A5101860857- Wireless Signal Modulation Classification
- Blind Source Separation Techniques
- Text and Document Classification Technologies
- Advanced Neural Network Applications
- Face and Expression Recognition
- Face recognition and analysis
- Visual Attention and Saliency Detection
- Generative Adversarial Networks and Image Synthesis
- Reinforcement Learning in Robotics
- Robot Manipulation and Learning
- Advanced Chemical Sensor Technologies
- Machine Learning in Bioinformatics
- Advanced Image and Video Retrieval Techniques
- Gaze Tracking and Assistive Technology
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- Advanced Electrical Measurement Techniques
- Model Reduction and Neural Networks
- Meat and Animal Product Quality
- 3D Shape Modeling and Analysis
- Olfactory and Sensory Function Studies
- Fractal and DNA sequence analysis
- Optical Systems and Laser Technology
- Technology and Data Analysis
- 3D Surveying and Cultural Heritage
Huazhong University of Science and Technology
2023-2024
Northeastern University
2023
Southeast University
2014
Nanjing University
2011
State Administration of Foreign Experts Affairs
2005
In this paper, a classification method based on Support Vector Machine (SVM) is given in the digital modulation signal classification. The second, fourth and sixth order cumulants of received signals are used as vectors firstly, then kernel thought to map feature vector high dimensional space optimum separating hyperplane constructed realize recognition. build an effective robust SVM classifier, radial basis function selected, one against or rest multi-class classifier designed, parameter...
An improved modulation classification algorithm of MPSK signals based on high order cumulants is proposed and analyzed. Under the condition unknown carrier frequency, first constant amplitude delayed complex conjugated multiplication used to preprocess original signal, then four are exploited construct classified character. The unchangeness character proved in detail, robustness analyzed aiming at short wave channels. Theoretical analysis practical signal testing justify effectiveness new algorithm.
In this paper, a new classification method based on relevance vector machine (RVM) is used in the MPSK signals classification. Compared with support (SVM), RVM sparse model Bayesian framework, not only solution highly sparse, but also it does need to adjust parameter and its kernel functions don't satisfy Mercer's condition. The fourth order cumulants of received are as firstly, then multi-class classifier designed. We first introduce model, transform learning maximization marginal...
Food recommendation systems serve as pivotal components in the realm of digital lifestyle services, designed to assist users discovering recipes and food items that resonate with their unique dietary predilections. Typically, multi-modal descriptions offer an exhaustive profile for each recipe, thereby ensuring recommendations are both personalized accurate. Our preliminary investigation two datasets indicates pre-trained dense representations might precipitate a deterioration performance...
Eye detection is required in many applications human-computer interaction, which plays an important role screen control, user recognition and auto-stereoscopic displays. Considering the defects of traditional methods human-eye detection, accurate human-eye-detection algorithm has been proposed. This paper proposes a novel technique combining Adaboost hybrid matching method. First, facial part whole image located with algorithm; area positioned through feature extraction In process, edge...
Hyperspectral imagery organically includes the spectral information and space of ground objects, so it can bring opportunity to objects recognition more precisely. Because performance many kinds classifiers often be dramatically improved by AdaBoost algorithm, in this paper, we introduce basic procedure Discrete algorithm for two-class classification problem, describe decision stump classifier used as weak learner, then forward multiclass Gentle using hamming loss hyperspectral...
In this paper, a new classification method based on Kernel Fisher Discriminant Analysis(KFDA) is brought forward in the MPSK signals modulation classification. The fourth order cumulants of received are used as vector firstly, then kernel thought to map feature impliedly high dimensional space and linear fisher discriminant analysis applied signal two classifiers function - Support Vector Machine Analysis introduced detail. build effective robust SVM KFDA compared with each other, radial...
In this paper, a new classification method based on kernel fisher discriminant analysis is used in the digital signals classification. The second, fourth and sixth order cumulants of received are as vector firstly, then thought to map feature high dimensional space linear applied signal radial basis function selected one against or rest multi-class classifier designed parameter selection using cross-validating grid adopted build an effective robust KFDA classifier. Through experiments it can...
3D object detection is an essential task for achieving autonomous driving. Existing anchor-based methods rely on empirical heuristics setting of anchors, which makes the algorithms lack elegance. In recent years, we have witnessed rise several generative models, among diffusion models show great potential learning transformation two distributions. Our proposed Diff3Det migrates model to proposal generation by considering boxes as targets. During training, diffuse from ground truth Gaussian...
Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems no interactions, a typical approach is Behavior Cloning (BC). However, BC-like methods tend to be affected by distribution shift. To mitigate this problem, we come up Robust Model-Based Imitation Learning (RMBIL) framework that casts as an end-to-end differentiable nonlinear closed-loop tracking problem. RMBIL applies Neural ODE learn...