A5100614733- Chaos-based Image/Signal Encryption
- Advanced Memory and Neural Computing
- Advanced Steganography and Watermarking Techniques
- Neuroscience and Neural Engineering
- Cryptographic Implementations and Security
- Cellular Automata and Applications
- Neural dynamics and brain function
- Chaos control and synchronization
- CCD and CMOS Imaging Sensors
- Digital Media Forensic Detection
- Ferroelectric and Negative Capacitance Devices
- Neural Networks and Reservoir Computing
- Traffic Prediction and Management Techniques
- EEG and Brain-Computer Interfaces
- Oxidative Organic Chemistry Reactions
- Sparse and Compressive Sensing Techniques
- Catalytic C–H Functionalization Methods
- Zeolite Catalysis and Synthesis
- Advanced Algorithms and Applications
- Traffic control and management
- Privacy-Preserving Technologies in Data
- Cloud Data Security Solutions
- Gene expression and cancer classification
- Axial and Atropisomeric Chirality Synthesis
- Advanced Measurement and Metrology Techniques
Guangxi Normal University
2016-2025
Shanghai University of Electric Power
2024
Guizhou University
2023-2024
Anhui Polytechnic University
2023-2024
Sichuan University
2024
West China Hospital of Sichuan University
2024
Guiyang College of Traditional Chinese Medicine
2024
The University of Sydney
2023
Cooperative Trials Group for Neuro-Oncology
2023
Southern Medical University
2022
Emotion classification based on brain-computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI and compared to traditional methods improved results have obtained. In this paper, a novel neural network proposed using EEG systems, which combines Convolutional Neural Network (CNN), Sparse Autoencoder (SAE) Deep (DNN) together. network, features extracted by CNN are sent SAE encoding decoding at first. Then...
Due to the potential security problem about key management and distribution for symmetric image encryption schemes, a novel asymmetric method is proposed in this paper, which based on elliptic curve ElGamal (EC-ElGamal) cryptography chaotic theory. Specifically, SHA-512 hash first adopted generate initial values of system, crossover permutation terms index sequence used scramble plain-image. Furthermore, generated scrambled embedded into encrypted by EC-ElGamal can not only improve but also...
In this paper, a novel image watermarking method is proposed which based on discrete wave transformation (DWT), Hessenberg decomposition (HD), and singular value (SVD). First, in the embedding process, host decomposed into number of sub-bands through multi-level DWT, resulting coefficients are then used as input for HD. The watermark operated SVD at same time. finally embedded by scaling factor. Fruit fly optimization algorithm, one natural-inspired algorithms devoted to find factor...
A novel method of using the spiking neural networks (SNNs) and electroencephalograph (EEG) processing techniques to recognize emotion states is proposed in this paper. Three algorithms including discrete wavelet transform (DWT), variance fast Fourier (FFT) are employed extract EEG signals, which further taken by SNN for classification. Two datasets, i.e., DEAP SEED, used validate method. For former dataset, emotional include arousal, valence, dominance liking where each state denoted as...
The chaotic map has complex dynamics under ideal conditions however it suffers from the problem of performance degradation in case finite computing precision. In order to prevent degradation, this paper continuous Chen system is used perturb both inputs and parameters Chebyshev minimize phenomenon Experimental evaluations corresponding analysis demonstrate that a good randomness dynamic by using proposed perturbation method, some attributes are stronger than original (e.g. chaos attractor...
In this paper, a color image encryption method using the memristive hyperchaotic system and deoxyribonucleic acid (DNA) is proposed. First, pseudo-random sequences are generated by keystream generation mechanism based on plain image. Due to this, has complex dynamical behavior highly sensitive initial conditions, proposed random which also dependent images. Second, permutation cycle-shift operation designed eliminate correlations between adjacent pixels in Then, scrambled processed DNA...
Intelligent traffic light control is one of the modern approaches to solve congestion, where reinforcement learning a widely used method. Conventionally, determine whether change current phase (or choose phase) after each small interval. One major drawback these that it makes duration uncertain before terminates. Directly determining can effectively avoid this shortcoming. An adaptive timing system proposed in paper which directly duration. In system, Q-learning algorithm employed and action...