Yusen Zhu

ORCID: 0009-0005-8286-6282
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • IoT and Edge/Fog Computing
  • Advanced Neural Network Applications
  • Poxvirus research and outbreaks
  • COVID-19 diagnosis using AI
  • Emotion and Mood Recognition
  • Anomaly Detection Techniques and Applications
  • Age of Information Optimization
  • Brain Tumor Detection and Classification
  • Advanced Vision and Imaging
  • Machine Learning and ELM
  • Advanced Image Processing Techniques
  • Radiomics and Machine Learning in Medical Imaging
  • AI in cancer detection
  • Advanced X-ray and CT Imaging
  • Colorectal Cancer Screening and Detection
  • Color perception and design
  • Sentiment Analysis and Opinion Mining
  • Virology and Viral Diseases
  • Advanced Bandit Algorithms Research
  • Gastrointestinal Bleeding Diagnosis and Treatment
  • Big Data Technologies and Applications
  • Medical Imaging and Analysis
  • Digital Imaging for Blood Diseases
  • Bluetooth and Wireless Communication Technologies
  • Reinforcement Learning in Robotics

Hunan University
2021-2024

Southeast University
2024

NetEase (China)
2023

Xinjiang University
2023

University of Leeds
2022

Xiangtan University
2022

Changsha University of Science and Technology
2022

University of Sussex
2021

Peking University
2016

Yuanpei University
2016

Aqueous solutions can be dispersed into picoliter droplets through a micro-channel array <italic>via</italic> centrifugation which produces monodispersed water-in-oil emulsion for digital PCR.

10.1039/c6lc01305h article EN Lab on a Chip 2016-12-09

Emotion recognition in conversation (ERC) aims to analyze the speaker’s state and identify their emotion conversation. Recent works ERC focus on context modeling but ignore representation of contextual emotional tendency. In order extract multi-modal information tendency utterance effectively, we propose a new structure named Emoformer vectors from different modalities fuse them with sentence vector be an capsule. Furthermore, design end-to-end model called EmoCaps, which extracts through...

10.18653/v1/2022.findings-acl.126 article EN cc-by Findings of the Association for Computational Linguistics: ACL 2022 2022-01-01

Accurate diagnosis of kidney disease is crucial, as it a significant health concern that demands precise identification for effective and appropriate treatment. Deep learning methods are increasingly recognized valuable tools in the biomedical field. However, current models utilizing deep networks often encounter challenges overfitting low accuracy, necessitating further refinement optimal performance. To overcome these challenges, this paper proposes introduction two ensemble designed stone...

10.1016/j.jksuci.2024.102130 article EN cc-by Journal of King Saud University - Computer and Information Sciences 2024-07-18

With the increasing demand for bulk data transmission, offloading techniques to transmit via mobile physical media is becoming common increasingly. The development of Internet Vehicles (IoV) provides new solutions offloading, as IoV brings massive storage and transmission capabilities. However, impact caused by mobility a challenge delay optimization route selection offloading. In this paper, we consider network architecture based on Manhattan model. vehicle carries fixed in scenario,...

10.1109/tnse.2022.3163193 article EN IEEE Transactions on Network Science and Engineering 2022-03-29

In the domain of medical diagnostics, precise identification various skin and oral diseases is vital for effective patient care. particular, Mpox a potentially dangerous viral disease with zoonotic origins, capable human-to-human transmission, underscoring urgency diagnostic methods timely intervention. This paper introduces novel approach named Choquet Fuzzy Integral-based Ensemble (CFI-Net) accurate classification diseases, specific emphasis on detecting Mpox, foot ulcers, mouth diseases....

10.1109/jbhi.2024.3411658 article EN IEEE Journal of Biomedical and Health Informatics 2024-06-10

The fiber's bridging effect across the shear cracks is considered to play an important role of resisting in engineered cementitious composite (ECC), and fiber reinforced material general. To quantify crack kinematics (i.e., opening sliding displacements) ECC (R/ECC) beams, a measuring algorithm based on full-field displacement spectrum developed by using Digital Image Correlation (DIC) technology. In addition, novel distributed strain-measuring methodology was used detect strain distribution...

10.1016/j.cscm.2024.e03587 article EN cc-by-nc Case Studies in Construction Materials 2024-07-30

Wireless sensor network is a new research field. It can be used in some special situation for signal collection, processing and transmitting. Zigbee technology characteristic of less distance low speed. wireless protocol stack IEEE 802.15.4. Lately traditional system to collects parameters Greenhouse widely agriculture. The adopts wired way wiring, which makes the complex expensive. Generally modern has hundreds square meters they may plant variety plants depending on different seasons. So...

10.1088/1742-6596/48/1/223 article EN Journal of Physics Conference Series 2006-10-01

With the massive increase of mobile user and sensor data in heterogeneous Internet Things (IoT), limited caching resources are challenging to meet people's increased traffic demand. Due ignoring influence uplink, existing joint studies cannot reflect actual network performance. Furthermore, some emerging delay-sensitive applications IoT, such as Virtual Reality, Augmented autonomous driving, require better reliability stability. Digital twins (DT) can provide real-time stable wireless...

10.1109/tnse.2023.3281398 article EN IEEE Transactions on Network Science and Engineering 2023-01-01

In the face of intensive computing tasks with massive data, cloud is difficult to provide high-quality services. Edge extends services edge network by introducing devices between terminal and cloud. For limited server resources, it especially important optimize offload strategies accurately predicting load on device. This paper proposes a C-LSTM prediction model based deep neural predict CPU utilization equipment in future, then distributed greedy algorithm for offloading decision. The...

10.1109/hpsr54439.2022.9831405 article EN 2022-06-06

Due to the uneven distribution of network resources and network, traffic, congestion is an inherent attribute Internet network. Network will increase data transmission delay, reduce throughput, packet loss rate in even cause overall performance degradation, which may large losses users. This article aims study multistage resource-aware control algorithms based on edge computing environments. first compares analyzes traditional cloud computing. There are certain differences between technology...

10.1016/j.egyr.2022.04.078 article EN cc-by-nc-nd Energy Reports 2022-05-14
Coming Soon ...