• International Journal of Computer Science & Network Security
• /
• 제24권7호
• /
• pp.11-23
• /
• 2024

Triage is a practice of accurately prioritizing patients in emergency department (ED) based on their medical condition to provide them with proper treatment service. The variation in triage assessment among medical staff can cause mis-triage which affect the patients negatively. Developing ED triage system based on machine learning (ML) techniques can lead to accurate and efficient triage outcomes. This study aspires to develop a triage system using machine learning techniques to predict ED triage levels using patients' information. We conducted a retrospective study using Security Forces Hospital ED data, from 2021 through 2023 during Hajj period in Saudia Arabi. Using demographics, vital signs, and chief complaints as predictors, two machine learning models were investigated, naming gradient boosted decision tree (XGB) and deep neural network (DNN). The models were trained to predict ED triage levels and their predictive performance was evaluated using area under the receiver operating characteristic curve (AUC) and confusion matrix. A total of 11,584 ED visits were collected and used in this study. XGB and DNN models exhibit high abilities in the predicting performance with AUC-ROC scores 0.85 and 0.82, respectively. Compared to the traditional approach, our proposed system demonstrated better performance and can be implemented in real-world clinical settings. Utilizing ML applications can power the triage decision-making, clinical care, and resource utilization.

• Journal of Communications and Networks
• /
• 제18권2호
• /
• pp.162-172
• /
• 2016

The placement of the complete baseband processing in a centralized pool results in high data rate requirement and inflexibility of the fronthaul network, which challenges the energy and cost effectiveness of the cloud radio access network (C-RAN). Recently, redesign of the C-RAN through functional split in the baseband processing chain has been proposed to overcome these challenges. This paper evaluates, by mathematical and simulation methods, different splits with respect to network level energy and cost efficiency having in the mind the expected quality of service. The proposed mathematical model quantifies the multiplexing gains and the trade-offs between centralization and decentralization concerning the cost of the pool, fronthaul network capacity and resource utilization. The event-based simulation captures the influence of the traffic load dynamics and traffic type variation on designing an efficient fronthaul network. Based on the obtained results, we derive a principle for fronthaul dimensioning based on the traffic profile. This principle allows for efficient radio access network with respect to multiplexing gains while achieving the expected users' quality of service.

• 한국컴퓨터산업학회논문지
• /
• 제2권9호
• /
• pp.1163-1174
• /
• 2001

ATM 네트워크의 목적은 다양한 네트워크의 접속을 지원하는 것이다. ATM 네트워크에서는 트래픽 제어 방식으로 ACR(Allowed Cell Rate)의 변화를 이용하여 링크 대역폭의 이용률을 증대시키는 트래픽 제어 방식인 EPRCA(Enhanced Proportional Rate Control Algorithm) 스위치를 이용한 ABR(Available Bit Rate) 서비스 방법을 사용한다. 그러나 ABR 서비스에서는 서로 다른 RTT(Round Trip Times) 접속에 따른 서로 다른 처리 방법을 사용한다. 따라서 본 논문에서는 서로 다른 처리방법에 따른 불공정성을 개선하기 위해 ABR 셀 지연 방법을 사용한다. 본 연구의 셀 지연방법에서는 3가지 셀 지연 참조 매개변수가 정의되어 있으며 RM(Resource Mana-gement) 셀 메시지에 반영된다. 제안한 방식의 성능을 평가하기 위하여 ABR 지연방법과 ABR RMM(Relative Rate Marking) 방법 사이에서 각각의 TCP 접속의 공정성을 비교한다. 그리고 병목 링크 대역폭을 공유하는 서로 다른 RTT를 갖는 6개의 TCP 접속과 백그라운드 트래픽을 갖는 간단한 ATM 네트워크 모델을 사용하여 시뮬레이션을 수행하였다. TCP 효율에 기반 한 시뮬레이션을 수행한 결과 ABR 셀 지연 방식이 TCP 접속 사이에서 공정성을 개선한다는 것을 알 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3619-3637
• /
• 2022

Big data analytics offers endless opportunities for operational enhancement by extracting valuable insights from complex voluminous data. Hadoop is a comprehensive technological suite which offers solutions for the large scale storage and computing needs of Big data. The performance of Hadoop is closely tied with its configuration settings which depends on the cluster capacity and the application profile. Since Hadoop has over 190 configuration parameters, tuning them to gain optimal application performance is a daunting challenge. Our approach is to extract a subset of impactful parameters from which the performance enhancing sub-optimal configuration is then narrowed down. This paper presents a statistical model to analyze the significance of the effect of Hadoop parameters on a variety of performance metrics. Our model decomposes the total observed performance variation and ascribes them to the main parameters, their interaction effects and noise factors. The method clearly segregates impactful parameters from the rest. The configuration setting determined by our methodology has reduced the Job completion time by 22%, resource utilization in terms of memory and CPU by 15% and 12% respectively, the number of killed Maps by 50% and Disk spillage by 23%. The proposed technique can be leveraged to ease the configuration tuning task of any Hadoop cluster despite the differences in the underlying infrastructure and the application running on it.

