• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.29-34
• /
• 2023

The flow from developing a machine learning model to deploying it in a production environment suffers challenges. Efficient and reliable deployment is critical for realizing the true value of machine learning models. Bridging this gap between development and publication has become a pivotal concern in the machine learning community. FastAPI, a modern and fast web framework for building APIs with Python, has gained substantial popularity for its speed, ease of use, and asynchronous capabilities. This paper focused on leveraging FastAPI for deploying machine learning models, addressing the potentials associated with integration, scalability, and performance in a production setting. In this work, we explored the seamless integration of machine learning models into FastAPI applications, enabling real-time predictions and showing a possibility of scaling up for a more diverse range of use cases. We discussed the intricacies of integrating popular machine learning frameworks with FastAPI, ensuring smooth interactions between data processing, model inference, and API responses. This study focused on elucidating the integration of machine learning models into production environments using FastAPI, exploring its capabilities, features, and best practices. We delved into the potential of FastAPI in providing a robust and efficient solution for deploying machine learning systems, handling real-time predictions, managing input/output data, and ensuring optimal performance and reliability.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.207-215
• /
• 2024

Cloud computing is now used by most companies, business centres and academic institutions to embrace new computer technology. Cloud Service Providers (CSPs) are limited to certain services, missing some of the assets requested by their customers, it means that different clouds need to interconnect to share resources and interoperate between them. The clouds may be interconnected in different characteristics and systems, and the network may be vulnerable to volatility or interference. While information technology and cloud computing are also advancing to accommodate the growing worldwide application, criminals use cyberspace to perform cybercrimes. Cloud services deployment is becoming highly prone to threats and intrusions. The unauthorised access or destruction of records yields significant catastrophic losses to organisations or agencies. Human intervention and Physical devices are not enough for protection and monitoring of cloud services; therefore, there is a need for more efficient design for cyber defence that is adaptable, flexible, robust and able to detect dangerous cybercrime such as a Denial of Service (DOS) and Distributed Denial of Service (DDOS) in heterogeneous cloud computing platforms and make essential real-time decisions for forensic investigation. This paper aims to develop a framework for digital forensic for the detection of cybercrime in a joined heterogeneous cloud setup. We developed a Digital Forensics model in this paper that can function in heterogeneous joint clouds. We used Unified Modeling Language (UML) specifically activity diagram in designing the proposed framework, then for deployment, we used an architectural modelling system in developing a framework. We developed an activity diagram that can accommodate the variability and complexities of the clouds when handling inter-cloud resources.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.163-166
• /
• 2007

This paper describes a IPv6 trial service provided by LG DACOM and discusses about the output of trial service. MIC has urged public organizations to introduce IPv6 technology into their network. As one of propelling policies, MIC and NIA launched some IPv6 trial project. LG DACOM, MIC's agent in doing IPv6 trial project, has selected three public organizations in order to deploy IPv6 based VoIP trial service. KMA, KISITI and MND gave out their different service requirements. In achieve this project we developed IPv6 supported voice IP phone, video IP phone, media gateway and IP-PBX. Furthermore, two KMA provincial offices adopted trial IP phone as working phone and replaced legacy PBX with IP-PBX. At the same time, public organizations introduced IPv6 technology into their local networks.

• Journal of Industrial Technology
• /
• v.24 no.B
• /
• pp.149-156
• /
• 2004

Quality services such as the integrated service and the differentiated service have been expected to be supported by public Internet as multimedia applications proliferate. Despite a lot of techniques for quality services have been devised, the prospect for the deployment of these techniques is not clear yet. In this research feasibility of real world quality service is investigated based on former experiments and recent trends in Internet applications. User network-based quality services are considered as the most feasible and economic short-term solution, which are also flexible in nature. Milestones and key technologies for some specific public network-based quality services are also described.

