• Economic and Environmental Geology
• /
• v.47 no.3
• /
• pp.205-217
• /
• 2014

As Mt. Backdu is expected to erupt, the social and economic impacts of the eruption on the Korean peninsula as well as on the world become a research topic of interest. If the volcano erupts, South Korea can be directly impacted by volcanic ash, which will bring out secondary damages in various ways. Given that the direct damage is a basis to estimate indirect and secondary damages, this paper was to review a method to estimate direct damages, called catastrophe risk models, and estimate the direct damages of available eruption scenarios of Mt. Baekdu. Based on the results, the damages by volcanic ash will occur mostly around Gangwon province if the Mt. Backdu erupts. Thus the inventory lists and their damage functions of Gangwon provinces were collected. In particular agricultural and forestry products were surveyed based on the land use. Direct damages were estimated using volcanic ash distribution of eruption scenarios, inventory information and their damage functions. In result, a scenario in winter caused the damage of 299.8 billion KRW (20.4% of total agricultural production in 2010) and 28.9 billion KRW (9.0% of total forestry production in 2010) in agriculture and forestry, respectively. The damages in agriculture was larger, and it is due to the damage functions which show the agricultural products are more vulnerable to volcanic ash than forestry products. Also the agricultural production (1,471.7 billion KRW in 2010) are more than 4.5 times the forestry production (322.3 billion KRW in 2010) in Gangwon province. Inje and Gangnung had the most damages in the scenario in winter. Inje had the most damage due to the thick ash deposit (8.5 mm in average) despite the low production. On the other hand, Goseong had a low damage compared to the ash thickness larger than 20mm, owing to the low production. The direct damage estimated through this process can be used to estimate indirect damages.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1447-1460
• /
• 2021

Urbanization increases the amount of impervious surface and artificial heat emission, resulting in urban heat island (UHI) effect. Local climate zones (LCZ) are a classification scheme for urban areas considering urban land cover characteristics and the geometry and structure of buildings, which can be used for analyzing urban heat island effect in detail. This study aimed to examine the UHI effect by urban structure in Suwon and Daegu using the LCZ scheme. First, the LCZ maps were generated using Landsat 8 images and convolutional neural network (CNN) deep learning over the two cities. Then, Surface UHI (SUHI), which indicates the land surface temperature (LST) difference between urban and rural areas, was analyzed by LCZ class. The results showed that the overall accuracies of the CNN models for LCZ classification were relatively high 87.9% and 81.7% for Suwon and Daegu, respectively. In general, Daegu had higher LST for all LCZ classes than Suwon. For both cities, LST tended to increase with increasing building density with relatively low building height. For both cities, the intensity of SUHI was very high in summer regardless of LCZ classes and was also relatively high except for a few classes in spring and fall. In winter the SUHI intensity was low, resulting in negative values for many LCZ classes. This implies that UHI is very strong in summer, and some urban areas often are colder than rural areas in winter. The research findings demonstrated the applicability of the LCZ data for SUHI analysis and can provide a basis for establishing timely strategies to respond urban on-going climate change over urban areas.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.14 no.1
• /
• pp.167-185
• /
• 2019

As most G-20 countries expect medical spending to grow rapidly over the next few decades, the burden of healthcare costs continues to grow globally due to an increase in the elderly population and chronic illnesses, and the ongoing quality improvement of health care services. However, under the rapidly changing technological environment of healthcare and IT convergence, the problem may become even bigger if not properly recognized and not properly prepared. In the context of the paradigm shift and the increasing problem of the medical field, complex responses in technical, institutional and business aspects are urgently needed. The key is to derive a business model that is appropriate for businesses that integrate IT in the medical field. With the arrival of the era of the 4th industrial revolution, new technologies such as Internet of Things have been applied to eHealthcare, and the need for new business models has emerged.In the e-healthcare of the Internet era, it became a traditional firm-based business model. However, due to the characteristics of dynamics and complexity of things Internet in the Internet of things, A business ecosystem-based approach is needed. In this paper, we present and analyze the major success factors of the ecosystem based on the 3 - layer structure of the e - healthcare business ecosystem as a result of research on e - healthcare business ecosystem based on emerging technology such as Internet of things. The three-layer business ecosystem was defined as (1) Infrastructure Layer, (2) Character Layer, and (3) Stakeholder Layer. As the key success factors for the eHealthCare business ecosystem, the following four factors are suggested: (1) introduction of the iHealthcare concept, (2) expansion of the business ecosystem, (3) business ecosystem change process innovation, and (4) business ecosystem leadership innovation.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1463-1478
• /
• 2022

