• Progress in Medical Physics
• /
• v.30 no.2
• /
• pp.49-58
• /
• 2019

Purpose: Automated analytical systems have begun to emerge as a database system that enables the scanning of medical images to be performed on computers and the construction of big data. Deep-learning artificial intelligence (AI) architectures have been developed and applied to medical images, making high-precision diagnosis possible. Materials and Methods: For diagnosis, the medical images need to be labeled and standardized. After pre-processing the data and entering them into the deep-learning architecture, the final diagnosis results can be obtained quickly and accurately. To solve the problem of overfitting because of an insufficient amount of labeled data, data augmentation is performed through rotation, using left and right flips to artificially increase the amount of data. Because various deep-learning architectures have been developed and publicized over the past few years, the results of the diagnosis can be obtained by entering a medical image. Results: Classification and regression are performed by a supervised machine-learning method and clustering and generation are performed by an unsupervised machine-learning method. When the convolutional neural network (CNN) method is applied to the deep-learning layer, feature extraction can be used to classify diseases very efficiently and thus to diagnose various diseases. Conclusions: AI, using a deep-learning architecture, has expertise in medical image analysis of the nerves, retina, lungs, digital pathology, breast, heart, abdomen, and musculo-skeletal system.

• Journal of Internet Computing and Services
• /
• v.19 no.1
• /
• pp.131-140
• /
• 2018

This study aims to analyze various discussions for influences on employment by the technologies related to the frequently mentioned Fourth Industrial Revolution and to conduct an exploratory research. For this aim, this paper analyzes and extends the survey related to realization possibility for managements and professionals of ICT sector in Global Agenda Council of World Economic Forum (WEF) in September 2015. Based upon these results, this study further conducts an empirical survey not only over realization possibility but also over its employment impact. For each 23 item of realization possibility, all the respondents (n=169) responded positively to each item to be actualized in 2025. In addition, for each 23 item of the strength of employment impact, most items were responded as decrease of employment but a few items were predicted as expansion of employment. This research has a meaning in providing a clue of empirical survey for employment impact by the Fourth Industrial Revolution in the future.

• Journal of Biosystems Engineering
• /
• v.17 no.1
• /
• pp.65-78
• /
• 1992

When using a computer vision system for a measurement, the geometrically distorted input image usually restricts the site and size of the measuring window. A geometrically distorted image caused by the image sensing and processing hardware degrades the accuracy of the visual measurement and prohibits the arbitrary selection of the measuring scope. Therefore, an image calibration is inevitable to improve the measuring accuracy. A calibration process is usually done via four steps such as measurement, modeling, parameter estimation, and compensation. In this paper, the efficient error calibration technique of a geometrically distorted input image was developed using a neural network. After calibrating a unit pixel, the distorted image was compensated by training CMLAN(Cerebellar Model Linear Associator Network) without modeling the behavior of any system element. The input/output training pairs for the network was obtained by processing the image of the devised sampled pattern. The generalization property of the network successfully compensates the distortion errors of the untrained arbitrary pixel points on the image space. The error convergence of the trained network with respect to the network control parameters were also presented. The compensated image through the network was then post processed using a simple DDA(Digital Differential Analyzer) to avoid the pixel disconnectivity. The compensation effect was verified using known sized geometric primitives. A way to extract directly a real scaled geometric quantity of the object from the 8-directional chain coding was also devised and coded. Since the developed calibration algorithm does not require any knowledge of modeling system elements and estimating parameters, it can be applied simply to any image processing system. Furthermore, it efficiently enhances the measurement accuracy and allows the arbitrary sizing and locating of the measuring window. The applied and developed algorithms were coded as a menu driven way using MS-C language Ver. 6.0, PC VISION PLUS library functions, and VGA graphic functions.

• Korean journal of communication and information
• /
• v.55
• /
• pp.164-183
• /
• 2011

Technology innovation of digital convergence in recent years of the media sector has produced a series of significant changes in journalist labor. This study analyzes how recent introduction of convergent newsroom changed the nature of journalist labor and what strategy the management used to control journalists within the technologically innovated working condition with case of CBS. As the labor process theory tells us, the analysis found that technological innovation in the newsroom has encouraged a couple of aspects regarding labor process. First, losing control over their own labor journalists have undergone the process of significant deskilling. Second, the management have made a constant effort to introduce ideological and political apparatuses with twofold purposes, effective control over workers on one hand and concealing oppressive labor conditions on the other. The effort generated journalists' acceptance of new news-making routine and their consent on labor-management culture founded upon naive familism, which at last resulted in reinforcement of corporate power and isolation of labor society by separating internal labor market.

