Global-Leading Research and Education in Brain and Cognitive engineering KOREA UNIVERSITY To understand the structure and the key principles of high-order information processing by which brains work,
and to implement these in artificial systems that interact intelligently with real world

Research Highlight

Research
Prof. Heung-Il Suk`s paper accepted in Brain Structure & Function
Author Administrator (IP: *.152.163.70) Date 2015-05-07 09:32 Views 905
원본사진보기

Prof. Heung-Il Suk`s new research on `Deep Sparse Multi-Task Learning for Feature Selection in Alzheimer’s Disease Diagnosis` was accepted in Brain Structure & Function.

 

Title: Deep Sparse Multi-Task Learning for Feature Selection in Alzheimer’s Disease Diagnosis

 

Abstract:

 

Recently, neuroimaging-based Alzheimers Disease (AD) or Mild Cognitive Impairment (MCI) diagnosis has attracted researchers in the field, due to the increasing prevalence of the diseases. Unfortunately, the unfavourable high-dimensional nature of neuroimaging, but a limited small number of samples available, makes it challenging to build a robust computer- aided diagnosis system. Machine learning techniques have been considered as a useful tool in this respect and, among various methods, sparse regression has shown its validity in the literature. However, to our best knowledge, the existing sparse regression methods mostly try to select features based on the optimal regression coefficients in one step. We argue that since the training feature vectors are composed of both informative and uninformative or less informative features, the resulting optimal regression coefficients are inevidently affected by the uninformative or less informative features. To this end, we first propose a novel deep architecture to recursively dis- card uninformative features by performing sparse multi-task learning in a hierarchical fashion. We further hypothesize that the optimal regression coefficients reflect the relative importance of features in representing the target response variables. In this regard, we use the optimal regression coefficients learned in one hierarchy as feature weighting factors in the following hierarchy, and formulate a weighted sparse multi-task learning method. Lastly, we also take into account the distributional characteristics of samples per class and use clustering-induced subclass label vectors as target response values in our sparse regression model. In our experiments on the ADNI cohort, we performed both binary and multi-class classification tasks in AD/MCI diagnosis and showed the superiority of the proposed method by comparing with the state-of-the-art methods. 

File re_img.gif(10.9K)


Research
Prof. Seong-Whan Lee's paper accepted in IEEE Trans. on Pattern Analysis and Machine Intelligence
Prof. Seong-Whan Lee's paper accepted in IEEE Trans. on Pattern Analysis and Mac…
Prof. Seong-Whan Lee's new research, A Novel Linelet-based Representation for Line Segment Detection was accepted in IEEE Trans. on Pattern Analysis and Machine Intelligence. Title: A Novel Linelet-based Representation for Line Segment Detection Abstract: This paper proposes a method for line segment detection in digital images.We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image …

2017-02-14

Prof.Jae-Ho Han’s paper accepted in IEEE/ASME Transactions on Mechatronics
Prof.Jae-Ho Han’s paper accepted in IEEE/ASME Transactions on Mechatronics
Prof. Jae-Ho Han’s new research on `Real-Time Triple Field of View Interferometry for Scan-Free Monitoring of Multiple Objects` was accepted in IEEE/ASME Transactions on Mechatronics. Title: Real-Time Triple Field of View Interferometry for Scan-Free Monitoring of Multiple ObjectsAbstract:Synchronous scanning of multiple objects is essential to health monitoring of cells with high reliability. In general, monitoring multiple objects with f…

2017-01-17

Prof.Heung-II Suk’s paper accepted in Medical Image Analysis
Prof.Heung-II Suk’s paper accepted in Medical Image Analysis
Prof. Heung-II Suk’s new research on `Deep Ensemble Learning of Sparse Regression Models for Brain Disease Diagnosis` was accepted in Medical Image Analysis. Title: Deep Ensemble Learning of Sparse Regression Models for Brain Disease DiagnosisAbstract: Recent studies on brain imaging analysis witnessed the core roles of machine learning techniques in computer-assisted intervention for brain disease diagnosis. Of various machine-l…

