• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.1-9
• /
• 2023

This study was conducted for the purpose of improving the usability of the product through the usability evaluation of the voice tag reader to improve the life convenience of the visually impaired. Perceived usability evaluation was conducted for 19 evaluation items based on the evaluation model considering the usability principle and the characteristics of the visually impaired. A total of 50 participants were included for the analysis. As a result of the perceived usability evaluation of the visually impaired, the safety of the voice tag reader, voice and sound quality, and accuracy of voice information were relatively satisfactory. It was found that the reader received a low evaluation in terms of efficiency in use, including the size and weight of the reader, and the convenience of carrying and storing. For the usability improvement, the procedure for using a product needs to be more simplified, and it would be helpful to input and supply tags for commonly used objects in advance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.15-20
• /
• 2023

This paper is a study on the development of an artificial intelligence (AI) system algorithm that recommends indirect advertising products suitable for character web dramas. The goal of this study is to increase viewers' content immersion and help them understand the story of the drama more deeply by recommending indirect advertising products that are suitable for writing lines for web dramas. In this study, we analyze dialogue and plot using the natural language processing model GPT, and develop two types of indirect advertising product recommendation systems, including prop type and background type, based on the analysis results. Through this, products that fit the story of the web drama are appropriately placed, allowing indirect advertisements to be exposed naturally, thereby increasing viewer immersion and enhancing the effectiveness of product promotion. There are limitations of artificial intelligence models, such as the difficulty in fully understanding hidden meanings or cultural nuances, and the difficulty in securing sufficient data for learning. However, this study will provide new insights into how AI can contribute to the production of creative works, and will be an important stepping stone to expand the possibilities of using natural language processing models in the creative industry.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.69-78
• /
• 2024

Recently, consumers have shown an increasing tendency to seek information related to environmental, social, and governance (ESG) aspects in order to choose products with higher social value and environmental friendliness. In this paper, we proposes a product recommendation system applying ESG indicators tailored to the recent consumer trend of value-based consumption, utilizing a model called MultiSAGE that combines GraphSAGE and GAT. To achieve this, ESG rating data for 1,033 companies in 2022 collected from the Korea ESG Standard Institute and actual product data from N companies were transformed into a Heterogeneous Graph format through a data processing pipeline. The MultiSAGE model was then applied in machine learning to implement a recommendation system that, given a specific product, suggests eco-friendly alternatives. The implementation results indicate that consumers can easily compare and purchase products with ESG indicators applied, and it is anticipated that this system will be utilized in recommending products with social value and environmental friendliness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.94-103
• /
• 2017

As automatic hacking tools and techniques have been improved, the number of new vulnerabilities has increased. The CVE registered from 2010 to 2015 numbered about 80,000, and it is expected that more vulnerabilities will be reported. In most cases, patching a vulnerability depends on the developers' capability, and most patching techniques are based on manual analysis, which requires nine months, on average. The techniques are composed of finding the vulnerability, conducting the analysis based on the source code, and writing new code for the patch. Zero-day is critical because the time gap between the first discovery and taking action is too long, as mentioned. To solve the problem, techniques for automatically detecting and analyzing software (SW) vulnerabilities have been proposed recently. Cyber Grand Challenge (CGC) held in 2016 was the first competition to create automatic defensive systems capable of reasoning over flaws in binary and formulating patches without experts' direct analysis. Darktrace and Cylance are similar projects for managing SW automatically with artificial intelligence and machine learning. Though many foreign commercial institutions and academies run their projects for automatic binary analysis, the domestic level of technology is much lower. This paper is to study developing automatic detection of SW vulnerabilities and defenses against them. We analyzed and compared relative works and tools as additional elements, and optimal techniques for automatic analysis are suggested.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.77-87
• /
• 2021

With the development of the Internet and personal computers, various and complex attacks begin to emerge. As the attacks become more complex, signature-based detection become difficult. It leads to the research on behavior-based log anomaly detection. Recent work utilizes deep learning to learn the order and it shows good performance. Despite its good performance, it does not provide any explanation for prediction. The lack of explanation can occur difficulty of finding contamination of data or the vulnerability of the model itself. As a result, the users lose their reliability of the model. To address this problem, this work proposes an explainable log anomaly detection system. In this study, log parsing is the first to proceed. Afterward, sequential rules are extracted by Bayesian posterior probability. As a result, the "If condition then results, post-probability" type rule set is extracted. If the sample is matched to the ruleset, it is normal, otherwise, it is an anomaly. We utilize HDFS datasets for the experiment, resulting in F1score 92.7% in test dataset.

