• Progress in Medical Physics
• /
• v.31 no.3
• /
• pp.111-123
• /
• 2020

Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2496-2512
• /
• 2021

The requirements for powerful computing capability, high capacity, low latency and low energy consumption of emerging services, pose severe challenges to the fifth-generation (5G) network. As a promising paradigm, mobile edge networks can provide services in proximity to users by deploying computing components and cache at the edge, which can effectively decrease service delay. However, the coexistence of heterogeneous services and the sharing of limited resources lead to the competition between various services for multiple resources. This paper considers two typical heterogeneous services: computing services and content delivery services, in order to properly configure resources, it is crucial to develop an effective offloading and caching strategies. Considering the high energy consumption of 5G base stations, this paper considers the hybrid energy supply model of traditional power grid and green energy. Therefore, it is necessary to design a reasonable association mechanism which can allocate more service load to base stations rich in green energy to improve the utilization of green energy. This paper formed the joint optimization problem of computing offloading, caching and resource allocation for heterogeneous services with the objective of minimizing the on-grid power consumption under the constraints of limited resources and QoS guarantee. Since the joint optimization problem is a mixed integer nonlinear programming problem that is impossible to solve, this paper uses deep reinforcement learning method to learn the optimal strategy through a lot of training. Extensive simulation experiments show that compared with other schemes, the proposed scheme can allocate resources to heterogeneous service according to the green energy distribution which can effectively reduce the traditional energy consumption.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.99-105
• /
• 2021

In addition to the OTT video production service represented by Nexflix and YouTube, a personalized recommendation system for content with artificial intelligence has become common. YouTube's personalized recommendation service system consists of two neural networks, one neural network consisting of a recommendation candidate generation model and the other consisting of a ranking network. Netflix's video recommendation system consists of two data classification systems, divided into content-based filtering and collaborative filtering. As the online platform-led content production is activated by the Corona Pandemic, the field of virtual influencers using artificial intelligence is emerging. Virtual influencers are produced with GAN (Generative Adversarial Networks) artificial intelligence, and are unsupervised learning algorithms in which two opposing systems compete with each other. This study also researched the possibility of developing AI platform based on individual recommendation and virtual influencer (metabus) as a core content of OTT in the future.

• Journal of English Language & Literature
• /
• v.58 no.2
• /
• pp.279-304
• /
• 2012

Since the publication of Foucault's Discipline and Punish, theatricality has become one of the key concepts in New Historicism. By defining theatricality as the most definitive feature of early modern society and culture, New Historicists have promoted the idea that theatrical practices in every day life were eventually replaced by textual practices as the western society started to undergo modernization with the advent of print culture and technologies. This paper questions this linear model of English literature, the shift of literary practices from theatricality to textuality in the event of modernization, by closely looking at the ways in which newsbooks and playlets during the English civil wars appealed to their target readers. The early print-based literary commodities during the English civil war (i.e. newsbooks and playlets) were able to win the attention of their audience not by breaking away from theatrical energy and creativity but instead by embracing and taking advantage of them through the use of dramatic conventions, dialogues, and many others. The newsbooks and the playlets during the time, however, did not simply replicate the dramatic forms and experiences of the previous generation. Instead, as the case study of Craftie Cromwell exemplifies, they went further to produce a different mode of theatricality by reshaping everyday lives into serialized drama, whose resolution is always already delayed and postponed into the ever-receding future. In conclusion, the study of the newsbook and playlets during the civil wars suggests that the textuality of modern times, materialized in print forms, have been co-evolved with the development of new theatricality, whose contents and forms are susceptible to the changes of everyday reality.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.1
• /
• pp.155-167
• /
• 2012

Cloud computing service is a next generation IT service which has pay-per-use billing model and supports elastically provisioning IT infra according to user demand. However it has many potential threats originating from outsourcing/supporting service structure that customers 'outsource' their own data and provider 'supports' infra, platform, application services, the complexity of applied technology, resource sharing and compliance with a law, etc. In activation of Cloud service, we need objective assessment standard to ensure safety and reliability which is one of the biggest obstacles to adopt cloud service. So far information security management system has been used as a security standard for a security management and IT operation within an organization. As for Cloud computing service it needs new security management and assessment different from those of the existing in-house IT environment. In this paper, to make a Information Security Management System considering cloud characteristics key components from threat management system are drawn and all control domain of existing information security management system as a control components are included. Especially we designed service security management to support service usage in an on-line self service environment and service contract and business status.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.283-287
• /
• 2021

The purpose of this study is to analyze personalized contents and previews of OTT service based on user experience and to suggest the improvements of the preview viewing experience. Current domestic OTT mobile applications were researched to find out how services are offering content. Plus, the 20s-30s were recruited to analyze user experience. An online survey and in-depth interview were conducted by using Stephen P. Anderson's Creating Pleasurable Interface Model. As a result, preview help users to select content but it doesn't suit their taste. Also, the preview is hard to watch however they want. Therefore, it can be inferred that the preview requires the function for improving efficiency, preference, and accessibility. This study is expected to be used as research material on user experience or preview experience of OTT content.

