Development of EEG based Identification of Learning Disability using Machine Learning Algorithms

doi:10.21203/rs.3.rs-2077375/v1

Download PDF

Research Article

Development of EEG based Identification of Learning Disability using Machine Learning Algorithms

https://doi.org/10.21203/rs.3.rs-2077375/v1

This work is licensed under a CC BY 4.0 License

Version 1

posted

You are reading this latest preprint version

A learning disability (LDs) is a comprehensive word used for various learning problems. Children with learning disabilities are not sluggish nor intelligently retarded. Learning disability is a neurological condition that is characterized by a vague understanding of words and poor reading skills. It affects many school-aged children, with fellows being more likely to be involved, placing them at risk for deprived academic concerts and low self-esteem for the rest of their lives. Our research entails developing a machine learning model to analyze EEG signals from people with learning difficulties and provide results in minutes with the highest level of accuracy. In this research, we have used Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA) methods were used for component analyze of the dataset. For classification purposes we have used Support Vector Machines (SVM), Random Forest (RF), Logistic Regression (LR), K-nearest neighbours (K-NN), Decision Trees and XGBoost, etc different types of algorithms. The goal is to determine which data pre-processing approaches and machine learning algorithms are the most effective in detecting learning disabilities.

Electroencephalography (EEG)

Learning disability

Feature extraction

Classification algorithms

Machine Learning

A learning disability is caused by a nervous condition [1] For a child with a learning disability, reading, writing, spelling, forming things, and so on can be hard.[1] It has nothing to do with the IQ of a child.[2] The children, however, can be aided in discovering their potential and determining future career decisions with the correct identification and assistance. Machine learning is now used in a variety of businesses to anticipate future events. Two of the most useful applications of machine learning include predicting learning impairments in children and determining the underlying causes. Learning difficulties can be caused by a variety of factors. [1, 2] A learning handicap affects one’s capacity to grasp knowledge. It’s tough to comprehend the nature of these disabilities. However, there has been substantial progress in mapping some of the challenges that learning impairment types face, as well as specific brain regions and structures.

If a person has a visual, hearing, or motor impairment, it is not considered a learning disability. mental retardation, emotional instability, or cultural issues are not considered learning disabilities. [3]

1.1 Electroencephalography (EEG) is one of the newer approaches being investigated for identifying specific brain activation patterns in learning disabilities. [1–5], Electroencephalography detects electrical activity present in our brain with the help of metal caps (electrodes) that are placed on our scalp by using 10–20 system as shown in Fig. 1. Even when you are sleeping, electrical impulses interact between your brain cells. This activity appears as wavy lines on an EEG recording.

Machine learning is being used to predict future events in a variety of sectors. The most useful areas of machine learning applications are predicting learning problems in children, diagnosing the actual disability, and determining how early it may be recognized.

In this research comprises creating a machine learning model that will assess a data set obtained from the EEG signals of different learning difficulties like dyslexia and ADHD (attention deficit hyper disorder) and offer accurate results in minutes.

2.1 Literature review

2.1.1 Advanced Machine Learning Techniques to Assist Dyslexic Children for Easy readability: [1]

This research focuses on a review of software and hardware choices that can assist dyslexic children. Machine learning techniques used include K Means, K Nearest Neighbor, Adaptive clustering, LS Algorithm, Support Vector Machine, and Human Markov Model. To extract speech features and measure accuracy and performance improvement in children, machine learning methods are often used. As a result, the research will concentrate on children aged five to seven who have trouble reading Hindi words. Machine learning techniques will be employed in the design process to assist dyslexic children. The letters two and three are utilized. With Hindi words as input, the system is trained with a dynamic Time Wrapping method. Once you’ve programmed the words into the system, you’re ready to go. Words will be taught to a dyslexic child. A child will be given another chance to read if he or she pronounces a word wrong the first time. If the same event occurs three times, the system will repeat the word out, along with an image, to ensure that the child learns the term. The child’s word for another 20 minutes, the same session with different words will be repeated for the child. To recognize speech in this scenario, machine learning techniques will be used. If the system is functioning properly, the child said the word. For another 20 minutes, the same program will be performed with different words for the child. In this situation, machine learning techniques will be used to recognize speech. The Dynamic Time Wrapping technique yields 90 percent to 100 percent accuracy if the system is evaluated with the same user, and 30 percent accuracy if the system is tested with a new user.

