A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding

Liu, Xi; Chen, Shuhang; Shen, Xiang; Zhang, Xiang; Wang, Yiwen

doi:10.3390/e23060743

Cited by 5 publications

(2 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…References [6] and [7] proposed that MCC as an appraisal criterion to replace MSE can improve prediction accuracy to varying degrees. Therefore, according to Equation (2), the maximum correntropy is simplified as…”

Section: Maximum Correlation Entropymentioning

confidence: 99%

Short period Wind Power Forecast Method Based on Maximum Correntropy Criterion

Liu¹,

Zheng²,

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Wind power forecast is an essential measure to increase the level of wind velocity consumption and also the basis of wind power dispatching operations. In the cause of increasing the precision of short-period wind velocity forecast, this srticle adopts a new evaluation criterion(MCC) in order to direct optimization of the parameters of the wind power model. The method first filters and normalizes the measured historical data and determines the optimal input variable dimension through a set of fixed parameters. Then, grid optimization and Particle Swarm Optimization (PSO) are used as evaluation criteria for parameter optimization. Finally, the obtained optimal parameters are used to forecast the short-term wind power, and four evaluation indexes are used to evaluate the forecasting results. The results show that the parameter optimization process using MCC as the evaluation criterion is more suitable for wind power output characteristics, and comparing with traditional optimisic methodthe the forecast accuracy is increased by 5 -10%.

show abstract

Section: Maximum Correlation Entropymentioning

confidence: 99%

Short period Wind Power Forecast Method Based on Maximum Correntropy Criterion

Liu¹,

Zheng²,

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…And 𝜃 𝑡 is the parameter of CKRL prior to the current time 𝑡 , which contains the previous neural activities 𝑢 𝑖 and the corresponding weights 𝛼 𝑖𝑥 . Given the state approximation from CKRL, the next step is to update the posterior prosthetic state in the form of information filter [39] as follows…”

Section: ) Adaptive Decoding During the Brain Control Processmentioning

confidence: 99%

Kernel Reinforcement Learning-Assisted Adaptive Decoder Facilitates Stable and Continuous Brain Control Tasks

Zhang,

Chen,

Wang

2023

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Brain-Machine Interfaces (BMIs) assist paralyzed people to brain control (BC) the neuro-prosthesis continuously moving in space. During the BC process, the subject imagines the movement of the real limb and adapts the brain activity according to the sensory feedback. The neural adaptation in the closed-loop control results in complex and changing brain signals. Simultaneously, the decoder interprets the time-varying functional mapping between neural activity and continuous trajectory. It is crucial and challenging to accurately and adaptively track the mapping to help the subject accomplish the BC task with a stable performance. Existing Kalman Filter (KF) based decoders achieve continuous trajectory control by linearly interpreting neural firing observations into self-evolving prosthetic states. However, the linear neural-state mapping might not accurately reflect the movement intention of the subject. In this paper, we propose a novel method that allows subjects to achieve continuous brain control efficiently and stably. The proposed method incorporates a kernel reinforcement learning method into a state-observation model to decode the nonlinearly neural observation into a continuous trajectory state. The state transition function ensures the continuity of the prosthetic state. The kernel reinforcement learning allows the quick adaptation of the nonlinear neural-movement mapping during the BC process. The proposed method is tested in an online brain control reaching task for rats. Compared with KF, our method achieved more successful trials, faster response time, shorter inter-trial time, and remained stable over days. These results demonstrate that the proposed method is an efficient tool to assist subjects in brain control tasks.

show abstract

Comparative Performance Analysis for Maximum Segmented Accuracy in Voice Stammer using Wiener Filter and Gaussian Filter Recognition

Priyadarshini

CharlynPushpaLatha

2022

2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N)

View full text Add to dashboard Cite

A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding

Cited by 5 publications

References 68 publications

Short period Wind Power Forecast Method Based on Maximum Correntropy Criterion

Short period Wind Power Forecast Method Based on Maximum Correntropy Criterion

Kernel Reinforcement Learning-Assisted Adaptive Decoder Facilitates Stable and Continuous Brain Control Tasks

Comparative Performance Analysis for Maximum Segmented Accuracy in Voice Stammer using Wiener Filter and Gaussian Filter Recognition

Contact Info

Product

Resources

About