Lisha Hu

Dr. Lisha Hu


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
17 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SWSuzhen Wang
Suzhen Wang
ZHZhongbo Hu
Zhongbo Hu
YDYongchen Deng
Yongchen Deng
LHLisha Hu
Lisha Hu
Task offloading and resource allocation are the major elements of edge computing. A reasonable task offloading strategy and resource allocation scheme can reduce task processing time and save system energy consumption. Most of the current studies on the task migration of edge computing only consider the resource allocation between terminals and edge servers, ignoring the huge computing resources in the cloud center. In order to sufficiently utilize the cloud and edge server resources, we propose a coarse-grained task offloading strategy and intelligent resource matching scheme under Cloud-Edge collaboration. We consider the heterogeneity of mobile devices and inter-channel interference, and we establish the task offloading decision of multiple end-users as a game-theory-based task migration model with the objective of maximizing system utility. In addition, we propose an improved game-theory-based particle swarm optimization algorithm to obtain task offloading strategies. Experimental results show that the proposed scheme outperforms other schemes with respect to latency and energy consumption, and it scales well with increases in the number of mobile devices.

30 August 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
LHLisha Hu
Lisha Hu
CHChunyu Hu
Chunyu Hu
ZHZheng HUO
Zheng HUO
XJXinlong Jiang
Xinlong Jiang
SWSuzhen Wang
Suzhen Wang
In this paper, we focus on training a support vector machine (SVM) online with a single pass over streaming data.Traditional batch-mode SVMs require previously prepared training data; these models may be unsuitable for streaming data circumstances. Online SVMs are effective tools for solving this problem by receiving data streams consistently and updating model weights accordingly. However, most online SVMs require multiple data passes before the updated weights converge to stable solutions, and may be unable to address high-rate data streams. This paper presents OSVM_SP, a new online SVM with a single pass over streaming data, and three budgeted versions to bound the space requirement with support vector removal principles. The experimental results obtained with five public datasets show that OSVM_SP outperforms most state-of-the-art single-pass online algorithms in terms of accuracy and is comparable to batch-mode SVMs. Furthermore, the proposed budgeted algorithms achieve comparable predictive performance with only 1/3 of the space requirement.

25 December 2017 in arXiv
Verified
Preprint
Open access
PDF file
JWJindong Wang
Jindong Wang
YCYiqiang Chen
Yiqiang Chen
LHLisha Hu
Lisha Hu
XPXiaohui Peng
Xiaohui Peng
PYPhilip S. Yu
Philip S. Yu
In activity recognition, it is often expensive and time-consuming to acquire sufficient activity labels. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labels. Existing approaches typically consider learning a global domain shift while ignoring the intra-affinity between classes, which will hinder the performance of the algorithms. In this paper, we propose a novel and general cross-domain learning framework that can exploit the intra-affinity of classes to perform intra-class knowledge transfer. The proposed framework, referred to as Stratified Transfer Learning (STL), can dramatically improve the classification accuracy for cross-domain activity recognition. Specifically, STL first obtains pseudo labels for the target domain via majority voting technique. Then, it performs intra-class knowledge transfer iteratively to transform both domains into the same subspaces. Finally, the labels of target domain are obtained via the second annotation. To evaluate the performance of STL, we conduct comprehensive experiments on three large public activity recognition datasets~(i.e. OPPORTUNITY, PAMAP2, and UCI DSADS), which demonstrates that STL significantly outperforms other state-of-the-art methods w.r.t. classification accuracy (improvement of 7.68%). Furthermore, we extensively investigate the performance of STL across different degrees of similarities and activity levels between domains. And we also discuss the potential of STL in other pervasive computing applications to provide empirical experience for future research.