2.1.2 Machine Learning based Learning Disability Detection using LMS: [2]

This research focuses on an E-learning system built with Moodle, an open-source Learning Management System (LMS) that enables tutors and students to work together more efficiently. This method recognizes couple of student profiles: students with and without Learning Disability (LD) by using keen courses constructed base on the topic of numerous features of an LD student (non-LD). Several elements of our informal testing approach for collecting learning aspects for Dyslexic students are also included in this paper. The first stage, data collection, is divided into two parts: the first group is the group having age between 8 to 10 years with a smaller number of constraints, and the other one is with age group of 11 to 13 years (Class of 6 to 8) with a greater number of parameters. On the computer, a speech-to-text (STT) conversion was done. Natural Language Processing was used to record the consumers’ audio responses (NLP). The Python programming language was used to analyse the responses. To detect whether or not a user has LD, machine learning (ML) is used (Dyslexia in this case). The dataset’s two classifications are LD and non-LD, and the binary classification is done using machine learning techniques like SVM (Support Vector Machine) and LR (Logistic Regression). The results are shown for both approaches, and a comparison of the datasets generated in another method for collecting parameters using NLP it shows that the dataset generated in the final technique is far better and accurate in case of accuracy level of comparisons. The LR method for ML outperforms SVM when it comes to detection based on the created dataset.

2.1.3 A survey paper on learning disability prediction using machine learning: [3]

This is a survey essay designed to learn about prior work on the subject and to find gaps that operational for various machine learning systems. A variety of machine learning algorithms are used to predict whether or not a child has a learning disability. It is easier to deal with such problems if a prognosis is given sooner rather than later. A comparison of existing machine learning algorithms for a particular data set can be used to see which one offers the best accurate prediction results. It is impossible to overestimate the importance of the pre-processing stage in preparing data for prediction. Several new strategies can be formalized to help forecast better outcomes.

2.1.4 Machine Learning and Dyslexia: Diagnostic and Classification System (DCS) for Kids with Learning Disabilities:[4]

In this study, they proposed an automated diagnosis and categorization method. The system was trained using pre- classified data from 857 school children’s spelling and reading scores. The twenty-fifth percentile was applied to the scores in order to categorize them. Dyslexia was diagnosed in children who scored below the twenty-fifth percentile, while non- dyslexic children scored above the twenty-fifth percentile. The diagnostic module is a prescreening tool that experts, trained users, and parents can use to detect dyslexia symptoms. The students are divided into two groups in the second module, classification: non-dyslexics and dyslexics with suspicion of dyslexia in spelling and reading. A research study implement is the third unit. In the final results it implies that 23 percent of children were at peril for dyslexia the LD in the training data and 20.7 percent in the testing data, with a 98 percent accuracy.

2.1.5 Diagnosis of Dyslexia using computation analysis: [5]

This study examines the use of a computer system to diagnose dyslexia, taking into account people’s difficulties in either writing, reading or in the speaking. As a result, a computer-based classifier can be built using dyslexia system of measurement approaches. As a result, the Gibson brain skills test will be used, which will consider the effects of working memory, auditory and filmic memory and thought, filmic and hearing sensitivities, inscription and motorized aids, math and time organization, performance, well-being, growth, and personality, and mental skill in people with LDs, particularly reading problems. Computational study with classifiers will be used to analyse the recommended dataset, which contains around eighty archives of children. This computing model was created by and used to aid in the uncovering of underlying issues that may interfere with learning to read and then write, as well as concerns that may cause difficulty with memorized understanding. This approach is utilized to help therapists and paternities know the problem and guide children down the right road to academical achievement.

2.2 Limitations of existing systems

The papers referred above have the following limitations: Behavioral elements of members during homogenous tests, such as writing, reading or working memory, are examined by psychologists in traditional dyslexia diagnosis procedures. Where as in ADHD suffering peoples have problems on visual attentions they are identified by their low scores on these exams. However, because symptoms differ between people, these procedures are generally time-consuming and useless for a wide group of people.

