Pub Date : 2022-11-23DOI: 10.1109/Informatics57926.2022.10083473
M. Ivanovs, Beate Banga, V. Abolins, K. Nesenbergs
Convolutional neural networks (CNN) have achieved state-of-the-art results in many Brain-Computer Interface (BCI) tasks, yet their applications in real-world scenarios and attempts at further optimizing them may be hindered by their non-transparent, black box-like nature. While there has been ex-tensive research on the intersection of the fields of explainable artificial intelligence (AI) and computer vision on explaining CNN for image classification, it is an open question how commonly the methods for explaining CNNs are used when CNNs are a part of a BCI setup. In the present study, we survey BCI studies from 2020 to 2022 that deploy CNNs to find out how many of them use explainable AI methods for better understanding of CNNs and which such methods are used in particular. Our findings are that explainable AI methods were used in 13.7 percent of the surveyed publications, and the majority of the studies in which these methods were used employed the t-distributed stochastic neighbour embedding (t-SNE) method.
{"title":"Methods for Explaining CNN-Based BCI: A Survey of Recent Applications","authors":"M. Ivanovs, Beate Banga, V. Abolins, K. Nesenbergs","doi":"10.1109/Informatics57926.2022.10083473","DOIUrl":"https://doi.org/10.1109/Informatics57926.2022.10083473","url":null,"abstract":"Convolutional neural networks (CNN) have achieved state-of-the-art results in many Brain-Computer Interface (BCI) tasks, yet their applications in real-world scenarios and attempts at further optimizing them may be hindered by their non-transparent, black box-like nature. While there has been ex-tensive research on the intersection of the fields of explainable artificial intelligence (AI) and computer vision on explaining CNN for image classification, it is an open question how commonly the methods for explaining CNNs are used when CNNs are a part of a BCI setup. In the present study, we survey BCI studies from 2020 to 2022 that deploy CNNs to find out how many of them use explainable AI methods for better understanding of CNNs and which such methods are used in particular. Our findings are that explainable AI methods were used in 13.7 percent of the surveyed publications, and the majority of the studies in which these methods were used employed the t-distributed stochastic neighbour embedding (t-SNE) method.","PeriodicalId":101488,"journal":{"name":"2022 IEEE 16th International Scientific Conference on Informatics (Informatics)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126558263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-23DOI: 10.1109/Informatics57926.2022.10083501
Sergej Chodarev, Sharoon Ilyas
Most of the parser tools are concentrated on the concrete syntax and grammar definition. This paper describes a language definition tool that uses a metamodel specification instead of a grammar as a basis of the language definition. Inspired by a similar Java tool known as YAJCo, the metamodel is defined using usual object-oriented techniques-as classes in the Python programming language. The result of the parsing process is a graph of objects. The tool is demonstrated in a case study of a state machine definition language.
{"title":"Metamodel-based Parser Generator for Python","authors":"Sergej Chodarev, Sharoon Ilyas","doi":"10.1109/Informatics57926.2022.10083501","DOIUrl":"https://doi.org/10.1109/Informatics57926.2022.10083501","url":null,"abstract":"Most of the parser tools are concentrated on the concrete syntax and grammar definition. This paper describes a language definition tool that uses a metamodel specification instead of a grammar as a basis of the language definition. Inspired by a similar Java tool known as YAJCo, the metamodel is defined using usual object-oriented techniques-as classes in the Python programming language. The result of the parsing process is a graph of objects. The tool is demonstrated in a case study of a state machine definition language.","PeriodicalId":101488,"journal":{"name":"2022 IEEE 16th International Scientific Conference on Informatics (Informatics)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124675204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：