A5100665425- Functional Brain Connectivity Studies
- Advanced Neuroimaging Techniques and Applications
- Neural dynamics and brain function
- Advanced MRI Techniques and Applications
- EEG and Brain-Computer Interfaces
- Privacy-Preserving Technologies in Data
- Topic Modeling
- Visual Attention and Saliency Detection
- Medical Image Segmentation Techniques
- Neonatal and fetal brain pathology
- Domain Adaptation and Few-Shot Learning
- Fetal and Pediatric Neurological Disorders
- Music and Audio Processing
- Advanced Memory and Neural Computing
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neural Network Applications
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Internet Traffic Analysis and Secure E-voting
- Cellular Automata and Applications
- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- COVID-19 diagnosis using AI
- Mental Health Research Topics
- Industrial Technology and Control Systems
Northwestern Polytechnical University
2016-2025
Harbin Institute of Technology
2024
China Southern Power Grid (China)
2024
University of Georgia
2011-2023
Northwest University
2019-2023
University of Electronic Science and Technology of China
2023
University of Southern California
2022-2023
Southern California University for Professional Studies
2023
The University of Texas at Arlington
2023
Massachusetts General Hospital
2023
Billions of IoT devices will be deployed in the near future, taking advantage faster Internet speed and possibility orders magnitude more endpoints brought by 5G/6G. With growth devices, vast quantities data that may contain users' private information generated. The high communication storage costs, mixed with privacy concerns, increasingly challenge traditional eco-system centralized over-the-cloud learning processing for platforms. Federated (FL) has emerged as most promising alternative...
Visual prompt engineering is a fundamental methodology in the field of visual and image artificial general intelligence. As development large vision models progresses, importance becomes increasingly evident. Designing suitable prompts for specific tasks has emerged as meaningful research direction. This review aims to summarize methods employed computer domain engineering, exploring latest advancements engineering. We present influential range on these models. It our hope that this provides...
Artificial General Intelligence (AGI) has been a long-standing goal of humanity, with the aim creating machines capable performing any intellectual task that humans can do. To achieve this, AGI researchers draw inspiration from human brain and seek to replicate its principles in intelligent machines. Brain-inspired artificial intelligence is field emerged this endeavor, combining insights neuroscience, psychology, computer science develop more efficient power- ful AI systems. In article, we...
The introduction of ChatGPT has led to a significant increase in the utilization Large Language Models (LLMs) for addressing downstream tasks. There's an increasing focus on cost-efficient training and deployment within this context. Low-cost LLMs represent future development trend. This paper reviews evolution large language model techniques inference technologies aligned with emerging discussion includes various aspects, including data preprocessing, architecture, pre-training tasks,...
The "Impression" section of a radiology report is critical basis for communication between radiologists and other physicians. Typically written by radiologists, this part derived from the "Findings" section, which can be laborious error-prone. Although deep-learning based models, such as BERT, have achieved promising results in Automatic Impression Generation (AIG), models often require substantial amounts medical data poor generalization performance. Recently, Large Language Models (LLMs)...
High-performance methods for automated detection of epileptic stereo-electroencephalography (SEEG) have important clinical research implications, improving the diagnostic efficiency and reducing physician burden. However, few studies been able to consider process seizure propagation, thus failing fully capture deep representations variations SEEG in temporal, spatial, spectral domains. In this paper, we construct a novel long-term dataset (XJSZ dataset), propose Signal Embedding...
Is there a common structural and functional cortical architecture that can be quantitatively encoded precisely reproduced across individuals populations? This question is still largely unanswered due to the vast complexity, variability, nonlinearity of cerebral cortex. Here, we hypothesize effectively represented by group-wise consistent fiber connections take novel data-driven approach explore architecture. We report dense map 358 landmarks, named Dense Individualized Common...
For decades, it has been largely unknown to what extent multiple functional networks spatially overlap/interact with each other and jointly realize the total cortical function. Here, by developing novel sparse representation of whole-brain fMRI signals using recently publicly released large-scale Human Connectome Project high-quality data, we show that a number reproducible robust networks, including both task-evoked resting state are simultaneously distributed in distant neuroanatomic areas...