2.3 Problem statement

Identify and evaluate the most commonly practiced techniques used to classify the EEG data associated with learning disabilities, and to evaluate the accuracy for various machine learning algorithms and identify which model is well suited for the specified dataset.

2.3.1 Dyslexia: The primary step is to identify the procedure is to demeanor a user survey and get information from them. In traditional dyslexia diagnosis techniques, psychologists assess participants’ behavior throughout uniform exams, such as writing or writing skills along with, phonological awareness, and working memory. [1, 5] Low results on these tests are used to identify dyslexics. However, because people’s symptoms vary, these methods are frequently time-intense and unsuccessful for a large group of people. As a result, academics are increasingly turning to machine learning techniques, which are less time intense and low-cost.

2.3.2 ADHD: ADHD patients may also have trouble focused on a solo task or sitting ideal for long time period. Anyone of any age can be affected by ADHD

EEG signal features can detect dyslexia, ADHD, dementia, sleeping problems, depression, and other brain illnesses. EEG headsets monitor brain activity by placing electrodes in an array along the user’s or research subject’s scalp.

2.4 PROPOSED SYSTEM

2.4.1 Data collection

Due to the pandemic situation, it was not anticipated for us to build our dataset using sampling of EEG signals of people woe for LDs. Instead, we search for an online benchmark data resource. The first dataset carries the information of dyslexic and non-dyslexic students which is available on Skit Learn. For dyslexia identification the dataset we have selected is unbiased dataset of 28 dyslexic and 21non dyslexic (25 male and 24 female). For the test purpose memory, vocabulary, speed, visual discrimination, audio discrimination feature is selected to discriminate between dyslexic and non-dyslectic persons. And the second dataset for ADHD and non-ADHD students was submitted by Ali Motie Nasrabadi, [14] it consists of unbiased data of 61 children with ADHD and 60 healthy controls (boys and girls, ages 7–12) on IEEE data port. For ADHD identification, on the basis of EEG recordings, children with ADHD and children without ADHD are classified. The data is broken down into four sections: ADHD part 1, ADHD part 2, Control part 1 and Control part 2. Each portion is made up of a number of mat files, each of which corresponds to a person’s EEG data. In the task, a set of pictures of cartoon characters was shown to the children and they were asked to count the characters. The number of characters in each copy was arbitrarily selected from 5 to 16 in numbers, and the magnitude of the copy/pictures was big sufficient to be simply observable and countable by children Thus, the duration of EEG recording throughout this cognitive visual task was dependent on the child’s performance (i.e., visual attention and response speed).

2.4.2 Pre-processing, feature extraction and feature selection

The dataset must be preprocessed and screened previously applying machine learning algorithms. This entails converting the data into a number or qualitative/textual format. To locate useful attributes and eliminate nulls, pre-processing is utilized. Following the initial processing step, the feature elimination/extraction technique, in which relevant features are recognized and a variety of standards is assigned. Here each frequency channel band is a feature and the threshold value of each wave is their respective frequency as stated.

We accomplish three types of component analysis on this dataset and the outcomes are specified later in this paper.

Principal component analysis
Independent component analysis
Linear discriminant analysis

2.4.3 System training and classification

ML Algorithms: Random Forest Classifier, Decision Tree Classifier, Linear Regression, XGB Classifier, support vector machine (SVM), K-Nearest Neighbor (K-NN), and are among the algorithms employed after the component analysis.

2.4.4 Performance evaluation

In the performance evaluation, Python-based tools are employed. In this scenario, accuracy score is utilized to assess the performance of machine learning-based on detection of LDs systems.

Dyslexia: Following Table gives the accuracy score for different ML based algorithms
ADHD: The following table and graph gives the accuracy score for different ML based algorithms
Dyslexia: Figure 5 shows the topographic map of a child diagnosed with Dyslexia and a normal child
ADHD: Figure 6 shows the topographic map of a child diagnosed with ADHD and a normal child

4.1 Discussion:

The basic idea of our project is to increase the accuracy of the learning disability assessment and reduce the time used for learning disability assessment. Machine learning is used in wide variety of fields and applications where certain outcomes have to be predicted.

