• Journal of Distribution Science
• /
• v.22 no.9
• /
• pp.85-95
• /
• 2024

Purpose: Online food delivery platforms face challenges to operational efficiency due to increasing demand, a shortage of drivers, and the constraint of a one-order-at-a-time delivery policy. It is imperative to find solutions to address the inefficiencies in the food delivery industry. Bundling multiple orders can help resolve these issues, but it requires complex computations due to the exponential increase in possible order combinations. Research design, data and methodology: This study proposes three bundle delivery systems-static, dynamic, and hybrid-utilizing a machine learning-based classification model to reduce the number of order combinations for efficient bundle computation. The proposed systems are analyzed through simulations using market data from South Korea's online food delivery platforms. Results: Our findings indicate that implementing bundle systems extends service coverage to more customers, increases average driver earnings, and maintains lead times comparable to standalone deliveries. Additionally, the platform experiences higher service completion rates and increased profitability. Conclusions: This suggests that bundle systems are cost-effective and beneficial for all stakeholders in online food delivery platforms, effectively addressing the inefficiencies in the industry.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.1
• /
• pp.63-74
• /
• 2024

The fundamental basis for revitalizing cultural resources and developing content is national heritage(cultural property). In national heritage, cultural heritage is a tangible cultural heritage that represents the uniqueness of history and tradition, identity, and changes in life. In the case of museums, the collections (a museum-owned cultural heritage) represent the unique characteristics of the institution. In South Korea, it is recommended that museum collections be registered and used in the Cultural Heritage Standard Management System so that cultural heritage can be managed and utilized in connection with academics, industry, and administration. However, due to a lack of awareness of modern and contemporary heritage, the thematic classification chronology of the system was set mainly before the Joseon Dynasty, and a cultural heritage classification system suitable for national land information has not been established. Therefore, this study aims to propose a classification system for cadastral cultural heritage, based on the modern era when cadastral terminology was first used, using the cultural heritage owned by the LX Museum. Cadastral cultural heritage is characterized by the fact that although it is a field of specialized technology, the surveying or the production of it is not done by specific individuals only, and that while the production is professional, there are many educational aspects in its use. Therefore, unlike other specialized museum collections that are classified based on the functional aspects of their production methods, intended use, and creators, the classification method for cadastral cultural artifacts should be based on the characteristics of the cadastral tools and the outputs. This classification follows a three-tier stages with reference to the items in the Cultural Heritage Standard Management System. This classification aims at the effective use of knowledge by categorizing concepts and systematizing the subjects of data into a series of orders. A safe conservation and management environment for cadastral cultural heritage can be established, and academic and socio-cultural interpretation of the collection is possible by this classfication. Moreover, It is also expected to serve the basis for the national land information as well as searching for the national land information research, planning a exhibition, and the field of education in museum.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.1-19
• /
• 2018

Since stock movements forecasting is an important issue both academically and practically, studies related to stock price prediction have been actively conducted. The stock price forecasting research is classified into structured data and unstructured data, and it is divided into technical analysis, fundamental analysis and media effect analysis in detail. In the big data era, research on stock price prediction combining big data is actively underway. Based on a large number of data, stock prediction research mainly focuses on machine learning techniques. Especially, research methods that combine the effects of media are attracting attention recently, among which researches that analyze online news and utilize online news to forecast stock prices are becoming main. Previous studies predicting stock prices through online news are mostly sentiment analysis of news, making different corpus for each company, and making a dictionary that predicts stock prices by recording responses according to the past stock price. Therefore, existing studies have examined the impact of online news on individual companies. For example, stock movements of Samsung Electronics are predicted with only online news of Samsung Electronics. In addition, a method of considering influences among highly relevant companies has also been studied recently. For example, stock movements of Samsung Electronics are predicted with news of Samsung Electronics and a highly related company like LG Electronics.These previous studies examine the effects of news of industrial sector with homogeneity on the individual company. In the previous studies, homogeneous industries are classified according to the Global Industrial Classification Standard. In other words, the existing studies were analyzed under the assumption that industries divided into Global Industrial Classification Standard have homogeneity. However, existing studies have limitations in that they do not take into account influential companies with high relevance or reflect the existence of heterogeneity within the same Global Industrial Classification Standard sectors. As a result of our examining the various sectors, it can be seen that there are sectors that show the industrial sectors are not a homogeneous group. To overcome these limitations of existing studies that do not reflect heterogeneity, our study suggests a methodology that reflects the heterogeneous effects of the industrial sector that affect the stock price by applying k-means clustering. Multiple Kernel Learning is mainly used to integrate data with various characteristics. Multiple Kernel Learning has several kernels, each of which receives and predicts different data. To incorporate effects of target firm and its relevant firms simultaneously, we used Multiple Kernel Learning. Each kernel was assigned to predict stock prices with variables of financial news of the industrial group divided by the target firm, K-means cluster analysis. In order to prove that the suggested methodology is appropriate, experiments were conducted through three years of online news and stock prices. The results of this study are as follows. (1) We confirmed that the information of the industrial sectors related to target company also contains meaningful information to predict stock movements of target company and confirmed that machine learning algorithm has better predictive power when considering the news of the relevant companies and target company's news together. (2) It is important to predict stock movements with varying number of clusters according to the level of homogeneity in the industrial sector. In other words, when stock prices are homogeneous in industrial sectors, it is important to use relational effect at the level of industry group without analyzing clusters or to use it in small number of clusters. When the stock price is heterogeneous in industry group, it is important to cluster them into groups. This study has a contribution that we testified firms classified as Global Industrial Classification Standard have heterogeneity and suggested it is necessary to define the relevance through machine learning and statistical analysis methodology rather than simply defining it in the Global Industrial Classification Standard. It has also contribution that we proved the efficiency of the prediction model reflecting heterogeneity.

