• Asia pacific journal of information systems
• /
• v.18 no.1
• /
• pp.145-162
• /
• 2008

One of the big concerns in e-society is privacy issue. In special, in developing robust ubiquitous smart space and corresponding services, user profile and preference are collected by the service providers. Privacy issue would be more critical in context-aware services simply because most of the context data themselves are private information: user's current location, current schedule, friends nearby and even her/his health data. To realize the potential of ubiquitous smart space, the systems embedded in the space should corporate personal privacy preferences. When the users invoke a set of services, they are asked to allow the service providers or smart space to make use of personal information which is related to privacy concerns. For this reason, the users unhappily provide the personal information or even deny to get served. On the other side, service provider needs personal information as rich as possible with minimal personal information to discern royal and trustworthy customers and those who are not. It would be desirable to enlarge the allowable personal information complying with the service provider's request, whereas minimizing service provider's requiring personal information which is not allowed to be submitted and user's submitting information which is of no value to the service provider. In special, if any personal information required by the service provider is not allowed, service will not be provided to the user. P3P (Platform for Privacy Preferences) has been regarded as one of the promising alternatives to preserve the personal information in the course of electronic transactions. However, P3P mainly focuses on preserving the buyers' personal information. From time to time, the service provider's business data should be protected from the unintended usage from the buyers. Moreover, even though the user's privacy preference could depend on the context happened to the user, legacy P3P does not handle the contextual change of privacy preferences. Hence, the purpose of this paper is to propose a mutual P3P-based negotiation mechanism. To do so, service provider's privacy concern is considered as well as the users'. User's privacy policy on the service provider's information also should be informed to the service providers before the service begins. Second, privacy policy is contextually designed according to the user's current context because the nomadic user's privacy concern structure may be altered contextually. Hence, the methodology includes mutual privacy policy and personalization. Overall framework of the mechanism and new code of ethics is described in section 2. Pervasive platform for mutual P3P considers user type and context field, which involves current activity, location, social context, objects nearby and physical environments. Our mutual P3P includes the privacy preference not only for the buyers but also the sellers, that is, service providers. Negotiation methodology for mutual P3P is proposed in section 3. Based on the fact that privacy concern occurs when there are needs for information access and at the same time those for information hiding. Our mechanism was implemented based on an actual shopping mall to increase the feasibility of the idea proposed in this paper. A shopping service is assumed as a context-aware service, and data groups for the service are enumerated. The privacy policy for each data group is represented as APPEL format. To examine the performance of the example service, in section 4, simulation approach is adopted in this paper. For the simulation, five data elements are considered: $\cdot$ UserID $\cdot$ User preference $\cdot$ Phone number $\cdot$ Home address $\cdot$ Product information $\cdot$ Service profile. For the negotiation, reputation is selected as a strategic value. Then the following cases are compared: $\cdot$ Legacy P3P is considered $\cdot$ Mutual P3P is considered without strategic value $\cdot$ Mutual P3P is considered with strategic value. The simulation results show that mutual P3P outperforms legacy P3P. Moreover, we could conclude that when mutual P3P is considered with strategic value, performance was better than that of mutual P3P is considered without strategic value in terms of service safety.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• Agribusiness and Information Management
• /
• v.8 no.1
• /
• pp.17-26
• /
• 2016

India is largest producer of banana in the world producing 29.72 million tonnes from an area of 0.803 million ha with a productivity of 35.7 MT ha-1 and accounted for 15.48 and 27.01 per cent of the world's area and production respectively (www.nhb.gov.in). In India, Tamil Nadu leads other states both in terms of area and production followed by Maharashtra, Gujarat and Andhra Pradesh. In Rayalaseema region of Andhra Pradesh, Kurnool district had special reputation in the cultivation of banana in an area of 5765 hectares with an annual production of 2.01 lakh tonnes in the year 2012-13 and hence, it was purposively chosen for the study. On $23^{rd}$ November 2003, the Government of Andhra Pradesh has commenced a comprehensive project called 'Andhra Pradesh Micro Irrigation Project (APMIP)', first of its kind in the world so as to promote water use efficiency. APMIP is offering 100 per cent of subsidy in case of SC, ST and 90 per cent in case of other categories of farmers up to 5.0 acres of land. In case of acreage between 5-10 acres, 70 per cent subsidy and acreage above 10, 50 per cent of subsidy is given to the farmer beneficiaries. The sampling frame consists of Kurnool district, two mandals, four villages and 180 sample farmers comprising of 60 farmers each from Marginal (<1ha), Small (1-2ha) and Other (>2ha) categories. A well structured pre-tested schedule was employed to collect the requisite information pertaining to the performance of drip irrigation among the sample farmers and Data Envelopment Analysis (DEA) model was employed to analyze the performance of drip irrigation in banana farms. The performance of drip irrigation was assessed based on the parameters like: Land Development Works (LDW), Fertigation costs (FC), Volume of water supplied (VWS), Annual maintenance costs of drip irrigation (AMC), Economic Status of the farmer (ES), Crop Productivity (CP) etc. The first four parameters are considered as inputs and last two as outputs for DEA modelling purposes. The findings revealed that, the number of farms operating at CRS are more in number in other farms (46.66%) followed by marginal (45%) and small farms (28.33%). Similarly, regarding the number of farmers operating at VRS, the other farms are again more in number with 61.66 per cent followed by marginal (53.33%) and small farms (35%). With reference to scale efficiency, marginal farms dominate the scenario with 57 per cent followed by others (55%) and small farms (50%). At pooled level, 26.11 per cent of the farms are being operated at CRS with an average technical efficiency score of 0.6138 i.e., 47 out of 180 farms. Nearly 40 per cent of the farmers at pooled level are being operated at VRS with an average technical efficiency score of 0.7241. As regards to scale efficiency, nearly 52 per cent of the farmers (94 out of 180 farmers) at pooled level, either performed at the optimum scale or were close to the optimum scale (farms having scale efficiency values equal to or more than 0.90). Majority of the farms (39.44%) are operating at IRS and only 29 per cent of the farmers are operating at DRS. This signifies that, more resources should be provided to these farms operating at IRS and the same should be decreased towards the farms operating at DRS. Nearly 32 per cent of the farms are operating at CRS indicating efficient utilization of resources. Log linear regression model was used to analyze the major determinants of input use efficiency in banana farms. The input variables considered under DEA model were again considered as influential factors for the CRS obtained for the three categories of farmers. Volume of water supplied ($X_1$) and fertigation cost ($X_2$) are the major determinants of banana farms across all the farmer categories and even at pooled level. In view of their positive influence on the CRS, it is essential to strengthen modern irrigation infrastructure like drip irrigation and offer more fertilizer subsidies to the farmer to enhance the crop production on cost-effective basis in Kurnool district of Andhra Pradesh, India. This study further suggests that, the present era of Information Technology will help the irrigation management in the context of generating new techniques, extension, adoption and information. It will also guide the farmers in irrigation scheduling and quantifying the irrigation water requirements in accordance with the water availability in a particular season. So, it is high time for the Government of India to pay adequate attention towards the applications of 'Information and Communication Technology (ICT) and its applications in irrigation water management' for facilitating the deployment of Decision Supports Systems (DSSs) at various levels of planning and management of water resources in the country.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.191-206
• /
• 2022