4.2 Innovation:

Machine learning outcomes it allows the software applications to learn and become more accurate in predicting outcomes. A comparison of machine learning algorithms is used for a particular data set to discover which one produces accurate prediction results. We tried to find which Machine Learning algorithm works best for identifying specific disability. After the outcomes obtained, it is understood in what way inventively the machine learning models classifies dyslexia and ADHD datasets.

By reducing features using various feature elimination techniques such as Variance threshold, correlation matrix, recursive elimination, we observed no significant increase in the test accuracy. Feature generation of degree 2 was performed on the 19 columns leading to a total of 210 columns out of which best 30 were selected. Even this proved useless as the final accuracy only fallen. After selecting the best 8 features out of the 19, only 61% of accuracy was obtained which proves that all of the features are substantially correlated to the output and they cannot be ignored.

For the tomographic graphs, the following inferences are made

From Fig. 5 topographic mapping of dyslexic brain electrical activity revealed four discrete regions of difference between the two groups involving both hemispheres, left more than right. aberrant dyslexic physiology was not restricted to a single locus but was found in much of the cortical region ordinarily involved in reading and speech.

From the Fig. 6 we can accomplish that visual cortex region of both ADHD and normal children were activated. In a normal (control) child we can see the left side of the head (central lateral sensory motor area) (F3-Fp1) lighting up. This indicates the child is responding to the visual stimulus. However, for a child with ADHD, this region doesn't seem to light up. This is because of visual attention is one of the deficits in ADHD children, therefore they are slower to respond to visual stimulus in comparison to normal children.

4.3 Conclusion:

The result shows that the accuracy of the Support Vector Machine (SVM) is better in both the cases for identifying the learning disabilities which is 97% and, 83% for dyslexia and ADHD respectively learning disabilities as compared to other algorithms mentioned over here.

4.4 Future scope

Here we have considered accuracy as only parameter to identify the learning disabilities in future we are using precision, recall and F1- score to be consider along with the accuracy score for better results. Although the technique achieves reasonable accuracy and success rates, it has room for improvement. In this case, data after many bases (e.g., pictures, text, games, and scans) it may be integrated for improvement and the prediction models’ performance. Text as comprehension, arithmetic, including calculation and problem resolving and written expression, including writing, predicting and structure Games like KINLDD which provides a gesture-based interface, computer- based video-game type tests like word identification, word attack that measure children’s reasoning attributes while they are using their motorized skills to relate with the game. Scans such as MRI and CT scan may be accommodating in diagnosis a traumatic brain injury or other nervous damage that may be at least part of the cause for a learning disability. These proposed tools can rummage-sale to grow a combined and user-friendly instrument that is extremely precise in classifying the syndromes, and propose the correct way and maximum suitable instructional events to paternities and tutors. In many cases, more than two classes are required. As a result, we’re interested in investigating different algorithms whose learning may be extended to several classes in order to achieve two goals boosting efficiency in terms of training and testing time frames, and enhancing accuracy by uncovering information concealed in interclass interactions.

Ethical Approval

we will conduct ourself with integrity, fidelity, and honesty. We will openly take responsibility for my actions, and only make agreements, which we intend to keep. we will not intentionally engage in or participate in any form of malicious harm to another person or animal.

Competing interests

The authors did not have any Competing interests

Authors' contributions

The first draft of the manuscript was written by Nitin Ahire and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Availability of data and materials

The datasets are freely available on the IEEE data port (https://ieee-dataport.org/open-access/eeg-data-adhd-control-children) and Kaggle dataset ( https://www.kaggle.com/datasets)

