• 반도체디스플레이기술학회지
• /
• 제16권4호
• /
• pp.36-40
• /
• 2017

With an attempt to enhance the visibility of laser beam, we have investigated a black matrix with scattering particles by ray tracing simulations. As the scattering particle density is increased, the detected power by the receiver is increased, thereby enhancing the visibility. In reality, the visibility is reduced with increasing incident angle (away from the normal incidence) of laser beam, a phenomenon also observed by ray tracing simulations. It is due to the fact that the mean path is increased within a highly absorptive BM layer or a smaller number of rays hit the BM area when the incident angle is high. Embedding a number of scattering particles into BM may bring in crosstalk among pixels. However, it is negligible because scattered rays inside highly absorptive BM are re-scattered due to the high scattering particle density, decreasing the power of scattered rays into the active areas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.771-791
• /
• 2022

Protein-protein interaction (PPI) extraction from original text is important for revealing the molecular mechanism of biological processes. With the rapid growth of biomedical literature, manually extracting PPI has become more time-consuming and laborious. Therefore, the automatic PPI extraction from the raw literature through natural language processing technology has attracted the attention of the majority of researchers. We propose a PPI extraction model based on the large pre-trained language model and adversarial training. It enhances the learning of semantic and syntactic features using BioBERT pre-trained weights, which are built on large-scale domain corpora, and adversarial perturbations are applied to the embedding layer to improve the robustness of the model. Experimental results showed that the proposed model achieved the highest F1 scores (83.93% and 90.31%) on two corpora with large sample sizes, namely, AIMed and BioInfer, respectively, compared with the previous method. It also achieved comparable performance on three corpora with small sample sizes, namely, HPRD50, IEPA, and LLL.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4024-4041
• /
• 2022

Robust reversible watermarking has attracted widespread attention in the field of information hiding in recent years. It should not only have robustness against attacks in transmission but also meet the reversibility of distortion-free transmission. According to our best knowledge, the most recent robust reversible watermarking methods adopt a single image as the carrier, which might lead to low efficiency in terms of carrier utilization. To address the issue, a novel dual-image robust reversible watermarking framework is proposed in this paper to effectively utilize the correlation between both carriers (namely dual images) and thus improve the efficiency of carrier utilization. In the dual-image robust reversible watermarking framework, a two-layer robust watermarking mechanism is designed to further improve the algorithm performances, i.e., embedding capacity and robustness. In addition, an optimization model is built to determine the parameters. Finally, the proposed framework is applied in different domains (namely domain-independent), i.e., Slantlet Transform and Singular Value Decomposition domain, and Zernike moments, respectively to demonstrate its effectiveness and generality. Experimental results demonstrate the superiority of the proposed dual-image robust reversible watermarking framework.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1075-1084
• /
• 2022

Internet of Things(IoT) has become a key available technology for efficiently implementing device to device(D2D) services in various domains such as smart home, healthcare, smart city, agriculture, energy, logistics, and transportation. A lightweight publish/subscribe(Pub/Sub) messaging protocol not only establishes data dissemination pattern but also supports connectivity between IoT devices and their applications. Also, a Pub/Sub broker is deployed to facilitate data exchange among IoT devices. A scalable edge-based publish/subscribe (Pub/Sub) broker overlay networks support latency-sensitive IoT applications. In this paper, we design a hypercube grid quorum(HGQ) for distributed Pub/Sub systems based IoT applications. In designing HGQ, the network of hypercube structures suitable for the publish/subscribe model is built in the edge layer, and the proposed HGQ is designed by embedding a mesh overlay network in the hypercube. As their applications, we propose an HGQ-based mechansim for dissemination of the data of sensors or the message/event of IoT devices in IoT environments. The performance of HGQ is evaluated by analytical models. As the results, the latency and load balancing of applications based on the distributed Pub/Sub system using HGQ are improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권1호
• /
• pp.51-73
• /
• 2023

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNetB0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.259-263
• /
• 2021

상호참조해결은 주어진 문서에서 상호참조해결 대상이 되는 멘션(mention)을 식별하고, 동일한 개체(entity)를 의미하는 멘션들을 찾아 그룹화하는 자연어처리 태스크이다. 최근 상호참조해결에서는 BERT를 이용하여 단어의 문맥 표현을 얻은 후, 멘션 탐지와 상호참조해결을 동시에 진행하는 end-to-end 모델이 주로 연구되었으나, 512 토큰 이상의 긴 문서를 처리하기 위해서는 512 토큰 이하로 문서를 분할하여 처리하기 때문에 길이가 긴 문서에 대해서는 상호참조해결 성능이 낮아지는 문제가 있다. 본 논문에서는 512 토큰 이상의 긴 문서를 위한 BERT 기반의 end-to-end 상호참조해결 모델을 제안한다. 본 모델은 긴 문서를 512 이하의 토큰으로 쪼개어 기존의 BERT에서 단어의 1차 문맥 표현을 얻은 후, 이들을 다시 연결하여 긴 문서의 Global Positional Encoding 또는 Embedding 값을 더한 후 Global BERT layer를 거쳐 단어의 최종 문맥 표현을 얻은 후, end-to-end 상호참조해결 모델을 적용한다. 실험 결과, 본 논문에서 제안한 모델이 기존 모델과 유사한 성능을 보이면서(테스트 셋에서 0.16% 성능 향상), GPU 메모리 사용량은 1.4배 감소하고 속도는 2.1배 향상되었다.

