no code implementations • 22 Dec 2023 • Yin Luo, Qingchao Kong, Nan Xu, Jia Cao, Bao Hao, Baoyu Qu, Bo Chen, Chao Zhu, Chenyang Zhao, Donglei Zhang, Fan Feng, Feifei Zhao, Hailong Sun, Hanxuan Yang, Haojun Pan, Hongyu Liu, Jianbin Guo, Jiangtao Du, Jingyi Wang, Junfeng Li, Lei Sun, Liduo Liu, Lifeng Dong, Lili Liu, Lin Wang, Liwen Zhang, Minzheng Wang, Pin Wang, Ping Yu, Qingxiao Li, Rui Yan, Rui Zou, Ruiqun Li, Taiwen Huang, Xiaodong Wang, Xiaofei Wu, Xin Peng, Xina Zhang, Xing Fang, Xinglin Xiao, Yanni Hao, Yao Dong, Yigang Wang, Ying Liu, Yongyu Jiang, Yungan Wang, Yuqi Wang, Zhangsheng Wang, Zhaoxin Yu, Zhen Luo, Wenji Mao, Lei Wang, Dajun Zeng
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence.
no code implementations • 30 Nov 2022 • Fan Li, Bo wang, Pin Wang, Yongming Li
Secondly, according to the characteristics of subset classes, a stage-wise hybrid sampling algorithm is designed to realize the de-overlapping and balancing of subsets.
no code implementations • 25 Oct 2022 • Chuanyan Zhou, Jie Ma, Fan Li, Yongming Li, Pin Wang, Xiaoheng Zhang
Second, an embedded stack autoencoder (ESAE) is proposed and trained in each layer of sample space to consider the original samples during training and in the network structure, thereby better finding the relationship between original feature samples and deep feature samples.
no code implementations • 25 Jun 2022 • Fan Li, Xiaoheng Zhang, Yongming Li, Pin Wang
Based on the analysis above, an imbalanced ensemble algorithm with the deep sample pre-envelope network (DSEN) and local-global structure consistency mechanism (LGSCM) is proposed here to solve the problem. This algorithm can guarantee high-quality deep envelope samples for considering the local manifold and global structures information, which is helpful for imbalance learning.
no code implementations • 17 Nov 2021 • Yiwen Wang, Fan Li, Xiaoheng Zhang, Pin Wang, Yongming Li
Therefore, it is necessary to reconstruct the existing large segments within one subject into few segments even one segment within one subject, which can facilitate the extraction of relevant speech features to characterize diagnostic markers for the whole subject.
no code implementations • 2 Nov 2021 • Fan Li, Xiaoheng Zhang, Pin Wang, Yongming Li
However, all existing clustering methods are based on a one-time approach.
no code implementations • 29 Sep 2021 • Yuke Li, Kenneth Li, Pin Wang, Donglai Wei, Hanspeter Pfister, Ching-Yao Chan
Non-stationary casual structures are prevalent in real-world physical systems.
no code implementations • 23 Aug 2021 • Yongming Li, Chengyu Liu, Pin Wang, Hehua Zhang, Anhai Wei
The results show that the proposed algorithm is effective.
no code implementations • 9 Aug 2021 • Mingfeng Jiang, Minghao Zhi, Liying Wei, Xiaocheng Yang, Jucheng Zhang, Yongming Li, Pin Wang, Jiahao Huang, Guang Yang
High-resolution magnetic resonance images can provide fine-grained anatomical information, but acquiring such data requires a long scanning time.
no code implementations • 29 May 2021 • Fei Ye, Shen Zhang, Pin Wang, Ching-Yao Chan
In this survey, we systematically summarize the current literature on studies that apply reinforcement learning (RL) to the motion planning and control of autonomous vehicles.
no code implementations • 23 Mar 2021 • Pin Wang, Hanhan Li, Ching-Yao Chan
Therefore, it is desirable for the trained model to adapt to new tasks that have limited data samples available.
no code implementations • 11 Mar 2021 • Fan Li, Yongming Li, Pin Wang, Jie Xiao, Fang Yan, Xinke Li
Traditional age estimation mechanism focuses estimation age error, but ignores that there is a deviation between the estimated age and real age due to disease.
no code implementations • 28 Aug 2020 • Fei Ye, Pin Wang, Ching-Yao Chan, Jiucai Zhang
The simulation results shows that the proposed method achieves an overall success rate up to 20% higher than the benchmark model when it is generalized to the new environment of heavy traffic density.
