• 한국멀티미디어학회논문지
• /
• 제17권8호
• /
• pp.946-952
• /
• 2014

Mobility prediction is one of hot topics using location history information. It is useful for not only user-level applications such as people finder and recommendation sharing service but also for system-level applications such as hand-off management, resource allocation, and quality of service of wireless services. Most of current prediction techniques often use a set of significant locations without taking into account possible location information changes for prediction. Markov-based, LZ-based and Prediction by Pattern Matching techniques consider interesting locations to enhance the prediction accuracy, but they do not consider interesting location changes. In our paper, we propose an algorithm which integrates the changing or emerging new location information. This approach is based on Active LeZi algorithm, but both of new location and all possible location contexts will be updated in the tree with the fixed depth. Furthermore, the tree will also be updated even when there is no new location detected but the expected route is changed. We find that our algorithm is adaptive to predict next location. We evaluate our proposed system on a part of Dartmouth dataset consisting of 1026 users. An accuracy rate of more than 84% is achieved.

• Genomics & Informatics
• /
• 제14권4호
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2010년도 춘계학술대회 논문집
• /
• pp.261-267
• /
• 2010

Present maintenance of a high speed railway is after the fack maintenance that executes a task when measured value goes over threshold value except some planned maintenance. It is difficult from efficient management of maintenance human resource and equipment commitment because it is difficult to predict quantity of maintenance targets. Corrective maintenance is pushed back on the repair priority of other target to need repair and it is exceeded repair cost potentially. For safety and dependable track management because track deterioration prediction is linked directly with track's life and safety of train service, it is very important that track management be based on preventive maintenance. In this study, we propose statistics model of track quality to use track inspection data and forecast model for track deterioration prediction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.30-45
• /
• 2024

This study introduces an effective method for predicting individual local tax delinquencies using prevalent machine learning and deep learning algorithms. The evaluation of credit risk holds great significance in the financial realm, impacting both companies and individuals. While credit risk prediction has been explored using statistical and machine learning techniques, their application to tax arrears prediction remains underexplored. We forecast individual local tax defaults in Republic of Korea using machine and deep learning algorithms, including convolutional neural networks (CNN), long short-term memory (LSTM), and sequence-to-sequence (seq2seq). Our model incorporates diverse credit and public information like loan history, delinquency records, credit card usage, and public taxation data, offering richer insights than prior studies. The results highlight the superior predictive accuracy of the CNN model. Anticipating local tax arrears more effectively could lead to efficient allocation of administrative resources. By leveraging advanced machine learning, this research offers a promising avenue for refining tax collection strategies and resource management.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제3권7호
• /
• pp.219-230
• /
• 2014

클라우드 컴퓨팅 환경에서, 클라우드 서비스 사용자는 클라우드 자원 제공자로부터 가상화된 컴퓨팅 자원을 사용할 시간만큼 구매하여 할당받는다. 일반적으로 아마존, 고그리드 및 마이크로소프트와 같은 대형 클라우드 자원 제공자들은 자원 과금 정책을 온디맨드와 예약형 기반 가상 자원의 두 가지로 구분하여 제공한다. 예약형 기반 가상 자원은 상대적으로 장기간 할당을 가지므로 단위 시간당 자원 사용 비용이 온디맨드 가상 자원과 비교하여 더 저렴하다. 이러한 과금 정책 특성을 기반으로 클라우드 서비스 사용자의 서비스 요구 사항을 고려하여 적절한 자원 할당을 수행함으로써 클라우드 서비스 제공자는 자원 할당 비용을 효과적으로 절감할 수 있다. 이를 위해서, 기존의 가상 자원 할당 기법들은 서비스 사용자의 요구사항 특성을 미리 예측하여 최적의 자원을 할당하는 방법들을 제안하였다. 그러나 실세계에서는 다양한 클라우드 서비스 사용자가 존재하고 서비스 요구사항이 동적으로 변하기 때문에 정확한 예측을 하기 어려우며, 최적화된 할당을 위한 연산 시간이 추가 오버헤드가 되어 자원 관리 성능을 떨어뜨릴 수 있다. 이를 해결하기 위해, 본 논문에서는 적응적 자원 할당 기법을 제안하여 요구사항 예측 및 최적화 기법을 수행하지 않으면서도 서비스 요구사항에 효과적으로 대응하여 자원을 제공할 수 있도록 한다. 실험 결과를 통해 제안된 기법이 자원 사용 비용을 크게 절감하면서도 클라우드 서비스 사용자의 QoS를 만족함을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권6호
• /
• pp.1398-1417
• /
• 2013

