Conventional visual target detection with EEG signals has been experimented by exposing target objects that are large enough to be noticed without searching on visual image in order to average their ...corresponding responses such as event-related potentials (ERPs) to raise signal-to-noise ratio. Recent studies turn attention to decoding single-trial ERPs, while their experiments still minimize target object search time. In this paper, we studied the temporal aspects of target recognition of human brain including target object search by introducing the concept of semi-targets that are features posterior to offset of target visual stimuli, and applying it into a type of contrastive learning, Triplet MatchNet. The results showed that features five seconds posterior to target visual stimuli help increase in performance of EEG decoding.
This paper presents a scalable page cache called ScaleCache for improving SSD scalability. Specifically, we first propose a concurrent data structure of page cache based on XArray (ccXArray) to ...enable access and update the page cache concurrently. Second, we introduce a direct page flush (dflush) which directly flushes pages to storage devices in a parallel and opportunistic manner. We implement ScaleCache with two techniques in the Linux kernel and evaluate it on a 64-core machine with eight NVMe SSDs. Our evaluations show that ScaleCache improves the performance of Linux file systems by up to 6.81× and 4.50× compared with the existing scheme and scalable scheme for multiple SSDs, respectively.
Wafer level reliability (WLR) issues of DRAM cell and peripheral transistors are discussed. Since the 70 nm technology node, recessed transistors have been accepted for assuring data retention time ...of DRAM cell transistors. Various recessed transistor structures suggest that the most important issue in reliability, in addition to optimizing data retention time, is the elimination of local regions of concentrated electric fields. In this paper, by modulating the cell gate oxidation process, local field concentration is effectively reduced. Particularly, the introduction of a radical oxidation process can create cell transistors that are more immune to Fowler-Nordheim (F-N) stress, which can degrade interface quality during cell transistor operation. On the other had, for DRAM peripheral transistors, for DRAM peripheral transistors, which currently use dual poly-Si gates and SiON dielectrics, high-k/metal gate (HK/MG) structure are expected to be adopted at the 20 nm technology node for improved equivalent oxide thickness (EOT) scaling. The high thermal budget of a conventional DRAM manufacturing process can significantly impact HK/MG WLR issues. However, we have evaluated reliability characteristics for HK/MG WLR on DRAM cell and peripheral devices, and concluded that WLR issues will not be critical for operation.
국내 건설수주 규모는 2013년 91.3조원에서 2021년 총 212조원으로 특히 민간부문에서 크게 성장하였다. 국내외 시장 규모가 성장하면서, EPC(Engineering, Procurement, Construction) 프로젝트의 규모와 복잡성이 더욱 증가되고, 이에 프로젝트 관리 및 ITB(Invitation to Bid) 문서의 위험 관리가 중요한 ...이슈가 되고 있다. EPC 프로젝트 발주 이후 입찰 절차에서 실제 건설 회사에게 부여되는 대응 시간은 한정적일 뿐만 아니라, 인력 및 비용의 문제로 ITB 문서 계약 조항의 모든 리스크를 검토하는데 매우 어려움이 있다. 기존 연구에서는 이와 같은 문제를 해결하고자 EPC 계약 문서의 위험 조항을 범주화하고, 이를 AI 기반으로 탐지하려는 시도가 있었으나, 이는 레이블링 데이터 활용의 한계와 클래스 불균형과 같은 데이터 측면의 문제로 실무에서 활용할 수 있는 수준의 지원 시스템으로 활용하기 어려운 상황이다. 따라서 본 연구는 기존 연구와 같이 위험조항 자체를 정의하고 분류하는 것이 아니라, FIDIC Yellow 2017(국제 컨설팅엔지니어링 연맹 표준 계약 조건) 기준 계약 조항을 세부적으로 분류할 수 있는 AI 모델을 개발하고자 한다. 프로젝트의 규모, 유형에 따라서 세부적으로 검토해야 하는 계약 조항이 다를 수 있기 때문에 이와 같은 다중 텍스트 분류 기능이 필요하다. 본 연구는 다중 텍스트 분류 모델의 성능 고도화를 위해서 최근 텍스트 데이터의 컨텍스트를 효율적으로 학습할 수 있는 ELECTRA PLM(Pre-trained Language Model)을 사전학습 단계부터 개발하고, 해당 모델의 성능을 검증하기 위해서 총 4단계 실험을 진행했다. 실험 결과, 자체 개발한 ITB-ELECTRA 모델 및 Legal-BERT의 앙상블 버전이 57개 계약 조항 분류에서 가중 평균 F1-Score 기준 76%로 가장 우수한 성능을 달성했다.
The Korean construction order volume in South Korea grew significantly from 91.3 trillion won in public orders in 2013 to a total of 212 trillion won in 2021, particularly in the private sector. As the size of the domestic and overseas markets grew, the scale and complexity of EPC (Engineering, Procurement, Construction) projects increased, and risk management of project management and ITB (Invitation to Bid) documents became a critical issue. The time granted to actual construction companies in the bidding process following the EPC project award is not only limited, but also extremely challenging to review all the risk terms in the ITB document due to manpower and cost issues. Previous research attempted to categorize the risk terms in EPC contract documents and detect them based on AI, but there were limitations to practical use due to problems related to data, such as the limit of labeled data utilization and class imbalance. Therefore, this study aims to develop an AI model that can categorize the contract terms based on the FIDIC Yellow 2017(Federation Internationale Des Ingenieurs-Conseils Contract terms) standard in detail, rather than defining and classifying risk terms like previous research. A multi-text classification function is necessary because the contract terms that need to be reviewed in detail may vary depending on the scale and type of the project. To enhance the performance of the multi-text classification model, we developed the ELECTRA PLM (Pre-trained Language Model) capable of efficiently learning the context of text data from the pre-training stage, and conducted a four-step experiment to validate the performance of the model. As a result, the ensemble version of the self-developed ITB-ELECTRA model and Legal-BERT achieved the best performance with a weighted average F1-Score of 76% in the classification of 57 contract terms.
Design of Fuzzy Entropy for Non Convex Membership Function Lee, Sanghyuk; Kim, Sangjin; Jang, Nam-Young
Advanced Intelligent Computing Theories and Applications. With Aspects of Contemporary Intelligent Computing Techniques
Book Chapter
Recenzirano
Fuzzy entropy is designed for non convex fuzzy membership function using well known Hamming distance measure. Design procedure of convex fuzzy membership function is represented through distance ...measure, furthermore characteristic analysis for non-convex function are also illustrated. Proof of proposed fuzzy entropy is discussed, and entropy computation is illustrated.
This paper present an optimal camera placement method that analyzes a spatial-temporal model and calculates priorities of spaces using simulation of pedestrian movement. In order to cover the space ...efficiently, we accomplished an agent-based simulation based on classification of space and pattern analysis of moving people. We have developed an agent-based camera placement method considering camera performance and space utility extracted from a path finding algorithm. We demonstrate that the method not only determines the optimal number of cameras, but also coordinates the position and orientation of the cameras with considering the installation costs. To validate the method, we show simulation results in a specific space.
We address a new inherent limitation of potential field methods, which is symmetrically aligned robot-obstacle-goal (SAROG). The SAROG involves one critical risk of local minima trap. For dealing ...with the problem, we investigate the way how the local minima trap is recognized, and present our random force algorithm. The force algorithm has two categories of random unit total force (RUTF) and random unit total force with repulsion removal (RUTF-RR) which are selected based on the conditions of a robot, an obstacle and a goal.