Search for: All records

Medical images exhibit latent anatomical groupings, such as organs, tissues, and pathological regions, that standard Vision Transformers (ViTs) fail to exploit.While recent work like SBM-Transformer attempts to incorporate such structures through stochastic binary masking, they suffer from non-differentiability, training instability, and the inability to model complex community structure. We present DCMM-Transformer, a novel ViT architecture for medical image analysis that incorporates a Degree-Corrected Mixed-Membership (DCMM) model as an additive bias in self-attention. Unlike prior approaches that rely on multiplicative masking and binary sampling, our method introduces community structure and degree heterogeneity in a fully differentiable and interpretable manner. Comprehensive experiments across diverse medical imaging datasets, including brain, chest, breast, and ocular modalities, demonstrate the superior performance and generalizability of the proposed approach. Furthermore, the learned group structure and structured attention modulation substantially enhance interpretability by yielding attention maps that are anatomically meaningful and semantically coherent. 

As machine learning and artificial intelligence are being integrated into cyber-physical systems, it is becoming important for engineers to know and understand these topics. In particular, sensor data is on the rise in these systems and therefore engineers need to understand which models are appropriate to time-series sensor data and how signal processing can be used with them. The Center for Cyber-Physical Systems (CCPS) at the University of Georgia (UGA) is addressing these issues. Student researchers in the CCPS require skills in these areas. This paper demonstrates a machine learning framework for time-series sensor data that can be used to quickly build, train, and test multiple models on CCPS testbed data. The framework is also a tool that can be used as a tutorial to help student researchers understand the concepts required to be successful in the CCPS. 

This study presents a comprehensive analysis of three types of multimodal data‐response accuracy, response times, and eye‐tracking data‐derived from a computer‐based spatial rotation test. To tackle the complexity of high‐dimensional data analysis challenges, we have developed a methodological framework incorporating various statistical and machine learning methods. The results of our study reveal that hidden state transition probabilities, based on eye‐tracking features, may be contingent on skill mastery estimated from the fluency CDM model. The hidden state trajectory offers additional diagnostic insights into spatial rotation problem‐solving, surpassing the information provided by the fluency CDM alone. Furthermore, the distribution of participants across different hidden states reflects the intricate nature of visualizing objects in each item, adding a nuanced dimension to the characterization of item features. This complements the information obtained from item parameters in the fluency CDM model, which relies on response accuracy and response time. Our findings have the potential to pave the way for the development of new psychometric and statistical models capable of seamlessly integrating various types of multimodal data. This integrated approach promises more meaningful and interpretable results, with implications for advancing the understanding of cognitive processes involved in spatial rotation tests.