• Korean Journal of Environment and Ecology
• /
• v.29 no.3
• /
• pp.454-461
• /
• 2015

This study aims to classify the biotope types based on the vegetation community in built-up areas by different land use and to map the plant communities. By classifying biotopes according to a taxonomic system, the characteristics of a biological community can be well-represented. The biotope classification indexes for the target area include human behavioral factors such as land use intensity, land-use patterns and land-cover types. The type classification was divided into four hierarchic ranks starting with Biotope Class, next by Biotope Group and Biotope Type and lastly by Biotope Sub-Type. The Biotope Class was first divided into two areas: the areas improved by humans and the areas unimproved by humans. The improved areas were again divided into permeable and non-permeable regions on the Biotope Group level. In the Biotope Type level, permeable paving areas were divided into areas with wide gap pavers and those with narrow gap pavers. The differential species of each biotope type are Lindera glauca, Conyza canadensis, Mazus pumilus, Vicia tetrasperma, Crepidiastrum sonchifolium, Zoysis japonica, Potentilla supina and Festuca arundinacea. The results of this study suggest that the biotope classification methodology, using a subjective phytosociological approach, is a useful and valuable tool and the results also suggest the possibility of applying more objective and scientific methods in mapping and classifying various environments.

• The Journal of Society for e-Business Studies
• /
• v.20 no.3
• /
• pp.113-125
• /
• 2015

Information Security Incidents that have recently happen rapidly spread and the scale of that incidents' damage is large. In addition, as it proceeds to the era of converged industry in the future environment and the virtual cyber world expands to the physical world, new types of security threats have occurred. Now, it is time to supply security professionals who have a multi-dimensional security capabilities that can manage the strategies of technological security and physical security from the management point of view, rather than the ones who primarily focus on the traditional technologic-centered strategies to solve new types of security threats. In conclusion, in this paper we try to produce the curriculum of information security featured in the occupational classification system and analyze the subjects that are additionally required for those who move to other occupations to cultivate security professionals who suited to the converged-industrial environment. It is expected that multi-dimensional security professionals who suited to the converged-industrial environment will be cultivated by harmoniously integrating information security subjects from technological and business/managerial perspectives, and education training courses will be developed that effectively provide core knowledges per occupational classification when people moves to other occupations in the areas of information security.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.847-857
• /
• 2018

As the number of malicious code increases steeply, cyber attack victims targeting corporations, public institutions, financial institutions, hospitals are also increasing. Accordingly, academia and security industry are conducting various researches on malicious code detection. In recent years, there have been a lot of researches using machine learning techniques including deep learning. In the case of research using Convolutional Neural Network, ResNet, etc. for classification of malicious code, it can be confirmed that the performance improvement is higher than the existing classification method. However, one of the characteristics of the target attack is that it is custom malicious code that makes it operate only for a specific company, so it is not a form spreading widely to a large number of users. Since there are not many malicious codes of this kind, it is difficult to apply the previously studied machine learning or deep learning techniques. In this paper, we propose a method to classify malicious codes when the amount of samples is insufficient such as targeting type malicious code. As a result of the study, we confirmed that the accuracy of 97% can be achieved even with a small amount of data by applying the Memory Augmented Neural Networks model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.135-144
• /
• 2024

