via Stable Diffusion
Research team led by Professor Sanghyun Park of DGIST has contributed to realizing AI medical services by developing a brain wave classification deep-learning model
– Research team led by Professor Sanghyun Park at DGIST developed a deep-learning technology capable of accurately classifying the brain waves of a subject using only a small amount of data
– Contributes significantly to improving the utilization of deep-learning models, which require a large amount of data from subjects to classify brain waves
– Research findings have been published in IEEE Transactions on Neural Networks and Learning Systems, a world-renowned academic journal in the AI field
The research team led by Professor Sanghyun Park from the Department of Robotics and Mechanical Engineering at DGIST (President Kuk Yang) announced that they have developed a few-shot learning model capable of accurately classifying brain waves using a small amount of information. A large amount of brain wave data[1] collected from target subjects is needed for classifying new brain waves using existing deep-learning models; however, the newly developed deep-learning model is capable of accurately classifying brain waves even with a small amount of data, which may contribute to future research related to brain waves.
Brain wave data vary significantly by person. The distribution of brain waves differs by performer even when the same task is performed; thus, most existing classification models collect data from performers and label them to be used for training, focusing only on intra-subject classification. Therefore, the brain waves of a person who did not participate in the training could not be classified using those classification models.
To overcome this drawback, research has been actively conducted on “domain adaptation” models in which deep-learning models are used to infer the brain wave signals of a target subject; however, the problem remains where the models cannot be easily applied to new subjects because they need to learn the brain wave data of those subjects as well. Furthermore, other studies are being conducted on the optimization of transfer learning models where brain wave data collected from multiple individuals are trained, but their usability is rather low since a large amount of brain wave data is still required.
The research team led by Professor Park thus developed a new deep-learning model capable of accurately classifying brain waves according to the brain wave characteristics of each subject when the ground truth of a small amount of data is given from the brain wave data obtained from target subjects. For effectively learning the relation between a small amount of data and the remaining brain waves, meaningful features are first extracted from the brain wave data by using the embedding module[2], and then the temporal attention module[3] is used to highlight important features from the extracted features while reducing unnecessary noise.
Subsequently, the aggregation attention module[4] is used to find only important data from the given brain wave data to identify the features of the target subject’s intention as represented in the brain waves. Lastly, the relation module[5] is used to calculate the relation between brain wave features and vectors. Also, brain wave classification fine-tuning technology was developed to ensure that brain waves are accurately classified through optimization.
The deep-learning model newly developed by the research team exhibited up to 76% classification accuracy for the intention of a target subject using 20 brain wave data points in inter-subject classification. Considering that the accuracy of previously proposed methods (intra-subject classification, transfer learning, and other few-shot learning methods) is 64–73%, the newly developed model demonstrated superior performance.
Professor Park said, “The brain wave classification deep-learning model developed in this study is capable of accurately classifying brain wave with only a small amount of information, without having to newly build learning data from subjects, and therefore, it is expected to contribute to other related research on brain waves requiring individualization.” He further added, “Our technology will be further enhanced to be more universally utilized in various biosignal analyses.”
This research was supported by the “Intelligent big data integrated platform development project for customized health management services of police officers” of the Korean National Police Agency and the “Commercialization project of immersive human robot multi-sensory exchange technology” of DGIST. The findings were published in IEEE Transactions on Neural Networks and Learning Systems, which is a world-renowned academic journal in the AI field.
Original Article: A brain wave classification deep-learning model
More from: Daegu Gyeongbuk Institute of Science and Technology
The Latest Updates from Bing News
Go deeper with Bing News on:
Brain wave data
- Are Your Brain Waves For Sale?
Companies quietly selling customer data has been in the news lately. Could your brain activity be their next product?
- New Products Collect Data From Your Brain. Where Does It Go?
An array of new products monitors users’ brain waves using caps or headbands. That neural data has few privacy protections.
- What Colorado’s new law means for brain-wave privacy in the Neuralink era
Lawmakers have long grappled with data privacy as it pertains to our devices and vehicles. But there’s a new battleground emerging in the privacy battles: our brains. Governor Jared Polis signed a ...
- Are Brain Waves the New Data Privacy Frontier? Novel Colorado Law Says Yes
In first-of-its kind legislation, the updated Colorado Privacy Act (CPA) will consider consumer neural data as sensitive information. California and Minnesota are likely to follow suit.
- When technology can read your brain waves, who owns your thoughts?
Though the technology like this is still relatively nascent, neural rights activists and cornered lawmakers want to be ready for when it is more widespread. Critics warn companies may already possess ...
Go deeper with Bing News on:
Deep learning model
- Deep Instinct Introduces DIANNA, the First Generative AI-Powered Cybersecurity Assistant to Provide Expert-Level Malware Analysis for Unknown Threats
Deep Instinct, the prevention-first cybersecurity company that stops unknown malware pre-execution with a purpose-built, AI-based deep learning (DL) framework, today announced the launch of Deep ...
- Deep Instinct Launches Advanced, GenAI-Based Security Analysis Assistant for Unknown Threats
DIANNA is composed of a large language model (LLM) that surfaces critical ... security teams to focus on what truly matters.” Deep Instinct’s latest innovation transcends traditional machine ...
- Apple builds a slimmed-down AI model using Stanford, Google innovations
The phone giant's open-source large language model beats previous models by melding the insights of many researchers.
- AI Model Predicts Heart Irregularities Before Onset
Researchers unveil an AI model predicting cardiac arrhythmia 30 mins before onset, aiding in timely preventive measures ...
- Deep learning predicts heart arrhrythmia 30 minutes in advance
Atrial fibrillation is the most common cardiac arrhythmia worldwide with around 59 million people concerned in 2019. This irregular heartbeat is associated with increased risks of heart failure, ...