• Information Systems Review
• /
• v.22 no.2
• /
• pp.25-41
• /
• 2020

Along with the expectation about 5G network commercialization, interests in realistic and immersive media industries such as virtual reality (VR) are increasing. However, most of studies on VR still focus on video technologies instead of factors for popularity and consumption. Thus, the main objective of this research is to identify meaningful factors, which affect the view counts of VR videos and to provide business implications of the content strategies for VR video creators and service providers. Using a regression analysis with 700 VR videos, this study tries to find major factors that affect the view counts of VR videos. As a result, user assessment factors such as number of likes and sicknesses have a strong influence on the view counts. In addition, the result shows that both general information factors (video length and age) and content characteristic factors (series, one source multi use (OSMU), and category) are all influential factors. The findings suggest that it is necessary to support recommendation and curation based on user assessments for increasing popularity and diffusion of VR video streaming.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.213-231
• /
• 2023

With the rapid development of live streaming commerce, online host as an information source plays a critical role in affecting live streaming performance. However, the impact of different product types on the relationship between online hosts and live streaming has been less studied. Based on the elaboration likelihood model (ELM) and information source theory, this study aims to empirically investigate what factors influence the sales of live streaming commerce and how product type moderates the relationship between them. The analysis of 11,422 live streaming commerce data collected for four months from October 10, 2021 to February 10, 2022 shows that, among the factors related to source credibility and attractiveness, multi-channel networks (MCN) and the number of followers positively affect the sales volume of live streaming commerce, whereas the reputation score harms the sales. Moreover, the moderating effect of the product type (i.e., ratio of involvement products) on the relationships is confirmed. The findings enrich the literature on live streaming commerce performance. The limitations and future research directions are also discussed.

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Information Systems Review
• /
• v.19 no.3
• /
• pp.23-45
• /
• 2017

The ROK military is making a great effort and investment in establishing network-centric warfare, a future battlefield concept, as a major step in the establishment of a basic plan for military innovation. In the military organization level, an advanced process is introduced to shorten the command control time of the military and the business process is improved to shorten the decision time. In the information system dimension, an efficient resource management is achieved by establishing an automated command control system and a resource management information system by using the battle management information system. However, despite these efforts, we must evaluate the present level of informatization in an objective manner and assess the current progress toward the future goal of the military by using objective indicators. In promoting informatization, we must systematically identify the correct areas of improvement and identify policy directions to supplement in the future. Therefore, by analyzing preliminary research, workshops, and expert discussions on the major informatization level evaluation models at home and abroad, this study develops an evaluation model and several indicators that systematically reflect the characteristics of military organizations. The developed informatization level evaluation model is verified by conducting a feasibility test for the troops of the operation class or higher. We expect that this model will be able to objectively diagnose the level of informatization of the ROK military by putting budget and resources into the right place at the right time and to rapidly improve the vulnerability of the information sector.

• Information Systems Review
• /
• v.21 no.1
• /
• pp.23-38
• /
• 2019

The social network service (SNS) is one of the important marketing channels, so many companies actively exploit SNSs by posting SNS messages with appropriate content and style for their customers. In this paper, we focused on the psychological distances embedded in the SNS messages and developed a method to measure the psychological distance in SNS message by mixing a traditional content analysis, natural language processing (NLP), and machine learning. Through a traditional content analysis by human coding, the psychological distance was extracted from the SNS message, and these coding results were used for input data for NLP and machine learning. With NLP, word embedding was executed and Bag of Word was created. The Support Vector Machine, one of machine learning techniques was performed to train and test the psychological distance in SNS message. As a result, sensitivity and precision of SVM prediction were significantly low because of the extreme skewness of dataset. We improved the performance of SVM by balancing the ratio of data by upsampling technique and using data coded with the same value in first content analysis. All performance index was more than 70%, which showed that psychological distance can be measured well.

• Information Systems Review
• /
• v.20 no.1
• /
• pp.137-158
• /
• 2018

Online platforms recently expanded their connectivity through an authing service. The growth of authing services enabled consumers to enjoy easy log in access without exerting extra effort. However, multiple points of access increases the security vulnerability of platform ecosystems. Despite the importance of balancing authing service and security, only a few studies examined platform connectivity. This study examines the optimal level of authing service of a platform and how authing strategies impact participants in a platform ecosystem. We used a game-theoretic approach to analyze security problems associated with authing services provided by online platforms for consumers and other linked platforms. The main findings are as follows: 1) the decreased expected loss of consumers will increase the number of players who participate in the platform; 2) linked platforms offer strong benefits from consumers involved in an authing service; 3) the main platform will increase its effort level, which includes security cost and checking of linked platform's security if the expected loss of the consumers is low. Our study contributes to the literature on the relationship between technology convenience and security risk and provides guidelines on authing strategies to platform managers.

• Information Systems Review
• /
• v.20 no.2
• /
• pp.21-37
• /
• 2018

Under ubiquitous work environment, innovative changes occur in work process with ICT. The work process for collaboration through mobile devices and network should be investigated. The research model consists of two major antecedents: autonomy and interdependence as a task characteristic and job satisfaction as ultimate consequence followed by work design theory. To elaborate work design theory, smartwork application (app) use, communication extent, and work-life balance were reviewed from the literature. Data were collected from three ICT firms, which adopted certain smartwork app, and a partial least squares analysis was made on 175 data points. The analysis results show that task interdependence exerts a statistically significant effect on the level of smartwork app usage. Communication extent directly affects job satisfaction and work-life balance. The remarkable point is that smartwork app usage does not affect employees' work-life balance; the former can only affect the latter indirectly by increasing communication extent. This study attempts to explain the organizational impact by considering smartwork app and the effects simultaneously. We proposed and empirically tested the extended work design theory including information technology and its environment. Based on the results, other theoretical and practical contributions are discussed at the end with limitations and further studies.

• Information Systems Review
• /
• v.19 no.4
• /
• pp.43-62
• /
• 2017

This study investigates the effect of bonding and bridging social capital on the technological innovation performance in the Pangyo Techno Valley. In particular, we consider the information technology (IT) usage in industrial cluster as an antecedent of social capital. IT instigates the intra and extra communication and information sharing between employees, thereby promoting the formation of a network of various members. Results show that the IT usage factor positively affects both bridging and bonding social capital, but an evident difference exists among the effects of social capital on the technological innovation performance. In case of Pangyo industrial cluster, bridging social capital exerts significant effect on the technological innovation performance, whereas bonding social capital shows insignificance. Bridging social capital is composed of the interactions of various networks. Bonding social capital is based on the strong tie from trust and internal cooperation. Results are related with the characteristics of Pangyo Techno Valley, where various IT ventures need active communication and information sharing with other organizations for technological innovation performance.