• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.819-832
• /
• 2022

Cross-domain recommender system transfers knowledge across different domains to improve the recommendation performance in a target domain that has a relatively sparse model. However, they suffer from the "negative transfer" in which transferred knowledge operates as noise. This paper proposes a novel Multiple Fusion-based Deep Cross-Domain Recommendation named MFDCR. We exploit Doc2Vec, one of the famous word embedding techniques, to fuse data user-wise and transfer knowledge across multi-domains. It alleviates the "negative transfer" problem. Additionally, we introduce a simple multi-layer perception to learn the user-item interactions and predict the possibility of preferring items by users. Extensive experiments with three domain datasets from one of the most famous services Amazon demonstrate that MFDCR outperforms recent single and cross-domain recommendation algorithms. Furthermore, experimental results show that MFDCR can address the problem of "negative transfer" and improve recommendation performance for multiple domains simultaneously. In addition, we show that our approach is efficient in extending toward more domains.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 추계학술발표대회
• /
• pp.507-510
• /
• 2024

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by a progressive decline in cognitive function. Accurate and early diagnosis of AD is crucial for effective management and treatment. Traditional machine learning models, though commonly applied, often fall short in capturing the intricate relationships between diverse tabular data. Furthermore, the missing data issue, typically addressed using conventional imputation techniques, leads to reduced accuracy and generalizability of AD classification models. This paper introduces ADxClass, a novel deep learning framework that enhances AD classification by leveraging multi-domain attention fusion and data type-based imputation techniques for handling missing heterogeneous tabular data. ADxClass integrates data from various domains, including demographic, cognitive, genetic, and biomarkers obtained from neuroimaging measurements, to improve the robustness and accuracy of AD classification models. The model's efficiency is validated via a 5-fold cross-validation on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, showing significant improvements in classification performance compared to traditional machine learning approaches.

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.39-47
• /
• 2023

This study compares various transformation techniques for multifocus image fusion. Multi-focus image fusion is a procedure of merging multiple images captured at unalike focus distances to produce a single composite image with improved sharpness and clarity. In this research, the purpose is to compare different popular frequency domain approaches for multi-focus image fusion, such as Discrete Wavelet Transforms (DWT), Stationary Wavelet Transforms (SWT), DCT-based Laplacian Pyramid (DCT-LP), Discrete Cosine Harmonic Wavelet Transform (DC-HWT), and Dual-Tree Complex Wavelet Transform (DT-CWT). The objective is to increase the understanding of these transformation techniques and how they can be utilized in conjunction with one another. The analysis will evaluate the 10 most crucial parameters and highlight the unique features of each method. The results will help determine which transformation technique is the best for multi-focus image fusion applications. Based on the visual and statistical analysis, it is suggested that the DCT-LP is the most appropriate technique, but the results also provide valuable insights into choosing the right approach.

• Journal of Electrical Engineering and Technology
• /
• 제10권6호
• /
• pp.2384-2392
• /
• 2015

The technical development and practical applications of big-data for health is one hot topic under the banner of big-data. Big-data medical image fusion is one of key problems. A new fusion approach with coding based on Spherical Coordinate Domain (SCD) in Wireless Sensor Network (WSN) for big-data medical image is proposed in this paper. In this approach, the three high-frequency coefficients in wavelet domain of medical image are pre-processed. This pre-processing strategy can reduce the redundant ratio of big-data medical image. Firstly, the high-frequency coefficients are transformed to the spherical coordinate domain to reduce the correlation in the same scale. Then, a multi-scale model product (MSMP) is used to control the shrinkage function so as to make the small wavelet coefficients and some noise removed. The high-frequency parts in spherical coordinate domain are coded by improved SPIHT algorithm. Finally, based on the multi-scale edge of medical image, it can be fused and reconstructed. Experimental results indicate the novel approach is effective and very useful for transmission of big-data medical image(especially, in the wireless environment).

• 한국정밀공학회지
• /
• 제22권6호
• /
• pp.15-21
• /
• 2005

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.95-99
• /
• 2022

오픈 도메인 질의 응답 (ODQA, Open-Domain Question Answering)은 주어진 질문에 대한 답을 찾는 과업으로서 질문과 관련있는 지식을 찾는 "검색" 단계를 필요로 한다. 최근 이미지, 테이블 등의 검색을 요구하는 멀티 모달 ODQA에 대한 연구가 많이 진행되었을 뿐만 아니라 산업에서의 중요도 또한 높아지고 있다. 본 논문은 여러 종류의 멀티 모달 ODQA 중에서도 테이블 - 텍스트 기반 멀티 모달 ODQA 데이터 집합으로 Fusion-in-Decoder (FiD)를 이용한 멀티 모달 오픈 도메인 질의 응답 연구를 제안하며 베이스라인 대비 최대 EM 20.5, F1 23.2 향상을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.813-829
• /
• 2022

In multi-view subspace clustering, how to integrate the complementary information between perspectives to construct a unified representation is a critical problem. In the existing works, the unified representation is usually constructed in the original data space. However, when the data representation in each view is very diverse, the unified representation derived directly in the original data domain may lead to a huge information loss. To address this issue, different to the existing works, inspired by the latest revelation that the data across all perspectives have a very similar or close spectral block structure, we try to construct the unified representation in the spectral embedding domain. In this way, the complementary information across all perspectives can be fused into a unified representation with little information loss, since the spectral block structure from all views shares high consistency. In addition, to capture the global structure of data on each view with high accuracy and robustness both, we propose a novel low-rank approximation via the tight lower bound on the rank function. Finally, experimental results prove that, the proposed method has the effectiveness and robustness at the same time, compared with the state-of-art approaches.

• ETRI Journal
• /
• 제46권2호
• /
• pp.277-289
• /
• 2024

In this paper, we describe a neural network-based application that recommends multiple items using dialog context input and simultaneously outputs a response sentence. Further, we describe a multi-item recommendation by specifying it as a set of clothing recommendations. For this, a multimodal fusion approach that can process both cloth-related text and images is required. We also examine achieving the requirements of downstream models using a pretrained language model. Moreover, we propose a gate-based multimodal fusion and multiprompt learning based on a pretrained language model. Specifically, we propose an automatic evaluation technique to solve the one-to-many mapping problem of multi-item recommendations. A fashion-domain multimodal dataset based on Koreans is constructed and tested. Various experimental environment settings are verified using an automatic evaluation method. The results show that our proposed method can be used to obtain confidence scores for multi-item recommendation results, which is different from traditional accuracy evaluation.

• 한국전기전자재료학회논문지
• /
• 제25권7호
• /
• pp.516-520
• /
• 2012

In this paper, we have theoretically analyzed and designed a dielectric multi-layer sensor with a SPR (surface plasmon resonance) using analytical calculation and FDTD (finite difference time-domain) methods. The proposed structure is composed of periodic layer and thin metal film. It has many advantages. One of that is a high sensitivity of the SPR. Another is a high Q-factor of the characteristics in the PhC (photonic crystals) micro-cavity structure. The incident light has double resonance characteristics, because the filtered light by PhC structure, dielectric multi-layer, is met the thin metal film for SPR effect. We have also observed the change of resonance characteristics according to the variation of effective index on the metal film.