Junjie Liang

Research on SOC equalization control strategy of chain-type energy storage converter

Zeyi Zhu, Yihang Liu, Chao Li, Junjie Liang et autres

As the “dual carbon” goals are increasingly advanced and high-voltage, high-power energy storage applications continue to develop rapidly, energy storage converters—serving as the critical interface between the energy storage system and the grid—are susceptible to both inter-phase and intra-phase State of Charge …

Multiparameter-driven gearbox health assessment using hybrid GAN-LSTM networks

Junjie Liang, Kaiyu Wu, Boming Chen, Runhao Yang et autres

Gearboxes represent a key feature of wind turbines, fulfilling the function of connecting and transmitting power. The analysis of gearbox health assessment has the capacity to predict the failure time of the wind turbine with both timeliness and accuracy, thus providing guidance …

jp, cn (code pays fourni par la source)

From Emotion to Depression: How to leverage Emotional Representations for Multimodal Depression Diagnosis?

Junjie Liang, Peng Cao, Jie Yang, Xiuyi Fan et autres

Existing depression diagnosis methods attempt to understand depression via general emotional representations learning and have achieved notable progress. However, these methods still remain limited in two key aspects: 1) coarse-grained emotional representation: these methods often struggle to capture fine-grained multimodal emotional cues; …

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

MoDEpression: Exploring Individual Differences in personalized Depression Diagnosis using Mixture-of-Expert

Junjie Liang, Peng Cao, Kun Hu, Jie Yang et autres

Depression is a widespread mental health disorder affecting individuals in diverse ways. Early detection of depression is crucial for treatment. Previous depression detection methods failed to consider the complexity and variability of capturing depression symptoms, particularly across different individuals and modalities, inevitably …

cn, ca (code pays fourni par la source)

Clinical Human-Derived Pathogen Signatures Captured by SERS and Deep Learning for Environmental Exposure Risk Assessment

Zhonghua Shen, Linguo Xie, Yu-wei Hou, Zhaofan He et autres

High Resolution Image Download MS PowerPoint Slide Microbial contamination and antibiotic-resistant bacteria (ARB) pose significant threats to environmental ecosystems, particularly in regions lacking adequate sanitation. Urinary pathogens of human origin, frequently detected in contaminated water and surfaces, represent early indicators of ARB-related …

cn (code pays fourni par la source)

Modeling Multimodal Depression Diagnosis From the Perspective of Local Depressive Representation

Junjie Liang, Peng Cao, Chongxiao Wang, Jinzhu Yang et autres

Depression recognition is critical for early detection and treatment. Existing works focus on modeling coarse-grained multimodal representation to estimate the depression level. However, these approaches often overlook the inherent locality of depressive representation, resulting in weak and sparse depressive frames being overlooked. …

cn, ca (code pays fourni par la source)

An Interpretable SERS–AI Platform for Rapid and Quantitative Diagnosis of Polymicrobial UTIs: Powered by Positively Charged Plasmonic Nanoparticles and Attention‐Based Deep Learning

Zhonghua Shen, Linguo Xie, Yu-wei Hou, Junjie Liang et autres

Abstract Polymicrobial urinary tract infections (UTIs) present diagnostic challenges due to overlapping symptoms and limitations of conventional methods. Although SERS and AI have shown potential for microbial diagnostics, existing approaches lack reproducibility, quantification capability, and interpretability—especially in complex clinical samples. Here, a …

cn (code pays fourni par la source)

Structure-Aware MRI Translation: Multi-modal Latent Diffusion Model with Arbitrary Missing Modalities

Junjie Liang, Peng Jun Cao, Jinzhu Yang, Osmar R. Zai͏̈ane

cn, ca (code pays fourni par la source)

Spatial distribution characteristics of major elements in sediments and their provenance implications in the Mu Us Sandy Land, China

Ruiyao Xu, Yuejun Si, Baosheng Li, Dongfeng Niu et autres

Thirty-five modern aeolian sand samples were analyzed for major elements from the Mu Us Sandy Land. In the combination of the existing major elements data of the paleo-aeolian sand from the Late Pleistocene profiles in the northeastern and southwestern margins of the …

IDRL: An Individual-Aware MultimodalDepression-Related Representation Learning Frameworkfor Inter-Modal Inconsistency and Depression-UnrelatedInformation

Chongxiao Wang, Junjie Liang, Peng Cao, Jinzhu Yang et autres

mx, us, ca (code pays fourni par la source)

IDRL: An Individual-Aware Multimodal Depression-Related Representation Learning Framework for Depression Diagnosis

Chongxiao Wang, Junjie Liang, Peng Cao, Jinzhu Yang et autres

mx, us, ca (code pays fourni par la source)

Metabolic Reprogramming in Gliocyte Post-cerebral Ischemia/ Reperfusion: From Pathophysiology to Therapeutic Potential

Lipeng Gong, Junjie Liang, Letian Xie, Zhanwei Zhang et autres

Ischemic stroke is a leading cause of disability and death worldwide. However, the clinical efficacy of recanalization therapy as a preferred option is significantly hindered by reperfusion injury. The transformation between different phenotypes of gliocytes is closely associated with cerebral ischemia/ reperfusion …

cn (code pays fourni par la source)