A method is proposed to reduce excess resources from a virtual machine(VM) while avoiding subsequent migrations for a computer cluster that provides cloud service. The proposed scheme cuts down on the resources of a VM based on the probability that migration may occur after a reduction. First, it finds a VM that can be scaled down by analyzing the history of the resource usage. Then, the migration probability is calculated as a function of the VM resource usage trend and the trend error. Finally, the amount of resources needed to eliminate from an underutilized VM is determined such that the migration probability after the resource reduction is less than or equal to an acceptable migration probability. The acceptable migration probability, to be set by the cloud service provider, is a criterion to assign a weight to the resource reduction either to prevent VM migrations or to enhance VM utilization. The results of simulation show that the proposed scheme lowers migration frequency by 31.6~60.8% depending on the consistency of resource demand while losing VM utilization by 9.1~21.5% compared to other known approaches, such as the static and the prediction-based methods. It is also verified that the proposed scheme extends the elapsed time before the first occurrence of migration after resource reduction 1.1~2.3-fold. In addition, changes in migration frequency and VM utilization are analyzed with varying acceptable migration probabilities and the consistency of resource demand patterns. It is expected that the analysis results can help service providers choose a right value of the acceptable migration probability under various environments having different migration costs and operational costs.

• 정보처리학회논문지C
• /
• 제11C권2호
• /
• pp.193-202
• /
• 2004

무선 셀룰러 환경에서 가장 중요한 기술중의 하나가 사용자의 이동성(Mobility)을 보장하기 위한 핸드오프 기술이다 이러한 핸드오프 기술은 사용자가 이동할 주변 셀에 대한 대역폭 예약과 관련이 있다. 무선 셀룰러 환경에서 효과적인 대역폭 사용을 위하여. 사용자의 이동성을 예즉하는 기술은 핸드오프 호의 실패율(Dropping Probability)과 핸드오프 지연을 줄이는 효과적인 방법이다. 기존의 연구에서는 사무실, 빌딩과 같은 제한된 범위나 셀 간의 히스토리에 기반하여 이동 예측 알고리즘을 수행하였다. 그러나, 마이크로-셀(Micro-Cell) 구조나 도로가 복잡하게 구성되어 있는 도심에는 잘 적용되지 못한다는 단점이 있다. 이러한 단점을 극복하기 위하여, 본 논문에서는 낀 내부 이동 패턴을 저장한 히스토리를 이용하여, 사용자가 이동할 셀을 예측하는 새로운 알고리즘을 제안한다

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권3호
• /
• pp.81-84
• /
• 2015

클라우드 서비스는 다양한 장점들 덕분에 현대 IT 사업에서 주목을 받고 있다. 클라우드 환경에서 사용자의 요구는 동적이기 때문에 서비스 제공자는 사용자 요구량을 예측하고 이를 기반으로 자원을 제공하는 VM(Virtual Machine) 프로비저닝 기법이 필요하다. VM 프로비저닝은 사용자의 QoS를 만족시키고 자원 관리 비용을 최소화하여 서비스 제공자의 이득을 최대화하는 것을 목적으로 한다. 본 논문에서는 효율적인 VM 프로비저닝을 위해 사용자의 자원 요구량을 예측하고, 이를 기반으로 서비스 제공자의 총 경비에 대한 기대 값을 최소화시키기 위한 새로운 VM 프로비저닝 기법을 제안한다. 또한 제안 기법의 성능 분석을 위하여 실제 데이터를 이용하여 자원 요구 예측량과 자원 제공량을 계산하고, 이를 다른 기법들과 비교함으로써 제안 기법이 서비스 제공자의 총 경비를 최소화함을 보여준다.

• 신재생에너지
• /
• 제1권2호
• /
• pp.19-25
• /
• 2005

This study explains ther procedure that should be taken to develp a successful wind park project. It provides a guideline for the activities and studies to be done as a step by step solution. This study follows a chronological flow throughout the whole development Process. This Paper covers technical consideration, assessment of wind energy resource, wind Park siting and energy yield calculation This presented knowledge h3s been mostly gained by the experience from Youngduk wind park project. The further comparison study will be performed between the theoretical prediction and the actual yield of the Youngduk wind park.

• 한국시스템다이내믹스연구
• /
• 제15권3호
• /
• pp.105-141
• /
• 2014

Human Resource Planning and Management(HRPM) is to make organization efficiently and effectively. Based on Promotion and Aging Chain Model, a revised personnel management prediction simulation is established in terms of mid- and long-term organizational changes, annual budget and personnel strategy including a promotion, aging and laying off for the best personnel architecture in organization. Also, the model is possible to find a solution for increasing the organizational capacity. An empirical application to quasi-governmental organization proceeded to testing and validating the model.