Dynamic Dictionary for Combined EEG Compression and Seizure Detection

Daou, Hoda; Labeau, Fabrice

doi:10.1109/jbhi.2013.2263198

Cited by 36 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, in EEG recordings, different EEG segments can display similar features and characteristics. In fact, EEG segments can be grouped based on certain features for manual classification and abnormality detection [12] [2]. In this method reference lists with dynamic update are used to achieve this grouping.…”

Section: Discussionmentioning

confidence: 99%

“…Average values of T P are almost as good as the dipolebased method, as seen in Figures 1 and 2. This method is able to detect seizure-like activity as shown in [2]. Thus, compression based on this method is recommended for recordings of patients suffering with epilepsy, where detection and compression of the data can be performed in parallel.…”

Section: Discussionmentioning

confidence: 99%

“…When analyzing EEG signals for the purpose of medical diagnosis, brain waves are identified in order to find the different functional stages of a patient's state of mind. As previously mentioned, these different rhythms can be used to characterize the different EEG segments [2]. Thus, depending on the state of mind of the patient, brain waves tend to extend and repeat throughout different segments of recording.…”

Section: B Dynamic Dictionary For Combined Eeg Compression and Seizumentioning

confidence: 99%

“…DWT, dynamic reference lists and SPIHT are used to compute and code the decorrelated subband coefficients. This method is able to both compress EEG channels and detect seizure-like activity [2].…”

Section: B Dynamic Dictionary For Combined Eeg Compression and Seizumentioning

confidence: 99%

“…Afterwards, performance results in terms of post compression seizure detection are shown. This recently proposed qualitative measure that is used to compare the original and reconstructed signals provides a better reflection of the information loss with respect to the medically relevant data [6] [2]. A comparative analysis that discusses the weaknesses and strengths of each suggested method is then presented.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Medically relevant criteria used in EEG compression for improved post-compression seizure detection

Daou

Labeau

2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Self Cite

View full text Add to dashboard Cite

Biomedical signals aid in the diagnosis of different disorders and abnormalities. When targeting lossy compression of such signals, the medically relevant information that lies within the data should maintain its accuracy and thus its reliability. In fact, signal models that are inspired by the biophysical properties of the signals at hand allow for a compression that preserves more naturally the clinically significant features of these signals. In this paper, we illustrate this through the example of EEG signals; more specifically, we analyze three specific lossy EEG compression schemes. These schemes are based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG. The resilience of these schemes is illustrated through the performance of seizure detection post compression.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: B Dynamic Dictionary For Combined Eeg Compression and Seizumentioning

confidence: 99%

Section: B Dynamic Dictionary For Combined Eeg Compression and Seizumentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Medically relevant criteria used in EEG compression for improved post-compression seizure detection

Daou

Labeau

2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Self Cite

View full text Add to dashboard Cite

show abstract

Hybrid compression of biomedical ECG and EEG signals based on differential clustering and encoding techniques

Angeline

Suja

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Signal processing techniques incorporated with data compression processes enrich the signals and boost up storage efficiency and transmission reliability. Transmitting uncompressed original data consume wide bandwidth, which increases transmission time and leads to data hammering. These limitations enforce to look for strategic data compression techniques. Lossless compression techniques are requisite where it is important that the original and the decompressed data should be identical or where deviations from the original data would lead to catastrophic consequences, especially in biomedical signal analysis and diagnostics. For which, the input signal preprocessed with differential pulse code modulation (DPCM) reduces the interchannel dependencies to get the desired output. A whole array of unique compression techniques are being utilized in the compression process. The combination of (K‐means clustering, arithmetic encoding [AE], Huffman encoding [HE]) clustering and coding compression techniques are analyzed using electro cardiogram (ECG) and electroencephalogram (EEG) signals. The proposed method employs k‐means clustering combined with Huffman encoding (DiKHE) and k‐means clustering combined with arithmetic encoding (DiKAE) individually. Compression ratio (CR) is analyzed with these combinations of compression techniques for various cluster size K (K = 2,3,4,5,6). A maximum CR of 6.03144 and 4.54126 is obtained for ECG and EEG signals respectively. The compressions based on these techniques are efficient since the compressed signal is reconstructed perfectly as it matches exactly with the original signal.

show abstract