A Lightweight Framework for Perception Analysis Based on Multimodal Cognition-Aware Computing.

The VUCA environment challenged neuropsychological research conducted in conventional laboratories. Researchers expected to perform complex multimodal testing tasks in natural, open, and non-laboratory settings. However, for most neuropsychological scientists, the independent construction of a multimodal laboratory in a VUCA environment, such as a construction site, was a significant and comprehensive technological challenge. This study presents a generalized lightweight framework for perception analysis based on multimodal cognition-aware computing, which provided practical updated strategies and technological guidelines for neuromanagement and automation. A real-life test experiment on a construction site was provided to illustrate the feasibility and superiority of the method. The study aimed to fill a technology gap in the application of multimodal physiological and neuropsychological techniques in an open VUCA environment. Meanwhile, it enabled the researchers to improve their systematic technological capabilities and reduce the threshold and trial-and-error costs of experiments to conform to the new trend of VUCA.

Graph-Based Region and Boundary Aggregation for Biomedical Image Segmentation.

Segmentation is a fundamental task in biomedical image analysis. Unlike the existing region-based dense pixel classification methods or boundary-based polygon regression methods, we build a novel graph neural network (GNN) based deep learning framework with multiple graph reasoning modules to explicitly leverage both region and boundary features in an end-to-end manner. The mechanism extracts discriminative region and boundary features, referred to as initialized region and boundary node embeddings, using a proposed Attention Enhancement Module (AEM). The weighted links between cross-domain nodes (region and boundary feature domains) in each graph are defined in a data-dependent way, which retains both global and local cross-node relationships. The iterative message aggregation and node update mechanism can enhance the interaction between each graph reasoning module's global semantic information and local spatial characteristics. Our model, in particular, is capable of concurrently addressing region and boundary feature reasoning and aggregation at several different feature levels due to the proposed multi-level feature node embeddings in different parallel graph reasoning modules. Experiments on two types of challenging datasets demonstrate that our method outperforms state-of-the-art approaches for segmentation of polyps in colonoscopy images and of the optic disc and optic cup in colour fundus images. The trained models will be made available at: https://github.com/smallmax00/Graph_Region_Boudnary.