• Smart Media Journal
• /
• v.7 no.2
• /
• pp.47-53
• /
• 2018

Along with the development of information and communication technology, smart education that can learn without restrictions of time, place and equipment is activated even in the field of education. Although smart education is provided with content-based training solutions, construction of a system that grasps individual characteristics of learners and provides personalized learning is relatively weak. The activity of free choice is an important play activity of early childhood education, but it is not implemented efficiently by relying on the clinical observation of the teacher. If the IoT(Internet of Things) technology based on Hyper-Connected is applied to free-choice activities, it is possible to provide the child's personalized activity type and play-form analysis based on objective and stylized data. In this paper, we design and implement a system to monitor the child's activity of free choice by building an IoT environment that is based on open source hardware. The proposed system provides children's activity information as objective data and will be used as teacher's work mitigation and custom training material for each child.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.115-122
• /
• 2022

Recently, the importance of CPR training for the layperson has been emphasized to improve the survival rate of out-of-hospital cardiac arrest patients. An accurate and realistic training strategy is required for the CPR training effect for laypersons. In this study, we develop an extended reality (XR) based CPR training system and evaluate its usability. The XR based CPR training system consisted of three applications. First, a 3D heart anatomy image registered to the manikin is transmitted to the smart glasses to guide the chest compression point. The second application provides visual and auditory information about the CPR process through smart glasses. At the same time, the smartwatch sends a vibration notification to guide the compression rate. The 'Add-on-kit' is a device that detects the depth and speed of chest compression via sensors installed on the manikin and sends immediate feedback to the smartphone. One hundred laypersons who participated in this study agreed that the XR based CPR training system has realism and effectiveness. XR based registration technology will contribute to improving the efficiency of CPR training by enhancing realism, immersion, and self-directed learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.175-182
• /
• 2020

The non-contact eye tracking is a nonintrusive human-computer interface providing hands-free communications for people with severe disabilities. Recently. it is expected to do an important role in non-contact systems due to the recent coronavirus COVID-19, etc. This paper proposes a novel approach for an eye mouse using an eye tracking method based on a context-aware based AdaBoost multi-region classifier and ASSL algorithm. The conventional AdaBoost algorithm, however, cannot provide sufficiently reliable performance in face tracking for eye cursor pointing estimation, because it cannot take advantage of the spatial context relations among facial features. Therefore, we propose the eye-region context based AdaBoost multiple classifier for the efficient non-contact gaze tracking and mouse implementation. The proposed method detects, tracks, and aggregates various eye features to evaluate the gaze and adjusts active and semi-supervised learning based on the on-screen cursor. The proposed system has been successfully employed in eye location, and it can also be used to detect and track eye features. This system controls the computer cursor along the user's gaze and it was postprocessing by applying Gaussian modeling to prevent shaking during the real-time tracking using Kalman filter. In this system, target objects were randomly generated and the eye tracking performance was analyzed according to the Fits law in real time. It is expected that the utilization of non-contact interfaces.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.4
• /
• pp.53-82
• /
• 2020

With the increase in smartphone ownership and Internet usage using smartphones, the information environment is shifting from the existing PC to the smart mobile. The current undergraduate students are called Generation Z who prefer smartphones to PCs and video contents to texts. This study attempted to understand their usage behaviors of electronic resources in an academic library in a smart mobile environment. This study conducted a usage statistics analysis with 61,433 usage records of e-books, audiobooks, and e-learning contents and 1,595 records of users in the A academic library during 3 years from 2016 to 2018. The scope of the data includes the date of use, the subject, the year of publication, the channel of use, and each user's gender, affiliation, status, admission date, and graduation date. This study investigated not only the general characteristics of electronic resource use, but also the usage behaviors according to the user's demographic characteristics. Based on the findings, this study suggested practical service plans that are applicable in the near future and reflect changing circumstances.