Active Learning for Semiautomatic Sleep Staging and Transitional EEG Segments

Macaš, Martin; Grimová, Nela; Gerla, Václav; Lhotská, Lenka; Saifutdinova, Elizaveta

doi:10.1109/bibm.2018.8621339

Cited by 5 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such state transitions correspond to the ambiguous data instances. In [7], we observed that such instances are located on the border between different classes. An example is depicted in Figure 3, where a data set with 2 features and four classes is depicted in a scatter plot.…”

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 81%

“…As in [7], this paper focuses on a pool-based sampling scenario of active learning [1], where a pool of unlabeled instances (feature vectors) is given and instances for labeling are sequentially selected. An uncertainty sampling is the most popular and the simplest strategy [8].…”

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 99%

“…In [7], only an unrealistic method for detection of transitions based on apriori known labels was considered. Its purpose was to demonstrate that the transitional instances disturb the iterative learning process and their removal can improve the learning.…”

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 99%

“…In [7], we proposed an active learning based semi-automatic sleep scoring approach. It was found that the training data instances whose labels differ from the labels of their adjacent instances tend to be noisy since they are hard to be assigned clearly to one of sleep stages.…”

Section: Introductionmentioning

confidence: 99%

“…This point is focused in this paper, which proposes to detect the transitions via hidden Markov models (HMMs). The paper follows the experimental scenario from [7], but describes the removal of HMM based transitions instead of label-based transitions. The difference is shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Semi-Automated Sleep EEG Scoring with Active Learning and HMM-Based Deletion of Ambiguous Instances

Macaš¹,

Grimová²,

Gerla³

et al. 2019

13th International Conference on Ubiquitous Computing and Ambient ‪Intelligence UCAmI 2019‬

View full text Add to dashboard Cite

Sleep scoring is an important tool for physicians. Assigning of segments of long biomedical signal into sleep stages is, however, a very time consuming, tedious and expensive task which is performed by an expert. Automatic sleep scoring is not well accepted in clinical practice because of low interactivity and unacceptable error, which is often caused by inter-patient variability. This is solved by proposing a semi-automatic approach, where parts of the signal are selected for manual labeling by active learning and the resulting classifier is used for automatic labeling of the remaining signal. The active learning is disturbed by noisy ambiguous data instances caused by continuous character of the sleep stage transitions and a removal of such transitional instances from the training set prior to active learning can improve the efficiency of the method. This paper proposes to use the hidden Markov model for the detection of the transitional instances. It shows experimentally on 35 sleep EEG recordings that such a method significantly improves the semi-automatic method. A complete methodology for semi-automatic sleep scoring is proposed and evaluated, which can be better accepted as a decision support tool for sleep scoring experts.

show abstract

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 81%

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 99%

Section: Active Learning and Ambiguous Instancesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations