Motor imagery based brain-computer interface: improving the EEG classification using Delta rhythm and LightGBM algorithm

The development of the cultural industry is now at the top of its national plan. When it comes to the development of the cultural industry, the most important thing is to speed up the transformation of commercial cultural institutions into businesses. This will help to rebuild the market players in the cultural industry, as well as integrate the social resources involved in the development of the cultural industry, form the advantages of resource combination, and build a platform for the cultural industry to grow. It is a good idea to have a system and mechanism in place to help the cultural industry grow, as well as a social environment and an undertaking carrier. Data resources can help drive the integration of resources in our country’s cultural and creative industries, as well as the optimization of industrial structure, intelligent transformation, and total growth. People who work in the cultural industry can predict rough data and get the essence out. They can calmly and objectively make decisions about data, and they can use data speed and diversity to drive content creation, communication innovation, and consumption upgrades in the cultural industry. In this study, large cultural businesses lead the way when it comes to integrating cultural industry resources based on data mining. Cultural industry parks are the places where clusters of businesses are built. To make a cultural industry chain, it looks at what customers do not say about their needs and looks at the resources in the industry to make sure it is a good fit. The government should help cultural businesses by making it easier for them to do business. This will help our country’s cultural industry be more competitive.

show abstract

“…XGBoost model [20], the LightGBM algorithm [19] has made a number of enhancements, notably the following points:…”

Section: Lightgbm Data Model On the Basis Of The Conventionalmentioning

confidence: 99%

Resource Integration of Cultural and Creative Industries Using Data Mining Technology

Zhang

Guo

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Many of the studies [10,11] try to distinguish data using linear or non-linear curves, margins, neural networks, or decision trees. We list a few classifiers that can be used with this technique, including the convolutional neural network (CNN) [12,13], linear discriminant analysis (LDA), k-nearest neighbour (k-NN), random forest (RF), support vector machine (SVM),and extreme gradient boosting (XGB) [14,15]. The three different types of information which include linearly separable clusters like text and speech information, non-linearly separable clusters like images, and non-separable clusters like EEG signals, present different obstacles for every approach [16,17].…”

Section: Introductionmentioning

confidence: 99%

“…On either hand, because of the complexities in the algorithms, effective classifiers frequently lack categorization performance. Thus it is essential to create classifiers that are both quick and highly accurate [13,14]. However, in the unavailability of these ideal classifiers, numerous investigators worked to increase accuracy by fusing rapid classifiers like LDA, SVM, and LGBM with optimization techniques [18] and the authors have made on studies of all the fearture extraction and classification used in physionet database [33].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Eeg Signal Classification for Motor Imagery Based Brain Computer Interface: A Fusion Approach Using Discrete Wavelet Transform and Quad Binary Pattern

Ananthi,

Subathra,

et al. 2024

Preprint

View full text Add to dashboard Cite

Motor Imagery - Brain-Computer Interface (MI-BCI) is a technique that acts as a non-muscular channel for disabled people to communicate. Because it is a communication link between the wired brain and an external device. In this paper, we propose a comprehensive feature extraction approach for electroencephalogram (EEG) signals to achieve maximum classification accuracy by fusion techniques. The Wavelet Packet Decomposition (WPD), Discrete Wavelet Transform (DWT), and Quad Binary Pattern (QBP) methods are applied to EEG signals. The proposed method consists of five strategies out of which two are fusion techniques based on EEG signal and pattern techniques. One hybrid method involves decomposing EEG signals using DWT, and feeding it into the QBP domain to extract the histogram features. In another hybrid model, the signals are decomposed using WPD and were given to the QBP for feature extraction. Artificial Neural Network (ANN) is used as a classifier in our work. Among the used algorithm DWT based QBP approach attained maximum accuracy. The proposed method is validated using well-known Physionet EEG dataset by considering binary class (imaginary movement of left and right fist). The extracted features are to classify the movement of the right and left fist EEG signals. Using a DWT-based QBP approach, the proposed technique attained a accuracy of 99.50 percent on physionet dataset.

show abstract

“…The organization of human memory consists of the existence of at least two systems with different durations: a shortterm memory (MCP) and a long-term memory (MLP) (Abenna et al, 2022). The formation of memories begins primarily with the acquisition of information in sensory systems (vision, hearing, touch, etc.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of long-term memory through electroencephalographic techniques

Silva

Nogueira

Santos

et al. 2023

RSD

View full text Add to dashboard Cite

This study aimed to evaluate the long term memory through electroencephalographic techniques. Were evaluated, in individuals from the human and exact sciences groups, during the following cognitive activities: task: 1 – MEMORIZING WORDS; 2 – REMEMBER THE WORDS OF ACTIVITY 1; 3 – MEMORIZING FIGURES; 4 REMEMBER THE FIGURES OF THE ACTIVITY 3. The gamma rhythm was recorded through the electroencephalogram (EEG), according to the 10-20 system. Thus, the tasks aimed to analyze the capacity for long-term memorization. EEG signals were monitored during the reading and response of the tasks and the means and standard deviation of the gamma rhythm were calculated. The statistical model was BioEstat 5.0, T test for paired samples (p<0.05), Mann-Witney non-parametric test - independent samples and Excel. The results of the intragroup and intergroup analysis in human and exact subjects showed a significant difference in processing brain, through the gamma rhythm, during activities. Individuals in the humanities area used the anterior left quadrant more, while individuals in the exact sciences area used the posterior right quadrant more, as evidenced in the tasks of memorizing pictures and evoking pictures. It seems that there is an association of the gamma rhythm with the states of greater activation of the cerebral cortex during the programming and execution of cognitive activities.

show abstract

Motor imagery based brain-computer interface: improving the EEG classification using Delta rhythm and LightGBM algorithm

Cited by 24 publications

References 47 publications

Resource Integration of Cultural and Creative Industries Using Data Mining Technology

Resource Integration of Cultural and Creative Industries Using Data Mining Technology

Enhanced Eeg Signal Classification for Motor Imagery Based Brain Computer Interface: A Fusion Approach Using Discrete Wavelet Transform and Quad Binary Pattern

Evaluation of long-term memory through electroencephalographic techniques

Contact Info

Product

Resources

About