A5059836848- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- IoT and Edge/Fog Computing
- Caching and Content Delivery
- Ubiquitin and proteasome pathways
- Internet Traffic Analysis and Secure E-voting
- Cancer-related Molecular Pathways
- Reinforcement Learning in Robotics
- Data Management and Algorithms
- Data Stream Mining Techniques
- Advanced Data Storage Technologies
- Age of Information Optimization
- Autophagy in Disease and Therapy
- Privacy-Preserving Technologies in Data
- Information Retrieval and Search Behavior
- Cell Image Analysis Techniques
- Domain Adaptation and Few-Shot Learning
- Metaheuristic Optimization Algorithms Research
- Peer-to-Peer Network Technologies
- Mobile Crowdsensing and Crowdsourcing
- Colorectal Cancer Surgical Treatments
- AI in cancer detection
- Energy Efficient Wireless Sensor Networks
- Image Processing Techniques and Applications
- Distributed Control Multi-Agent Systems
Wenzhou Medical University
2023-2025
First Affiliated Hospital of Wenzhou Medical University
2023-2025
Shenzhen Institutes of Advanced Technology
2021-2024
University of Chinese Academy of Sciences
2022-2024
Chinese Academy of Sciences
2021-2023
The University of Melbourne
2020
Data scarcity hinders the usability of data-dependent algorithms when tackling IoT intrusion detection (IID). To address this, we utilize data-rich network (NID) domain to facilitate more accurate for IID domains. In this article, a geometric graph alignment (GGA) approach is leveraged mask heterogeneities between domains better knowledge transfer. Specifically, each formulated as where vertices and edges represent categories category-wise inter-relationships, respectively. The overall shape...
Heterogeneous domain adaptation (HDA) transfers knowledge across source and target domains that present heterogeneities e.g., distinct distributions difference in feature type or dimension. Most previous HDA methods tackle this problem through learning a domain-invariant subspace to reduce the discrepancy between domains. However, intrinsic semantic properties contained data are under-explored such alignment strategy, which is also indispensable achieve promising adaptability. In paper, we...
In this article, we propose a joint semantic transfer network (JSTN) toward effective intrusion detection (ID) for large-scale scarcely labeled Internet of Things (IoT) domain. As multisource heterogeneous domain adaptation (MS-HDA) method, the JSTN integrates knowledge-rich (NI) and another small-scale IoT (II) as source domains preserves intrinsic properties to assist target II ID. The jointly transfers following three semantics learn domain-invariant discriminative feature representation....
A large volume of remote sensing (RS) data has been generated with the deployment satellite technologies. The facilitates research in ecological monitoring, land management and desertification, etc. characteristics RS (e.g., enormous volume, single-file size demanding requirement fault tolerance) make Hadoop Distributed File System (HDFS) an ideal choice for storage as it is efficient, scalable equipped a replication mechanism failure resilience. To use data, one most important techniques...
As Internet of Things (IoT) devices become prevalent, using intrusion detection to protect IoT from malicious intrusions is vital importance. However, the data scarcity hinders effectiveness traditional methods. To tackle this issue, in article, we propose adaptive bi-recommendation and self-improving network (ABRSI) based on unsupervised heterogeneous domain adaptation (HDA). The ABRSI transfers enrich knowledge a data-rich source facilitate effective for data-scarce target domains....
Abstract Current research on DNA storage usually focuses the improvement of density by developing effective encoding and decoding schemes while lacking consideration uncertainty in ultra-long-term data retention. Consequently, current systems are often not self-contained, implying that they have to resort external tools for restoration stored data. This may result high risks loss since required might be available due far future. To address this issue, we propose paper a self-contained system...
With the fast growth of mobile edge computing (MEC), deep neural network (DNN) has gained more opportunities in application to various services. Given tremendous number learning parameters and large model size, DNN is often trained cloud center then dispatched end devices for inference via network. Therefore, maximizing cost-efficiency learned dispatch would be a critical problem serving contexts. To reach this goal, article we focus mainly on reducing total cost while maintaining efficiency...
With the fast growing quantity of data generated by smart devices and exponential surge processing demand in Internet Things (IoT) era, resource-rich cloud centres have been utilised to tackle these challenges. To relieve burden on centres, edge-cloud computation offloading becomes a promising solution since shortening proximity between source tasks from edge can improve performance Quality Service (QoS). Several optimisation models proposed that take costs heterogeneous communication into...
As one of the most useful online processing techniques, theta-join operation has been utilized by many applications to fully excavate relationships between data streams in various scenarios. such, constant research efforts have put optimize its performance distributed environment, which is typically characterized reducing number Cartesian products as much possible. In this article, we design and implement a novel fast algorithm, called Prefap, developing two distinct techniques -...
In this paper, we study a data caching problem in the cloud environment, where multiple frequently co-utilised items could be packed as single item being transferred to serve sequence of requests dynamically with reduced cost. To end, propose an online algorithm respect homogeneous cost model, called PackCache, that can leverage FP-Tree technique mine those for packing whereby incoming cost-effectively served by exploiting concept anticipatory caching. We show is 2\alpha competitive,...
As Internet of Things devices become widely used in the real-world, it is crucial to protect them from malicious intrusions. However, data scarcity IoT limits applicability traditional intrusion detection methods, which are highly data-dependent. To address this, this article, we propose Open-Set Dandelion Network (OSDN) based on unsupervised heterogeneous domain adaptation an open-set manner. The OSDN model performs knowledge transfer knowledge-rich source network facilitate more accurate...
<title>Abstract</title> Metastasis is a major challenge for colorectal cancer (CRC) treatment. Here, we uncovered CENPF may be involved in CRC metastasis through bioinformatics mining and small interfering RNA (siRNA) targeted functional screening. We observed expression was preferentially increased tissues compared to adjacent normal tissues. More importantly, multicenter cohort study identified upregulated significantly correlated with poor survival CRC. Knockdown of inhibited cell...
Summary As the capacity of Solid‐State Drives (SSDs) is constantly being optimised and boosted with gradually reduced cost, SSD cluster now widely deployed as part hybrid storage system in various scenarios such cloud computing big data processing. However, despite its rapid developments, performance remains largely under‐investigated, leaving sub‐optimal applications reality. To address this issue, paper we conduct extensive empirical studies for a comprehensive understanding diverse...
As IoT devices become widely, it is crucial to protect them from malicious intrusions. However, the data scarcity of limits applicability traditional intrusion detection methods, which are highly data-dependent. To address this, in this paper we propose Open-Set Dandelion Network (OSDN) based on unsupervised heterogeneous domain adaptation an open-set manner. The OSDN model performs knowledge transfer knowledge-rich source network facilitate more accurate for data-scarce target domain. Under...
Over the past decades, researchers had put lots of effort investigating ranking techniques used to rank query results retrieved during information retrieval, or recommended products in recommender systems. In this project, we aim investigate searching, ranking, as well recommendation help realize a university academia searching platform. Unlike usual retrieval scenarios where ground truth data is present, our case, have only limited knowledge regarding ranking. For instance, given some...