Hao Zhang

Multimodal Bionic Magnetic Miniature Amphibious Soft Robots

Fujun Wang, Chuhan Zhang, Hao Zhang, Dingfan Xu et autres

Miniature amphibious soft robots (MASRs) show great potential for operation in unstructured and complex environments, owing to their ability to move flexibly through narrow spaces with complex obstacles. However, existing MASRs still lack diverse movement modes and struggle with inefficient performance in …

cn, gb (code pays fourni par la source)

Optimizing Convolutional Operation and Dataflow in FPGA Acceleration of Bayesian Convolutional Neural Network

Shulei Wang, Yun Ling, Daolin Cai, Hao Zhang et autres

A Bayesian convolutional neural network (BCNN) quantifies prediction uncertainty by introducing randomness into weights or activations, which is important for safety-critical applications such as medical diagnosis and autonomous driving. However, BCNN inference typically relies on Monte Carlo sampling requiring multiple forward passes, …

cn (code pays fourni par la source)

Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation

Wei‐Cheng Tseng, Xuanru Zhou, Mingyue Huo, Yiwen Shao et autres

Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored.Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales.We identify …

us, cn (code pays fourni par la source)

Semantic-Aware Model Cache and Resource Allocation for Air-Ground Embodied Intelligence: A Two-Timescale M2ADRL Algorithm

Bingxin Tian, Ruoguang Li, Zijun Huang, Lei Wang et autres

cn, us (code pays fourni par la source)

SpectrumFM: A Foundation Model for Intelligent Spectrum Management

Fuhui Zhou, Chunyu Liu, Hao Zhang, Wei Wu et autres

Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer from notable limitations in recognition accuracy, convergence speed, and generalization, particularly in the complex …

cn, sg, kr (code pays fourni par la source)

ADFE-DET: An Adaptive Dynamic Feature Enhancement Algorithm for Weld Defect Detection

Xiaocui Wu, Changjun Liu, Hao Zhang, Pengyu Xu

Welding is a critical joining process in modern manufacturing, with defects contributing to 50–80% of structural failures. Traditional inspection methods are often inefficient, subjective, and inconsistent. To address challenges in weld defect detection—including scale variation, morphological complexity, low contrast, and sample imbalance—this …

cn (code pays fourni par la source)

Bifidobacterium longum subsp. longum CCFM1375 Mitigates Chronic Kidney Disease Progression via Gut Microbiota Modulation and Gut Barrier Restoration

Hongchao Wang, Xinchen Lv, Yue Zhang, Jinlin Zhu et autres

ABSTRACT Chronic kidney disease (CKD) is associated with impaired kidney function, intestinal barrier dysfunction, accumulation of uremic toxins, and gut microbiota dysbiosis. In this study, we used an adenine‐induced CKD mouse model to evaluate the effects of Bifidobacterium longum subsp. longum CCFM1375 …

cn (code pays fourni par la source)

Micro-YOLOv8: a lightweight real-time object detector

Shuo Li, Rui Yao, Aobo Jia, Hao Zhang et autres

Significant advancements have been made in object detection performance through the use of deep learning models. However, traditional models like Faster R-CNN and YOLO challenges in deployment on embedded mobile devices due to their large network size, which is constrained by limited …

cn (code pays fourni par la source)

An intelligent diagnosis method for PMSM radial misalignment based on current signal and Swin-BiGRU multimodal fusion

Hao Yu, Junhao Guo, Hao Zhang

Motor Current Signature Analysis (MCSA) faces considerable challenges in diagnosing mechanical faults in motors, particularly in accurately detecting misalignment in rotating machinery. Traditional vibration-based methods often suffer from high hardware costs and difficulties associated with sensor installation. To address these limitations, this …

cn (code pays fourni par la source)

Distributed Multi-Task Learning for Joint Wireless Signal Enhancement and Recognition

Hao Zhang, Fuhui Zhou, Qihui Wu, Chau Yuen

Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify the properties of the received signal in a no-collaborative manner. However, it is challenging to accurately classify signals in low signal-to-noise ratio (SNR) conditions …

cn, sg (code pays fourni par la source)

Distributed Multi-Task Learning for Joint Wireless Signal Enhancement and Recognition

Hao Zhang, Fuhui Zhou, Qihui Wu, Chau Yuen

Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify the properties of the received signal in a no-collaborative manner. However, it is challenging to accurately classify signals in low signal-to-noise ratio (SNR) conditions …

Controlling the Digital to Analog and Multilevel Switching in Memristors Based on Zr-Doped HfO2 by Interface Engineering

Cong Han, Haiming Qin, Weijing Shao, Hanbing Fang et autres

Metal oxides are the most widely used material for the resistive switching layer of memristors. Nevertheless, the majority of oxide-based memristors exhibit binary switching, restricting the emulation of neuronal synaptic behaviors. In this paper, the shift from digital-to-analog switching behavior is achieved …

cn (code pays fourni par la source)