EIQ: EEG based IQ test using wavelet packet transform and hierarchical extreme learning machine

Kadam, Shashikant T.; Dhaimodker, Vineet; Patil, Milind M.; Edla, Damodar Reddy; Kuppili, Venkatanareshbabu

doi:10.1016/j.jneumeth.2019.04.008

Cited by 13 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavelet packet analysis can adaptively select the best odd function matching the original signal to achieve a stronger signal decomposition level while taking into account the high and low frequency components of the signal [44, 45] . Therefore, wavelet packet analysis is suitable for analysing the non‐stationary and non‐linear signals of this kind of human body.…”

Section: Methodsmentioning

confidence: 99%

Research on the evaluation of rectal function after LAR based on CEEMDAN‐Fast‐ICA algorithm

Zan

Zhao

Zhong

et al. 2023

IET Science Measure & Tech

View full text Add to dashboard Cite

Rectal cancer is one of the most common lower gastrointestinal diseases worldwide. Currently, the common treatment is low anterior resection (LAR) of the rectum, which preserves the anus of the patient. However, it is easy to cause low anterior resection syndrome after surgery, which has a significant negative impact on the life of patients, and there is no unified evaluation standard for postoperative rectal function. To solve this problem, a multi-sensor fusion rectal information acquisition system is designed in this paper, and a rectal signal processing method is proposed to theoretically evaluate the rectal function of postoperative patients. The method uses the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the one-dimensional rectal signal to solve the underdetermined ICA problem, uses the Fast independent component analysis (Fast-ICA) to separate the pure rectal signal, uses the wavelet packet to extract features, and uses the particle swarm optimization optimizes support vector machine (PSO-SVM) to classify and evaluate postoperative function. According to the experimental results, the rectal signal preprocessing effect is good, the evaluation prediction rate is 99.5565%, and the algorithm classification results are accurate, which provides a certain preliminary theoretical basis and reference value for the evaluation of rectal function after LAR.

show abstract

Section: Methodsmentioning

confidence: 99%

Research on the evaluation of rectal function after LAR based on CEEMDAN‐Fast‐ICA algorithm

Zan

Zhao

Zhong

et al. 2023

IET Science Measure & Tech

View full text Add to dashboard Cite

show abstract

“…She et al [109] proposed the hierarchical semi-supervised ELM (HSS-ELM) for motor imagery EEG classification, in which H-ELM was used for feature extraction, and semi-supervised ELM for the final classification. Furthermore, Kadam et al [110] combined wavelet packet transform and H-ELM for EEG based IQ test. Yin et al [111] proposed dynamic deep ELM (DD-ELM) to adapt the variation of the EEG feature distributions across two mental tasks for task-generic mental fatigue recognition.…”

Section: Applicationsmentioning

confidence: 99%

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

Zhang

Xiao

et al. 2020

Journal of the Franklin Institute

158

View full text Add to dashboard Cite

In the past decade, deep learning techniques have powered many aspects of our daily life, and drawn ever-increasing research interests. However, conventional deep learning approaches, such as deep belief network (DBN), restricted Boltzmann machine (RBM), and convolutional neural network (CNN), suffer from time-consuming training process due to fine-tuning of a large number of parameters and the complicated hierarchical structure. Furthermore, the above complication makes it difficult to theoretically analyze and prove the universal approximation of those conventional deep learning approaches. In order to tackle the issues, multilayer extreme learning machines (ML-ELM) were proposed, which accelerate the development of deep learning. Compared with conventional deep learning, ML-ELMs are non-iterative and fast due to the random feature mapping mechanism. In this paper, we perform a thorough review on the development of ML-ELMs, including stacked ELM autoencoder (ELM-AE), residual ELM, and local receptive field based ELM (ELM-LRF), as well as address their applications. In addition, we also discuss the connection between random neural networks and conventional deep learning.

show abstract

“…IQ is characterized by the ability to adapt to environment, rational thinking, comprehend intricate concepts and acquire knowledge proficiently [3]. Intelligence is essentially linked to attention due to the significance of stimulus selection in a system with constrained capacity to process the information simultaneously [4]. Emotional quotient, commonly referred to as emotional intelligence is the ability of an individual to acknowledge and deal with their own feelings as well as their social environment [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

A Study of Engineering Student IQ and EQ Based on Analyzing of Electroencephalogram (EEG) Signals

Norsepri,

Sulaiman,

Mustafa

et al. 2023

MEKATRONIKA

View full text Add to dashboard Cite

This paper elaborates about the analyzing of Intelligent Quotient (IQ) and Emotional Quotient (EQ) of an engineering student based on Electroencephalogram (EEG) or brain signals using a computing tool such as MATLAB. The influence of individual’s IQ and EQ on the development of innovative thinking is significant. An IQ alone is not adequate to measure the success of a person. An EQ somehow is found to have a substantial correlation with individual’s performance which shows that both IQ and EQ are important in determining the character and manner of individual’s thinking skills. The main objective of this project is to analyze the output of EEG signals produced by an engineering student based on their IQ and EQ level. A comparison of which quotient influences the student’s thinking skill is also observed in this study. In this project, a single channel EEG amplifier is used to record the EEG signals from 6 different subjects with three different conditions: while not doing anything, during an IQ test and during an EQ test. The data is recorded using the EEG sensors with Unicorn Recorder software that is connected to the amplifier while recording is run. The result of the experiment also explained in terms of the mean value and standard deviation of the EEG bands for each subject and condition. The results of the study conclude that the IQ level of an individual is affected by the Beta band of the EEG signals. Meanwhile, Alpha band of the EEG signals is more dominant in the determination of EQ level of an individual. When Alpha band is higher than Beta band, it shows that the subject is dominant to an EQ dominant person. If Beta band is higher than Alpha band, then IQ is the dominant quotient for the subject. The highest k-NN classification accuracy is obtained at 80:20 classification with 81.84% accuracy using Mean features and 79.53% accuracy using Standard Deviaton features. This study also included the development of Graphical User Interface (GUI) in MATLAB. The GUI is used for the classification of the chosen EEG features. Theta, Alpha, and Beta power band are observed from the EEG signals to identify brain activity. In addition, IQ and EQ analyzer is constructed using Arduino microcontroller once the analysis of the EEG signals are done through GUI.

show abstract

EIQ: EEG based IQ test using wavelet packet transform and hierarchical extreme learning machine

Cited by 13 publications

References 14 publications

Research on the evaluation of rectal function after LAR based on CEEMDAN‐Fast‐ICA algorithm

Research on the evaluation of rectal function after LAR based on CEEMDAN‐Fast‐ICA algorithm

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

A Study of Engineering Student IQ and EQ Based on Analyzing of Electroencephalogram (EEG) Signals

Contact Info

Product

Resources

About