A5100786008- Emotion and Mood Recognition
- Forecasting Techniques and Applications
- Speech Recognition and Synthesis
- Stock Market Forecasting Methods
- Speech and Audio Processing
- Time Series Analysis and Forecasting
- Phonocardiography and Auscultation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Model Reduction and Neural Networks
- Advanced Steganography and Watermarking Techniques
- Traffic Prediction and Management Techniques
- Ocular Diseases and Behçet’s Syndrome
- Retinal and Optic Conditions
- Dam Engineering and Safety
- Radiation Detection and Scintillator Technologies
- MRI in cancer diagnosis
- Retinal Imaging and Analysis
- Advanced Algorithms and Applications
- Nuclear Physics and Applications
- Traditional Chinese Medicine Studies
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Remote-Sensing Image Classification
- Remote Sensing in Agriculture
- Multisensory perception and integration
Anhui University of Finance and Economics
2023-2024
Jilin University
2002-2021
Jilin Medical University
2021
Shanghai Public Health Clinical Center
2020
Central University of Finance and Economics
2019
University of Science and Technology of China
2014
Jilin Province Science and Technology Department
2009
Heart sounds are an important basis for evaluating heart disease. In recent years, auxiliary diagnosis technology of cardiovascular disease based on the detection sound signals has become a research hotspot. A lightweight automatic classification method is presented in this study. It only needs to perform simple pre-processing data, and neural network model constructed automatically extract time-frequency features data: where convolution module extracts frequency domain characteristics, loop...
When extracting winter wheat spatial distribution by using convolutional neural network (CNN) from Gaofen-2 (GF-2) remote sensing images, accurate identification of edge pixel is the key to improving result accuracy. In this paper, an approach for based on CNN proposed. A hybrid structure (HSCNN) was first constructed, which consists two independent sub-networks different depths. The deeper sub-network used extract pixels present in interior field, whereas shallower extracts at field. model...
The unmanned automobile has become a major research project in the industry. will meet obstacles unavoidably on road, so it is necessary to design feasible controller for avoiding obstacles. Because of complexity automatic obstacle system itself and uncertainty parameters, original method designing by establishing models limited. Driver experience provides good control example controllers one can make use this obstacles, which simulates driving behaviors humans. At present, fuzzy technology...
Magnetic resonance imaging is affected by intensity inhomogeneity, also known as the bias field, which mainly caused imperfections in radio frequency coils or inhomogeneous coil sensitivities receiving coils. In this paper, we proposed a new method automatically correct field using regularized method. The does not need extra scan devices empirical data. This includes minimizing cost function containing both data-fit term and regularization term, provide robust inhomogeneity estimates. choose...
Speech Emotion recognition (SER) aims to help machines recognize human emotions from utterances. Emotions are usually presented as audio and text in However, existing SER studies mostly use a single modality or feature, ignoring the integration of multiple modalities features. In this paper, we propose multi-modal feature fusion network using cross-modal attention extract emotion-related features text. More specifically, both text, where utilizes wav2vec 2.0 Mel spectrograms. First, combine...
The Coronavirus disease 2019 (COVID-19) has affected several million people. With the outbreak of epidemic, many researchers are devoting themselves to COVID-19 screening system. standard practices for rapid risk CT imaging or RT-PCR (real-time polymerase chain reaction). However, these methods demand professional efforts acquisition images and saliva samples, a certain amount waiting time, most importantly prohibitive examination fee in some countries. Recently, literatures have shown that...
This paper discusses how to apply the fuzzy control system food presser. The basic structure and realization methods of presser based on principle are described. It proves advantages by simulation computers.