no code implementations • 20 Jun 2020 • Yongming Li, Lang Zhou, Lingyun Qin, Yuwei Zeng, Yuchuan Liu, Yan Lei, Pin Wang, Fan Li
To solve these two problems, based on the existing Parkinson speech feature data set, a deep double-side learning ensemble model is designed in this paper that can reconstruct speech features and samples deeply and simultaneously.
no code implementations • 17 Feb 2020 • Yongming Li, Yan Lei, Pin Wang, Yuchuan Liu
For the issue that class representation ability of abstract information is limited by small sample problem, a feature fusion strategy has been designed aiming to combining abstract information learned by HFESAE with original feature and obtain hybrid features for feature reduction.
no code implementations • 10 Feb 2020 • Xiaoheng Zhang, Yongming Li, Pin Wang, Xiaoheng Tan, Yuchuan Liu
In this paper, a novel PD classification algorithm based on sparse kernel transfer learning combined with a parallel optimization of samples and features is proposed.
no code implementations • 7 Feb 2020 • Fei Ye, Xuxin Cheng, Pin Wang, Ching-Yao Chan, Jiucai Zhang
The simulation results demonstrate the lane change maneuvers can be efficiently learned and executed in a safe, smooth, and efficient manner.
no code implementations • 4 Feb 2020 • Hanhan Li, Pin Wang
In recent years, video analysis tools for automatically extracting meaningful information from videos are widely studied and deployed.
no code implementations • 4 Feb 2020 • Biao Yang, Caizhen He, Pin Wang, Ching-Yao Chan, Xiaofeng Liu, Yang Chen
A latent variable predictor is proposed to estimate latent variable distributions from observed and ground-truth trajectories.
no code implementations • 2 Feb 2020 • Biao Yang, Guocheng Yan, Pin Wang, Ching-Yao Chan, Xiang Song, Yang Chen
Recent studies focus on modeling pedestrians' motion patterns with recurrent neural networks, capturing social interactions with pooling-based or graph-based methods, and handling future uncertainties by using random Gaussian noise as the latent variable.
no code implementations • 29 Nov 2019 • Pin Wang, Hanhan Li, Ching-Yao Chan
Reinforcement Learning algorithms have recently been proposed to learn time-sequential control policies in the field of autonomous driving.
no code implementations • 19 Nov 2019 • Pin Wang, Dapeng Liu, Jiayu Chen, Hanhan Li, Ching-Yao Chan
Simulation results show that the augmented AIRL outperforms all the baseline methods, and its performance is comparable with that of the experts on all of the four metrics.
no code implementations • 6 Jun 2019 • Long Xin, Pin Wang, Ching-Yao Chan, Jianyu Chen, Shengbo Eben Li, Bo Cheng
As autonomous vehicles (AVs) need to interact with other road users, it is of importance to comprehensively understand the dynamic traffic environment, especially the future possible trajectories of surrounding vehicles.
no code implementations • 5 Jun 2019 • Pin Wang, Hanhan Li, Ching-Yao Chan
Lane change is a challenging task which requires delicate actions to ensure safety and comfort.
no code implementations • 23 Apr 2019 • Tianyu Shi, Pin Wang, Xuxin Cheng, Ching-Yao Chan, Ding Huang
We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver.
no code implementations • 31 Jan 2019 • Tianyu Shi, Pin Wang, Ching-Yao Chan, Chonghao Zou
A reliable controller is critical and essential for the execution of safe and smooth maneuvers of an autonomous vehicle. The controller must be robust to external disturbances, such as road surface, weather, and wind conditions, and so on. It also needs to deal with the internal parametric variations of vehicle sub-systems, including power-train efficiency, measurement errors, time delay, so on. Moreover, as in most production vehicles, the low-control commands for the engine, brake, and steering systems are delivered through separate electronic control units. These aforementioned factors introduce opaque and ineffectiveness issues in controller performance. In this paper, we design a feed-forward compensate process via a data-driven method to model and further optimize the controller performance. We apply the principal component analysis to the extraction of most influential features. Subsequently, we adopt a time delay neural network and include the accuracy of the predicted error in a future time horizon. Utilizing the predicted error, we then design a feed-forward compensate process to improve the control performance. Finally, we demonstrate the effectiveness of the proposed feed-forward compensate process in simulation scenarios.
no code implementations • 25 Mar 2018 • Pin Wang, Ching-Yao Chan
Most importantly, in contrast to most reinforcement learning applications in which the action space is resolved as discrete, our approach treats the action space as well as the state space as continuous without incurring additional computational costs.
no code implementations • 7 Sep 2017 • Pin Wang, Ching-Yao Chan
To tackle such a complicated control problem, we propose to apply Deep Reinforcement Learning (DRL) techniques for finding an optimal driving policy by maximizing the long-term reward in an interactive environment.