A5066563263- Remote-Sensing Image Classification
- Domain Adaptation and Few-Shot Learning
- Neurological disorders and treatments
- Speech and Audio Processing
- Blind Source Separation Techniques
- Sparse and Compressive Sensing Techniques
- Fish Ecology and Management Studies
- Remote Sensing and Land Use
- Aquaculture Nutrition and Growth
- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Genetic Mapping and Diversity in Plants and Animals
- Physiological and biochemical adaptations
- Genetic and phenotypic traits in livestock
- Photoacoustic and Ultrasonic Imaging
- melanin and skin pigmentation
- Spectroscopy Techniques in Biomedical and Chemical Research
Beijing Institute of Technology
2024
China Agricultural University
2024
University of Denver
2014-2015
Training a deep-learning classifier notoriously requires hundreds of labeled samples at least. Many practical hyperspectral image (HSI) scenarios suffer from substantial cost associated with obtaining number samples. Few-shot learning (FSL), which can realize accurate classification prior knowledge and limited supervisory experience, has demonstrated superior performance in the HSI classification. However, previous few-shot algorithms assume that training testing data are distributed same...
To infer unknown remote sensing scenarios, for scene classification (RSSC) most existing deep neural networks (DNNs) are trained on closed datasets. When the acquisition speed and quantity of images increases rapidly, these models cannot be used to classify new scenes. Currently, incremental learning as an effective solution solving <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">catastrophic forgetting</i> issue, but ignoring...
Plumage color is a characteristic trait of ducks that originates as result natural and artificial selection. As conspicuous phenotypic feature, it breed characteristic. Previous studies have identified some genes associated with the formation black white plumage in ducks. However, on genetic basis underlying red phenotype are limited. Here, genome-wide association analysis (GWAS) selection signal detection (Fst, θπ ratio, cross-population composite likelihood ratio [XP-CLR]) were conducted...
Cross-domain methods have been proposed to learn the domain invariant knowledge that can be transferred from source target domain. Existing cross-domain attempt minimize distribution discrepancy of domains. However, these fail explore subspace due samples different classes between two domains may overlap in new subspace. They consider features original space data unnecessary or irrelevant final classification, and neglect preserve local manifold structure To solve problems, a novel feature...
We propose adaptive learning methods for identifying different behavioral tasks of patients with Parkinson's disease (PD). The use local field potential (LFP) signals that were collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are first extracted and then clustered in the feature space using two methods. method requires training uses a hybrid model combines support vector machines hidden Markov models. second does...
We present a new automated onset detection approach for behavioral tasks of patients with Parkinson's disease (PD) using Local Field Potential (LFP) signals collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are extracted and clustered in the feature space. A supervised Discrete Hidden Markov Models (DHMM) is employed merged Support Vector Machines (SVM) two-layer classifier to boost up rate. According our...