Epileptic Seizure Detection Using Piecewise Linear Reduction

Paul, Yash; Fridli, S.

doi:10.1007/978-3-030-45096-0_45

Cited by 4 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature survey we studied number of sleep states detection techniques and we found that recent research is focusing on dynamic parameters like correlation dimension, Lyponov exponent, approximate entropy etc to extract comprehensive information from non linear signals like EEG, blood and respiratory [39]. Originally the halfwave was used in seizure detection but new halfwave method proposed by us can be used with Franklin transformation (a hybrid approach) [40] to detect epileptic seizures and sleep states classifications in an efficent way by using different biomedical signals. We believe that this method with slight modification in the parameters if needed can be useful to solve many problems in biomedical field in an efficient way.…”

Section: Related Workmentioning

confidence: 99%

Sleep states detection using halfwave and Franklin transformation

Paul¹,

Fridli

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Sleep is a physiological phenomenon and a sufficient amount of sleep is mandatory for a human for his/her health. Three biomedical signals namely Blood, EEG and Nasal are used to identify various sleep stages. The discrete version of these signals is piecewise linear function and applied two piecewise linear data reduction techniques namely a new Halfwave method in time domain and Franklin transformation in frequency domain on the discrete versions of these selected signals. As a result we obtained two piecewise linear functions with low complexity that still preserve the characteristics of the stages of the sleep in the signals. The components of the feature vector are generated from the parameters of the two reduced piece wise linear functions. Algorithm is tested on MIT-BIH Polysomnographic Database having more than 70 hours long term EEG, Blood and Nasal signals with six different sleep classes. Proposed method shows better performance so far on such long duration data in terms of Sensitivity, Specificity, Accuracy and False Alarm Rate/hour. Algorithm achieved an average sensitivity, specificity accuracy and false alarm rate of 98.35% and 97.32%, 96.96%, 0.029 respectively for two classes, 96.62% and 97.10%, 93.94%, 0.030 for 4 classes, 96.13% and 98.33%, 93.84%, 0.016 for all (six) classes.

show abstract

Section: Related Workmentioning

confidence: 99%

Sleep states detection using halfwave and Franklin transformation

Paul¹,

Fridli

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To this order we develop a so called Half-wave type method [8], [9], [10] in time domain and use the Franklin system [14], [15] for orthogonal projection. Here we extend our method [20], originally developed and successfully applied for epilepsy seizure detection. The novelty of the algorithm is the adaptation of the Half-wave and Franklin transformation for the actual problem and we are combining three The study done by Shayan et al [81] collected various disadvantages of the existing studies.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…in less peaky signals. This is quite dierent from epileptic seizure periods [20], when fast and peaky activities occur. One of the advantages of Half-wave method is that we can customize the method based on the problems in hands.…”

Section: Frequency Domain: Franklin Transformmentioning

confidence: 99%

“…Moreover, several studies and surveys including [20], [81], [21] concluded that these are eective features in time domain for the analysis of the dierent biomedical signals. In fact, during our studies we extracted a number of statistical features in time domain.…”

Section: Feature Extraction and Classicationmentioning

confidence: 99%

“…to extract comprehensive information from non linear signals like EEG, blood and respiratory. Originally the Half-wave method was used in seizure detection but the new Half-wave method proposed by us can be used with Franklin transformation (a hybrid approach) [20] to detect epileptic seizures and sleep states classications in an ecient way by using dierent biomedical signals. We believe that this method with slight modication in the parameters if needed can be useful to solve dierent problems in biomedical eld in an ecient way.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Epileptic seizures and sleep states detection using hybrid approaches

Paul¹

View full text Add to dashboard Cite

As the author of the doctoral dissertation, I agree to public disclosure of my doctoral dissertation after obtaining a doctoral degree in the storage of ELTE Digital Institutional Repository. I authorize Adina Kulcsar, the administrator of the ELTE Doctoral School of Informatics to upload the dissertation and the abstract to ELTE Digital Institutional Repository, and I authorize the administrator to ll all the declarations that are required in this procedure. I request in case the doctoral dissertation contains qualied data pertaining to national security, to disclose the doctoral dissertation publicly to the University Library and the ELTE Digital Institutional Repository ensuing the lapse of the period of the qualication process. I request to defer public disclosure to the University Library and the ELTE Digital Institutional Repository, in case there is a publishing contract concluded during the doctoral procedure or up until the award of the degree. However, the bibliographical data of the work shall be accessible to the public. If the publication of the doctoral dissertation will not be carried out within a year from the award of the degree subject to the publishing contract, I agree to the public disclosure of the doctoral dissertation and abstract to the University Library and the ELTE Digital Institutional Repository. As the author of the doctoral dissertation, I declare that the doctoral dissertation and abstract uploaded to the ELTE Digital Institutional Repository are entirely the result of my own intellectual work and as far as I know, I did not infringe anyone's intellectual property rights. The printed version of the doctoral dissertation and the abstract are identical with the doctoral dissertation les (texts and diagrams) submitted on electronic device. As the author of the doctoral dissertation, I agree to the inspection of the dissertation and the abstract by uploading them to a plagiarism checker software. Signature of dissertation author Contents called central focal seizures. These seizures fall into two classications: focal seizures without loss of awareness. called basic simple partial seizures, these seizures don't cause a deciency of awareness. They may adjust feelings or change the manner in which things look, smell, feel, taste or sound. They may likewise bring about compulsory jolting of a body part, like an arm or leg, and unconstrained tangible indications like shivering, dazedness and blazing lights. Focal seizures with impaired awareness. called complex partial seizures, these seizures include a change or loss of cognizance or mindfulness. During an intricate incomplete seizure, you may gaze into space and not react ordinarily to your current circumstance or perform tedious developments, for example, hand scouring, biting, gulping or strolling around and around. Seizures that seem to include all regions of the brain are called generalized seizures. Six kinds of generalized seizures exist.

show abstract