LHLisha Hu

Lisha Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lisha Hu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Online Support Vector Machine with a Single Pass for Streaming Data

    by Lisha Hu, Chunyu Hu, Zheng Huo, Xinlong Jiang, 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.


  • Open Access

    Game-Theory-Based Task Offloading and Resource Scheduling in Cloud-Edge Collaborative Systems

    by Suzhen Wang, Zhongbo Hu, Yongchen Deng, 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.


  • Open Access

    Stratified Transfer Learning for Cross-domain Activity Recognition

    by Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, 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.