With the rapid growth of the global population, diseases related to motor dysfunction, such as stroke, spinal cord injury, and other diseases related to motor dysfunction, are becoming an increasing challenge to public health. These diseases may lead to a series of functional declines such as cognitive impairment and emotional instability in patients, which seriously affects people's quality of life, and even endangers people's life and health, imposing heavy burdens on patients, families, and society. However, the pathogenesis of motor dysfunction-related diseases is complex, we currently lack effective and objective clinical diagnosis and intervention strategies. Artificial intelligence (AI) technology is developing rapidly, furthermore, it is attracting more attention from researchers and medical staff around the world in the brain-computer interface (BCI) and the clinical rehabilitation of motor dysfunction.
Nowadays, more and more researches focus on AI-assisted BCI diagnosis and intervention of these diseases. For example, in response to the scarcity of patient EEG data, researchers have used CycleGAN to augment the brain activity to expand the dataset, and the generated dataset could achieve better algorithm performance. Another example is that researchers have proposed a framework based on deep convolutional neural networks to decode attention information from EEG time series, and the average classification accuracy is better than traditional classification algorithms. Therefore, we believe AI can bring new insights into BCI and neurological diseases. The use of AI advances neuroprosthetics and BCI research to facilitate the rehabilitation of patients with various neurological diseases.
This Research Topic aims to explore the decoding of relevant attentional information from the brain and to build high-performance BCI systems by applying machine learning, deep learning, and other intelligent computing methods and models. In this Topic, we focus on collecting and studying the application of AI technology in the diagnosis and intervention of neurological diseases., and aim to find new algorithms, models, systems, and applications to facilitate the intersection of AI and neuroscience. As well as overcoming the various challenges of AI methods in disease research.
Topics of interest include but are not limited to:
• Efficient EEG feature extraction methods and pattern recognition models can help improve the performance of BCI systems
• Before and after BCI intervention leads to changes in brain functional mechanisms, particularly at the brain network level
• Systematic review of the application of AI in BCI and neurological disease intervention and rehabilitation
• New methods for decoding and mapping EEG/ECoG time series signals in various feature spaces
• Application of AI in neuroprosthetics and BCI
• Application of deep and/or reinforcement learning to neural computing
• Data processing and modeling for disease diagnosis, brain decoding, and neural computing
With the rapid growth of the global population, diseases related to motor dysfunction, such as stroke, spinal cord injury, and other diseases related to motor dysfunction, are becoming an increasing challenge to public health. These diseases may lead to a series of functional declines such as cognitive impairment and emotional instability in patients, which seriously affects people's quality of life, and even endangers people's life and health, imposing heavy burdens on patients, families, and society. However, the pathogenesis of motor dysfunction-related diseases is complex, we currently lack effective and objective clinical diagnosis and intervention strategies. Artificial intelligence (AI) technology is developing rapidly, furthermore, it is attracting more attention from researchers and medical staff around the world in the brain-computer interface (BCI) and the clinical rehabilitation of motor dysfunction.
Nowadays, more and more researches focus on AI-assisted BCI diagnosis and intervention of these diseases. For example, in response to the scarcity of patient EEG data, researchers have used CycleGAN to augment the brain activity to expand the dataset, and the generated dataset could achieve better algorithm performance. Another example is that researchers have proposed a framework based on deep convolutional neural networks to decode attention information from EEG time series, and the average classification accuracy is better than traditional classification algorithms. Therefore, we believe AI can bring new insights into BCI and neurological diseases. The use of AI advances neuroprosthetics and BCI research to facilitate the rehabilitation of patients with various neurological diseases.
This Research Topic aims to explore the decoding of relevant attentional information from the brain and to build high-performance BCI systems by applying machine learning, deep learning, and other intelligent computing methods and models. In this Topic, we focus on collecting and studying the application of AI technology in the diagnosis and intervention of neurological diseases., and aim to find new algorithms, models, systems, and applications to facilitate the intersection of AI and neuroscience. As well as overcoming the various challenges of AI methods in disease research.
Topics of interest include but are not limited to:
• Efficient EEG feature extraction methods and pattern recognition models can help improve the performance of BCI systems
• Before and after BCI intervention leads to changes in brain functional mechanisms, particularly at the brain network level
• Systematic review of the application of AI in BCI and neurological disease intervention and rehabilitation
• New methods for decoding and mapping EEG/ECoG time series signals in various feature spaces
• Application of AI in neuroprosthetics and BCI
• Application of deep and/or reinforcement learning to neural computing
• Data processing and modeling for disease diagnosis, brain decoding, and neural computing