Relative Wave Energy based Adaptive Neuro-Fuzzy Inference System model for the Estimation of Depth of Anaesthesia

被引:1
作者
Benzy, V. K. [1 ]
Jasmin, E. A. [1 ]
Koshy, Rachel Cherian [2 ]
Amal, Frank [3 ]
Indiradevi, K. P. [1 ]
机构
[1] Govt Engn Coll, Dept Elect Engn, Trichur, Kerala, India
[2] Reg Canc Ctr, Dept Anaesthesiol, Trivandrum, Kerala, India
[3] Railway Hosp, Dept Anaesthesiol, Palakkad, Kerala, India
关键词
Electroencephalogram; Relative Wave Energy; Discrete Wavelet Transform; Depth of Anaesthesia; Adaptive Neuro-Fuzzy System; EEG SIGNALS; COMPLEXITY-MEASURES; ENTROPY; CLASSIFICATION; TRANSFORM; FEATURES;
D O I
10.31083/JIN-170039
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
The advancement in medical research and intelligent modeling techniques has lead to the developments in anaesthesia management. The present study is targeted to estimate the depth of anaesthesia using cognitive signal processing and intelligent modeling techniques. The neurophysiological signal that reflects cognitive state of anaesthetic drugs is the electroencephalogram signal. The information available on electroencephalogram signals during anaesthesia are drawn by extracting relative wave energy features from the anaesthetic electroencephalogram signals. Discrete wavelet transform is used to decomposes the electroencephalogram signals into four levels and then relative wave energy is computed from approximate and detail coefficients of sub-band signals. Relative wave energy is extracted to find out the degree of importance of different electroencephalogram frequency bands associated with different anaesthetic phases awake, induction, maintenance and recovery. The Kruskal-Wallis statistical test is applied on the relative wave energy features to check the discriminating capability of relative wave energy features as awake, light anaesthesia, moderate anaesthesia and deep anaesthesia. A novel depth of anaesthesia index is generated by implementing a Adaptive neuro-fuzzy inference system based fuzzy c-means clustering algorithm which uses relative wave energy features as inputs. Finally, the generated depth of anaesthesia index is compared with a commercially available depth of anaesthesia monitor Bispectral index.
引用
收藏
页码:43 / 51
页数:8
相关论文
共 33 条
[1]  
Abraham Ajith, 2005, FUZZY SYSTEMS ENG, P914
[2]   Evolution of Electroencephalogram Signal Analysis Techniques during Anesthesia [J].
Al-Kadi, Mahmoud I. ;
Reaz, Mamun Bin Ibne ;
Ali, Mohd Alauddin Mohd .
SENSORS, 2013, 13 (05) :6605-6635
[3]  
[Anonymous], WAVELET TOUR SIGNAL
[4]  
[Anonymous], 1990, Applied Nonparametric Statistics
[5]  
[Anonymous], 1973, PhD Thesis
[6]  
Benzy V. K., 2016, 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN), P616, DOI 10.1109/SPIN.2016.7566770
[7]  
Benzy V. K., 2016, 2016 International Conference on Computational Techniques in Information and Communication Technologies (ICCTICT). Proceedings, P521, DOI 10.1109/ICCTICT.2016.7514635
[8]  
Bilgiç T, 2000, HDB FUZZ SET SER, V7, P195
[9]   Estimating the depth of anesthesia using fuzzy soft computation applied to EEG features [J].
Esmaeili, V. ;
Assareh, A. ;
Shamsollahi, M. B. ;
Moradi, M. H. ;
Arefian, N. M. .
INTELLIGENT DATA ANALYSIS, 2008, 12 (04) :393-407
[10]   Comparison of EEG Approximate Entropy and Complexity Measures of Depth of Anaesthesia During Inhalational General Anaesthesia [J].
Fan, Shou-Zen ;
Yeh, Jia-Rong ;
Chen, Bo-Cun ;
Shieh, Jiann-Shing .
JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING, 2011, 31 (05) :359-366