scholarly journals Hybrid Machine Learning Scheme for Classification of BECTS and TLE Patients Using EEG Brain Signals

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 218924-218935
Author(s):  
Wonsik Yang ◽  
Minsoo Joo ◽  
Yujaung Kim ◽  
Se Hee Kim ◽  
Jong-Moon Chung
Keyword(s):  
Machine Learning ◽  
Brain Signals ◽  
Learning Scheme ◽  
Hybrid Machine

scholarly journals Framework for the Classification of Emotions in People With Visual Disabilities Through Brain Signals

2021 ◽  
Vol 15 ◽  
Author(s):  
Jesús Leonardo López-Hernández ◽  
Israel González-Carrasco ◽  
José Luis López-Cuadrado ◽  
Belén Ruiz-Mezcua
Keyword(s):  
Machine Learning ◽  
Positive Emotions ◽  
Machine Learning Techniques ◽  
Visual Disabilities ◽  
Brain Signals ◽  
Learning Techniques ◽  
Sensory Disabilities ◽  
Recognition Of Emotions

Nowadays, the recognition of emotions in people with sensory disabilities still represents a challenge due to the difficulty of generalizing and modeling the set of brain signals. In recent years, the technology that has been used to study a person’s behavior and emotions based on brain signals is the brain–computer interface (BCI). Although previous works have already proposed the classification of emotions in people with sensory disabilities using machine learning techniques, a model of recognition of emotions in people with visual disabilities has not yet been evaluated. Consequently, in this work, the authors present a twofold framework focused on people with visual disabilities. Firstly, auditory stimuli have been used, and a component of acquisition and extraction of brain signals has been defined. Secondly, analysis techniques for the modeling of emotions have been developed, and machine learning models for the classification of emotions have been defined. Based on the results, the algorithm with the best performance in the validation is random forest (RF), with an accuracy of 85 and 88% in the classification for negative and positive emotions, respectively. According to the results, the framework is able to classify positive and negative emotions, but the experimentation performed also shows that the framework performance depends on the number of features in the dataset and the quality of the Electroencephalogram (EEG) signals is a determining factor.

Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme

2019 ◽  
Vol 61 (7) ◽  
pp. 757-765 ◽  
Author(s):  
Shai Shrot ◽  
Moshe Salhov ◽  
Nir Dvorski ◽  
Eli Konen ◽  
Amir Averbuch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Brain Tumors ◽  
Perfusion Imaging ◽  
Diffusion Tensor ◽  
Learning Scheme

scholarly journals Visual Social Data Clustersfor Effective Topics Tendnecy with Hybrid Machine Learning Techniques

2020 ◽  
Vol 8 (5) ◽  
pp. 4100-4104
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Social Data ◽  
Learning Techniques ◽  
Social Classification ◽  
Data Clusters ◽  
Hybrid Machine

The machine learning is an emerging field in social classification of data, which enable the learning of social data patterns and classify the data by unsupervised approaches. Majorly, k-means and graph-based machine learning algorithms are used for discovering of social data clusters based on similarity features of user views, opinions. This paper presents the sentimental analysis of social users for the topics using the cluster tendency of derived clusters. The experimental of social data clusters and the cluster tendency are visualized for effective sentiment of topics analysis.

A Hybrid Tumour Detection and Classification Based on Machine Learning

2020 ◽  
Vol 17 (6) ◽  
pp. 2539-2544
Author(s):  
Umesh Kumar Lilhore ◽  
Sarita Simaiya ◽  
Devendra Prasad ◽  
Kalpna Guleria
Keyword(s):  
Machine Learning ◽  
Detection System ◽  
Descriptive Statistics ◽  
Fuzzy C Means ◽  
Novel Approach ◽  
Hybrid Machine ◽  
Difficult Challenge ◽  
The Many ◽  
The Brain

Every excess tissue or impaired production of brain tissue in the human embryo is known as something of a tumor. Inside the brain, there may have been a tumor or any other orifice. Recognition of tumors and proper treatment at all times are still a difficult challenge. MRI devices are used mostly for the identification of specific tumors. MRI technologies are most often used for either the identification of specific tumors. Use artificial intelligence, medical diagnosis by imaging and machine learning is considered one of the many important issues for systems. Brain tumor evaluation generally requires greater accuracy, although small differences in assessment may turn to hazards. Because of this, the segmentation of both the tumor is a serious medical obstacle. Here proposed work introduces a hybrid machine learning-based tumor detection system (HMLBTD) for MR frames. The Fuzzy C-Means and K-Means Clustering Composite Clustering methodology have been used by the proposed HMLBTD frameworks and subsequently improved the classification of SVM and classification of normal and abnormal tumors. Across clustering, throughout order to achieve statistically valid performance, HMLBTD incorporates Fuzzy C-Means hybrid versions to achieve precision and K-means through segmentation. Throughout the second clustering step, HMLBTD employs Enhanced SVM (and use the ADA-boost framework with SVM) As well as the suggested HMLBTD strategy and also the proposed solution being implemented by utilizing different performance descriptive statistics using the MATLAB framework. An experimental study demonstrates that HMLBTD’s novel approach delivers higher yields than those of the traditional methods.

Sign in / Sign up

Export Citation Format

Share Document