A co-training algorithm for EEG classification with biomimetic pattern recognition and sparse representation

Ren, Yuanfang; Wu, Yan; Ge, Yanbin

doi:10.1016/j.neucom.2013.05.045

Cited by 20 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While most of these methods are constrained to one set of sensors [44]–[50], a few efforts have focused on transfer between sensor types. In addition to the teacher-learner model we will discuss later [51], Hu and Yang [52] introduced a between-modality transfer technique that requires externally-provided information about the relationship between the source and domain spaces.…”

Section: Transfer Learning For Activity Recognitionmentioning

confidence: 99%

Collegial activity learning between heterogeneous sensors

Feuz

Cook

2017

Knowl Inf Syst

View full text Add to dashboard Cite

Activity recognition algorithms have matured and become more ubiquitous in recent years. However, these algorithms are typically customized for a particular sensor platform. In this paper we introduce PECO, a Personalized activity ECOsystem, that transfers learned activity information seamlessly between sensor platforms in real time so that any available sensor can continue to track activities without requiring its own extensive labeled training data. We introduce a multi-view transfer learning algorithm that facilitates this information handoff between sensor platforms and provide theoretical performance bounds for the algorithm. In addition, we empirically evaluate PECO using datasets that utilize heterogeneous sensor platforms to perform activity recognition. These results indicate that not only can activity recognition algorithms transfer important information to new sensor platforms, but any number of platforms can work together as colleagues to boost performance.

show abstract

Section: Transfer Learning For Activity Recognitionmentioning

confidence: 99%

Collegial activity learning between heterogeneous sensors

Feuz

Cook

2017

Knowl Inf Syst

View full text Add to dashboard Cite

show abstract

“…There are more articles about the classification algorithms innovation [122][123][124][125][126][127]. Reference [125] uses a semi-supervised training method with cooperation of two kinds of classifiers to build a integrated classifier.…”

Section: Feature Classificationmentioning

confidence: 99%

“…Reference [125] uses a semi-supervised training method with cooperation of two kinds of classifiers to build a integrated classifier. Reference [127] proposes a classification method based on hidden conditional random field to classify MI signals.…”

Section: Feature Classificationmentioning

confidence: 99%

Review of Brain Computer Interface Components and Corresponding Research Topics

Wang¹,

Wang²,

Liang³

et al. 2016

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract-This paper conducts a research on the literature of Brain Computer Interface(BCI) in recent years, inducing the four components of BCI and the research topics respectively, and providing a guide to newcomers for exploring BCI. BCI is divided into four parts including signal collection, feature extraction, feature classification and practical application. Papers of above four parts are retrieved respectively from the SCI database. Topics of all papers are concluded, based on which the research topics of BCI are assigned to the four parts of BCI. In topics of each part of BCI, similar topics are summarized to the unique topic. Finally some research topics may cover dozens of papers while some topics may cover only several papers. In each of the four BCI components, there are several topics attracting most of the attention. BCI still has a great research value and good prospects for study.

show abstract

“…This is a very strong conclusion, which implies that if the two assumptions are satisfied and the target class is learnable from random classification noise, then the predictive accuracy of an initial weak learner can be boosted arbitrarily high using only unlabeled examples by co-training. Later, some theoretical analysis [7][13] was performed to relax the two remarkably powerful and easily violated assumptions. The theoretical details are not mentioned in this section.…”

Section: { }mentioning

confidence: 99%

“…As a consequence, semi-supervised learning [1][2] [3], which attempts to make use of costless and abundant unlabeled data in addition to labeled data to improve the performance, has attracted considerable attention. During the past decade, many semisupervised learning approaches have been developed, such as generative-based methods, graph-based methods, semi-supervised support vector machines (S3VMs) and co-training [5][6] [7].…”

Section: Introductionmentioning

confidence: 99%