In this study, we propose an automatic classification model for quantitative multidimensional analysis based on facet theory to understand public opinions and demands on major issues through big data analysis. Civil complaints, as a form of public feedback, are generated by various individuals on multiple topics repeatedly and continuously in real-time, which can be challenging for officials to read and analyze efficiently. Specifically, our research introduces a new classification framework that utilizes facet theory and political analysis models to analyze the characteristics of citizen complaints and apply them to the policy-making process. Furthermore, to reduce administrative tasks related to complaint analysis and processing and to facilitate citizen policy participation, we employ deep learning to automatically extract and classify attributes based on the facet analysis framework. The results of this study are expected to provide important insights into understanding and analyzing the characteristics of big data related to citizen complaints, which can pave the way for future research in various fields beyond the public sector, such as education, industry, and healthcare, for quantifying unstructured data and utilizing multidimensional analysis. In practical terms, improving the processing system for large-scale electronic complaints and automation through deep learning can enhance the efficiency and responsiveness of complaint handling, and this approach can also be applied to text data processing in other fields.

• Journal of Navigation and Port Research
• /
• v.39 no.3
• /
• pp.267-275
• /
• 2015

Port Logistics Industry plays a crucial role in trade creating added value, and contributes greatly in economic growth of a nation. Multitude of studies have been conducted to develop this industry as a means of intensifying national competitiveness. In line with this trend, this study aims to examine the effect of the Port Logistics Industry on the regional economy focusing on Ulsan, and also compare the industry among five port cities by using Korean Standard Industrial Classification (KSIC) Rev. 9 and 2010 Economy Census. The results of this study demonstrate that the Port Logistics Industry has significant regional employment rate and economic importance, showing the high number of workers (11.7%) and sales (13.1%) in 2010. According to the comparison among five port cities between 2007 and 2011, the increase of annual average in the number of companies of Gwangyang (5.72%) and Ulsan (4.23%) is higher than the national average (1.74%), and Ulsan (23.82%) and Pyeongtaek (25.74%) show high increase of annual average in the number of workers.

• Survey Research
• /
• v.7 no.1
• /
• pp.55-84
• /
• 2006

This study has classified development stages (Embryonic-Growth-Maturity) of mobile telecommunication industry based on Industry Life Cycle theory. There are two steps to be analyzed in this study, In the first step, cluster was investigated through cluster analysis using mobile density to categorize development stages of mobile telecommunication industry. In the second step, we compared on indexes of market structure, market efficiency and market performance to find out characteristics of each stage of development. The results are as follows. First, HHI is higher at embryonic stage than at growth and maturity stages, Second, ARPU(Average Revenue Per User) and RPM(Revenue Per Minute) are getting higher as the stages move on. Third, EBITDA margins, an index of market performance, is decreasing along the three stages. Finally, this study presents a clue to define the stage of development of mobile telecommunication industry and build a proper strategy for the market change.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.1
• /
• pp.99-115
• /
• 2021

The aim of this study is to improve the curriculum of the physical education by recognizing the necessity of new physical education to meet the needs of the sports industry. As a preliminary study for this, the subjects of physical education at American universities and those at regular domestic universities have been investigated. Then, the current state of operation of the physical education system of the credit bank system has been investigated. The first is the definition of the credit banking system, the investigation of accreditation of credits and the institutions of education and training. The Second is the investigation of the educational goals and qualifications of each major in the standard education curriculum and the current status of accredited credits. The third is the type and operation of institutions by degree in physical education, and the survey on current majors in progress. The fourth is the survey on the current status of operating institutions by region. The fifth is the classification of detailed subjects by major and the survey on the status of subjects by major. The last is the detailed subjects by major, and the analysis of the consistent or similar subjects in domestic and international sports industry subjects. Through the findings of this investigation, the following directions for improvement of the credit bank system curriculum have been suggested. Firstly, it is necessary to newly establish major courses tailored to social change. Secondly, it is necessary to develop mandatory and optional courses that meet the needs of the times. Thirdly, it is necessary to increase courses centered on field training that can meet the needs of the sports industry. Fourthly, in relation to the evaluation and recognition of the credit banking system, the conclusion have been derived that institutional improvement should be urgently performed.