• 품질경영학회지
• /
• 제46권4호
• /
• pp.959-972
• /
• 2018

Purpose: This study developed a simulation model that incorporates the uncertainty of demand and yield to obtain optimized results for supply chain coordination within environmental constraints. The objective of this study is to examine whether yield management for perishable products can achieve the goal of supply chain coordination between a single buyer and a single supplier under a variety of environmental conditions. Methods: We investigated the efficiency of a revenue-sharing contract and a wholesale price contract by considering demand and yield uncertainty, profit maximizing ratio, and success ratio. The implications for environmental variation were derived through a comparative analysis between the wholesale price contract and the revenue-sharing contract. We performed Monte Carlo simulations to give us the results of an optimized supply chain within the environments defined by the experimental factors and parameters. Results: We found that a revised revenue-sharing contracting model was more efficient than the wholesale price contract model and allowed all members of the supply chain to achieve higher profits. First, as the demand variation (${\sigma}$) increased, the profit of the total supply chain increased. Second, as the revenue-sharing ratio (${\Phi}$) increased, the profits of the manufacturer gradually decreased, while the profits of the retailer gradually increased, and this change was linear. Third, as the quality of yield increased, the profits of suppliers appear to increased. At last, success rate was expressed as the profit increased in the revenue-sharing contract compared to the profit increase in the wholesale price contract. Conclusion: The managerial implications of the simulation findings are: (1) a strategic approach to demand and yield uncertainty helps in efficient resource utilization and improved supply chain performance, (2) a revenue-sharing contract amplifies the effect of yield uncertainty, and (3) revised revenue-sharing contracts fetch more profits for both buyers and suppliers in the supply chain.

• 정보처리학회논문지C
• /
• 제18C권1호
• /
• pp.51-60
• /
• 2011

본 논문에서는 라이브 멀티미디어 스트리밍의 서비스 품질을 지원할 수 있는 P4P(Proactive network Provider Participation for P2P) 기반의 P2P(Peer-to-Peer) 시스템을 제안한다. 라이브 멀티미디어의 엄격한 지연 요구를 지원하기 위해, 제안하는 방안에서는 P4P의 네트워크 제공자 측 서버가 네트워크 자원 활용 최적화를 위한 정보와 더불어 지연 및 혼잡 링크에 관한 네트워크 상태 정보를 수집하여 이를 명시적으로 P2P 시스템에 제시하도록 하고, 이에 기반하여 P2P 시스템 측 서버가 피어링 제의를 수행하도록 하였다. 또한 모든 피어들이 소스 피어의 재생 지점을 기준으로 일정 범위 내에서 재생을 시작하도록 하는 라이브 멀티미디어 스트리밍 재생 동기화 방안을 제안한다. 시뮬레이션을 통해 성능을 평가한 결과, 제안 방안은 P4P의 기본 목적인 네트워크 자원 활용 문제를 효과적으로 다루면서 라이브 멀티미디어 스트리밍 서비스의 지속성을 향상시키고, 재생 시작 지연 및 제어 오버헤드를 줄임을 확인하였다. 또한 시스템 전체 피어들 간 재생 지점의 편차를 줄임으로써 실시간성을 개선함을 볼 수 있었다.

• 지능정보연구
• /
• 제15권2호
• /
• pp.15-31
• /
• 2009

차세대 전산환경은 사용자들이 필요한 전산자원을 네트워크를 통해 공급받는 그리드 컴퓨팅 기반의 개방형 전산환경으로 진화할 것으로 예상된다. 개방형 전산환경의 도입은 전산자원 활용의 효율성을 높이고 협업을 증진시키며 공급의 유연성과 비용 절감 등의 효과를 가져올 수 있다. 그러나 네트워크를 통해 공급되는 특성으로 인해 개방형 전산 자원의 성능에는 변동성이 수반된다. 전산자원의 성능에 변동성이 있는 경우, 주어진 예산과 시간만 고려하여 전산자원 서비스를 구성하는 단순 최적화 방법을 사용했을 때는 서비스의 최종 성능과 실행 시간 등을 규정한 서비스 수준계약(Service Level Agreement, SLA)을 만족시키지 못할 위험이 높다. 따라서 개방형 전산환경의 서비스 브로커는 전산자원 공급의 안정성을 높이기 위해서 서비스를 구성하는 개별 전산자원의 성능 변동성을 고려하여 위험을 최소화 하는전산자원포트폴리오를구성할것이요구된다. 본연구에서는평균절대편차(Mean-Absolute Deviation, MAD) 포트폴리오 최적화 기법을 이용하여 서비스 브로커의 공급 안정성을 향상시키는 방법을 제시하였다. 제시된 최적화 기법의 효과를 알아보기 위한 방법으로 가상의 개방형 전산환경을 모델링하고, 고객의 제약 조건과 개방형 전산환경의 변동성 정도에 따라 전산자원 공급 서비스의 성공률을 시뮬레이션 하였다. 시뮬레이션 결과로서, 첫째, 단순 최적화방법보다 변동성을 감안한 MAD 포트폴리오 최적화 기법을 이용했을 때 공급의 안정성이 뛰어난 것을 확인할 수 있었다. 둘째로는 특히 개별 전산자원의 변동성 예측의 정확성이 높아질수록 성능도 더욱 향상되는 결과를 가져왔다. 셋째, 측정된 변동성을 이용하여 개방형 전산자원의 가격을 할인하는 정책을 추진할 경우 서비스 공급 범위의 확대에도 효과가 클 것으로 예상되었다.

