http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Prefetching Scheme for Improving the Web Page Loading Time with NVRAM
Seungkyu Hong,Kyusik Kim,김태석 대한전자공학회 2018 Journal of semiconductor technology and science Vol.18 No.1
How to effectively make use of NVRAM in computing devices is still an open problem. In this paper, we present a practical scheme that reduces the user latency, specially the page loading time in browser by using NVRAM. We first employ two-level caching architecture that uses the fast data access speed of NVRAM, and then propose a prefetching scheme that exploits the non-volatility and the byte-addressability of NVRAM. Unlike other existing prefetching schemes that consider only the prefetching accuracy, our prefetching predicts web pages to be visited next time in terms of the user latency. To this end, we maintain a graph that represents page loading time of web page and access pattern of user in NVRAM. The predicted web pages are processed in the background by using hidden tab of browsers while user reads a web page. Through implementation on open-source web browser QT-webkit, we demonstrate that our scheme improves average page loading time by up to 40%.
Supporting the Priorities in the Multi-queue Block I/O Layer for NVMe SSDs
Kyusik Kim,Seungkyu Hong,김태석 대한전자공학회 2020 Journal of semiconductor technology and science Vol.20 No.1
Recently, a multi-queue block I/O layer has been introduced in the Linux kernel to support NVMe SSDs efficiently. It can provide a high I/O bandwidth by employing several queues but does not provide a differentiated I/O services yet. In this paper, we present a new scheme that supports the priorities in the multi-queue block I/O layer. Our scheme brings the CFS (Completely Fair Scheduler) technique that is one of CPU scheduler into the I/O layer. In this way, we can provide a differentiated I/O service regardless of whether processes are CPU-intensive or I/O intensive. Besides, by considering the I/O request type, read requests are preferentially handled over write requests. Through implementation on the Linux kernel, we show that the proposed scheme appropriately services the I/O requests according to priority and request type and improves runtimes of read-intensive and write-intensive processes by 33% and 15%, respectively.
가정편의식(HMR) 제품의 전자상거래 소비자 불만족에 대한 연구
김성은(Seungeun Kim),홍승규(Seungkyu Hong),김동수(Dongsoo Kim) 한국전자거래학회 2017 한국전자거래학회지 Vol.22 No.3
식품의 구입, 조리, 소비에서 편의성과 신속성을 찾는 소비자의 니즈 증대로, 조리가 간단하고 가정식을 대체할 수 있는 가정편의식(HMR) 제품 관련 시장이 매년 성장하고 있다. 또한, 전자상거래를 통한 구매 편의의 증대로 온라인 또는 모바일을 통한 HMR 구입이 증대되고 있다. 기업의 입장에서 구매 만족도를 높이기 위해 소비자들의 불만족 원인과 사후반응에 대한 분석이 필요하다. 하지만 온라인과 모바일을 통해 제품을 판매하는 기업이 직접 불만을 표현하지 않는 소비자의 불만 분석을 수행하기는 비대면 거래의 특성으로 인해 어렵다. 따라서 본 연구는 SPSS와 R을 이용하여 온라인, 모바일을 통해 HMR을 구매해 불만족한 경험이 있는 20대를 대상으로 소비자 특성, 불만족 요인, 불평행동 방식, 재구매 의도 간의 영향 관계를 살펴보고자 한다. 또한, 연구에 구성된 불만족 요인에 대해 직접 경험하지 않았더라도 지각되는 불만의 정도를 분석하여 그 관련성을 알아보고자 한다. 기존 HMR 연구에서 거의 다루어지지 않았던 소비자 불만족 연구를 확장하고, 기업의 불만 관리를 위한 소비자에 대한 이해도를 높임으로써 이에 따른 시사점을 제공한다는 점에서 본 연구의 의의가 있다. The market for Home Meal Replacement (HMR), which is simple to cook and replace home cooking, is growing every year since customers need to find convenience and speed in purchasing, cooking, and consuming food. In addition, the purchase of HMR through online and mobile is increasing because convenience of purchasing through e-Commerce is growing. However, there are difficulties in analyzing complaints of customers who do not directly express their dissatisfaction with companies that sell products through online and mobile. Therefore, this study examines the influential relationship between customer’s characteristics, dissatisfaction factors, complaint behavior, and repurchase intention of 20s who have dissatisfaction experience of purchasing HMR through online or mobile using SPSS and R. In addition, we attempt to analyze the degree of perceived dissatisfaction and its relevance even though customers did not directly experience dissatisfaction factors. As a result, it is meaningful to extend the study of customer dissatisfaction that is rarely handled in the existing HMR research, and to raise the understanding of customers for the management of complaints.