secretory peptides. This study combines the transfer learning method with the SMILES enumeration data augmentation strategy to solve the data scarcity problem. It establishes a fusion model of the hierarchical attention network (HAN) and bidirectional long short-term memory (BiLSTM), which fully extracts peptide chain features to predict CCK-secretory peptides efficiently. The average accuracy of the proposed method in this study is 95.99%, with an AUC of 98.07%. The experimental results show that the proposed method is significantly superior to other comparative methods in accuracy and robustness. Therefore, this method is expected to be applied to the preliminary screening of CCK-secretory peptides.

Characterization of Synthetic Health Data Using Rule-Based Artificial Intelligence Models

The aim of this study is to apply and characterize eXplainable AI (XAI) to assess the quality of synthetic health data generated using a data augmentation algorithm. In this exploratory study, several synthetic datasets are generated using various configurations of a conditional Generative Adversarial Network (GAN) from a set of 156 observations related to adult hearing screening. A rule-based native XAI algorithm, the Logic Learning Machine, is used in combination with conventional utility metrics. The classification performance in different conditions is assessed: models trained and tested on synthetic data, models trained on synthetic data and tested on real data, and models trained on real data and tested on synthetic data. The rules extracted from real and synthetic data are then compared using a rule similarity metric. The results indicate that XAI may be used to assess the quality of synthetic data by (i) the analysis of classification performance and (ii) the analysis of the rules extracted on real and synthetic data (number, covering, structure, cut-off values, and similarity). These results suggest that XAI can be used in an original way to assess synthetic health data and extract knowledge about the mechanisms underlying the generated data.

Data augmentation in natural language processing: a novel text generation approach for long and short text classifiers

In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve classifiers by artificially created training data. In NLP, there is the challenge of establishing universal rules for text transformations which provide new linguistic patterns. In this paper, we present and evaluate a text generation method suitable to increase the performance of classifiers for long and short texts. We achieved promising improvements when evaluating short as well as long text tasks with the enhancement by our text generation method. Especially with regard to small data analytics, additive accuracy gains of up to 15.53% and 3.56% are achieved within a constructed low data regime, compared to the no augmentation baseline and another data augmentation technique. As the current track of these constructed regimes is not universally applicable, we also show major improvements in several real world low data tasks (up to +4.84 F1-score). Since we are evaluating the method from many perspectives (in total 11 datasets), we also observe situations where the method might not be suitable. We discuss implications and patterns for the successful application of our approach on different types of datasets.

An Extended Review Concerning the Relevance of Deep Learning and Privacy Techniques for Data-Driven Soft Sensors

The continuously increasing number of mobile devices actively being used in the world amounted to approximately 6.8 billion by 2022. Consequently, this implies a substantial increase in the amount of personal data collected, transported, processed, and stored. The authors of this paper designed and implemented an integrated personal health data management system, which considers data-driven software and hardware sensors, comprehensive data privacy techniques, and machine-learning-based algorithmic models. It was determined that there are very few relevant and complete surveys concerning this specific problem. Therefore, the current scientific research was considered, and this paper comprehensively analyzes the importance of deep learning techniques that are applied to the overall management of data collected by data-driven soft sensors. This survey considers aspects that are related to demographics, health and body parameters, and human activity and behaviour pattern detection. Additionally, the relatively complex problem of designing and implementing data privacy mechanisms, while ensuring efficient data access, is also discussed, and the relevant metrics are presented. The paper concludes by presenting the most important open research questions and challenges. The paper provides a comprehensive and thorough scientific literature survey, which is useful for any researcher or practitioner in the scope of data-driven soft sensors and privacy techniques, in relation to the relevant machine-learning-based models.