Min Xu

Deeply-Supervised Networks With Threshold Loss for Cancer Detection in Automated Breast Ultrasound

2019 · IEEE Transactions on Medical Imaging

ABUS, or Automated breast ultrasound, is an innovative and promising method of screening for breast examination. Comparing to common B-mode 2D ultrasound, ABUS attains operator-independent image acquisition and also provides 3D views of the whole …

Towards Counteracting Adversarial Perturbations to Resist Adversarial Examples

2021

Studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based artificial intelligence systems. We observe that the probability of the correct result outputted by the network increases …

Joint Classification of IoT Devices and Relations in the Internet with Network Traffic

2022 · 2022 IEEE Wireless Communications and Networking Conference (WCNC)

With the rapid growth and popularization of Internet of Things (IoT), more and more devices are deployed in homes, enterprises, cities, etc. The existed methods to classify types and relations of devices are usually two …

Comparative Evaluation of Language Models in Summarizing Chinese Healthcare Exam Findings

2024 · Research Square

Abstract Background and Objectives: Summarizing Chinese healthcare exam findings (SCHEF) is a critical and challenging task that requires extensive medical knowledge. Despite its importance, research on automating the generation of such summaries remains limited.We aim …

IHFBF: A High-Performance Blockchain Framework for Improving Hyperledger Fabric Permissioned Chain

2023

Permissioned blockchain frameworks typically employ efficient Byzantine fault-tolerant consensus protocols, making them appealing for the deployment of fast transaction applications among a large number of mutually distrustful participants. However, existing permissioned blockchain frameworks typically use …

FIAS: Feature Imbalance-Aware Medical Image Segmentation with Dynamic Fusion and Mixing Attention

2025

With the growing application of transformer in computer vision, hybrid architectures that combine convolutional neural networks (CNNs) and transformers demonstrate competitive ability in medical image segmentation. However, direct fusion of features from CNNs and transformers …

Enhancing News Recommendation with Hierarchical LLM Prompting

2025

Personalized news recommendation systems often struggle to effectively capture the complexity of user preferences, as they rely heavily on shallow representations, such as article titles and abstracts. To address this problem, we introduce a novel …

Safety-Constrained Deep Reinforcement Learning for Source–Load–Storage Coordinated Operation of Green Low-Carbon Data Centers

2026 · Energies

Green low-carbon data centers operate as coupled cyber-energy systems whose dispatch must coordinate renewable generation, grid exchange, battery storage, cooling load, flexible computing workload, carbon-intensity signals, and reliability constraints. This study develops and evaluates a …