EEG based classification of children with learning disabilities using shallow and deep neural network

Seshadri, N. P. Guhan; Agrawal, Sunil; Singh, Bikesh Kumar; Geethanjali, B.; Mahesh, V.; Pachori, Ram Bilas

doi:10.1016/j.bspc.2022.104553

Cited by 18 publications

(8 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a wealth of well-established methods in the ML literature that can effectively decrease feature size, thereby relaxing computational complexity and reducing feature redundancy. Common methods include dimensionality reduction [414], [414]- [421] and feature ranking and selection [8], [125], [414], [422]- [434]. In DL-based feature extraction methods, the substantial size of the resultant deep-learned features necessitates dimensionality reduction since these features constitute a multi-dimensional latent space.…”

Section: Computational Complexitymentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

Recent advancements in sensing, measurement, and computing technologies have significantly expanded the potential for signal-based applications, leveraging the synergy between signal processing and Machine Learning (ML) to improve both performance and reliability. This fusion represents a critical point in the evolution of signal-based systems, highlighting the need to bridge the existing knowledge gap between these two interdisciplinary fields. Despite many attempts in the existing literature to bridge this gap, most are limited to specific applications and focus mainly on feature extraction, often assuming extensive prior knowledge in signal processing. This assumption creates a significant obstacle for a wide range of readers. To address these challenges, this paper takes an integrated article approach. It begins with a detailed tutorial on the fundamentals of signal processing, providing the reader with the necessary background knowledge. Following this, it explores the key stages of a standard signal processing-based ML pipeline, offering an in-depth review of feature extraction techniques, their inherent challenges, and solutions. Differing from existing literature, this work offers an application-independent review and introduces a novel classification taxonomy for feature extraction techniques. Furthermore, it aims at linking theoretical concepts with practical applications, and demonstrates this through two specific use cases: a spectral-based method for condition monitoring of rolling bearings and a wavelet energy analysis for epilepsy detection using EEG signals. In addition to theoretical contributions, this work promotes a collaborative research culture by providing a public repository of relevant Python and MATLAB signal processing codes. This effort is intended to support collaborative research efforts and ensure the reproducibility of the results presented.

show abstract

Section: Computational Complexitymentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…RQ2 is the most important question of this work. We divided it into three different ones because several studies [90][91][92] consider that there is this number of steps (3) before feeding the AI model with data. RQ2.1 deals with the data transformation techniques, in which the data change their domain, from raw EEG signal to 2D images, graphs networks, Wavelets or another domain.…”

Section: Screening Of Papers Several Exclusion and Inclusion Cri-mentioning

confidence: 99%

Feature engineering of EEG applied to mental disorders: a systematic mapping study

García-Ponsoda,

García-Carrasco,

Teruel

et al. 2023

Appl Intell

View full text Add to dashboard Cite

Around a third of the total population of Europe suffers from mental disorders. The use of electroencephalography (EEG) together with Machine Learning (ML) algorithms to diagnose mental disorders has recently been shown to be a prominent research area, as exposed by several reviews focused on the field. Nevertheless, previous to the application of ML algorithms, EEG data should be correctly preprocessed and prepared via Feature Engineering (FE). In fact, the choice of FE techniques can make the difference between an unusable ML model and a simple, effective model. In other words, it can be said that FE is crucial, especially when using complex, non-stationary data such as EEG. To this aim, in this paper we present a Systematic Mapping Study (SMS) focused on FE from EEG data used to identify mental disorders. Our SMS covers more than 900 papers, making it one of the most comprehensive to date, to the best of our knowledge. We gathered the mental disorder addressed, all the FE techniques used, and the Artificial Intelligence (AI) algorithm applied for classification from each paper. Our main contributions are: (i) we offer a starting point for new researchers on these topics, (ii) we extract the most used FE techniques to classify mental disorders, (iii) we show several graphical distributions of all used techniques, and (iv) we provide critical conclusions for detecting mental disorders. To provide a better overview of existing techniques, the FE process is divided into three parts: (i) signal transformation, (ii) feature extraction, and (iii) feature selection. Moreover, we classify and analyze the distribution of existing papers according to the mental disorder they treat, the FE processes used, and the ML techniques applied. As a result, we provide a valuable reference for the scientific community to identify which techniques have been proven and tested and where the gaps are located in the current state of the art. Graphical Abstract

show abstract

“…Despite extensive research, it is still necessary to find essential features to identify them accurately. Seshadri et al [23] proposed an approach to detect learning disabilities (LD), a neurodevelopmental disorder that severely impacts children's lives. They assessed classification performance using various ML classifiers, including DT, KNN, SVM, ensemble classifiers, Naive Bayes, linear discriminant analysis (LDA), and LR, and neural network (shallow and deep) models.…”

Section: Previous Workmentioning

confidence: 99%

Identifying Patterns for Neurological Disabilities by Integrating Discrete Wavelet Transform and Visualization

Ji,

Jayarathna,

Perrotti

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Neurological disabilities cause diverse health and mental challenges, impacting quality of life and imposing financial burdens on both the individuals diagnosed with these conditions and their caregivers. Abnormal brain activity, stemming from malfunctions in the human nervous system, characterizes neurological disorders. Therefore, the early identification of these abnormalities is crucial for devising suitable treatments and interventions aimed at promoting and sustaining quality of life. Electroencephalogram (EEG), a non-invasive method for monitoring brain activity, is frequently employed to detect abnormal brain activity in neurological and mental disorders. This study introduces an approach that extends the understanding and identification of neurological disabilities by integrating feature extraction, machine learning, and visual analysis based on EEG signals collected from individuals with neurological and mental disorders. The classification performance of four feature approaches—EEG frequency band, raw data, power spectral density, and wavelet transform—is assessed using machine learning techniques to evaluate their capability to differentiate neurological disabilities in short EEG segmentations (one second and two seconds). In detail, the classification analysis is conducted under two conditions: single-channel-based classification and region-based classification. While a clear demarcation between normal (healthy) and abnormal (neurological disabilities) EEG metrics may not be evident, their similarities and distinctions are observed through visualization, employing wavelet features. Notably, the frontal brain region (frontal lobe) emerges as a crucial area for distinguishing abnormalities among different brain regions. Also, the integration of wavelet features and visual analysis proves effective in identifying and understanding neurological disabilities.

show abstract

EEG based classification of children with learning disabilities using shallow and deep neural network

Cited by 18 publications

References 51 publications

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Feature engineering of EEG applied to mental disorders: a systematic mapping study

Identifying Patterns for Neurological Disabilities by Integrating Discrete Wavelet Transform and Visualization

Contact Info

Product

Resources

About