• The Journal of the Convergence on Culture Technology
• /
• v.2 no.2
• /
• pp.17-22
• /
• 2016

As the change in the analog age to the digital age with the development of civilization, people are living in a more friendly smart phone screen more books. In the past, people can easily see the text in the book, and now letters are disappearing from people's minds. And although they can see the letters easily anytime, anywhere using smart devices, they have no interest in the letters, they are interested only in information. So, the letters will disappear. However, there are people who try to keep the development of disappearing letters. In this paper, we are planning to produce a documentary about those people. We show that the letters survive in a modern society through Letterpress print shop, calligraphy, a computer font. And it seeks to inform that the letters are valuable.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.139-144
• /
• 2009

As it got through the step of super-high speed internet, mobile and digital convergence, the Ubiquitous Society is being attained gradually. Now, it is being variously spread not only the little ordinaries of communication but also fields of economy and industry. Specially, RFID and Navigation system are being used at home and foreign. These are prospected to give assistances that it brings along the competitive power of nation. But inflection range of RFID and Navigation is localized in the most simplest. This paper proposes system to reflect the individual and special quality using RFID and Navigation and to fit easily changing environment. And we studied to use what kind of information in the special environment. We used Fuzzy Logic and TSP for making the intelligence path searching and guiding system with more information.

• Journal of Industrial Convergence
• /
• v.18 no.5
• /
• pp.23-29
• /
• 2020

The Internet of things (IoT) is the extension of Internet connectivity into various devices and everyday objects. Embedded with electronics, Internet connectivity and other forms of hardware. The IoT poses significant risk to the entire digital ecosystem. This is because so many of these devices are designed without a built-in security system to keep them from being hijacked by hackers. This paper proposed a mutual authentication protocol for IoT Devices using symmetric-key algorithm. The proposed protocol use symmetric key cryptographic algorithm to securely encrypt data on radio channel. In addition, the secret key used for encryption is random number of devices that improves security by using variable secret keys. The proposed protocol blocked attacker and enabled legal deives to communicate because only authenticated devices transmit data by a mutual authentication protocol. Finally, our scheme is safe for attacks such as eavesdropping attack, location tracking, replay attack, spoofing attack and denial of service attack and we confirmed the safety by attack scenario.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.2
• /
• pp.53-74
• /
• 2021

Objective : The purpose of this study was to examine foreign literature on the evaluation and interventions for motor functions in children. Methods : Studies in this review were identified by searching the PubMed, Cochrane Library (Embase) databases from those published form January 2010 to March 2020 using the following keywords: "motor function test" or "motor function measure" or "movement assessment" or "motor proficiency test" or "motor scale" or "motor skill" and children. Results : Of the total 37 identified studies, 14 analyzed evaluations, 23 analyzed interventions, all of which were randomized control trials. Studies on evaluations were increasingly more common, in contrast to studies on interventions for motor functions. The most frequent field of research was rehabilitation. The studies on evaluations included the AIMS and MABC-II, and GMFM was the most frequently used intervention. Interventions were most commonly used in task-oriented training (six studies). Conclusion : This study aimed to provide a basis for therapists to choose effective motor function evaluation and interventions for clinical trials by analyzing studies related to interventions for and evaluation of motor function in children.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.37-44
• /
• 2019

With the advance of digital IT technology, the performance of the printing and scanning devices is improved and their price becomes cheaper. As a result, the public can easily access these devices for crimes such as forgery of official and private documents. Therefore, if we can identify which printing device is used to print the documents, it would help to narrow the investigation and identify suspects. In this paper, we propose a deep learning model for printer identification. A convolutional neural network model based on local features which is widely used for identification in recent is presented. Then, another model including a step to calculate global features and hence improving the convergence speed and accuracy is presented. Using 8 printer models, the performance of the presented models was compared with previous feature-based identification methods. Experimental results show that the presented model using local feature and global feature achieved 97.23% and 99.98% accuracy respectively, which is much better than other previous methods in accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2631-2649
• /
• 2021

Device-to-Device (D2D) communication is one of the enabling technologies for 5G networks that support proximity-based service (ProSe) for wireless network communications. This paper proposes a power control algorithm based on the Nash equilibrium and game theory to eliminate the interference between the cellular user device and D2D links. This leadsto reliable connectivity with minimal power consumption in wireless communication. The power control in D2D is modeled as a non-cooperative game. Each device is allowed to independently select and transmit its power to maximize (or minimize) user utility. The aim is to guide user devices to converge with the Nash equilibrium by establishing connectivity with network resources. The proposed algorithm with pricing factors is used for power consumption and reduces overall interference of D2Ds communication. The proposed algorithm is evaluated in terms of the energy efficiency of the average power consumption, the number of D2D communication, and the number of iterations. Besides, the algorithm has a relatively fast convergence with the Nash Equilibrium rate. It guarantees that the user devices can achieve their required Quality of Service (QoS) by adjusting the residual cost coefficient and residual energy factor. Simulation results show that the power control shows a significant reduction in power consumption that has been achieved by approximately 20% compared with algorithms in [11].