• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.225-234
• /
• 2010

To investigate the role of positive emotion in education, we have reviewed the previous studies on positive emotion, learning and motivation. In the present study, we examined the definition of positive emotion, and influences of positive emotion on cognition, creativity, social relationship, psychological resource such as life satisfaction, and interactive relationship among positive emotion, motivation and learning. To investigate the role of positive emotion on motivation and learning more scientifically, we examined the recent results of neuroscience. In other words, we have reviewed diverse research on positive emotion, learning and motivation based on brain-based learning. We also examined the research of autonomy-supportive environment as the specific example of improving positive emotion. As one of the most effective methods for emotional education, we discussed brain-based learning, the new research field. As the future prospects, we discussed the implications, possibilities and limitations of brain-based learning.

• Journal of Computing Science and Engineering
• /
• v.7 no.2
• /
• pp.112-121
• /
• 2013

The last years have seen a rise of interest in using electroencephalography-based brain computer interfacing methodology for investigating non-medical questions, beyond the purpose of communication and control. One of these novel applications is to examine how signal quality is being processed neurally, which is of particular interest for industry, besides providing neuroscientific insights. As for most behavioral experiments in the neurosciences, the assessment of a given stimulus by a subject is required. Based on an EEG study on speech quality of phonemes, we will first discuss the information contained in the neural correlate of this judgement. Typically, this is done by analyzing the data along behavioral responses/labels. However, participants in such complex experiments often guess at the threshold of perception. This leads to labels that are only partly correct, and oftentimes random, which is a problematic scenario for using supervised learning. Therefore, we propose a novel supervised-unsupervised learning scheme, which aims to differentiate true labels from random ones in a data-driven way. We show that this approach provides a more crisp view of the brain states that experimenters are looking for, besides discovering additional brain states to which the classical analysis is blind.

• Journal of The Korean Association For Science Education
• /
• v.30 no.8
• /
• pp.1031-1043
• /
• 2010

The purpose of this study was to develop the brain compatibility index equation for the brain-based analysis method of science teaching-learning program. To develop the index equation, one sample unit in middle school science programs was selected and analyzed by the brain-based analysis frame (CORE Brain Map). Then, the index equation was derived by the CORE Brain Map. In addition, four sample units in elementary science programs were selected to validate the brain compatibleness index equation. From the random network theory of Erdos and Renyi, this study derived the brain compatibility index equation; (BCI=$\frac{L_o}{11(N_o-1)}{\cdot}{\sum}\limits_{i=1}^4l_iw_i$) for quantitative analysis of science teaching-learning program. With this equation, this study could find the quantitative difference among the teaching-learning programs through the unit and curriculum. Brain-based analysis methods for the qualitative and quantitative analysis of science teaching-learning program, which was developed in this study is expected, to be a useful application to analyze and diagnose various science teaching-learning programs.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.289-294
• /
• 2015

This paper proposes an autonomous machine learning method applicable to the BCI(Brain-Computer Interface) is based on the self-organizing Kohonen method, one of the exemplary method of unsupervised learning. In addition we propose control method of learning region and self machine learning rule using an interactive function. The learning region control and machine learning was used to control the side effects caused by interaction function that is based on the self-organizing Kohonen method. After determining the winner neuron, we decided to adjust the connection weights based on the learning rules, and learning region is gradually decreased as the number of learning is increased by the learning. So we proposed the autonomous machine learning to reach to the network equilibrium state by reducing the flow toward the input to weights of output layer neurons.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.37-44
• /
• 2021

Automatic classification of brain MRI images play an important role in early diagnosis of brain tumors. In this work, we present a deep learning-based brain tumor classification model in MRI images using ensemble of deep features. In our proposed framework, three different deep features from brain MR image are extracted using three different pre-trained models. After that, the extracted deep features are fed to the classification module. In the classification module, the three different deep features are first fed into the fully-connected layers individually to reduce the dimension of the features. After that, the output features from the fully-connected layers are concatenated and fed into the fully-connected layer to predict the final output. To evaluate our proposed model, we use openly accessible brain MRI dataset from web. Experimental results show that our proposed model outperforms other machine learning-based models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.601-603
• /
• 2018

Studies are under way to understand how the brain learns and how it works most effectively through the development of brain science. The purpose of this study is to apply brain - based learning principles as a way to effectively overcome the characteristics of the programming lesson and the difficulties that arise during the practice. In other words, by applying the brain-based learning principle appropriate to the characteristics of the Android programming class, the teaching and learning is designed so that the learner can effectively learn the programming.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.

• Journal of Gifted/Talented Education
• /
• v.21 no.2
• /
• pp.255-268
• /
• 2011

The 21st century is called as the "Age of knowledge flood", and thus the importance of the ability which can use knowledge creatively is more emphasized. Also, not only individual problem solving but also solving problems through effective communication skills with group members are needed, and therefore, it is requested to train potential gifted learner working together with others to practice cooperation and eventually grown up as a competitive human resource to adapt successfully in future environment. In this paper, to show the effectiveness of cooperative learning in gifted learners, members for cooperative learning group has been selected using whole brain theory from the 42 gifted middle school students who participated in summer gifted learner vacation program. From the analysis of the learners' learning motivation and frequency of interactions whole brain based cooperative learning is effective for enhancing both learning motivation and interactions. Therefore, the whole brain based cooperative learning is an effective pedagogy for enhancing the motivation as well as facilitating interactions within gifted learners.

• Journal of The Korean Association For Science Education
• /
• v.30 no.5
• /
• pp.647-667
• /
• 2010

The purpose of this study was to develop a brain-based analysis framework for evaluating teachinglearning program in science. To develop the framework, this study categorized educational constructs of the teachinglearning programs into one of three teaching-learning factors: cognition, motive, and emotion, using previous studies on science program. Ninety-three articles on the brain functions associated with science program were analyzed to extract brain activation regions related to the three educational constructs. After delineating the brain activation regions, we designed the brain function map, "the CORE Brain Map." Based on this brain map, we developed a brain-based analysis framework for evaluating science teaching-learning program using R & D processes. This framework consists of the brain regions, the bilateral dorsolateral prefrontal cortex, the bilateral ventrolateral prefrontal cortex, the bilateral orbitofrontal cortex, the anterior cingulate gyrus, the bilateral parietal cortex, the bilateral temporal cortex, the bilateral occipital cortex, the bilateral hippocampus, the bilateral amygdala, the bilateral nucleus accumbens, the bilateral striatum and the midbrain regions. These brain regions are associated with the aforementioned three educational factors; cognition, motivation, and emotion. The framework could be applied to the analysis and diagnosis of various teaching and learning programs in science.