• ETRI Journal
• /
• 제25권5호
• /
• pp.401-406
• /
• 2003

A biometric system determines the identity of a person by measuring physical features that can distinguish that person from others. Since biometric features have many variations and can be easily corrupted by noises and deformations, it is necessary to apply machine learning techniques to treat the data. When applying the conventional machine learning methods in designing a specific biometric system, however, one first runs into the difficulty of collecting sufficient data for each person to be registered to the system. In addition, there can be an almost infinite number of variations of non-registered data. Therefore, it is difficult to analyze and predict the distributional properties of real data that are essential for the system to deal with in practical applications. These difficulties require a new framework of identification and verification that is appropriate and efficient for the specific situations of biometric systems. As a preliminary solution, this paper proposes a simple but theoretically well-defined method based on a statistical test theory. Our computational experiments on real-world data show that the proposed method has potential for coping with the actual difficulties in biometrics.

• Journal of Korea Multimedia Society
• /
• 제23권12호
• /
• pp.1486-1495
• /
• 2020

The analysis of digital microscopy images plays a vital role in computer-aided diagnosis (CAD) and prognosis. The main purpose of this paper is to develop a machine learning technique to predict the histological grades in prostate biopsy. To perform a multiclass classification, an AI-based deep learning algorithm, a multichannel convolutional neural network (MCCNN) was developed by connecting layers with artificial neurons inspired by the human brain system. The histological grades that were used for the analysis are benign, grade 3, grade 4, and grade 5. The proposed approach aims to classify multiple patterns of images extracted from the whole slide image (WSI) of a prostate biopsy based on the Gleason grading system. The Multichannel Convolution Neural Network (MCCNN) model takes three input channels (Red, Green, and Blue) to extract the computational features from each channel and concatenate them for multiclass classification. Stain normalization was carried out for each histological grade to standardize the intensity and contrast level in the image. The proposed model has been trained, validated, and tested with the histopathological images and has achieved an average accuracy of 96.4%, 94.6%, and 95.1%, respectively.

• The Journal of Korean Association of Computer Education
• /
• 제21권2호
• /
• pp.59-71
• /
• 2018

The purpose of this study is suggesting the direction for improving web accessibility by analyzing the state of abiding by the web accessibility by the centers for teaching and learning support at the education offices in cities and provinces which provide the learning and teaching materials to the K-12 members and the interested people. For this aim, nine centers for teaching and learning support were evaluated. The primary manual evaluation by two experts and the evaluation by 18 users were conducted. The users were comprised of hearing-impaired people, visually-impaired people, brain-disabled people, the elderly, various browser users, and a variety of operating system users. As a result of the analysis, not a single center for teaching and learning support had conformed to web accessibility in the expert evaluation and the user evaluation. As a result of the expert evaluation, the errors regarding web design improvement, HTML source error correction, and provision of alternative measures for the disabled were found. This study is meaningful in the sense that it provided various discussions with regard to the direction of the future web accessibility evaluation based on the improved web accessibility evaluation method.

• Journal of Ginseng Research
• /
• 제47권5호
• /
• pp.662-671
• /
• 2023

Background: 20(S)-protopanaxadiol (PPD), a ginsenoside metabolite, has prominent benefits for the central nervous system, especially in improving learning and memory. However, its transcriptional targets in brain tissue remain unknown. Methods: In this study, we first used mass spectrometry-based drug affinity responsive target stability (DARTS) to identify the potential proteins of ginsenosides and intersected them with the transcription factor library. Second, the transcription factor PURA was confirmed as a target of PPD by biolayer interferometry (BLI) and molecular docking. Next, the effect of PPD on the transcriptional levels of target genes of PURA in brain tissues was determined by qRT-PCR. Finally, bioinformatics analysis was used to analyze the potential biological features of these target proteins. Results: The results showed three overlapping transcription factors between the proteomics of DARTS and transcription factor library. BLI analysis further showed that PPD had a higher direct interaction with PURA than parent ginsenosides. Subsequently, BLI kinetic analysis, molecular docking, and mutations in key amino acids of PURA indicated that PPD specifically bound to PURA. The results of qRT-PCR showed that PPD could increase the transcription levels of PURA target genes in brain. Finally, bioinformatics analysis showed that these target proteins were involved in learning and memory function. Conclusion: The above-mentioned findings indicate that PURA is a transcription target of PPD in brain, and PPD upregulate the transcription levels of target genes related to cognitive dysfunction by binding PURA, which could provide a chemical and biological basis for the study of treating cognitive impairment by targeting PURA.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.416-418
• /
• 2022

