• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• 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%.

• Journal of the Ergonomics Society of Korea
• /
• v.24 no.1
• /
• 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.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1420-1427
• /
• 2016

This paper proposes a method taking advantage of Fog computing and SDN in the connected vehicle environment which is having an unstable communication channel and a dynamic topology. For this purpose, the controller should understand the current state of the overall network by maintaining recent network topology, especially, the mobility information of mobile nodes. These are managed by the controller, and are important in unstable conditions in the mobile environment. The mobility levels are divided into 3 categories. We can efficiently exploit that information. By utilizing network state information, we suggest two outcomes. First, we reduce the control message overhead by adjusting the period of beacon messages. Second, we propose a recovery process to prepare the communication failure. We can efficiently recover connection failure through mobility information. Furthermore, we suggest a path recovery by decoupling the cloud level and the fog level in accordance with application data types. The simulation results show that the control message overhead and the connection failure time are decreased by approximately 55% and 5%, respectively in comparison to the existing method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• 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
• /
• 2009.08a
• /
• 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.

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.189-199
• /
• 2005

The grid computing is a technique to solve big problems such as a field of scientific technique by sharing the computing power and a big storage space of the numerous computers on the distributed network. The environment of the grid computing is composed with the WAN which has a different performance and a heterogeneous network condition. Therefore, it is more important to reflect heterogeneous performance elements to calculation work. In this paper, we propose an efficient method that decides work process number of each node by considering a network state information. The network state information considers the latency, the bandwidth and latency-bandwidth mixture information. First, using information which was measured, we compute the performance ratio and decide work process number of each node. Finally, RSL file was created automatically based on work process number which was decided, and then accomplishes a work. The network performance information is collected by the NWS. According to experimental results, the method which was considered of network performance information is improved respectively 23%, 31%, and 57%, compared to the methods of existing in a viewpoint of work amount, work process number, and node number.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.6
• /
• pp.27-35
• /
• 2005

While the current world wide network offers an incredibly rich base of information, it causes network management problem because users should have many independent IDs and passwords for accessing different sewers located in many places. In order to solve this problem users have employed single circle of trust(COT) ID management system, but it is still not sufficient for clearing the problem because the coming ubiquitous network computing environment will be integrated and complex networks combined with wired and wireless network devices. The purpose of this paper is to describe the employment and evaluation of federated ID interoperability method for solving the problem. The use of the proposed model can be a solution for solving network management problem in the age of mobile computing environment as well as wired network computing environment.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• 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
• /
• v.24 no.1
• /
• 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
• /
• v.24 no.2
• /
• 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.