Geeta Atkar, Dr.Priyadarshini J “Advanced Machine Learning Techniques To Assist Dyslexic Children For Easy Readability” International Journal of Scientific &Technology Research Vol 9,Issue 03,March 2020.
M. Modak, O. Warade, G. Saiprasad and S. Shekhar,” Machine Learning based Learning Disability Detection using LMS,” 2020 IEEE 5th In- ternational Conference on Computing Communication and Automation (ICCCA), 2020, pp. 414-419, doi: 10.1109/ICCCA49541.2020.9250761.
Chakraborty, Vani. (2020). A survey paper on learning disability prediction using machine learning.
Rehman Ullah Khan,Julia Lee Ai Chang,Oon Yin Bee, Machine learning and Dyslexia: Diagnostic and classification system (DCS) for kids with learning disabilities, International Journal of Engineering and Technol- ogy3.18(2018) 97-10
H. M. Al-Barhamtoshy and D. M. Motaweh, “Diagnosis of Dyslexia using computation analysis,” 2017 International Conference on Informatics, Health and Technology (ICIHT), 2017, pp. 1-7, doi: 10.1109/ICIHT.2017.7899141
Lateef, Usman Muniyandi, Ravie Omar, Khairuddin Mohamad, Ma- zlyfarina. (2021). Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges. IEEE Access. PP. 1-1. 10.1109/ACCESS.2021.3062709.
H. Perera, M. F. Shiratuddin, K. W. Wong and K. Fullarton, “EEG Signal Analysis of Real Word Reading and Nonsense-Word Reading between Adults with Dyslexia and without Dyslexia,” 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), 2017, pp. 73-78, doi: 10.1109/CBMS.2017.108.
Hayes AM, Dombrowski E, Shefcyk A, et al. Learning Disabilities Screening and Evaluation Guide for Low- and Middle-Income Countries [Internet]. Research Triangle Park (NC): RTI Press; 2018 Apr. Available from: https://www.ncbi.nlm.nih.gov/books/NBK545498/ doi: 10.3768/rtipress.2018. op.0052.1804
David, Julie and Balakrishnan, Kannan. (2010). Machine Learning Approach for Prediction of Learning Disabilities in School-Age Children. International Journal of Computer Applications. 9. 10.5120/1432-1931.
Selvi, H. and Saravanan, M., 2019. Diagnosis of Dyslexia Students Us- ing Classification Mining Techniques. International Journal of Computer Sciences and Engineering, 7(5), pp.28-33.
Pooja Manghirmalani Mishra, Dr. Sushil Kulkarni, Classification of data using semi-supervised learning (a learning disability case study), International Journal of Computer Engineering and Technology (IJCET), ISSN 09766367(Print), ISSN 0976 – 6375(Online) Volume 4, Issue 4, JulyAugust (2013).
KASIM, O., 2022. Identification of Attention Deficit Hyperactivity Disorder with Deep Learning¨ Model Anuradha, J et al, “Diagnosis of ADHD using SVM algorithm”, Proceedings of the Third Annual ACM Bangalore Conference (2010) https://doi.org/10.1145/1754288.1754317.
Medicalnewstoday.com. 2022.Dyslexia: Symptoms, treatment, and types. [online] Available at: https://www.medicalnewstoday.com/articles/186787what-is-dyslexia.
Ali Motie Nasrabadi, Armin Allahverdy, Mehdi Samavati, Mohammad Reza Mohammadi, June 10, 2020,” EEG data for ADHD / Control children”, IEEE Data port, doi: https://dx.doi.org/10.21227/rzfh-zn36.

No competing interests reported.

Download PDF

Version 1

posted

You are reading this latest preprint version

Development of EEG based Identification of Learning Disability using Machine Learning Algorithms

Status:

Version 1

Abstract

Figures

1. Introduction

2. Method

2.1 Literature review

2.1.1 Advanced Machine Learning Techniques to Assist Dyslexic Children for Easy readability: [1]

2.1.2 Machine Learning based Learning Disability Detection using LMS: [2]

2.1.3 A survey paper on learning disability prediction using machine learning: [3]

2.1.4 Machine Learning and Dyslexia: Diagnostic and Classification System (DCS) for Kids with Learning Disabilities:[4]

2.1.5 Diagnosis of Dyslexia using computation analysis: [5]

2.2 Limitations of existing systems

2.3 Problem statement

2.4 PROPOSED SYSTEM

2.4.1 Data collection

2.4.2 Pre-processing, feature extraction and feature selection

2.4.3 System training and classification

2.4.4 Performance evaluation

3. Results

4. Discussion And Conclusions:

4.1 Discussion:

4.2 Innovation:

4.3 Conclusion:

4.4 Future scope

Declarations

References

Additional Declarations

Status:

Version 1