Conversational machine reading comprehension (CMRC) requires models to effectively combine dialogue historyandanswer current questions. Previous works have shortcomings in handling historical information as they did not consider the role of historical questions in the learning process. Moreover, in the reasoning process, parallel input of multiplerounds of dialogue does not conform to human reasoning habits. Therefore, to address these limitations, this paperproposes the HistoryintoFlow model. In our model, we incorporate historical questions into the encoding layer, whichenables the model to extract complete historical information. In the reasoning layer of the model, we designa flowmodule that integrates intermediate representations generated from past conversations and performs reasoninginaccordance with the order of conversations. The final results show that the HistoryintoFlow model achieves an accuracyrate of 67.1% on the QuAC. Compared with some publicly available models, our model has improved in F1, HEQ-Q, and HEQ-D.
KEYWORDS: Brain, Feature extraction, Functional magnetic resonance imaging, Control systems, Nonlinear optics, Alzheimer's disease, Simulation of CCA and DLA aggregates, Neuroimaging, Machine learning, Genetic algorithms
Machine learning and pattern recognition have been widely used in resting-state functional magnetic resonance imaging (rs-fMRI) data to investigate Alzheimer’s disease (AD). However, many previous methods have not focused on the pre-Alzheimer's disease, mild cognitive impairment (MCI), have mostly classified features from functional separation or functional integration alone, which may have overlooked the correlation between the two. We propose a novel method for MCI diagnosis using the fusion local features of brain area signals as features for functional separation and brain network properties as features for functional integration. The rs-fMRI data of 43 MCI patients and 46 normal cognitive (NC) controls were analyzed using graph theory and nonlinear time series analysis to extract the brain network properties and local cortex signal features. The classifier-SVM achieved an accuracy of 92.8% based on the above features, which is generally higher than those of conventional methods based on functional integration using brain network properties alone or functional separation using local features alone. Our method demonstrates the measure of multi-feature integration of functional integration and functional separation as a powerful tool to classify MCI patients.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.