A5100779113- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Digital Media Forensic Detection
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Image Retrieval and Classification Techniques
- Image Processing Techniques and Applications
- Brain Tumor Detection and Classification
- Data Mining Algorithms and Applications
- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Rough Sets and Fuzzy Logic
- Neural dynamics and brain function
- Advanced Image Processing Techniques
- EEG and Brain-Computer Interfaces
- Data Management and Algorithms
- Radiomics and Machine Learning in Medical Imaging
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Remote-Sensing Image Classification
- Chaos control and synchronization
- Advanced Neural Network Applications
- Cellular Automata and Applications
- Image and Signal Denoising Methods
- Remote Sensing and Land Use
Wuhan University
2024
Renmin Hospital of Wuhan University
2024
Kunming University of Science and Technology
2017-2024
Anhui University of Science and Technology
2024
State Grid Corporation of China (China)
2024
Xi'an Jiaotong University
2013-2024
Qingdao University of Technology
2023-2024
Beijing Academy of Artificial Intelligence
2023-2024
Chengdu University of Information Technology
2023-2024
Northwestern Polytechnical University
2023
Using two mutually coupled semiconductor lasers (MC-SLs) outputs as chaotic entropy sources, a scheme for generating Tbits/s ultra-fast physical random bit (PRB) is demonstrated and analyzed experimentally. Firstly, sources originating from of MC-SLs are obtained in parallel. Secondly, by adopting multiple optimized post-processing methods, PRB streams with the generation rate 0.56 extracted their randomness verified using NIST Special Publication 800-22 statistical tests. Through merging...
With the increasing popularity of location-aware social media services, next-Point-of-Interest (POI) recommendation has gained significant research interest. The key challenge next-POI is to precisely learn users' sequential movements from sparse check-in data. To this end, various embedding methods have been proposed representations data in Euclidean space. However, their ability complex patterns, especially hierarchical structures, limited by dimensionality we propose a new direction that...
Recently, infrared–visible image fusion has attracted more and attention, numerous excellent methods in this field have emerged. However, when the low-resolution images are being fused, most results of low resolution, limiting practical application results. Although some can simultaneously realize super-resolution images, improvement performance is limited due to lack guidance high-resolution To address issue, we propose a heterogeneous knowledge distillation network (HKDnet) with multilayer...
Domain adaptation person re-identification (Re-ID) is a challenging task, which aims to transfer the knowledge learned from labeled source domain unlabeled target domain. Recently, some clustering-based Re-ID methods have achieved great success. However, these ignore inferior influence on pseudo-label prediction due different camera styles. The reliability of plays key role in Re-ID, while styles bring challenges for prediction. To this end, novel method proposed, bridges gap cameras and...
Association rules are useful for determining correlations between items and have applications in marketing, financial retail sectors. Lots of algorithms been proposed finding the association databases. Most these t
The time delay (TD) signature concealment of optical feedback induced chaos in an external cavity semiconductor laser is experimentally demonstrated. Both the evolution curve and distribution map TD are obtained parameter space strength injection current. optimum scope also specified. Furthermore, approximately periodic relation between length observed indicates that intrinsic relaxation oscillation may play important role during process suppression.
Accurate and reliable segmentation of polyp targets is crucial in the treatment colorectal cancer. However, clinical practice, structures represent only a small portion image, which essential for accurate diagnosis The size lesion areas leads to reduction feature representation, thereby affecting performance traditional methods. To address this issue, recent advancements methods medical objects meticulously extract information from these using attention mechanisms. mainly focus on general...
Device-to-device (D2D) is a new paradigm that enhances network performance by offering wide variety of advantages over traditional cellular networks, e.g., efficient spectral usage and extended coverage. Efficient data dissemination indispensable for supporting many D2D applications such as content distribution location-aware advertisement. In this work, we study the problem multi-copy with probabilistic delay constraint in mobile opportunistic networks. We first formally formulate introduce...
Hyperspectral image (HSI) denoising is essential for enhancing HSI quality and facilitating processing tasks. However, the reduction of noise in a difficult work, primarily due to fact that consists much more spectral bands than other remote sensing images. Therefore, comparing with jobs rely on spatial information, efficient requires utilization both information. In this paper, we design an unsupervised spatial-spectral approach based Monte Carlo sampling (MCS) technique. This allows...
The rapid and accurate identification of complex samples still remains a great challenge, especially for those with similar compositions. In this work, we report an integration strategy consisting surface-enhanced Raman scattering (SERS) machine learning to discriminate analytes, in case green tea products different storage times. Surface-functionalized Ag nanoparticles (NPs) were used as SERS substrate reveal the changes sensory components variable time. Principal analysis (PCA)-based...
Surface-enhanced Raman scattering (SERS) displays great potential for food analysis due to the molecular fingerprint providing capability. Herein, we explore effectiveness of strategy based on multidimensional SERS tea differentiation. It is known that a complex target analyte can generate different signal responses once combination functionalized substrates has been introduced (multidimensional SERS). The hypothesis increasing spectral data dimension could improve possibility and accuracy...