Xin Liu

Dr. Xin Liu

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 July 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LFLei Fu
Lei Fu
HZHuanle Zhang
Huanle Zhang
GGGe Gao
Ge Gao
MZMi Zhang
Mi Zhang
XLXin Liu
Xin Liu
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. Thus, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement. In this paper, we systematically present recent advances in the emerging field of FL client selection and its challenges and research opportunities. We hope to facilitate practitioners in choosing the most suitable client selection mechanisms for their applications, as well as inspire researchers and newcomers to better understand this exciting research topic.

24 December 2019 in IEEE Access
Verified
Journal Article
Open access
SRShahbaz Rezaei
Shahbaz Rezaei
BKBryce Kroencke
Bryce Kroencke
XLXin Liu
Xin Liu
Many network services and tools (e.g. network monitors, malware-detection systems, routing and billing policy enforcement modules in ISPs) depend on identifying the type of traffic that passes through the network. With the widespread use of mobile devices, the vast diversity of mobile apps, and the massive adoption of encryption protocols (such as TLS), large-scale encrypted traffic classification becomes increasingly difficult. In this paper, we propose a deep learning model for mobile app identification that works even with encrypted traffic. The proposed model only needs the payload of the first few packets for classification, and, hence, it is suitable even for applications that rely on early prediction, such as routing and QoS provisioning. The deep model achieves between 84% to 98% accuracy for the identification of 80 popular apps. We also perform occlusion analysis to bring insight into what data is leaked from SSL/TLS protocol that allows accurate app identification. Moreover, our traffic analysis shows that many apps generate not only app-specific traffic, but also numerous ambiguous flows. Ambiguous flows are flows generated by common functionality modules, such as advertisement and traffic analytics. Because such flows are common among many different apps, identifying the source app that generates ambiguous flows is challenging. To address this challenge, we propose a CNN+LSTM model that uses adjacent flows to learn the order and pattern of multiple flows, to better identify the app that generates them. We show that such flow association considerably improves the accuracy, particularly for ambiguous flows. Furthermore, we show that our approach is robust to mixed traffic scenarios where some unrelated flows may appear in adjacent flows. To the best of our knowledge, this is the first work that identifies the source app for ambiguous flows.

8 June 2023 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
DXDa Xiao
Da Xiao
AZAndrew Zhang
Andrew Zhang
XLXin Liu
Xin Liu
YQYiwen Qu
Yiwen Qu
WNWei Ni
Wei Ni
Ren Ping LiuRen Ping Liu
Ren Ping Liu
Network Function Virtualization (NFV), which decouples network functions from hardware and transforms them into Virtual Network Functions (VNFs), is a crucial technology for data center (DC) networks. A service function chain (SFC) is composed of an ordered set of VNFs and virtual links (VLs) connecting them. To optimize the resource allocation in DC networks, we need to efficiently map SFCs onto the physical network. Nevertheless, the dynamics and diversity of SFC requests in multi-datacenter (MDC) networks pose a significant challenge in embedding SFCs. To overcome this challenge, we design a two-stage graph convolutional network (GCN) assisted deep reinforcement learning (DRL) scheme. This framework aims to maximize the overall acceptance ratio of SFC requests while minimizing the total cost in an MDC network. In the first stage, we propose a GCN-based DRL algorithm as a coarse granularity solution to the SFC embedding problem from the macro perspective. This solution outlines a local observation scope (LOS) for each agent in the multi-agent system of the second stage, where all agents simultaneously handle SFC requests from their respective DCs using a multi-agent framework from the micro perspective. Numerical evaluations show that, compared to state-of-the-art methods, the proposed scheme improves the acceptance ratio by approximately 13% compared with the Kolin algorithm and 18% compared with the DQN algorithm and saves the cost by around 28% compared with the Kolin and the DQN.

1 December 2021
Verified
Conference Paper
Closed access
WLWei Liu
Wei Liu
GZGuangda Zhuang
Guangda Zhuang
XLXin Liu
Xin Liu
SHShaobo Hu
Shaobo Hu
RHRuilin He
Ruilin He
YWYuhu Wang
Yuhu Wang
At present, the development of artificial intelligence technology has entered a new bottleneck period, and the algorithm dividend based on statistics has been exhausted. In the future, we should pay more attention to improving the efficient, intelligent collaboration among humans, machines, and the environment. This review first discusses the bottleneck problems encountered in the current artificial intelligence technology, then analyzes the essence of human intelligence and the differences, advantages, and disadvantages of the current machine intelligence and human intelligence. Based on this, it puts forward that the enhancement point of artificial intelligence technology is to enhance the efficient cooperation of the human-computer environment and states our solution, namely the deep situation awareness method based on human-computer integration technology. In the end, we put forward some thoughts about intelligence.

20 September 2024 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
DLDan Luo
Dan Luo
RLRong Luo
Rong Luo
JCJie Cheng
Jie Cheng
XLXin Liu
Xin Liu
The grading of products is important in many ways. One of the important activities after harvesting agricultural products is product grading based on shape and color dimensions. This activity in the agricultural transformation industries, Bas Controller, improves various processes on fruits and vegetables with the same dimensions, which improves the storage conditions of the product, creates added value for the farmer, and gives the consumer the power to choose. The main focus of this study is the application of image processing in the field of identification and classification of fruits. It is an application that has received much less attention than other applications of image processing. The proposed systems presented in this article, are software solutions based on image processing techniques, including histogram matching techniques, for detection, Sable edge detection algorithms, Private edge and Kenny edge, Otsu threshold limit, and clustering method It is an automatic mean and classification of different degrees of fruit. In addition, it has been mentioned more about the examination and description of product grading and clustering methods, that by using the proposed application hardware and its connection with the software, a big step can be taken in product quality grading. This method can be used in product classification and packaging. The accuracy rate for peaches, lemons, apples, and tomatoes is 94.58%, 88.23%, 70%, and 93.33%, respectively. The best accuracy for all 20 sample levels is for peach fruit.

20 April 2008 in Mobile Networks and Applications
Verified
Journal Article
Closed access
PDF file
HYHua Yu
Hua Yu
PMPrasant Mohapatra
Prasant Mohapatra
XLXin Liu
Xin Liu