• Wind and Structures
• /
• v.32 no.1
• /
• pp.55-69
• /
• 2021

Ultrapure ferritic stainless steel provides a new generation of long-span metal roof systems with continuous welding technology, which exhibits many unknown behaviors during wind excitation. This study focuses on the wind-resistant capacity of a new continuous welding stainless steel roof (CWSSR) system. Full-scale testing on the welding joints and the CWSSR system is performed under uniaxial tension and static ultimate wind uplift loadings, respectively. A finite element model is developed with mesh refinement optimization and is further validated with the testing results, which provides a reliable way of investigating the parameter effect on the wind-induced structural responses, namely, the width and thickness of the roof sheeting and welding height. Research results show that the CWSSR system has predominant wind-resistant performance and can bear an ultimate wind uplift loading of 10.4 kPa without observable failures. The welding joints achieve equivalent mechanical behaviors as those of base material is produced with the current of 65 A. Independent structural responses can be found for the roof sheeting of the CWSSR system, and the maximum displacement appears at the middle of the roof sheeting, while the maximum stress appears at the connection supports between the roof sheeting with a significant stress concentration effect. The responses of the CWSSR system are greatly influenced by the width and thickness of the roof sheeting but are less influenced by the welding height.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1123-1131
• /
• 2020

The quick-response (QR) code is a two-dimensional barcode which is widely being used. Due to several interesting features such as small code size, high error correction capabilities, easy code generation and reading process, the QR codes are used in many applications. Nowadays, a printed color QR code for offline applications is being studied to improve the information storage capacity. By multiplexing color information into the conventional black-white QR code, the storage capacity is increased, however, it is hard to extract the embedded information due to the color crosstalk and geometrical distortion. In this paper, to overcome these problems, a new type of QR code is designed based on the CMYK color model and the local spatial searching as well as the global spatial matching is introduced in the reading process. These results in the recognition rate increase. Through practical experiments, it is shown that the proposed algorithm can perform the bit recognition rate improvement of about 3% to 5%.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.954-960
• /
• 2020

This paper proposes a speed variable proportional resonant current control method for a single-phase permanent magnet synchronous motor(PMSM). Due to the electromagnetic characteristics of a single-phase PMSM, negative and zero torques are generated in the part corresponding to the phase difference between the stator current and the back electromotive force. In addition, overcurrent limitation is required because of the low stator resistance and inductance in sensorless operation. When using the vector control for current control of single-phase PMSM under these conditions, processes of coordinate transformation, inverse coordinate transformation, and generation of virtual dq-axis components are required. However, the proposed variable speed proportional resonant current control method does not need the coordinate transformation used for AC motors. In this paper, we have confirmed stable maneuverability by using variable proportional resonant current control algorithm, and proposed sensorless control based on a mathematical model of a single-phase PMSM without a position sensor when reaching a constant speed. The usefulness of the current control method was verified through several experiments.

• The Korean Journal of Physiology and Pharmacology
• /
• v.25 no.2
• /
• pp.97-109
• /
• 2021

Neonatal hypoxia/ischemia (H/I), injures white matter, results in neuronal loss, disturbs myelin formation, and neural network development. Neuroinflammation and oxidative stress have been reported in neonatal hypoxic brain injuries. We investigated whether Paeoniflorin treatment reduced H/I-induced inflammation and oxidative stress and improved white matter integrity in a neonatal rodent model. Seven-day old Sprague-Dawley pups were exposed to H/I. Paeoniflorin (6.25, 12.5, or 25 mg/kg body weight) was administered every day via oral gavage from postpartum day 3 (P3) to P14, and an hour before induction of H/I. Pups were sacrificed 24 h (P8) and 72 h (P10) following H/I. Paeoniflorin reduced the apoptosis of neurons and attenuated cerebral infarct volume. Elevated expression of cleaved caspase-3 and Bad were regulated. Paeoniflorin decreased oxidative stress by lowering levels of malondialdehyde and reactive oxygen species generation and while, and it enhanced glutathione content. Microglial activation and the TLR4/NF-κB signaling were significantly down-regulated. The degree of inflammatory mediators (interleukin 1β and tumor necrosis factor-α) were reduced. Paeoniflorin markedly prevented white matter injury via improving expression of myelin binding protein and increasing O1-positive olidgodendrocyte and O4-positive oligodendrocyte counts. The present investigation demonstrates the potent protective efficiency of paeoniflorin supplementation against H/I-induced brain injury by effectually preventing neuronal loss, microglial activation, and white matter injury via reducing oxidative stress and inflammatory pathways.