A5047085200- Functional Brain Connectivity Studies
- Natural Language Processing Techniques
- Brain Tumor Detection and Classification
- Topic Modeling
- Neural dynamics and brain function
- Speech and dialogue systems
- EEG and Brain-Computer Interfaces
- AI in cancer detection
- Dementia and Cognitive Impairment Research
- Mental Health Research Topics
- Emotion and Mood Recognition
- Advanced Fiber Optic Sensors
- Advanced Sensor and Energy Harvesting Materials
- Machine Learning in Healthcare
- Face and Expression Recognition
- Neonatal and fetal brain pathology
- Alzheimer's disease research and treatments
- Advanced Graph Neural Networks
- Advanced Neural Network Applications
- Color perception and design
- Fungal Biology and Applications
- Digital Imaging for Blood Diseases
- Polydiacetylene-based materials and applications
- Diet and metabolism studies
University of Shanghai for Science and Technology
2024-2025
Shanghai University of Medicine and Health Sciences
2023-2025
Shanghai Hospital Development Center
2024
Shanghai Jiao Tong University
2024
Baoshan College
2023
Chongqing University of Posts and Telecommunications
2023
Alzheimer’s disease (AD) is a leading cause of disability worldwide. Early detection critical for preventing progression and formulating effective treatment plans. This study aims to develop novel deep learning (DL) model, Hybrid-RViT, enhance the AD. The proposed Hybrid-RViT model integrates pre-trained convolutional neural network (ResNet-50) with Vision Transformer (ViT) classify brain MRI images across different stages ResNet-50 adopted transfer learning, facilitates inductive bias...
Multi-party dialogue machine reading comprehension (MRC) brings an unprecedented challenge due to the multiple speakers and complex discourse linkages among speaker-aware utterances. The majority of current methods only consider textual aspects situations, pay little attention crucial cues. This prevents a model from capturing speaker's intention important information for questions in relationship, leading giving wrong answers. In this paper, we construct logic graph module by relational...
Poisoned by the edible fungus accident occurred frequently in recent years since that there were no effective and quick recognition methods for wild fungus. To tackle problem, a classification algorithm based on deep convolutional neural network (CNN) Residual Network (ResNet), is proposed this paper. An optimization method also training. In order to verify effectiveness of model method, database, total 1280 images, used The experimental results show can effectively complete task mushrooms,...
The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex realistic scenarios. However, EQA real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration response, bringing challenges especially for beginners non-expert users. To address this, we introduce a...
The emergence of BERT and Knowledge Graph (KG) has promoted the development Question Answering (QA), however, existing QA systems are still inadequate in terms accuracy relational reasoning interpretability answers. In this paper, we combine KG, following optimizing methods to build a medical system with better performance - KBMQA. final experimental results show that KBMQA performs on both MedQA MedNLI datasets compared previous biomedical baseline models MOP models.
Alzheimer's disease (AD) represents a prevalent, progressive neurodegenerative ailment marked by the gradual deterioration of memory and cognitive faculties. Resting-state functional magnetic resonance imaging (rs-fMRI) offers good specificity in AD reflecting early changes brain network. As result, combining popular deep learning methods with rs-fMRI network features has attracted wide attention. In our experiment, A cohort comprising 325 participants, sourced from Disease Neuroimaging...