2017-01-13

Prof.Byoung-Kyong Min’s paper accepted in Scientific Reports
Prof.Byoung-Kyong Min’s paper accepted in Scientific Reports
Prof. Byoung-Kyong Min’s new research on `Decoding of top-down cognitive processing for SSVEP-controlled BMI` was accepted in Scientific Reports. Title: Decoding of top-down cognitive processing for SSVEP-controlled BMI Abstract:We present a fast and accurate non-invasive brain-machine interface (BMI) based on demodulating steady-state visual evoked potentials (SSVEPs) in electroencephalography (EEG). Our study reports an SSVEP-BMI that, f…

2016-10-13

Prof.Byoung-Kyong Min’s paper accepted in Hearing Research
Prof.Byoung-Kyong Min’s paper accepted in Hearing Research
Prof. Byoung-Kyong Min’s new research on `Top-down and Bottom-up Neurodynamic Evidence in Patients with Tinnitus` was accepted in Hearing Research. Title: Top-down and Bottom-up Neurodynamic Evidence in Patients with Tinnitus Abstract:Although a peripheral auditory (bottom-up) deficit is an essential prerequisite for the generation of tinnitus, central cognitive (top-down) impairment has also been shown to be an inherent neuropatholog…

2016-10-07

Prof. Christian Wallraven’s paper accepted in Human Brain Mapping
Prof. Christian Wallraven’s paper accepted in Human Brain Mapping
Prof. Christian Wallraven’s new research on ` “Can touch this”: cross-modal shape categorization performance is associated with micro-structural characteristics of white matter association pathways` was accepted in Human Brain Mapping.Title: “Can touch this”: cross-modal shape categorization performance is associated with micro-structural characteristics of white matter association pathwaysAbstract: Previous studies on visuo-haptic shap…

2016-09-26

Prof. Christian Wallraven`s paper accepted in Psychonomic Bulletin & Review
Prof. Christian Wallraven`s paper accepted in Psychonomic Bulletin & Review
Prof. Christian Wallraven’s new research on `Cannot Avert the Eyes: Reduced Attentional Blink toward Others’ Emotional Expressions in Empathic People` was accepted in Psychonomic Bulletin & Review.Title: Cannot Avert the Eyes: Reduced Attentional Blink toward Others’ Emotional Expressions in Empathic PeopleAbstract: Empathy is one of the core components of social interaction. Although current models of empathy emphasize the role of attention, few…

2016-09-22

Prof. Seong-Whan Lee`s paper accepted in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Prof. Seong-Whan Lee`s paper accepted in IEEE Transactions on Neural Systems and…
Prof. Seong-Whan Lee`s new research on `Commanding a Brain-Controlled Wheelchair using Steady-State Somatosensory Evoked Potentials` was accepted in IEEE Transactions on Neural Systems and Rehabilitation Engineering.Title: Commanding a Brain-Controlled Wheelchair using Steady-State Somatosensory Evoked Potentials Abstract: In this work, we propose a novel brain-controlled wheelchair, one of the major applications of brain-machine interf…

2016-05-27

Prof. Jae-Ho Han`s paper accepted in IEEE/OSA Journal of Lightwave Technology
Prof. Jae-Ho Han`s paper accepted in IEEE/OSA Journal of Lightwave Technology
Prof. Jae-Ho Han`s new research on `In vitro Monitoring of a Cultured Human Retinal Pigment Epithelium Using 1,375-nm Spectral Domain Optical Coherence Tomography` was accepted in IEEE/OSA Journal of Lightwave Technology.Title: In vitro Monitoring of a Cultured Human Retinal Pigment Epithelium Using 1,375-nm Spectral Domain Optical Coherence TomographyAbstract: Measurement of cell number is important in cell-based in vitro screenings for the…

2016-05-27

Prof. Heung-Il Suk`s paper accepted in NeuroImage
Prof. Heung-Il Suk`s paper accepted in NeuroImage
Prof. Heung-Il Suk`s new research on `State-Space Model with Deep Learning for Functional Dynamics Estimation in Resting-State fMRI` was accepted in NeuroImage.Title: State-Space Model with Deep Learning for Functional Dynamics Estimation in Resting-State fMRIAbstract: Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and …

2016-01-05

 1 2 3 4 5 6 7 8 9