Hao Tang

Prof. Hao Tang


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
9 November 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SWShurun Wang
Shurun Wang
HTHao Tang
Hao Tang
BWBin Wang
Bin Wang
JMJia Mo
Jia Mo
Muscle fatigue detection is of great significance to human physiological activities, but many complex factors increase the difficulty of this task. In this article, we integrate several effective techniques to distinguish muscle states under fatigue and nonfatigue conditions via surface electromyography (sEMG) signals. First, we perform an isometric contraction experiment of biceps brachii to collect sEMG signals. Second, we propose a neural architecture search (NAS) framework based on reinforcement learning to autogenerate neural networks. Finally, we present an effective two-step training strategy to improve the performance by combining CNN with three types of commonly used statistical algorithms. Meanwhile, we propose a data enhancement algorithm based on empirical mode decomposition (EMD) to generate time-series data for expanding the dataset. The results show that this search algorithm can hunt for high-performing networks, and the accuracy of the best-selected model combined with support vector machine (SVM) for the group is 96.5%. With the same architecture, the average accuracy in individual models is 97.8%. The proposed data enhancement technique can effectively improve the fatigue detection performance, which allows further implementations in the human-exoskeleton interaction systems.

1 January 2020 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Hai WangHai Wang
Hai Wang
CMChunlong Mi
Chunlong Mi
ZCZhenwei Cao
Zhenwei Cao
Jinchuan ZhengJinchuan Zheng
Jinchuan Zheng
ZMZhihong Man
Zhihong Man
HTHao Tang
Hao Tang
In this article, a novel dynamic model of robotic fish with the data-assisted method is established and a discrete-time super-twisting-like controller (DTSTC) is proposed to effectively control the steering for a robotic fish. Although the thrust of the robotic fish is generated by the body motion in surrounding water environment, it is rather difficult to model the hydrodynamics in practice. Therefore, the data-assisted modelling method is applied where the reaction force generated by the yawing of fish head is also considered to obtain a more accurate model. The DTSTC is then designed to achieve robust steering control performance against system uncertainties. The experimental results are presented in support of the effectiveness and excellent performance of the proposed steering control scheme of the robotic fish.

18 April 2021 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
HTHao Tang
Hao Tang
KLKai Lv
Kai Lv
BBBirgitte Bak-Jensen
Birgitte Bak-Jensen
JPJayakrishnan Radhakrishna Pillai
Jayakrishnan Radhakrishna Pillai
ZWZhengfeng Wang
Zhengfeng Wang

15 April 2020 in IEEE Access
Verified
Journal Article
Open access
YLYijin Li
Yijin Li
HTHao Tang
Hao Tang
KLKai Lv
Kai Lv
KWKe Wang
Ke Wang
GWGang Wang
Gang Wang
The integrated energy system (IES) with various energy demands and distributed energy resources has been a significant approach to improve the efficiency of energy utilization. Considering the uncertainties of renewable energy sources and loads, the energy dispatch optimization for multiarea IESs is studied in this paper. Different from the most current studies, not only the electrical power and heat distribution in each area is optimized, but also the coordination power dispatch between areas. A hierarchical learning method is proposed inhere to improve the operation performance of the multiarea IESs. The proposed method with data-driven way is a model-free method which has no requirement for the accurate mathematical model. With the hierarchical structure, the electrical power dispatched between areas is optimized in upper layer, together with the dispatching optimization in each area at lower layer, to decrease the operation cost for the system and power demand from the power grid. Finite horizon discrete dynamic process model is adopted to simulate the data for learning. The simulation results show the effectiveness of the optimization policy can achieve an economic and stable operation for the multiarea IES.

16 August 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
SWShurun Wang
Shurun Wang
HTHao Tang
Hao Tang
LGLifu Gao
Lifu Gao
QTQi Tan
Qi Tan
Intention recognition based on surface electromyography (sEMG) signals is pivotal in human-machine interaction (HMI), where continuous motion estimation with high accuracy has been the challenge. The convolutional neural network (CNN) possesses excellent feature extraction capability. Still, it is difficult for ordinary CNN to explore the dependencies of time-series data, so most researchers adopt the recurrent neural network or its variants (e.g., LSTM) for motion estimation tasks. This paper proposes a multi-feature temporal convolutional attention-based network (MFTCAN) to recognize joint angles continuously. First, we recruited ten subjects to accomplish the signal acquisition experiments in different motion patterns. Then, we developed a joint training mechanism that integrates MFTCAN with commonly used statistical algorithms, and the integrated architectures were named MFTCAN-KNR, MFTCAN-SVR and MFTCAN-LR. Last, we utilized two performance indicators (RMSE and $\text{R}^{2}$) to evaluate the effect of different methods. Moreover, we further validated the performance of the proposed method on the open dataset (Ninapro DB2). When evaluating on the original dataset, the average RMSE of the estimations obtained by MFTCAN-KNR is 0.14, which is significantly less than the results obtained by LSTM (0.20) and BP (0.21). The average $\text{R}^{2}$ of the estimations obtained by MFTCAN-KNR is 0.87, indicating the anti-disturbance ability of the architecture. Moreover, MFTCAN-KNR also achieves high performance when evaluating on the open dataset. The proposed methods can effectively accomplish the task of motion estimation, allowing further implementations in the human-exoskeleton interaction systems.

21 October 2021 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
JGJinyu Guan
Jinyu Guan
HTHao Tang
Hao Tang
JWJiye Wang
Jiye Wang
JYJianguo Yao
Jianguo Yao
KWKe Wang
Ke Wang
WMWenbo Mao
Wenbo Mao
In order to reduce the dependence on accumulated experience that is difficult to replicate for the human dispatchers to make power generation scheduling more automatically, quickly, and intelligently, higher requirements are placed on the level of the auxiliary decision-making system. In this paper, a short-term scheduling problem was treated as a regression task that concentrates on how to learn a reliable statistic model that concludes the intrinsic logic of the dispatching policy from extensive historical dispatching experience. In this way, since Kullback-Leibler distance can better measure the distance between two distributions, we designed a novel GAN-based learning method for the scheduling task. Also, we proposed a feasible framework that combines the stage of learning, decision-making, and deployment to support the practical implementation of the proposed algorithm. In the experiment, a real case that takes short-term scheduling tasks on a regional large-scale power system is considered in our experiments. As a result, the comparison of several methods further shows the superiority of the proposed GAN-based method under our implementations.