A5100366146- AI in cancer detection
- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Electromagnetic wave absorption materials
- Solar Thermal and Photovoltaic Systems
- Natural Language Processing Techniques
- Forensic Anthropology and Bioarchaeology Studies
- Integrated Energy Systems Optimization
- Speech Recognition and Synthesis
- Advanced Neural Network Applications
- Remote Sensing and LiDAR Applications
- Microgrid Control and Optimization
- Brain Tumor Detection and Classification
- Dental Radiography and Imaging
- Metamaterials and Metasurfaces Applications
- Phase Change Materials Research
- Photovoltaic System Optimization Techniques
- Adsorption and Cooling Systems
- Seismic Imaging and Inversion Techniques
- Advanced Antenna and Metasurface Technologies
- 3D Surveying and Cultural Heritage
- Hybrid Renewable Energy Systems
- Smart Grid Energy Management
- Photoacoustic and Ultrasonic Imaging
Lanzhou University of Technology
2013-2024
Northwest University
2024
Beijing Solar Energy Research Institute
2024
Capital University of Physical Education and Sports
2024
China Mobile (China)
2020-2024
Xi'an Jiaotong University
2007-2023
Inspur (China)
2019-2023
Fudan University
2023
Western University
2021
Institute of Acoustics
2021
The coronavirus disease 2019 (COVID-19) breaking out in late December is gradually being controlled China, but it still spreading rapidly many other countries and regions worldwide. It urgent to conduct prediction research on the development spread of epidemic. In this article, a hybrid artificial-intelligence (AI) model proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with having same infection rate, an improved susceptible–infected (ISI)...
Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language typically adopt cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, model intrinsic cross-modal conversational abilities, capable perceiving generating multi-modal content. With discrete speech representations, construct SpeechInstruct,...
Microelectromechanical system (MEMS) pressure sensors based on silicon are widely used and offer the benefits of miniaturization high precision. However, they cannot easily withstand temperatures exceeding 150 °C because intrinsic material limits. Herein, we proposed executed a systematic full-process study SiC-based MEMS that operate stably from -50 to 300 °C. First, explore nonlinear piezoresistive effect, temperature coefficient resistance (TCR) values 4H-SiC piezoresistors were obtained...
Weather-dependent photovoltaic (PV) system power variation may become frequent and rapid, which could be regarded as perturbation for the microgrid (MG). This would lead to voltage frequency fluctuations dramatically degrade MG performances. Conventional secondary control strategy restore after a certain time delay, but it cannot satisfy speed demands when rapid perturbations appear. To overcome limitation, this paper proposes novel real-time compensation suppress fluctuations. The proposed...
Thanks to the recent achievements in task-driven image quality enhancement (IQE) models like ESTR, model and visual recognition can mutually enhance each other's quantitation while producing high-quality processed images that are perceivable by our human vision systems. However, existing IQE tend overlook an underlying fact -- different levels of tasks have varying sometimes conflicting requirements features. To address this problem, paper proposes a generalized gradient promotion (GradProm)...
In Sub-Saharan Africa (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) technology raises questions about applicability machine learning methods for clinical tasks. This study aims to provide a robust deep learning-based brain tumor segmentation (BraTS) method tailored SSA population using threefold approach. Firstly, impact domain shift from training data on model efficacy was examined, revealing no significant effect. Secondly, comparative analysis 3D and 2D...
Background: The coronavirus disease 2019 (COVID-19) breaking out in late December is gradually being controlled China, but it still spreading other countries and regions worldwide. It urgent to conduct prediction research on the development spread of epidemic.Methods: A hybrid AI model proposed for COVID-19 prediction. First, by analyzing change infectious capacity virus carriers within a few days after infection, an improved SI (ISI) proposed. Second, considering effects prevention control...
China has set out an ambitious target of emission abatement; that is, a 60–65% reduction in CO2 intensity by 2030 compared with the 2005 baseline level and peak realisation. This paper aimed to forecast whether can fulfil based on historical time series data from 1990 2018. Four different forecasting techniques were used improve accuracy results: autoregressive integrated moving average (ARIMA) model three grey system-based models, including traditional (1,1), discrete (DGM) rolling DGM. The...
Gliomas are the most common type of primary brain tumors. Although gliomas relatively rare, they among deadliest types cancer, with a survival rate less than 2 years after diagnosis. challenging to diagnose, hard treat and inherently resistant conventional therapy. Years extensive research improve diagnosis treatment have decreased mortality rates across Global North, while chances individuals in low- middle-income countries (LMICs) remain unchanged significantly worse Sub-Saharan Africa...