• Genomics & Informatics
• /
• 제19권1호
• /
• pp.10.1-10.7
• /
• 2021

Although many models have been proposed to accurately predict the response of drugs in cell lines recent years, understanding the genome related to drug response is also the key for completing oncology precision medicine. In this paper, based on the cancer cell line gene expression and the drug response data, we established a reliable and accurate drug response prediction model and found predictor genes for some drugs of interest. To this end, we first performed pre-selection of genes based on the Pearson correlation coefficient and then used ElasticNet regression model for drug response prediction and fine gene selection. To find more reliable set of predictor genes, we performed regression twice for each drug, one with IC₅₀ and the other with area under the curve (AUC) (or activity area). For the 12 drugs we tested, the predictive performance in terms of Pearson correlation coefficient exceeded 0.6 and the highest one was 17-AAG for which Pearson correlation coefficient was 0.811 for IC₅₀ and 0.81 for AUC. We identify common predictor genes for IC₅₀ and AUC, with which the performance was similar to those with genes separately found for IC₅₀ and AUC, but with much smaller number of predictor genes. By using only common predictor genes, the highest performance was AZD6244 (0.8016 for IC₅₀, 0.7945 for AUC) with 321 predictor genes.

• Journal of Communications and Networks
• /
• 제17권3호
• /
• pp.306-320
• /
• 2015

Due to an explosive growth in services running in different datacenters, there is need for service selection and routing to deliver user requests to the best service instance. In current solutions, it is generally the client that must first select a datacenter to forward the request to before an internal load-balancer of the selected datacenter can select the optimal instance. An optimal selection requires knowledge of both network and server characteristics, making clients less suitable to make this decision. Information-Centric Networking (ICN) research solved a similar selection problem for static data retrieval by integrating content delivery as a native network feature. We address the selection problem for services by extending the ICN-principles for services. In this paper we present Queue and Latency, a network-driven service selection algorithm which maps user demand to service instances, taking into account both network and server metrics. To reduce the size of service router forwarding tables, we present a statistical method to approximate an optimal load distribution with minimized router state required. Simulation results show that our statistical routing approach approximates the average system response time of source-based routing with minimized state in forwarding tables.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.38-59
• /
• 2022

Web services instances can be classified into two categories, namely trusted and untrusted from users. A web service with high throughput (TP) and low response time (RT) instance values is a trusted web service. Web services are not trustworthy due to the mismatch in the guaranteed instance values and the actual values achieved by users. To perform web services selection from users' attained TP and RT values, we need to verify the correct prediction of trusted and untrusted instances from invoked web services. This accurate prediction of web services instances is used to perform the selection of web services. We propose to construct fuzzy rules to label web services instances correctly. This paper presents web services selection using a well-known machine learning algorithm, namely REPTree, for the correct prediction of trusted and untrusted instances. Performance comparison of REPTree with five machine learning models is conducted on web services datasets. We have performed experiments on web services datasets using a ten k-fold cross-validation method. To evaluate the performance of the REPTree classifier, we used accuracy metrics (Sensitivity and Specificity). Experimental results showed that web service (WS1) gained top selection score with the (47.0588%) trusted instances, and web service (WS2) was selected the least with (25.00%) trusted instances. Evaluation results of the proposed web services selection approach were found as (asymptotic sig. = 0.019), demonstrating the relationship between final selection and recommended trust score of web services.

• Asian-Australasian Journal of Animal Sciences
• /
• 제16권6호
• /
• pp.789-793
• /
• 2003

An investigation was conducted on 729 Hariana cows maintained at Government Livestock Farm, Hisar, from 1973 to 1999, with an objective to compare the efficiency of various selection indices for attaining desired genetic gains in the index traits. The various traits included were age at first calving (AFC), service period (SP), calving interval (CI), days to first service (DFS), number of services per conception (NSPC), lactation milk yield (LY), peak yield (PY), dry period (DP). Except for LY, PY and AFC the heritabilities of all other traits were low. Desirable associations among reproductive traits are supportive of the fact that any one of these traits incorporated in simultaneous selection is expected to cause correlated response in other traits. Production traits (LY and PY) were positively correlated, while DP had low negative genetic correlation with LY, and high genetic correlation with PY. Thus, DP can be taken as additional criteria in selection index for better over all improvement. Almost all production traits except DP had low negative correlation with AFC, SP, DFS and CI meaning that reduction in reproduction traits up to certain level may increase production performance. While, the correlation of NSPC with LY and PY was moderate positive. Among four trait indices I23: incorporating PY, AFC, SP and NSPC and among three trait indices I1: incorporating LY, AFC and SP were the best as these required least number of generations (4.87 and 1.35, respectively) to attain desired goals. Next in order of preference were PY or LY along with DP and SP as the best indices (I20 and I16) of which, index with PY may be preferred instead of LY as it produced considerably high correlated response in LY and reduction in NSPC as well.

