A5010220478- Cooperative Communication and Network Coding
- Caching and Content Delivery
- Opportunistic and Delay-Tolerant Networks
- Anomaly Detection Techniques and Applications
- Video Surveillance and Tracking Methods
- Wireless Signal Modulation Classification
- Energy Harvesting in Wireless Networks
- Energy Efficient Wireless Sensor Networks
- Advanced MIMO Systems Optimization
- Advanced Neural Network Applications
- Error Correcting Code Techniques
- Advanced Data Compression Techniques
- Radiomics and Machine Learning in Medical Imaging
- Indoor and Outdoor Localization Technologies
- Wireless Communication Security Techniques
- Peer-to-Peer Network Technologies
- Cognitive Computing and Networks
- Advanced Wireless Network Optimization
- Advanced Wireless Communication Techniques
- COVID-19 diagnosis using AI
- Privacy-Preserving Technologies in Data
- COVID-19 epidemiological studies
- Robotics and Automated Systems
- COVID-19 Clinical Research Studies
- Stochastic Gradient Optimization Techniques
Zhejiang University
2012-2025
Huaian First People’s Hospital
2024
Nanjing Medical University
2024
University of Science and Technology of China
2020-2024
State Key Laboratory of Industrial Control Technology
2012-2024
University of Shanghai for Science and Technology
2024
Zhejiang University of Technology
2014-2024
Xiamen University
2024
Changhai Hospital
2023
Xi'an Jiaotong University
2022-2023
Abstract Data from patients with coronavirus disease 2019 (COVID-19) are essential for guiding clinical decision making, furthering the understanding of this viral disease, and diagnostic modelling. Here, we describe an open resource containing data 1,521 pneumonia (including COVID-19 pneumonia) consisting chest computed tomography (CT) images, 130 features (from a range biochemical cellular analyses blood urine samples) laboratory-confirmed severe acute respiratory syndrome 2 (SARS-CoV-2)...
Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless that focus on abstract symbols, approaches attempt achieve better efficiency by only sending semantic-related information source data. this paper, we consider semantic-oriented which transmits semantic-relevant over channel recognition task, a compact additional set semantic-irrelevant reconstruction task....
As the binary sensing model is a coarse approximation of reality, probabilistic has been proposed as more realistic for characterizing region. A point covered by sensor networks under if joint probability from multiple sensors larger than predefined threshold ε. Existing work focused on coverage since it extremely difficult to verify full continuous area (i.e., coverage). In this paper, we tackle such challenging problem. We first study probabilities two points with distance d and obtain...
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs compress feedback its CSI BS. The overhead scales with number of antennas, users subcarriers, becomes major bottleneck for overall spectral efficiency. this paper, we propose deep learning (DL)-based compression scheme, called...
The conventional federated learning (FL) framework usually assumes synchronous reception and fusion of all the local models at central aggregator updating training global model agents as well. However, in a wireless network, due to limited radio resource, inevitable transmission failures heterogeneous computing capacity, it is very hard realize strict synchronization among involved user equipments (UEs). In this paper, we propose novel asynchronous FL framework, which well adapts...
Decentralized proactive caching and coded delivery is studied in a content network, where each user equipped with cache memory, not necessarily of equal capacity. Cache memories are filled advance during the off-peak traffic period decentralized manner, i.e., without knowledge number active users, their identities, or particular demands. User demands revealed peak period, served simultaneously through an error-free shared link. The goal to find minimum rate that sufficient satisfy all...
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, huge CSI feedback overhead becomes restrictive degrades overall spectral efficiency. In this paper, we propose deep learning based matrix compression scheme, called DeepCMC, composed of convolutional layers followed by quantization...
The novel 2019 Coronavirus (COVID-19) infection has spread worldwide and is currently a major healthcare challenge around the world. Chest computed tomography (CT) X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due faster imaging time considerably lower cost than CT, detecting in chest (CXR) preferred efficient diagnosis, assessment, treatment. However, considering similarity between pneumonia, CXR samples with deep features...
Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model further improve the efficiency of image transmission and protect private information. particular, transmitter extracts interpretable latent representation from original by exploiting GAN inversion method. We also employ privacy filter knowledge base erase information replace it with natural features base. The simulation...
Recently, there has been a growing interest in learning-based semantic communication because it can prioritize the preservation of meaningful information over accuracy transmitted symbols, resulting improved efficiency. However, existing approaches still face limitations defining level loss and often struggle to find good trade-off between preserving intricate details. In addition, cannot effectively train encoders decoders without support downstream models. To address these limitations,...
We consider the coded caching problem with a central server containing N files, each of length F bits, and K users, equipped cache capacity MF bits. assume that contents can be proactively placed into users' caches at no cost during placement phase. During delivery phase, user requests exactly one file from database, all are served simultaneously by over an error-free common link. The goal is to utilize local memories users reduce rate peak period. Here, we focus on system which has more...
Cache-aided coded content delivery is studied for devices with diverse quality-of-service requirements, specified by a different average distortion target. The network consists of server holding database independent contents, and users equipped local caches capacities. User are filled the during low traffic period without knowledge particular user demands. As opposed to current literature, which assumes that request files in their entirety, it assumed system have distinct requirements;...
Abstract The outbreak of coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome 2 (SARS-CoV-2) was initially reported in Wuhan, China since December, 2019. Here, we a timely and comprehensive resource named iCTCF to archive 256,356 chest computed tomography (CT) images, 127 types clinical features (CFs), laboratory-confirmed SARS-CoV-2 status from 1170 patients, reaching data volume 38.2 GB. To facilitate COVID-19 diagnosis, integrated the heterogeneous CT CF...
The RNA profiles of tumor-educated platelets (TEPs) possess pathological features that could be used for early cancer detection. However, the utility TEP profiling in detecting colorectal (CRC) versus noncancerous diseases has not yet been investigated. This study assesses diagnostic capacity a cohort patients with CRC and diseases.Transcriptome sequencing isolated from 132 at late stages 190 controls consisting healthy donors ulcerative disease, Crohn's polyps, adenomas was performed...
Semantic-oriented communication has been considered a promising method to boost bandwidth efficiency by only transmitting the semantics of data. In this paper, we propose multi-level semantic aware system for wireless image transmission, named MLSC-image, which is based on deep learning (DL) techniques and trained in an end-to-end manner. particular, proposed model includes multilevel feature extractor, that extracts both high-level information, such as text segmentation semantics, low-level...
Deep learning based approaches have achieved great success on the automatic cardiac image segmentation task. However, performance remains limited due to significant difference across domains, which is referred as domain shift. Unsupervised adaptation (UDA), a promising method mitigate this effect, trains model reduce discrepancy between source (with labels) and target (without domains in common latent feature space. In work, we propose novel framework, named Partial Unbalanced Feature...