• Journal of Forest and Environmental Science
• /
• 제37권2호
• /
• pp.104-115
• /
• 2021

The research attempted to analyze the medicinal plant species richness in the vertical gradient from lower to the highest elevation of Makawanpur, focusing on the relationship between species richness and elevation which is very important for conservation and management of species diversity. Inventory was carried out in the study area by taking sampling intensity of 0.5% in the effective area. Altogether, 42 sample plots were laid in the field with the help of GIS software maintaining 50 m altitude difference. High species diversity was found in the herbs species whereas shrubs have comparatively low species diversity. The maximum species richness is found in herbs and poles whereas shrubs and trees have relatively low species richness. Research showed that species richness of medicinal plants increased with altitudinal gradient. While analyzing the species richness from 350 to 2,550 m (msl), the highest species richness was received with the elevation ranges from 1,800 m to 2,300 m. There was a positive relationship between species richness and altitudinal gradient in the study area. In addition, we have recorded the high value medicinal plants after 1,800 m altitude and rarely within 1,000 m. Medicinal plants correlated both positive and negative relationships with the increased altitude. The altitudinal response has positively seen except density (n/ha) of Shrubs. Domestication and cultivation of high value medicinal plants should be promoted in community forest including private lands. Training, workshops and awareness programs should be conducted to make people aware about medicinal plants resource utilization, conservation and commercialization of available medicinal plants.

• Asian-Australasian Journal of Animal Sciences
• /
• 제33권12호
• /
• pp.1905-1911
• /
• 2020

Objective: Tibetan pigs, an excellent species unique to China, face serious threats, which in turn affects the development and utilization of the outstanding advantages of plateau hypoxia adaptability and reduces their genetic diversity. Therefore, a discussion of measures to conserve this genetic resource is necessary. The method, based on genetic diversity, genetic divergence and total genetic contribution rate of population, reflects the priority conservation order and varies depending on the three different purposes of conservation. Methods: We analyzed mitochondrial DNA control region (D-loop) variation in 1,201 individuals from nine Tibetan pig populations across five provinces and downloaded 564 mtDNA D-loop sequences from three indigenous pig breeds in Qinghai, Sichuan, and Yunnan Provinces distributed near the Tibetan pigs. Results: We analyzed three different aspects: Changdu Tibetan pigs have the highest genetic diversity, and from the perspective of genetic diversity, the priority conservation is Changdu Tibetan pigs. Hezuo Tibetan pigs have the highest genetic contribution, so the priority conservation is Hezuo Tibetan pigs in the genetic contribution aspect. Rkaze Tibetan pigs were severely affected by indigenous pig breeds, so if considering from the perspective of introgression, the priority conservation is Rkaze Tibetan pigs. Conclusion: This study evaluated genetic diversity and comprehensively assessed conservation priority from three different aspects in nine Tibetan pig populations.

• International Journal of Industrial Entomology and Biomaterials
• /
• 제27권1호
• /
• pp.142-158
• /
• 2013

The bumblebee, Bombus ignitus (Hymenoptera: Apidae), is a valuable natural resource that is widely utilized for greenhouse pollination in South Korea. Understanding the magnitude of genetic diversity and geographic relationships is of fundamental importance for long term preservation and utilization. As a first step, we sequenced a partial COI gene of mitochondrial DNA (mtDNA) corresponding to the "DNA barcode" region and the complete internal transcribed spacer 2 (ITS2) of nuclear ribosomal DNA from 88 individuals collected in nine South Korean localities. The complete ITS2 sequences were longest among known insects, ranging in size from 2,034 bp ~ 2,052 bp, harboring two duplicated 112-bp long repeats. The 658-bp long mtDNA sequences provided only six haplotypes with a maximum sequence divergence of 0.61% (4 bp), whereas the ITS sequences provided 84 sequence types with a maximum sequence divergence of 1.02% (21 sites). The combination of the current COI data with those of published data suggest that the B. ignitus in South Korea and China are genetically a large group, but those in Japan can be roughly separated into another group. Overall, a very high per generation migration ratio, a very low level of genetic fixation, and no discernable hierarchical population were found to exist among the South Korean populations of B. ignitus, which suggests panmixia. This finding is consistent with our understanding of the dispersal capability of the species.