• Journal of the Optical Society of Korea
• /
• v.11 no.3
• /
• pp.101-107
• /
• 2007

In this paper, we have presented the results of Wavelength Division Multiplexing-Passive Optical Network (WDM-PON) based fiber-to-the-home (FTTH) field trial test which was held in the city of Gwangju. We have implemented an injection locked Fabry-Perot Laser Diode (FP-LD) based WDM-PON system and reliably delivered Internet Protocol TV (IP-TV), networked Personal Video Recorder (N-PVR), High-Definition Video on Demand (HD-VoD), Education on Demand (EoD) and Internet service as FTTH service through the system during the field trial test. We have also verified that the WDM-PON system worked well to provide quality of service (QoS) guaranteed 100Mbps bandwidth per subscriber. Furthermore, we have presented network designing issues in Outside Plant (OSP) and Customer Premises Network (CPN) that should be overcome to efficiently deploy FTTH service. Finally, based on the field trial test results, we proposed FTTH service deployment strategies.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.25-33
• /
• 2018

This paper proposes a cloud workflow model theoretically supported by the information control net modeling methodology as a cloud workflow modeling methodology that is mandatory in implementing realtime enterprise workflow management systems running with cloud computing environments. The eventual goal of the cloud workflow model proposed in this paper is to support those cloud workflow architectures reflecting the types of cloud deployment models such as private, community, public, and hybrid cloud deployment models. Moreover, the proposed model is a mathematical graph model that is extended from the information control net modeling methodology used in conventional enterprise workflow modeling, and it aims to theoretically couple this methodology with the cloud deployment models. Finally, this paper tries to verify the feasibility of the proposed model by building a possible cloud workflow architecture and its cloud workflow services on a realtime enterpeise cloud workflow management system.

• 한국정보통신설비학회:학술대회논문집
• /
• 2003.08a
• /
• pp.307-309
• /
• 2003

In the initial deployment stage of optical access networks, optical network systems and optical fiber cables have been provided mainly for commercial buildings or users in KT. According to the demand of residential users who expect to subscribe broadband multimedia services as high bit rate services, the optical access networks get closer to the residential users as FTTCab or FTTH So, it is very important to install optical access networks economically and effectively because that the total cost and usability of optical fiber cables depends on that. Especially, one of characteristics in access networks is the possibility of variation on services demands and technology evolution. Also access networks must be prepared for the final deployment, FTTH. Therefore, the designing and planning of optical access networks are coming to be very important activity for most of telecommunications service providers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1091-1110
• /
• 2016

Hybrid deployment under current cloud data centers is a combination of online and offline services, which improves the utilization of the cluster resources. However, the performance of the cluster is often affected by the online services in the hybrid deployment environment. To improve the response time of online service (e.g. search engine), an effective scheduling algorithm based on Storm is proposed. At the component level, the algorithm dispatches the component with more influence to the optimal performance node. Inside the component, a reasonable resource allocation strategy is used. By searching the compressed index first and then filtering the complete index, the execution speed of the component is improved with similar accuracy. Experiments show that our algorithm can guarantee search accuracy of 95.94%, while increasing the response speed by 68.03%.

• International conference on construction engineering and project management
• /
• 2007.03a
• /
• pp.9-18
• /
• 2007

The success of a building design team is achieved as a result of a combination of multiple events/factors and interactions, and has a great impact on the quality of the building construction process. While most of previous studies have focused on quality of the construction process, the success of a design team has not been completely investigated. This paper presents the critical factors that impact the success of a building design team and describes an assessment tool to measure the successful performance of the design team with respect to the critical factors. The development of the assessment tool employs the concept of quality function deployment (QFD), a technique to measure the service quality of an organization.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.223-228
• /
• 2008

Recently, various types of wireless access networks, such as WLAN, WiBro and HSDPA, etc, have been successfully deployed by commercial service providers (i.e., KT, KTF). In this situation, there are many efforts to provide high quality of services to guarantee seamless mobility between heterogeneous networks. The IP layer mobility protocols are efficient mechanisms to provide seamless mobility between IP based heterogeneous networks as well as homogeneous networks. However, to apply IP mobility protocols in real heterogeneous networks (i.e., WiBro and HSDPA), we must consider not only the basic features of techniques of wireless access networks (i.e., Data rate, Coverage, Quality of Service) but also the problem of real environment of service provider (i.e., Expanse cost to change the access network). Due to this reason, it is difficult to satisfy required conditions by using only one IP mobility protocol in real heterogeneous networks. Therefore, in this paper, we propose an efficient mobility protocol to solve the complex problems that are occurred in real heterogeneous networks. The proposed protocol, so-called, "Hybrid Mobile IP" tries to provide a synergy effect by integrating Client Mobile IPv4 (CMIPv4) and Proxy Mobile IPv4 (PMIPv4), and using the two mobility protocols selectively according to the situation of real heterogeneous networks.