Novel Method for Early Detection and Classification of Neuro Degenerative Disorder Amyotrophic Lateral Sclerosis
Krishna Kumar NJ1, Balakrishna R2

1Krishna Kumar NJ *, Department of Computer Science, Rayalaseema University, Kurnool, Andhra Pradesh, India.
2Balakrishna R, Department of Computer Science, Rayalaseema University, Kurnool, Andhra Pradesh, India.
Manuscript received on September 22, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 2936-2944 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1271109119/2019©BEIESP | DOI: 10.35940/ijeat.A1271.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: The most common progressive neurodegenerative disorder in the fetal nature is amyotrophic lateral sclerosis (ALS). The ALS incidence is approximately 2 per 100 000, with the maximum life span being two to three years after the start of symptomatic growth. However, premature identification may increase the lives of the impacted people. EEG is the most convenient and cheapest technique for measuring brain electrical activity. Automated EEG can be used as the coherent identification biomarker technique which is always connected with fronto-temporal dementia (FTD) in seconds to detect ALS in previous phases of growth. The EEG spatial assessment will show spatial and behavioral structure changes in the fundamental cellular network resulting from FTD and may produce prospective biomarkers for premature identification of ALS. The use of the Dual Tree Complex Wavelet Transformation (DTCWT) technique has developed a novel algorithm. DTCWT can solve the abbreviation of current EEG removal functionality techniques. The spectral leakage is reduced by a ideal rebuilding of the DTCWT measurements, so the suggested algorithm has led to an effective and coherent ALS ranking with a Neural Network (NN). For analyzes, eight EEG datasets, each of the Normal Group and Subject were used, and spectral EEG analysis provided a source of definite biomarkers. The proposed algorithm produced 100 percentage accuracy with respect to the dataset considered in this analysis.
Keywords: Amyotrophic Lateral Sclerosis (ALS); Fronto-temporal dementia (FTD); DTCWT; Neuro Degenerative Disorder; EEG.s.