Mingyu Gao

Impact of number of dissected lymph nodes on long-term survival in lung adenocarcinoma with mixed ground-glass opacity

Huiqin Yang, Han Lin, Mingyu Gao, Hari B. Keshava et autres

Robust Inverse Design of Metasurfaces Under Geometric Damage via Hyperlearning

Zhedong Wang, Zhekang Dong, Huipin Lin, Xudong Lv et autres

The accelerated development of intelligent meta-surfaces is reshaping electromagnetic manipulation technologies, spanning applications from wireless communications to invisibility cloaks. Central to these advances lies the precise and efficient inverse design of metasurface global patterns. Yet, unpredictable accidents such as structural deformation exacerbate …

cn (code pays fourni par la source)

Data-Driven SOH Estimation for Second-Life Batteries Based on Partial Charging Segments: An Industrial Case Study

Tingting Luo, Hongtao Tong, Jiahao Nie, Zhengyi Bao et autres

cn (code pays fourni par la source)

CMIF-Calib: A Novel LiDAR–Camera Extrinsic Calibration System With Cross-Modal Information Fusion

Xudong Lv, Shuo Wang, Zhekang Dong, Mingyu Gao et autres

The complexity of unmanned system operating environments necessitates multi-sensor fusion for robust, long-term perception. Precise extrinsic calibration across heterogeneous sensors is fundamental to effective fusion. While data-driven calibration methods with artificial intelligence offer high accuracy and efficiency, their generalization to unseen scenarios …

cn (code pays fourni par la source)

Current Status and Future Prospects of Carbon Capture and Storage Technology

Mingyu Gao

Carbon Capture and Storage (CCS) is widely recognized as a pivotal technological solution for mitigating climate change and achieving global carbon neutrality goals. This article provides a systematic review of the entire CCS technological chain, elucidating its core principles and system components, …

cn (code pays fourni par la source)

PID-NN: A Dual-Branch Neural Network With Physics-Informed Constraints for State-of-Health Estimation of Lithium-Ion Batteries

Xudong Lv, Zhekang Dong, Mingyu Gao

Accurate prediction of the state of health (SOH) of lithium-ion batteries is crucial for ensuring the safety of on-board battery management systems (BMS) and for optimizing their lifetime. However, existing data-driven approaches face challenges in multi-scale feature extraction and lack physical interpretability, …

cn (code pays fourni par la source)

STAMP: Accelerating Second-Order DNN Training Via ReRAM-Based Processing-in-Memory Architecture

Yilong Zhao, Fangxin Liu, Mingyu Gao, Xiaoyao Liang et autres

cn (code pays fourni par la source)

Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving

Ziming Liu, Boyu Tian, Guoteng Wang, Zhen Jiang et autres

Mixture-of-Experts (MoE) models challenge serving infrastructures with dynamic, sparse expert utilization, causing instability on conventional systems designed for dense architectures. We propose EaaS, a novel serving system to enable efficient, scalable, and robust MoE deployment. Our system disaggregates MoE modules into independent, …

MTSBV Algorithm Design for Real-Time Battery Data Segmentation

Ping Li, Yuxiang Yang, Zhiwei He, Mingyu Gao

With the increasing number of new energy vehicles, the safety of power batteries has gained significant attention. A prerequisite for accurate estimation of battery state is effective segmentation of battery data. In response to this issue, this paper develops a frequency-domain feature-based …

cn (code pays fourni par la source)

Propagation Characteristics and Path Loss Analysis of Electromagnetic Waves in Stratified Seawater in Shallow Sea

Yizhe Wang, Ke Yang, Mingyu Gao, Peng Lin et autres

As the core carrier of information transmission in shallow waters, the propagation characteristics of electromagnetic waves in stratified seawater are crucial. Based on the measured seawater conductivity parameters, a layered medium model of “air-multilayered seawater-seabed” was established. The influence of frequency and …

cn (code pays fourni par la source)

Status, challenges, and techniques of echelon utilization of retired lithium-ion batteries

Siwei Guan, Hongtao Tong, Zhiwei He, Zhekang Dong et autres

With the rapid development of the global electric vehicle (EV) market, substantial quantities of lithium-ion batteries (LIBs) will be retired from electric vehicles. Proper handling of these retired LIBs is becoming an urgent and serious issue. The echelon utilization of retired LIBs …

cn (code pays fourni par la source)

Ironman: Accelerating Oblivious Transfer Extension for Privacy-Preserving AI with Near-Memory Processing

Kang Yang, Tianshi Xu, Ling Liang, Yufei Wang et autres

With the wide application of machine learning (ML), privacy concerns arise with user data as they may contain sensitive information. Privacy-preserving ML (PPML) based on cryptographic primitives has emerged as a promising solution in which an ML model is directly computed on …