• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• 대한인간공학회지
• /
• 제24권1호
• /
• pp.43-46
• /
• 2005

The future information technologies and service paradigm will move from PC, the general purpose desktop computing environment, to the next-generation PC that provides information any where, any time, and any device. The next-generation PC such as wearable computers are specialized to the human-centric functionalities and always-on connected services. In this study, service infrastructure of wearable computing with WBAN(Wearable Body Area Network) was suggested for the ubiquitous computing environment.

• 정보과학회 논문지
• /
• 제43권12호
• /
• pp.1420-1427
• /
• 2016

본 논문은 통신 환경이 불안정하고 토폴로지가 수시로 변하는 CV(Connected Vehicle) 환경에서 Fog computing과 SDN의 장점을 활용하는 방법에 대해 제시한다. 이를 위해서 먼저 중앙의 컨트롤러는 최신의 네트워크 토폴로지를 유지함으로써 현재 네트워크 상황을 파악할 수 있어야한다. 특히 모바일 환경에서는 컨트롤러가 수집하는 정보 중에서 노드의 움직임 정보가 중요하기 때문에 본 논문에서는 움직임 정보를 세 가지 종류로 세분화하여 관리하고 해당 정보를 효율적으로 활용하고자한다. 본 논문에서 제안하는 모바일 노드의 움직임 정보의 활용 방안은 크게 두 가지로 컨트롤 메시지 횟수를 조절함으로써 컨트롤 오버헤드를 줄이는 것과 통신 단절 시 효율적으로 복구할 수 있는 복구 프로세스를 제안하는 것이다. 복구 프로세스는 두 가지로 모바일 노드의 움직임 정보를 활용하여 연결 상태를 효율적으로 복구하는 방법과 cloud level과 fog level을 구별하여 경로 복구를 수행하는 방법이다. 시뮬레이션 결과, 주어진 환경에서 본 논문이 제안한 방법이 기존 방법에 비해 55% 가량의 컨트롤 오버헤드를 줄이고 통신 단절 시 끊김 시간을 5% 가량 단축시킬 수 있음을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4682-4705
• /
• 2020

The Unmanned Aerial Vehicles (UAV) networks consisting of low-cost UAVs are very vulnerable to smart jammers that can choose their jamming policies based on the ongoing communication policies accordingly. In this article, we propose a novel cloud and edge-aided mobile communication scheme for low-cost UAV network against smart jamming. The challenge of this problem is to design a communication scheme that not only meets the requirements of defending against smart jamming attack, but also can be deployed on low-cost UAV platforms. In addition, related studies neglect the problem of decision-making algorithm failure caused by intermittent ground-to-air communication. In this scheme, we use the policy network deployed on the cloud and edge servers to generate an emergency policy tables, and regularly update the generated policy table to the UAVs to solve the decision-making problem when communications are interrupted. In the operation of this communication scheme, UAVs need to offload massive computing tasks to the cloud or the edge servers. In order to prevent these computing tasks from being offloaded to a single computing resource, we deployed a lightweight game algorithm to ensure that the three types of computing resources, namely local, edge and cloud, can maximize their effectiveness. The simulation results show that our communication scheme has only a small decrease in the SINR of UAVs network in the case of momentary communication interruption, and the SINR performance of our algorithm is higher than that of the original Q-learning algorithm.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2009년도 정보통신설비 학술대회
• /
• pp.131-135
• /
• 2009

This paper is the introduction of our work on distributed load scheduling in single-level tree network. In this paper, we derive a new calculation model in single-level tree network and show a closed-form formulation of the time for computation system. There are so many examples of the application of this technology such as distributed database, biology computation on genus, grid computing, numerical computing, video and audio signal processing, etc.

• 한국콘텐츠학회논문지
• /
• 제5권1호
• /
• pp.189-199
• /
• 2005

그리드 컴퓨팅은 과학기술 분야의 큰 문제들을 해결하기 위해 네트워크 상에 분산된 수많은 컴퓨터들의 컴퓨팅 파워와 대용량 저장장치를 공유하여 문제들을 해결할 수 있는 기술이다. 그리드 컴퓨팅의 환경은 WAN으로 구성된 각기 다른 성능과 이질적인 네트워크 상태들로 구성된다. 그래서, 이러한 이질적인 성능요소들을 고려하여 계산 작업에 반영시키는 것이 무엇보다 중요하다. 본 논문에서는 네트워크 상태정보를 고려한 노드별 작업 프로세스 수를 결정하는 효율적인 방법을 제안한다. 네트워크 상태정보는 latency, bandwidth, latency-bandwidth 혼합정보를 고려한다. 먼저, 측정된 네트워크 상태정보를 이용하여 노드별 성능비율을 구하고 이를 통해 작업 프로세스 수를 결정한다. 마지막 단계에서는, 결정된 노드별 작업 프로세스 수를 기반으로 자동으로 RSL 파일을 생성하여 작업을 수행한다. 네트워크 성능정보는 NWS(Network Weather Service)에 의해 수집된다. 실험결과에 따르면, 네트워크 성능정보를 고려한 방법이 그렇지 않은 기존의 균등방식보다 작업량, 작업 프로세스 수, 노드 수 관점에서 각각 23%, 31%, 57% 성능이 향상되었다.