Maritime transport accounts for 99.7% of the exports and imports of the Republic of Korea; therefore, developing a vessel monitoring system for efficient operation is of significant interest. Several studies have focused on tracking and monitoring vessel movements based on automatic identification system (AIS) data; however, ships without AIS have limited monitoring and tracking ability. High-resolution optical satellite images can provide the missing layer of information in AIS-based monitoring systems because they can identify non-AIS vessels and small ships over a wide range. Therefore, it is necessary to investigate vessel monitoring and small vessel classification systems using high-resolution optical satellite images. This study examined the possibility of developing ship monitoring systems using Compact Advanced Satellite 500-1 (CAS500-1) satellite images by first training a deep learning model using satellite image data and then performing detection in other images. To determine the effectiveness of the proposed method, the learning data was acquired from ships in the Yellow Sea and its major ports, and the detection model was established using the You Only Look Once (YOLO) algorithm. The ship detection performance was evaluated for a domestic and an international port. The results obtained using the detection model in ships in the anchorage and berth areas were compared with the ship classification information obtained using AIS, and an accuracy of 85.5% and 70% was achieved using domestic and international classification models, respectively. The results indicate that high-resolution satellite images can be used in mooring ships for vessel monitoring. The developed approach can potentially be used in vessel tracking and monitoring systems at major ports around the world if the accuracy of the detection model is improved through continuous learning data construction.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.287-316
• /
• 2023

As global energy crisis and the COVID-19 pandemic have emerged as social issues, there is a growing demand for companies to move away from profit-centric business models and embrace sustainable management that balances environmental, social, and governance (ESG) factors. ESG activities of companies vary across industries, and industry-specific weights are applied in ESG evaluations. Therefore, it is important to develop strategic management approaches that reflect the characteristics of each industry and the importance of each ESG factor. Additionally, with the stance of strengthened focus on ESG disclosures, specific guidelines are needed to identify and report on sustainable management activities of domestic companies. To understand corporate sustainability strategies, analyzing ESG reports and news articles by industry can help identify strategic characteristics in specific industries. However, each company has its own unique strategies and report structures, making it difficult to grasp detailed trends or action items. In our study, we analyzed ESG reports (2019-2021) and news articles (2019-2022) of six companies in the 'Finance,' 'Manufacturing,' and 'IT' sectors to examine the sustainability strategies of leading domestic ESG companies. Text mining techniques such as keyword frequency analysis and topic modeling were applied to identify industry-specific, ESG element-specific management strategies and issues. The analysis revealed that in the 'Finance' sector, customer-centric management strategies and efforts to promote an inclusive culture within and outside the company were prominent. Strategies addressing climate change, such as carbon neutrality and expanding green finance, were also emphasized. In the 'Manufacturing' sector, the focus was on creating sustainable communities through occupational health and safety issues, sustainable supply chain management, low-carbon technology development, and eco-friendly investments to achieve carbon neutrality. In the 'IT' sector, there was a tendency to focus on technological innovation and digital responsibility to enhance social value through technology. Furthermore, the key issues identified in the ESG factors were as follows: under the 'Environmental' element, issues such as greenhouse gas and carbon emission management, industry-specific eco-friendly activities, and green partnerships were identified. Under the 'Social' element, key issues included social contribution activities through stakeholder engagement, supporting the growth and coexistence of members and partner companies, and enhancing customer value through stable service provision. Under the 'Governance' element, key issues were identified as strengthening board independence through the appointment of outside directors, risk management and communication for sustainable growth, and establishing transparent governance structures. The exploration of the relationship between ESG disclosures in reports and ESG issues in news articles revealed that the sustainability strategies disclosed in reports were aligned with the issues related to ESG disclosed in news articles. However, there was a tendency to strengthen ESG activities for prevention and improvement after negative media coverage that could have a negative impact on corporate image. Additionally, environmental issues were mentioned more frequently in news articles compared to ESG reports, with environmental-related keywords being emphasized in the 'Finance' sector in the reports. Thus, ESG reports and news articles shared some similarities in content due to the sharing of information sources. However, the impact of media coverage influenced the emphasis on specific sustainability strategies, and the extent of mentioning environmental issues varied across documents. Based on our study, the following contributions were derived. From a practical perspective, companies need to consider their characteristics and establish sustainability strategies that align with their capabilities and situations. From an academic perspective, unlike previous studies on ESG strategies, we present a subdivided methodology through analysis considering the industry-specific characteristics of companies.

