• Title/Summary/Keyword: Subject-independent classification

Search Result 37, Processing Time 0.031 seconds

Improving the Subject Independent Classification of Implicit Intention By Generating Additional Training Data with PCA and ICA

  • Oh, Sang-Hoon
    • International Journal of Contents
    • /
    • v.14 no.4
    • /
    • 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.

Subject Independent Classification of Implicit Intention Based on EEG Signals

  • Oh, Sang-Hoon
    • International Journal of Contents
    • /
    • v.12 no.3
    • /
    • pp.12-16
    • /
    • 2016
  • Brain computer interfaces (BCI) usually have focused on classifying the explicitly-expressed intentions of humans. In contrast, implicit intentions should be considered to develop more intelligent systems. However, classifying implicit intention is more difficult than explicit intentions, and the difficulty severely increases for subject independent classification. In this paper, we address the subject independent classification of implicit intention based on electroencephalography (EEG) signals. Among many machine learning models, we use the support vector machine (SVM) with radial basis kernel functions to classify the EEG signals. The Fisher scores are evaluated after extracting the gamma, beta, alpha and theta band powers of the EEG signals from thirty electrodes. Since a more discriminant feature has a larger Fisher score value, the band powers of the EEG signals are presented to SVM based on the Fisher score. By training the SVM with 1-out of-9 validation, the best classification accuracy is approximately 65% with gamma and theta components.

Sensibility Classification Algorithm of EEGs using Multi-template Method (다중 템플릿 방법을 이용한 뇌파의 감성 분류 알고리즘)

  • Kim Dong-Jun
    • The Transactions of the Korean Institute of Electrical Engineers D
    • /
    • v.53 no.12
    • /
    • pp.834-838
    • /
    • 2004
  • This paper proposes an algorithm for EEG pattern classification using the Multi-template method, which is a kind of speaker adaptation method for speech signal processing. 10-channel EEG signals are collected in various environments. The linear prediction coefficients of the EEGs are extracted as the feature parameter of human sensibility. The human sensibility classification algorithm is developed using neural networks. Using EEGs of comfortable or uncomfortable seats, the proposed algorithm showed about 75% of classification performance in subject-independent test. In the tests using EEG signals according to room temperature and humidity variations, the proposed algorithm showed good performance in tracking of pleasantness changes and the subject-independent tests produced similar performances with subject-dependent ones.

Brain Computer Interfacing: A Multi-Modal Perspective

  • Fazli, Siamac;Lee, Seong-Whan
    • Journal of Computing Science and Engineering
    • /
    • v.7 no.2
    • /
    • pp.132-138
    • /
    • 2013
  • Multi-modal techniques have received increasing interest in the neuroscientific and brain computer interface (BCI) communities in recent times. Two aspects of multi-modal imaging for BCI will be reviewed. First, the use of recordings of multiple subjects to help find subject-independent BCI classifiers is considered. Then, multi-modal neuroimaging methods involving combined electroencephalogram and near-infrared spectroscopy measurements are discussed, which can help achieve enhanced and robust BCI performance.

A Study on the Development of an Independent Movement Collection Classification System: Focus on the Gonghun Digital Archive (독립 운동 컬렉션 분류 체계 개발에 관한 연구 - 공훈전자사료관을 중심으로 -)

  • Oh, Jung Hee;Chung, Yeon Kyoung
    • Journal of Korean Society of Archives and Records Management
    • /
    • v.18 no.4
    • /
    • pp.99-124
    • /
    • 2018
  • This study suggests the development of a classification system for the Independent Movement Records of the Ministry of Patriots and Veterans Affairs based on the collection of Gonghun Digital Archive based on sources, subjects, and media types. First, the classification system by source is organized by hierarchy, and the records classified by source are classified into the second category based on the related keyword. Then, the records are classified into 17 media types. Finally, it is described in the citation order of "source-subject-media type." In addition, a meaningful collection using inductive methods based on the subject words is derived. Finally, Gonghun Digital Archive collections are categorized by media types, sources, and subjects so that users can easily find the records. The result of this study is a classification system to support records retrieval of an independent movement collection, and it will become a basis for expanding the accessibility of the user and the service of independent movement records.

A Study on the Improvement of the Classification System on Archives and Records Management Studies in KDC (한국십진분류법 기록관리학 분야 분류체계 개선에 관한 연구)

  • Park, Su-Hyun;Lee, Myoung-Gyu
    • Journal of the Korean BIBLIA Society for library and Information Science
    • /
    • v.27 no.3
    • /
    • pp.25-50
    • /
    • 2016
  • Archives and Records Management Studies is being developed its own independent domains. However, the existing library classification scheme such as the KDC don't properly reflect the characteristics of Archives and Records Management Studies. This classification scheme has the irrational part of the arrangement of the subject items and should be required to rearrange subdivision of the subject areas. In this study, According to the characteristics of Archives and Records Management Studies, It is set up 8 subject areas, Records Management (General), the law and polices of records management, the collection and appraisal of the records, the documentary organization, recording information services, preservation of the records, archives management, archives and records center, etc. After analyzing the major contemporary library classification system such as KDC, DDC, NDC, UDC, LCC, then It is suggested that improvement measures through analyzing classification status and keywords of the Archives and Records Management data contained in Korean National Bibliography. In Archives and records management studies, The contents of the eight subject areas related to the field are changed to allow integration with KDC 028.

