• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.649-652
• /
• 2019

Serverless 플랫폼은 작업이 요청되었을 때 인스턴스를 생성하였다가 작업이 끝난 후 제거되기 때문에 실제 작업을 처리할 때만 요금이 부과되어 경제적이다. 하지만 작업이 요청될 경우 인스턴스가 생성되고 작업에 필요한 리소스를 가져오는 지연시간 즉, Cold Start 가 발생한다. 특히 워크플로 실행에서 각 작업이 개별적으로 처리되기 때문에 워크플로의 각 단계마다 Cold Start 가 발생하는데, 워크플로는 사전에 정의되기 때문에 이러한 Cold Start 의 누적은 회피 될 수 있다. 본 논문은 Serverless 환경에서 워크플로를 실행할 때 누적되는 Cold Start 를 완화하기 위해 앞의 단계에서 다음 단계를 미리 준비시키는 런타임 인터페이스들에 대하여 제안한다. 이미지 프로세싱 워크플로에 제안한 런타임 인터페이스를 적용시켜 Cold Start 를 제외한 워크플로의 실행시간을 최대 21%까지 줄였다.

• 한국수소및신에너지학회논문집
• /
• 제23권1호
• /
• pp.8-18
• /
• 2012

This paper presents a three-dimensional, transient cold-start polymer electrolyte fuel cell (PEFC) model to numerically evaluate the effects of membrane electrode assembly (MEA) design and cell location in a PEFC stack on PEFC cold start behaviors. The cold-start simulations show that the end cell experiences significant heat loss to the sub-freezing ambient and thus finally cold-start failure due to considerable ice filling in the cathode catalyst layer. On the other hand, the middle cells in the stack successfully start from $-30^{\circ}C$ sub-freezing temperature due to rapid cell temperature rise owing to the efficient use of waste heat generated during the cold-start. In addition, the simulation results clearly indicate that the cathode catalyst layer (CL) composition and thickness have an substantial influence on PEFC cold-start behaviors while membrane thickness has limited effect mainly due to inefficient water absorption and transport capability at subzero temperatures.

• International Journal of Automotive Technology
• /
• 제8권3호
• /
• pp.289-298
• /
• 2007

A nonlinear dynamic simulation model from cranking to idle speed is developed to optimize the cold start process of a diesel engine. Physically-based first order nonlinear differential equations and some algebraic equations describing engine dynamics and starter motor dynamics are used to model the performance of cold starting process which is very complex and involves many components including the cold start aiding method. These equations are solved using numerical schemes to describe the starting process of a diesel engine and to study the effects of cold starting parameters. The validity of this model is examined by a cold start test at $-20^{\circ}C$. Using the developed model the effects of the important starting variables on the cold starting processes were investigated. This model can be served as a tool for designing computer aided control systems that improve cold start performance.

• 한국정보통신학회논문지
• /
• 제19권1호
• /
• pp.113-118
• /
• 2015

추천 시스템은 증가되고 있는 정보에서 사용자가 요구하는 적합한 정보를 선별해 제공해준다. 추천 시스템은 기존에 입력된 정보들을 알고리즘을 통해 선별하는 과정을 거치고 사용자의 정보나 내용 기반으로 정보를 제공한다. 추천 시스템의 문제점으로는 Cold-Start가 있으며, Cold-Start는 새로운 사용자의 정보가 충분하지 않아서 추천 시스템에서 새로운 사용자에게 정보를 추천할 때 발생한다. Cold-Start를 해결하기 위해선 사용자의 정보나 항목 정보가 충족해야 한다. 이에 본 논문에서는 협업 필터링 기법과 내용 기반의 필터링 기법을 혼합한 혼합 필터링 기법 기반으로 Cold-Start 문제를 해결하고 이를 사용하는 영화 추천 시스템을 제안한다.

• 한국멀티미디어학회논문지
• /
• 제24권12호
• /
• pp.1673-1681
• /
• 2021

Item cold start is a well studied problem in the research field of recommender systems. Still, many existing collaborative filters cannot recommend items accurately when only a few user-item interaction data are available for newly introduced items (Cold items). We propose a interaction feature prediction method to mitigate item cold start problem. The proposed method predicts the interaction features that collaborative filters can calculate for the cold items. For prediction, in addition to content features of the cold-items used by state-of-the-art methods, our method exploits the interaction features of k-nearest content neighbors of the cold-items. An attention network is adopted to extract appropriate information from the interaction features of the neighbors by examining the contents feature similarity between the cold-item and its neighbors. Our evaluation on a real dataset CiteULike shows that the proposed method outperforms state-of-the-art methods 0.027 in Recall@20 metric and 0.023 in NDCG@20 metric.

• International Journal of Automotive Technology
• /
• 제6권6호
• /
• pp.585-590
• /
• 2005

The effects of spark timing and exhaust valve timing change on exhaust gas temperature during cold start period of an SI engine are studied through engine bench tests. The exhaust gas temperature increases when the spark timing or valve timing are retarded individually, due to late combustion or slow flame speed. Therefore, exhaust gas temperature shows a large increase when the two timings are retarded simultaneously. However, it is considered that combustion stability during cold start deteriorated under these retarded conditions. To increase exhaust gas temperature for fast warmup of catalysts while maintaining combustion stability, an optimal condition for spark and valve timing retard should be applied for the cold start period.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.914-915
• /
• 2017

Importance and usage of the recommender system increases with the increase of information. The accuracy of the system recommendation primarily depends on the data. There is a problem in recommender systems, known as cold start problem. The lack of data about new products and users causes the cold start problem, and the system will not be able to give correct recommendation. This paper deals with cold start problem by comparing product specification and the review of the resembled products. The user, who likes the resembled product of the new one has more probability of taking interest in the new product as well. However, if a user disagreed with resembled product due to some reasons which the user mentioned in the reviews. The new product overcomes that issue, so the user will greatly accept the new product. Therefore, the system needs to recommend new product to those users as well, in this way the cold start problem will get resolved.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2008년도 추계학술대회 논문집
• /
• pp.17-20
• /
• 2008

Cold start of a fuel cell system is a major obstacle should be overcome as to commercialize it, especially for passenger vehicle applications. However, the cold start characteristics is so complicated since it involves various phenomenon such as ice-blocking in GDL, ionic conductivity in membrane affected by water activity with phase change, heat transfer through components such as bipolarplates or endplates, electro-chemical reactions affected by circumferential temperature and humidity as well. Axiomatic design provides a systematic method to investigate the complex phenomenon although it was developed as a methodology to establish logical design procedure by Nam P. Suh in 1990s. This paper presents a framework to approach the complex cold start problem using Axiomatic Design which features simplifying a problem through hierarchical decomposition and decoupling from the view of functional requirements and design parameters.

• 대한기계학회논문집B
• /
• 제29권3호
• /
• pp.384-389
• /
• 2005

Experimental study of variation of exhaust gas temperature was carried out with the changes of spark timing and exhaust valve timing during the cold start operation of an SI engine. To investigate the effects of these variables on combustion stability, cylinder pressure and exhaust gas temperature were measured and analyzed. Experimental results showed that exhaust gas temperature increased when spark and exhaust valve timings were retarded from the baseline cases. However, combustion stability during cold start deteriorated under the retarded conditions. To increase exhaust gas temperature for fast warmup of catalysts while maintaining combustion stability, an optimal condition for spark and valve timing retard should be appied for the cold start period.