• Information Systems Review
• /
• v.18 no.3
• /
• pp.209-233
• /
• 2016

Internet companies that utilize social network have increased in number. The introduction of diverse social media services facilitated innovative changes in e-business. Social network service (SNS), which is a domain of social media, is a web-based service designed to strengthen human relations in the Internet and build new social relations. The remarkable growth of social network services and the profit generation and perception of this service are the new growth engines of this digital age. Given this development, many global IT companies views SNS as the most powerful form of social media. Thus, they invest efforts to develop business models using SNS.2) This study verifies the impact of privacy exposure in SNS as a result of privacy invasion. This study examines the purpose of using the SNS and user's awareness of the significance of personal information, which are key factors that affect self-disclosure of personal information. This study utilizes theory of reasoned action (TRA) to provide a theoretical platform that describes the specific behavior and emotional response of individuals. This study presents a research model that considers negative attitude (negatude). In this model, self-disclosure in SNS is considered a TRA. TRA is a subjective norm, a behavioral intention, and a key variable of exposure behavior. A survey was conducted on college students at Y university in Seoul to empirically verify the research model. The students have experiences in using SNS. A total of 198 samples were collected. Path analysis was applied to analyze the relations of factors. The results of path analysis show the statistically insignificant impact of privacy invasion on negatude, subjective norm, behavioral intention, and exposure behavior. The impact of unrecognized privacy invasion was also considered insignificant. The impacts of intention to use SNS on negatude, subjective norm, behavioral intention, and exposure behavior was significant. A significant impact was also found for the significance of personal information on subjective norm, behavioral intention, and exposure behavior, whereas the impact on negatude was insignificant. The impact of subjective norm on behavioral intention was significant. Lastly, the impact of behavioral intention on exposure behavior was insignificant. These findings are significant because the study examined the process of self-disclosure by integrating psychological and social factors based on theoretical discussion.

• Journal of Korean Society of Forest Science
• /
• v.113 no.1
• /
• pp.97-106
• /
• 2024

Evaluating carbon (C) and nitrogen (N) inputs from litterfall is important for soil nutrient management to enhance forest productivity and to understand the mechanisms of nutrient cycling in forest ecosystems. This study was conducted to compare C and N inputs from litterfall components of Cryptomeria japonica D. Don an d Chamaecyparis obtusa Endlicher planted in adjacent sites in the Jinju Research and Experimental Forests in Gyeongsangnam-do, South Korea. Litterfall into litter traps was collected at three-month intervals between December 2020 and December 2021, and the C and N concentrations of the litterfall components were measured. Litterfall amounts were not significantly different between the plantations, except for reproductive litterfall components. Litterfall accumulation peaked between December and March. The litterfall C concentration in the needle and seed litterfall was significantly higher for C. obtusa than for C. japonica. By contrast, the C concentrations in needle and flower litterfall differed seasonally. The mean N concentration of needle litterfall was significantly higher in C. japonica (0.96%) and C. obtusa collected between June and September (1.01%) than in the other seasons (C. japonica: 0.43%; C. obtusa: 0.53%). Carbon and N inputs in both plantations were highest in needle litterfall collected from December to March and lowest in needle litterfall collected from June to September. Annual C input by litterfall was similar between the plantations (C. japonica: 3,054 kg C ha^-1 yr^-1; C. obtusa: 3,129 kg C ha^-1 yr^-1), whereas total N input was higher for C. japonica (46.93 kg N ha^-1 yr^-1) than for C. obtusa (25.17 kg N ha^-1 yr^-1). The higher N input in the C. japonica plantation than in the C. obtusa plantation was associated with the input of reproductive components. These results could be applied to improve stand-scale models of C and N cycling by litterfall components in C. japonica an d C. obtusa plantations.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.55-79
• /
• 2013