Management system of thesis in university library (대학도서관의 석. 박사학위논문 관리체제)

  • 손문철
    • Journal of Korean Library and Information Science Society
    • /
    • v.14
    • /
    • pp.71-98
    • /
    • 1987
  • After 1970s, because of an increasing peoples for higher education and graduate school-oriented education system, quantities of thesis were produced for short term and they began to be an important part of gift materials in university libraries. As an unpublished documents, thesis is narrow in subject, deep in content, irregular is page, incomplete in binding and produce limited-edition during short time simultaneously at most institutions. So most libraries are in difficulties for acquisition processing and circulation. Because of an increasing number of thesis will be produce and cutback of budget, shortage of staff, library service for user will be difficult and rational and efficient management is absolutely essential to library. In form and content, thesis is in distinction with other library materials, they must be handler as an independent item and library will seek an a n.0, ppropriate processing and using method of them. Analysis and synthesis of this study are summarized as follows. 1. In acquisition of thesis, it is desirable that they has an independent accession book with a simplified processing procedure and the binding of them is desirable together with subject field(major or department) by institutions. 2. In classification and cataloging of thesis, it is rational that library use the same classification scheme as other materials and expand in details. Simplified catalog will be reduce the time and/or personnel problem than using the traditional KCR or AACR. 3. As an retrieval tool, author, title, shelf and subject catalog must be prepared in thesis room. Index of thesis will be available for retrieval with the trend of union list and Korean periodicals index (National Assembly Library, Republic of Korea) must include the thesis. 4. Because of the nature and characteristics of thesis, library has to equip an independent room and open stack for the a n.0, ppropriate retrieval and frequent use. Qualified librarian must serve for the efficient circulation service.

  • PDF

Multimodal Parametric Fusion for Emotion Recognition

  • Kim, Jonghwa
    • International journal of advanced smart convergence
    • /
    • v.9 no.1
    • /
    • pp.193-201
    • /
    • 2020
  • The main objective of this study is to investigate the impact of additional modalities on the performance of emotion recognition using speech, facial expression and physiological measurements. In order to compare different approaches, we designed a feature-based recognition system as a benchmark which carries out linear supervised classification followed by the leave-one-out cross-validation. For the classification of four emotions, it turned out that bimodal fusion in our experiment improves recognition accuracy of unimodal approach, while the performance of trimodal fusion varies strongly depending on the individual. Furthermore, we experienced extremely high disparity between single class recognition rates, while we could not observe a best performing single modality in our experiment. Based on these observations, we developed a novel fusion method, called parametric decision fusion (PDF), which lies in building emotion-specific classifiers and exploits advantage of a parametrized decision process. By using the PDF scheme we achieved 16% improvement in accuracy of subject-dependent recognition and 10% for subject-independent recognition compared to the best unimodal results.

A FAST KACZMARZ-KOVARIK ALGORITHM FOR CONSISTENT LEAST-SQUARES PROBLEMS

  • Popa, Constantin
    • Journal of applied mathematics & informatics
    • /
    • v.8 no.1
    • /
    • pp.9-26
    • /
    • 2001
  • In some previous papers the author extended two algorithms proposed by Z. Kovarik for approximate orthogonalization of a finite set of linearly independent vectors from a Hibert space, to the case when the vectors are rows (not necessary linearly independent) of an arbitrary rectangular matrix. In this paper we describe combinations between these two methods and the classical Kaczmarz’s iteration. We prove that, in the case of a consistent least-squares problem, the new algorithms so obtained converge ti any of its solutions (depending on the initial approximation). The numerical experiments described in the last section of the paper on a problem obtained after the discretization of a first kind integral equation ilustrate the fast convergence of the new algorithms. AMS Mathematics Subject Classification : 65F10, 65F20.

A CEPHALOMETRIC STUDY ON THE SOFT TISSUE PROFILE CHANGES BY ORTHODONTIC TREATMENT IN FEMALE PATIENTS (여자 부정교합자의 치료전후 연조직 측모 변화에 관한 두부 방사선학적 연구)

  • Park, Sook-Kyu;Suhr, Cheong-Hoon
    • The korean journal of orthodontics
    • /
    • v.21 no.1 s.33
    • /
    • pp.113-130
    • /
    • 1991
  • This study was undertaken to investigate soft tissue profile changes by orthodontic treatment in female patients. Traditional cephalometric appraisal yields data of dubious scientific value, the soft tissue profile forms were evaluated by finite element method. The subject was divided into three groups according to Angle's classification and each group was composed of 25 female patients averaged aged 12-14 years at the start of treatment. The changes in soft tissue form were evaluated by computing the degree of distortion in each triangle after treatment compared with the triangle before treatment. The conclusions were as follows; 1. The soft tissue profile forms were evaluated by finite element method and independent evaluation of each element by local changes was possible. 2. Maximum and minimum principal strains showed marked variability depending on the particular finite element and each group and Class II, III sample was greater than Class I sample. 3. Soft tissue size changes as a result of orthodontic treatment was not related to those of shape. 4. Soft tissue changes by orthodontic treatment were variable in individual patient, and were not related to Angle's classification.

  • PDF