Detection of EEG Signal and De-Noising for Hypoglycemia detection by Brain Wave Sensor
Praveena Sindagi1, Mahesh P K2
1Praveena Sindagi, Assistant Professor, Dept. of Electronics and Communication, Government Engineering College Raichur.
2Dr. Mahesh P K, Professor and HOD. Dept. of Electronics and Communication, ATME College of Engineering, Mysuru.

Manuscript received on November 15, 2019. | Revised Manuscript received on November 28, 2019. | Manuscript published on 30 November, 2019. | PP: 8936-8940 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9715118419/2019©BEIESP | DOI: 10.35940/ijrte.D9715.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Electroencephalography (EEG) signs have remained proven an identical adaptable apparatus for recognition of dissimilar types of Brain infections. Nevertheless through footage of these signs, EEG records gets soiled by different clatter signs produced through supply line interfering, base-line-wander, probe association, muscle-movement etc. Such sound signs misinform analysis of brain that is not anticipated. To circumvent such problematic elimination of the sound signals been develop crucial. Owing to development of data and information equipment tele-medicine and e-health have developed prevalent in emerging and urbanized republics. In the examination drudgery we partake verified three dissimilar categories of adjustable filtering procedures to associate the presentations for scheming EEG signal as of arbitrary and Gaussian-noise. The main idea of the work is to interface the human brain signals and machine in an easy and cheapest manner to find out the various abnormalities in him. The methodology is as follows, we took brain-wave senor for acquiring of data from the person, and this is standard device available in market. The senor is connected to the laptop or system with the help of Bluetooth and the signals are acquired. The acquired signal will be a noisy signal which is to be de-noised and filtered for further process of detection. Random and white-Gaussian-noise is added with EEG signal and Adaptive filter with three different algorithms have been tested to reduce the noise that is added during transmission through the telemedicine system. Further based on the sum, mean and standard deviation parameters the individual is been evaluated the condition is been predicted. After an experimental learning of teenagers with type-1-diabetes (T1D), accompanying with hypoglycemic incident night, centroid, alpha-frequency condensed meaningfully and the centroid theta-frequency augmented meaningfully. The complete data remained prearranged hooked on a preparation set and examination customary arbitrarily designated. By means of proposed methodology, which was resultant as of teaching set through maximum log indication, projected blood-glucose summaries created a noteworthy relationship in contradiction of measured standards in assessment set.
Keywords: Electroencephalography, Adaptive Filtering Algorithms, T1D, Gaussian Noise, Optimal Bayesian Neural Network
Scope of the Article: Optimal Design of Structures.