In this paper, we propose a hybrid genetic algorithm (HGA) approach to effectively solve the reverse logistics network with centralized centers (RLNCC). For the proposed HGA approach, genetic algorithm (GA) is used as a main algorithm. For implementing GA, a new bit-string representation scheme using 0 and 1 values is suggested, which can easily make initial population of GA. As genetic operators, the elitist strategy in enlarged sampling space developed by Gen and Chang (1997), a new two-point crossover operator, and a new random mutation operator are used for selection, crossover and mutation, respectively. For hybrid concept of GA, an iterative hill climbing method (IHCM) developed by Michalewicz (1994) is inserted into HGA search loop. The IHCM is one of local search techniques and precisely explores the space converged by GA search. The RLNCC is composed of collection centers, remanufacturing centers, redistribution centers, and secondary markets in reverse logistics networks. Of the centers and secondary markets, only one collection center, remanufacturing center, redistribution center, and secondary market should be opened in reverse logistics networks. Some assumptions are considered for effectively implementing the RLNCC The RLNCC is represented by a mixed integer programming (MIP) model using indexes, parameters and decision variables. The objective function of the MIP model is to minimize the total cost which is consisted of transportation cost, fixed cost, and handling cost. The transportation cost is obtained by transporting the returned products between each centers and secondary markets. The fixed cost is calculated by opening or closing decision at each center and secondary markets. That is, if there are three collection centers (the opening costs of collection center 1 2, and 3 are 10.5, 12.1, 8.9, respectively), and the collection center 1 is opened and the remainders are all closed, then the fixed cost is 10.5. The handling cost means the cost of treating the products returned from customers at each center and secondary markets which are opened at each RLNCC stage. The RLNCC is solved by the proposed HGA approach. In numerical experiment, the proposed HGA and a conventional competing approach is compared with each other using various measures of performance. For the conventional competing approach, the GA approach by Yun (2013) is used. The GA approach has not any local search technique such as the IHCM proposed the HGA approach. As measures of performance, CPU time, optimal solution, and optimal setting are used. Two types of the RLNCC with different numbers of customers, collection centers, remanufacturing centers, redistribution centers and secondary markets are presented for comparing the performances of the HGA and GA approaches. The MIP models using the two types of the RLNCC are programmed by Visual Basic Version 6.0, and the computer implementing environment is the IBM compatible PC with 3.06Ghz CPU speed and 1GB RAM on Windows XP. The parameters used in the HGA and GA approaches are that the total number of generations is 10,000, population size 20, crossover rate 0.5, mutation rate 0.1, and the search range for the IHCM is 2.0. Total 20 iterations are made for eliminating the randomness of the searches of the HGA and GA approaches. With performance comparisons, network representations by opening/closing decision, and convergence processes using two types of the RLNCCs, the experimental result shows that the HGA has significantly better performance in terms of the optimal solution than the GA, though the GA is slightly quicker than the HGA in terms of the CPU time. Finally, it has been proved that the proposed HGA approach is more efficient than conventional GA approach in two types of the RLNCC since the former has a GA search process as well as a local search process for additional search scheme, while the latter has a GA search process alone. For a future study, much more large-sized RLNCCs will be tested for robustness of our approach.