Glioma is a type of brain tumor that occurs in glial cells and is classified into two types: high hrade hlioma with a poor prognosis and low grade glioma. Magnetic resonance imaging (MRI) as a non-invasive method is widely used in glioma diagnosis research. Studies to obtain complementary information by combining multiple modalities to overcome the incomplete information limitation of single modality are being conducted. In this study, we developed a 3D CNN-based model that applied input-level fusion to MRI of four modalities (T1, T1Gd, T2, T2-FLAIR). The trained model showed classification performance of 0.8926 accuracy, 0.9688 sensitivity, 0.6400 specificity, and 0.9467 AUC on the validation data. Through this, it was confirmed that the grade of glioma was effectively classified by learning the internal relationship between various modalities.

• Journal of Institute of Control, Robotics and Systems
• /
• 제13권9호
• /
• pp.832-837
• /
• 2007

Electroencephalographic(EEG) is used to record activities of human brain in the area of psychology for many years. As technology develope, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study Emotion Recognition method which uses one of EEG signals and Gestures in the existing research. In this paper, we use together EEG signals and Gestures for Emotion Recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both EEG signals and gestures gets high recognition rates better than using EEG signals or gestures. Both EEG signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on a reinforcement learning.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• Smart Media Journal
• /
• 제13권4호
• /
• pp.86-93
• /
• 2024

The development of functional magnetic resonance imaging (fMRI) has significantly contributed to mapping brain functions and understanding brain networks during rest. This paper proposes a CNN-LSTM-based classification model to classify the progression stages of Alzheimer's disease. Firstly, four preprocessing steps are performed to remove noise from the fMRI data before feature extraction. Secondly, the U-Net architecture is utilized to extract spatial features once preprocessing is completed. Thirdly, the extracted spatial features undergo LSTM processing to extract temporal features, ultimately leading to classification. Experiments were conducted by adjusting the temporal dimension of the data. Using 5-fold cross-validation, an average accuracy of 96.4% was achieved, indicating that the proposed method has high potential for identifying the progression of Alzheimer's disease by analyzing fMRI data.

• International Journal of Contents
• /
• 제14권4호
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• Journal of Korean Elementary Science Education
• /
• 제35권4호
• /
• pp.469-478
• /
• 2016

A brain-based evolutionary approach developed by reflecting the brain functions and authentic science is consisted of Affective, Behavioral, and Cognitive domains, and within each domain the processes of Diversifying, Evaluating, and Furthering are proceeded (ABC-DEF). Two core components of creativity of originality and usefulness are inherent in each step. So, this study analyzed scientific creativity with the originality and usefulness components in cognitive domain, which is composed of diversifying the meanings inherent in the results of observations or experiments (C-D), evaluating the meanings (C-E), and furthering (C-F) in learning of 'World of Plants' unit which includes two topics of 'Plants on Land' and 'Plants in Water and Special Environment'. A total of 20 fourth grade students at Y elementary school in Gyeonggi province participated in the study. The main results of this study are as follows. First, the scientific creativity in step C-D (Diversifying stage) was assessed according to the scientific creativity assessment formula. The scores of scientific creativity were quite different with topics and showed different pattern in the originality and usefulness components. Second, when the students compare and evaluate the values of each meaning (C-E stage), they weighed more on usefulness than originality, such as "because it is useful" or "because it solve many everyday problems". Third, the overall scores of scientific creativity in step C-F (Furthering stage), as compared with those of step C-D, were low and showed decrease in the average scores of originality from 9.8 to 7.5 points, whereas increase in the average scores of usefulness from 5.4 to 6.1 points. In conclusion, these results showed that, even though the levels were not so high, the students, as scientists, can exhibit the scientific creativity in the processes of diversifying, comparing and evaluating, and applying the meanings about the results obtained by observations or experiments. The specific and various strategies to help students express their potential scientific creativity more effectively need to be developed.