{"title":"基于统计接近准则的无声语音识别任务脑命令字典优化","authors":"Alexandra Bernadotte, Alexandr D. Mazurin","doi":"10.20537/2076-7633-2023-15-3-675-690","DOIUrl":null,"url":null,"abstract":"In our research, we focus on the problem of classification for silent speech recognition to develop a brain– computer interface (BCI) based on electroencephalographic (EEG) data, which will be capable of assisting people with mental and physical disabilities and expanding human capabilities in everyday life. Our previous research has shown that the silent pronouncing of some words results in almost identical distributions of electroencephalographic signal data. Such a phenomenon has a suppressive impact on the quality of neural network model behavior. This paper proposes a data processing technique that distinguishes between statistically remote and inseparable classes in the dataset. Applying the proposed approach helps us reach the goal of maximizing the semantic load of the dictionary used in BCI. Furthermore, we propose the existence of a statistical predictive criterion for the accuracy of binary classification of the words in a dictionary. Such a criterion aims to estimate the lower and the upper bounds of classifiers’ behavior only by measuring quantitative statistical properties of the data (in particular, using the Kolmogorov– Smirnov method). We show that higher levels of classification accuracy can be achieved by means of applying the proposed predictive criterion, making it possible to form an optimized dictionary in terms of semantic load for the EEG-based BCIs. Furthermore, using such a dictionary as a training dataset for classification problems grants the statistical remoteness of the classes by taking into account the semantic and phonetic properties of the corresponding words and improves the classification behavior of silent speech recognition models.","PeriodicalId":37429,"journal":{"name":"Computer Research and Modeling","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimization of the brain command dictionary based on the statistical proximity criterion in silent speech recognition task\",\"authors\":\"Alexandra Bernadotte, Alexandr D. Mazurin\",\"doi\":\"10.20537/2076-7633-2023-15-3-675-690\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In our research, we focus on the problem of classification for silent speech recognition to develop a brain– computer interface (BCI) based on electroencephalographic (EEG) data, which will be capable of assisting people with mental and physical disabilities and expanding human capabilities in everyday life. Our previous research has shown that the silent pronouncing of some words results in almost identical distributions of electroencephalographic signal data. Such a phenomenon has a suppressive impact on the quality of neural network model behavior. This paper proposes a data processing technique that distinguishes between statistically remote and inseparable classes in the dataset. Applying the proposed approach helps us reach the goal of maximizing the semantic load of the dictionary used in BCI. Furthermore, we propose the existence of a statistical predictive criterion for the accuracy of binary classification of the words in a dictionary. Such a criterion aims to estimate the lower and the upper bounds of classifiers’ behavior only by measuring quantitative statistical properties of the data (in particular, using the Kolmogorov– Smirnov method). We show that higher levels of classification accuracy can be achieved by means of applying the proposed predictive criterion, making it possible to form an optimized dictionary in terms of semantic load for the EEG-based BCIs. Furthermore, using such a dictionary as a training dataset for classification problems grants the statistical remoteness of the classes by taking into account the semantic and phonetic properties of the corresponding words and improves the classification behavior of silent speech recognition models.\",\"PeriodicalId\":37429,\"journal\":{\"name\":\"Computer Research and Modeling\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Research and Modeling\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.20537/2076-7633-2023-15-3-675-690\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Research and Modeling","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.20537/2076-7633-2023-15-3-675-690","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}
Optimization of the brain command dictionary based on the statistical proximity criterion in silent speech recognition task
In our research, we focus on the problem of classification for silent speech recognition to develop a brain– computer interface (BCI) based on electroencephalographic (EEG) data, which will be capable of assisting people with mental and physical disabilities and expanding human capabilities in everyday life. Our previous research has shown that the silent pronouncing of some words results in almost identical distributions of electroencephalographic signal data. Such a phenomenon has a suppressive impact on the quality of neural network model behavior. This paper proposes a data processing technique that distinguishes between statistically remote and inseparable classes in the dataset. Applying the proposed approach helps us reach the goal of maximizing the semantic load of the dictionary used in BCI. Furthermore, we propose the existence of a statistical predictive criterion for the accuracy of binary classification of the words in a dictionary. Such a criterion aims to estimate the lower and the upper bounds of classifiers’ behavior only by measuring quantitative statistical properties of the data (in particular, using the Kolmogorov– Smirnov method). We show that higher levels of classification accuracy can be achieved by means of applying the proposed predictive criterion, making it possible to form an optimized dictionary in terms of semantic load for the EEG-based BCIs. Furthermore, using such a dictionary as a training dataset for classification problems grants the statistical remoteness of the classes by taking into account the semantic and phonetic properties of the corresponding words and improves the classification behavior of silent speech recognition models.
期刊介绍:
The journal publishes original research papers and review articles in the field of computer research and mathematical modeling in physics, engineering, biology, ecology, economics, psychology etc. The journal covers research on computer methods and simulation of systems of various nature in the leading scientific schools of Russia and other countries. Of particular interest are papers devoted to simulation in thriving fields of science such as nanotechnology, bioinformatics, and econophysics. The main goal of the journal is to cover the development of computer and mathematical methods for the study of processes in complex structured and developing systems. The primary criterion for publication of papers in the journal is their scientific level. The journal does not charge a publication fee. The decision made on publication is based on the results of an independent review. The journal is oriented towards a wide readership – specialists in mathematical modeling in various areas of science and engineering. The scope of the journal includes: — mathematical modeling and numerical simulation; — numerical methods and the basics of their application; — models in physics and technology; — analysis and modeling of complex living systems; — models of economic and social systems. New sections and headings may be included in the next volumes.