Convoluted cortical folding and neuronal wiring are 2 prominent attributes of the mammalian brain. However, macroscale intrinsic relationship between these general cross-species attributes, as well underlying principles that sculpt architecture cerebral cortex, remains unclear. Here, we show axonal fibers connected to gyri significantly denser than those sulci. In human, chimpanzee, macaque brains, a dominant fraction were found be gyri. This finding has been replicated in range brains via...
The birth of Bitcoin ushered in the era cryptocurrency, which has now become a financial market attracted extensive attention worldwide. phenomenon startups launching Initial Coin Offerings (ICOs) to raise capital led thousands tokens being distributed on blockchains. Many studies have analyzed this from an economic perspective. However, little is know about characteristics participants ecosystem. To fill gap and considering over 80% ICOs launched based ERC20 token Ethereum, paper, we...
Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize non-Euclidean structure of brain based on magnetic resonance (MRI) data. However, previous studies are largely node-centralized and ignore edge features for classification tasks, resulting moderate performance accuracy. Moreover, generalizability GNN model is still far from satisfactory disorder [e.g., autism spectrum (ASD)] identification...
The 'Impression' section of a radiology report is critical basis for communication between radiologists and other physicians, it typically written by based on the 'Findings' section. However, writing numerous impressions can be laborious error-prone radiologists. Although recent studies have achieved promising results in automatic impression generation using large-scale medical text data pre-training fine-tuning pre-trained language models, such models often require substantial amounts poor...
In Federated Learning (FL), a common approach for aggregating local solutions across clients is periodic full model averaging. It is, however, known that different layers of neural networks can have degree discrepancy the clients. The conventional aggregation scheme does not consider such difference and synchronizes whole parameters at once, resulting in inefficient network bandwidth consumption. Aggregating are similar make meaningful training progress while increasing communication cost....
The introduction of ChatGPT has led to a significant increase in the utilization Large Language Models (LLMs) for addressing downstream tasks. There's an increasing focus on cost-efficient training and deployment within this context. Low-cost LLMs represent future development trend. This paper reviews evolution large language model techniques inference technologies aligned with emerging discussion includes various aspects, including data preprocessing, architecture, pre-training tasks,...
Both cortical folding and structural connection patterns are more elaborated during the evolution of primate neocortex. For instance, gyral shapes in humans complex variable than those chimpanzees macaques. However, intrinsic relationship between their coevolution across primates remain unclear. Here, our qualitative quantitative analyses vivo diffusion tensor imaging (DTI) magnetic resonance (MRI) data consistently demonstrate that fiber closely follow direction "tangent" to sphere, this...
Abstract The recently publicly released Human Connectome Project (HCP) grayordinate‐based fMRI data not only has high spatial and temporal resolution, but also offers group‐corresponding signals across a large population for the first time in brain imaging field, thus significantly facilitating mapping functional architecture with much higher resolution group‐wise fashion. In this article, we adopt HCP grayordinate task‐based (tfMRI) to systematically identify characterize heterogeneous...
Abstract Folding of the cerebral cortex is a prominent characteristic mammalian brains. Alterations or deficits in cortical folding are strongly correlated with abnormal brain function, cognition, and behavior. Therefore, precise mapping between anatomy function critical to our understanding mechanisms structural architecture both health diseases. Gyri sulci, standard nomenclature for anatomy, serve as building blocks make up complex patterns, providing window decipher its relation...
Learning harmful shortcuts such as spurious correlations and biases prevents deep neural networks from learning meaningful useful representations, thus jeopardizing the generalizability interpretability of learned representation. The situation becomes even more serious in medical image analysis, where clinical data are limited scarce while reliability, transparency model highly required. To rectify imaging applications, this paper, we propose a novel eye-gaze-guided vision transformer...
Federated learning (FL) has gained substantial attention in recent years due to data privacy concerns related the pervasiveness of consumer devices that continuously collect from users. While a number FL benchmarks have been developed facilitate research, none them include audio and audio-related tasks. In this paper, we fill critical gap by introducing new benchmark for tasks which refer as FedAudio. FedAudio includes four representative commonly used datasets three important are well...