• Earthquakes and Structures
• /
• 제11권3호
• /
• pp.445-459
• /
• 2016

Quantitative estimation of seismic response of various structural systems at the collapse limit state is one of the most significant objectives in Performance-Based Earthquake Engineering (PBEE). Assessing the effects of uncertainties, due to variability in ground motion characteristics and random nature of earthquakes, on nonlinear structural response is a pivotal issue regarding collapse safety prediction. Incremental Dynamic Analysis (IDA) and fragility curves are utilized to estimate demand parameters and seismic performance levels of structures. Since producing these curves based on a large number of nonlinear dynamic analyses would be time-consuming, selection of appropriate earthquake ground motion records resulting in reliable responses with sufficient accuracy seems to be quite essential. The aim of this research study is to propose a methodology to assess the seismic behavior of reinforced concrete frames at collapse limit state via accurate estimation of seismic fragility curves for different Engineering Demand Parameters (EDPs) by using a limited number of ground motion records. Research results demonstrate that accurate estimating of structural collapse capacity is feasible through applying the proposed method offering an appropriate suite of limited ground motion records.

• 한국전자통신학회논문지
• /
• 제2권3호
• /
• pp.174-179
• /
• 2007

본 논문에서는 유전자 알고리듬을 이용하여 전력, 면적, 속도를 고려한 저전력 모듈 선택을 제안한다. 제안한 알고리듬은 최적의 모듈 선택을 통해서 전력 소모를 최소화 할 수 있다. 비교 실험에서는 최적 모듈 선택을 고려한 알고리듬은 최대 전력 감소량은 26.9 %를 얻을 수 있었고, 반면에 최소 전력 감소량은 9.0% 얻었다. 모든 벤치마크 평균 전력 감소량은 15.525%가 되었다.

• 융합보안논문지
• /
• 제6권3호
• /
• pp.87-95
• /
• 2006

침입은 컴퓨터 자원의 무결성, 기밀성, 유효성을 저해하고 컴퓨터 시스템의 보안정책을 파괴하는 일련의 행위의 집합이다. 이러한 침입을 탐지하는 침입탐지시스템은 데이터 수집, 데이터의 가공 및 축약, 침입 분석 및 탐지 그리고 보고 및 대응의 4 단계로 구성되어진다. 침입탐지시스템의 방대한 데이터가 수집된 후, 침입을 효율적으로 탐지하기 위해서는 특징 선택이 중요하다. 이 논문에서 유전자 알고리즘과 결정트리를 활용한 특징 선택 방법을 제안한다. 또한 KDD 데이터에서 실험을 통해 방법의 유효성을 검증한다.

• Journal of Ecology and Environment
• /
• 제36권3호
• /
• pp.151-158
• /
• 2013

We estimated phenotypic selection on the height and number of flowering-stalks in a rosette annual Cardamine hirsuta by applying path analysis to the data collected at three natural populations located in central Japan. The path from rosette size was positively connected with the fruit production through the both height and number of flowering-stalks. In the all three populations, the paths from the number of stalks were more strongly connected with the fruit production than from the height of stalks. The paths from the rosette size showed similar magnitude with the number of stalks and the height of stalks. The direct path from rosette size to the fruit production was detected only at one site. These results suggest stronger phenotypic selection on the rosette size through the number of stalks than the height of stalks. The lateral branching rather than increment of individual inflorescence size is the major response to control the fruit production for C. hirsuta growing in a natural habitat.

• 한국IT서비스학회지
• /
• 제6권2호
• /
• pp.125-143
• /
• 2007

IT Services market is growing rapidly in the business industry and SOA-based Web Services have been introduced as an effective vehicle for the integration of enterprise-wide applications within organizations. The number of publicly available Web Services is ever increasing recently in a variety of areas, and as the number of public Web Services increases, there will be many Web Services with the same functionality. These services, however, will vary in their QoS properties, such as price, response time and availability, and it is very important to choose a right service while satisfying given QoS constraints. This paper addresses the issue of selecting composite Web Services which involves conditional branches in business processes. It is essential to have any conditional branches satisfy the global QoS constraints at service selection phase, since the branches are chosen to execute at run-time dynamically. We proposed service selection procedures for basic structure of conditional branches and explained them by examples. Experiments were conducted to analyze the impact of the number of candidate services and service types on the time of finding service solutions.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.178-182
• /
• 2002

For action selection as well as teaming, simple associations between stimulus and response have been employed in most of literatures. But, for successful task accomplishment, it is required that artificial life system can team and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with behavioral sequences. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a tree with behavioral motivations. The vertical path of the tree represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new behavioral sequence is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.