• 정보보호학회논문지
• /
• 제15권6호
• /
• pp.27-35
• /
• 2005

현재의 네트워크 환경에서는 사용자들이 인터넷상의 여러 서버에 대하여 각각의 독립된 ID(Identity)를 사용하고 있기 때문에 사용자들이 많은 수의 ID와 패스워드를 관리해야하는 불편함이 있다. 이러한 문제를 해결하기 위해 ID 관리 시스템을 사용하지만, 앞으로 도래할 유비쿼터스 컴퓨팅 환경에서는 유무선 네트워크상의 수많은 컴퓨터들이 유기적으로 연결되기 때문에 사용자 ID 및 패스워드 관리가 더욱 복잡해지고, 기존의 단일 신뢰영역(COT: Circle of Trust)의 ID 관리 시스템으로는 이러한 어려움을 해결하기에 충분하지 않다. 본 논문에서는 이러한 문제를 해결하기 위해, 다중 신뢰영역 간의 federated ID 연동을 유선 컴퓨팅 환경에서뿐만 아니라 모바일 컴퓨팅 환경으로 확장하기 위한 federated ID 연동 모델을 제안하고 평가하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.147-158
• /
• 2022

Cloud Computing offers flexible, on demand, ubiquitous resources for cloud users. Cloud users are provided computing resources in a virtualized environment. In order to meet the growing demands for computing resources, data centres contain a large number of physical machines accommodating multiple virtual machines. However, cloud data centres cannot utilize their computing resources to their total capacity. Several policies have been proposed for improving energy proficiency and computing resource utilization in cloud data centres. Virtual machine placement is an effective method involving efficient mapping of virtual machines to physical machines. However, the availability of many physical machines accommodating multiple virtual machines in a data centre has made the virtual machine placement problem a non deterministic polynomial time hard (NP hard) problem. Metaheuristic algorithms have been widely used to solve the NP hard problems of multiple and conflicting objectives, such as the virtual machine placement problem. In this context, we presented essential concepts regarding virtual machine placement and objective functions for optimizing different parameters. This paper provides a taxonomy of metaheuristic algorithms for the virtual machine placement method. It is followed by a review of prominent research of virtual machine placement methods using meta heuristic algorithms and comparing them. Finally, this paper provides a conclusion and future research directions in virtual machine placement of cloud computing.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.61-70
• /
• 2024

Cloud Computing is internet-based computing, where the users are provided with whatever service they need from the resources, software, and information. Recently, the security of cloud computing is considered as one of the major issues for both cloud service providers CSP and end-users. Privacy and highly confidential data make many users refuse to store their data within cloud computing, since data on cloud computing is not dully secured. The cryptographic algorithm is a technique which is used to maintain the security and privacy of the data on the cloud. In this research, we applied eight different cryptographic algorithms on Xen and KVM as hypervisors on cloud computing, to be able to measure and compare the performance of the two hypervisors. Response time and CPU utilization while encryption and decryption have been our aspects to measure the performance. In terms of response time and CPU utilization, results show that KVM is more efficient than Xen on average at 11.5% and 11% respectively. While TripleDES cryptographic algorithm shows a more efficient time response at Xen hypervisor than KVM.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.59-66
• /
• 2024

This paper presents the concept and characteristics of cloud computing, and it addresses how cloud computing delivers quality of service (QoS) to the end-user. Next, it discusses how to schedule one's workload in the infrastructure using technologies that have recently emerged such as Machine Learning (ML). That is followed by an overview of how ML can be used for resource management. This paper then looks at the primary goal of this project, which is to outline the benefits of using ML to schedule upcoming demands to achieve QoS and conserve energy. In this survey, we reviewed the research related to ML methods for predicting workloads in cloud computing. It also provides information on the approaches to elasticity, while another section discusses the methods of prediction used in previous studies and those that used in this field. The paper concludes with a summary of the literature on predicting workloads and optimising QoS in the cloud computing.