Publications by authors named "Xingzhong Xiong"
Article Synopsis
- Current AI image recognition technology is effective for defect detection in massive grid transmission line inspections, following two main approaches: lightweight networks for efficiency at the cost of accuracy, and complex networks for higher accuracy but with reduced efficiency.
- This paper introduces a new method called DCP-YOLOv8 that optimizes defect detection by using deformable convolution and a unique feature fusion structure to improve the model's ability to recognize multiple defect types while maintaining a lightweight design.
- Experimental results show that DCP-YOLOv8 achieves a 72.2% accuracy rate on a dataset of real transmission line defects, reduces model parameters by 9.15%, and processes 103 frames per second, effectively balancing accuracy and performance for real-time applications.*
Article Synopsis
- * A new BILSTM-SimAM network model has been developed that utilizes Variational Mode Decomposition (VMD) for noise reduction and feature extraction, in combination with a CNN to enhance model accuracy and training speed.
- * The BILSTM-SimAM model demonstrates impressive performance, achieving a prediction accuracy of 97.8%, outperforming other leading models like Transformer, MLP, and Prophet.
Article Synopsis
- Low-light image enhancement (LLIE) aims to improve poorly lit images, but current methods struggle to fully use valuable positional and frequency information from the images.
- The proposed HPCDNet network combines hybrid positional coding with self-attention to enhance spatial information and incorporates frequency domain recovery techniques to better restore lost details.
- Experiments show that HPCDNet significantly improves visibility, contrast, and color quality in low-light images while preserving important details and textures compared to existing methods.
The fusion tracking of RGB and thermal infrared image (RGBT) is paid wide attention to due to their complementary advantages. Currently, most algorithms obtain modality weights through attention mechanisms to integrate multi-modalities information. They do not fully exploit the multi-scale information and ignore the rich contextual information among features, which limits the tracking performance to some extent.
View Article and Find Full Text PDFModulation format identification (MFI) is a critical technology for autonomous digital coherent receivers in next-generation elastic optical networks. A novel and simple MFI scheme, to the best of our knowledge, based on signal envelope flatness is proposed without requiring any training or other prior information. After amplitude normalization and partition, the incoming polarization division multiplexed (PDM) signals can be classified into quadrature phase shift keying (QPSK), 8 quadrature amplitude modulation (QAM), 16QAM, and 64QAM signals according to envelope flatnesses , , and of signals in different amplitude ranges.
View Article and Find Full Text PDFThe Satellite network is an important part of the global network. However, the complex architecture, changeable constellation topology, and frequent inter-satellite connection switching problems bring great challenges to the routing designs of satellite networks, making the study of the routing methods in satellite networks a research hotspot. Therefore, this paper investigates the latest existing routing works to tackle the dynamic routing problems in satellite networks.
View Article and Find Full Text PDFRadio Frequency Identification (RFID) has been one of the critical technologies of the Internet of Things (IoT). With the rapid development of the IoT, the RFID systems are required to be more efficient and with high throughput capacity. In the widespread IoT application scenes, the collision problem of the RFID tags has become the increasingly remarkable problem in RFID systems.
View Article and Find Full Text PDFAttention-dependent reduction in the tendency for neurons to fire bursts (burstiness) is widely observed in the visual cortex. However, the underlying mechanism and the functional role of this phenomenon remain unclear. We recorded well-isolated single-unit activities in primary visual cortex (V1) from two primates (Macaca mulatta) while they performed a detection task engaging spatial attention with two levels of difficulty (hard/easy).
View Article and Find Full Text PDFArticle Synopsis
- Brain metastases are the most common type of brain tumors, and understanding resting state networks (RSNs) involved in perception and cognition is crucial for minimizing cognitive impairments during surgery.
- This study evaluated the effectiveness of independent component analysis (ICA) for localizing RSNs using resting-state fMRI data in 12 patients with brain metastases and 14 healthy controls, successfully identifying seven common RSNs.
- The research found that RSNs in patients exhibited spatial shifts correlated with tumor location, with larger shifts observed in higher cognitive networks compared to perceptual networks, indicating a complex interplay of functional disruptions caused by metastases.
White matter lesions (WMLs) have been associated with cognitive and motor decline. Resting state networks (RSNs) are spatially coherent patterns in the human brain and their interactions sustain our daily function. Therefore, investigating the altered intra- and inter-network connectivity among the RSNs may help to understand the association of WMLs with impaired cognitive and motor function.
View Article and Find Full Text PDFThere is increasing evidence that white matter lesions (WMLs) are associated with cognitive impairments. The purpose of this study was to explore the relationship of WMLs with cognitive impairments from the aspect of cortical functional activity. Briefly, Sixteen patients with ischemic WMLs and 13 controls participated in this study.
View Article and Find Full Text PDFWhite matter lesions (WMLs) are frequently detected in elderly people. Previous structural and functional studies have demonstrated that WMLs are associated with cognitive and motor decline. However, the underlying mechanism of how WMLs lead to cognitive decline and motor disturbance remains unclear.
View Article and Find Full Text PDF