• 멤브레인
• /
• 제17권3호
• /
• pp.269-275
• /
• 2007

분리층 두께가 5${\mu}m$이며 Si/Al 몰비가 1.5인 Na형 faujasite 제올라이트 분리막을 이차성장 공정에 의하여 제조하였고, 투과부에 13X 제올라이트 흡착제 충진 전후의 진공모드에서의 $CO_2/N_2$ 분리거동을 $CO_2/N_2$ 몰비가 1인 혼합기체에 대하여 $30^{\circ}C$에서 평가하였다. 충진된 13X 제올라이트 흡착제는 $CO_2$ 투과도와 $CO_2/N_2$ 선택도를 동시에 증진시켰다. 이 현상은 13X 제올라이트 흡착제 충진이 다공성 $\alpha$-알루미나 지지체의 기공채널을 통한 $CO_2$ 탈출을 증진시킴으로써 faujasite 제올라이트/$\alpha$-알루미나 상계면에서의 $CO_2$ 탈착을 증진시켰기 때문으로 설명되었다. 본 논문으로부터 흡착제와 분리막의 혼성화는 일반적으로 보여지는 선택도와 투과도의 역비례 관계를 획기적으로 개선할 방법임이 확인되었다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2008년도 하계학술대회 논문집 Vol.9
• /
• pp.62-62
• /
• 2008

As micro-system move toward higher speed and miniaturization, requirements for embedding the passive components into printed circuit boards (PCBs) grow consistently. They should be fabricated in smaller size with maintaining and even improving the overall performance. Miniaturization potential steps from the replacement of surface-mount components and the subsequent reduction of the required wiring-board real estate. Among the embedded passive components, capacitors are most widely studied because they are the major components in terms of size and number. Embedding of passive components such as capacitors into polymer-based PCB is becoming an important strategy for electronics miniaturization, device reliability, and manufacturing cost reduction Now days, the dielectric films deposited directly on the polymer substrate are also studied widely. The processing temperature below $200^{\circ}C$ is required for polymer substrates. For a low temperature deposition, bismuth-based pyrochlore materials are known as promising candidate for capacitor $B_2Mg_{2/3}Nb_{4/3}O_7$ ($B_2MN$) multi layers were deposited on Pt/$TiO_2/SiO_2$/Si substrates by radio frequency magnetron sputtering system at room temperature. The physical and structural properties of them are investigated by SEM, AFM, TEM, XPS. The dielectric properties of MIM structured capacitors were evaluated by impedance analyzer (Agilent HP4194A). The leakage current characteristics of MIM structured capacitor were measured by semiconductor parameter analysis (Agilent HP4145B). 200 nm-thick $B_2MN$ muti layer were deposited at room temperature had capacitance density about $1{\mu}F/cm^2$ at 100kHz, dissipation factor of < 1% and dielectric constant of > 100 at 100kHz.

• 지식경영연구
• /
• 제22권4호
• /
• pp.27-40
• /
• 2021

Click-Through Rate(CTR) 예측은 추천시스템에서 후보 항목의 순위를 결정하고 높은 순위의 항목들을 추천하여 고객의 정보 과부하를 줄임과 동시에 판매 촉진을 통한 수익 극대화를 달성할 수 있는 핵심 기능이다. 자연어 처리와 이미지 분류 분야는 심층신경망(deep neural network)의 활용을 통한 괄목한 성장을 하고 있다. 최근 이 분야의 주류를 이루던 모델과 차별화된 어텐션(attention) 메커니즘 기반의 트랜스포머(transformer) 모델이 제안되어 state-of-the-art를 달성하였다. 본 연구에서는 CTR 예측을 위한 트랜스포머 기반 모델의 성능 향상 방안을 제시한다. 자연어와 이미지 데이터와는 다른 이산적(discrete)이며 범주적(categorical)인 CTR 데이터 특성이 모델 성능에 미치는 영향력을 분석하기 위해 임베딩의 일반화(regularization)와 트랜스포머의 정규화(normalization)에 관한 실험을 수행한다. 실험 결과에 따르면, CTR 데이터 입력 처리를 위한 임베딩 과정에서 L2 일반화의 적용과 트랜스포머 모델의 기본 정규화 방법인 레이어 정규화 대신 배치 정규화를 적용할 때 예측 성능이 크게 향상됨을 확인하였다.