Haotian Zhu

LightGT: Lightweight graph-aware LLM-style transformer for industrial control intrusion detection

Yuhan Cao, Haotian Zhu, Bimei Zhao, Wenbo Guan et autres

cn (code pays fourni par la source)

Mineral prospectivity mapping for Gejiu tin district using random forest and convolutional neural network methods

Mingguo Wang, Jiangnan Zhao, Jiawen Wan, Yu Sui et autres

• HPF fusion technique was used to integrate multi-sensor remote sensing data. • The S-A model was used to separate the geochemical anomaly from the background. • CNN model was demonstrated superior performance in mapping tin prospectivity. The Gejiu district, the world’s …

cn, Rwanda (code pays fourni par la source)

Path-Based Knowledge Graph Link Prediction Method With Graph Context

Jiawei Lu, Jianwei Chen, Haotian Zhu, Zhongcheng Xiao et autres

cn (code pays fourni par la source)

Comparison of manifold learning algorithms for identifying geochemical anomalies associated with copper mineralization

Jiangnan Zhao, Yu Sui, Jiangtao Liu, Haotian Zhu

The Baiyin district, situated within the northern Qilian orogenic belt, hosts the largest concentration of copper mineral resources in Gansu Province, Northwestern China. Geochemical anomaly patterns are crucial indicators for mineral exploration in this region; however, they are frequently concealed within complex …

cn (code pays fourni par la source)

Design and Implementation of an Adaptive Impedance Matching Resistor Network for Transient Electromagnetic Transmitting Coils

Haotian Zhu, G WANG, Zhibo Dai, Pei Tang et autres

cn (code pays fourni par la source)

PVTv2-SegFormer: A Lightweight Transformer for Edge-Efficient Ship Segmentation in Remote Sensing Imagery

Pei Tang, G WANG, Haotian Zhu

cn (code pays fourni par la source)

Apoptosis and autophagy promote Babesia microti infection in tick midguts: insights from transcriptomic and functional RNAi studies

Songqin Chen, Shanming Hu, Haotian Zhu, Yongzhi Zhou et autres

Introduction Ticks are the primary vectors of Babesia sp, with the midgut as the initial site of pathogen invasion following blood feeding. Elucidating the molecular interactions between tick midguts and Babesia is essential for developing targeted strategies to control tick-borne babesiosis. However, …

cn (code pays fourni par la source)

Identifying Targets and Drugs for Rheumatoid Arthritis Stratified Therapy Using Mendelian Randomization and a Pretraining Model

Yuqing Yan, You Wu, Yu Sun, Tian Wu et autres

The prevalence of rheumatoid arthritis (RA) subtypes, including seropositive and seronegative, is influenced by lifestyle factors and exhibits high heterogeneity, resulting in reduced drug efficacy. This study aims to identify cytokines mediating the effects of different lifestyles on RA subtypes and to …

cn (code pays fourni par la source)

Transcriptome reveals the roles and potential mechanisms of CeRNA in the regulation of salivary gland development in the tick Rhipicephalus haemaphysaloides

Shanming Hu, Songqin Chen, Haotian Zhu, Yanan Wang et autres

Introduction: The salivary glands of female ticks rapidly degenerate after feeding. The mechanism involves programmed cell death mediated by an ecdysteroid receptor. A competing endogenous RNA (ceRNA) network has been established using miRNA and the competitive binding of three types of RNA …

cn (code pays fourni par la source)

MACS-BNet: A Stealthy Multiconstraint Adversarial Backdoor Network Against Compressed Learning

Haotian Zhu, Wei Wu, Haipeng Peng, Dawei Zhao

Deep learning-based compressed sensing techniques have exhibited exceptional prowess in signal reconstruction and data-sharing applications, particularly within the realm of IoT sensor data processing. However, existing methods overlook a critical security vulnerability: the susceptibility of compressed sensing techniques to backdoor attacks during …

cn (code pays fourni par la source)

Update in the molecular mechanism and biomarkers of diabetic retinopathy

Hui Zhu, Bingqi Li, Tao Huang, Bin Wang et autres

cn (code pays fourni par la source)

E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models

Liming Lü, Shuchao Pang, Siyuan Liang, Haotian Zhu et autres

Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently tune massive weight parameters and \ding{173} how to ensure robustness against …