Recently, it is a de-facto approach to utilize a pre-trained language model(PLM) to achieve the state-of-the-art performance for various natural language tasks(called downstream tasks) such as sentiment analysis and question answering. However, similar to any other machine learning method, PLM tends to depend on the data distribution seen during the training phase and shows worse performance on the unseen (Out-of-Distribution) domain. Due to the aforementioned reason, there have been many efforts to develop domain-specified PLM for various fields such as medical and legal industries. In this paper, we discuss the training of a finance domain-specified PLM for the Korean language and its applications. Our finance domain-specified PLM, KB-BERT, is trained on a carefully curated financial corpus that includes domain-specific documents such as financial reports. We provide extensive performance evaluation results on three natural language tasks, topic classification, sentiment analysis, and question answering. Compared to the state-of-the-art Korean PLM models such as KoELECTRA and KLUE-RoBERTa, KB-BERT shows comparable performance on general datasets based on common corpora like Wikipedia and news articles. Moreover, KB-BERT outperforms compared models on finance domain datasets that require finance-specific knowledge to solve given problems.

• Journal of Korea Port Economic Association
• /
• v.37 no.3
• /
• pp.117-128
• /
• 2021

In order for the users (shipping firms and shippers) and suppliers (stevedoring firms) in the container terminal industry to win-win, it is necessary to have some appropriate diverse market conditions for the industry. This study analyses the basic conditions and demand and supply characteristics of the industry and investigates the market performance of Busan container ports. First, this article analyses the basic characteristics of demand and supply. As the demand characteristics, there are five ones such as 1) exogeneity of demand, 2) function as export/import transportation and hub for transshipment, 3) increase of users' bargaining power, 4) high substituting elasticity, 5) reduction of volume growth. As the supply characteristics, there are seven ones such as 1) inelasticity of supply, 2) homogeneity of stevedoring services, 3) over-supply, 4) adoption of cutting-edge stevedoring technology, 5) scale economy and impossibility of storage, 6) labor market rigidity, 7) enhancing port's role in SCM. In addition, this study conducts the so-called structure-conduct-performance analysis. For the structure analysis, 1) lacks of scale economy in stevedoring companies, 2) high entry barrier, 3) strengthening of shipping firms' bargaining power, 4) transitory permission scheme for tariff are analyzed. For the conduct analysis, 1) price discrimination between export/import and transshipment, 2) mid-term length of terminal use contract, 3) continuous investment in equipment, 4) low level of cooperation among terminal operating firms are derived. For the performance analysis, 1) inequality in profitability, 2) reduction of export/import cost, 3) delay in adopting cutting-edge technology, 4) idle equipment are analyzed. Following this logical flow, the hypothesis that the market structure influences the market conduct is tested based on the actual dataset. As a future agenda in the conclusion, this article recommends the so-called port industrial policy.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• The Journal of Society for e-Business Studies
• /
• v.17 no.4
• /
• pp.69-93
• /
• 2012

Various influence-related relationships in Social Network Services (SNS) among users, posts, and user-and-post, can be expressed using links. The current research evaluates the influence of specific users or posts by analyzing the link structure of relevant social network graphs to identify influential users. We applied the concept of mutual interactions proposed for ranking semantic web resources, rather than the voting notion of Page Rank or HITS, to blogosphere, one of the early SNS. Through many experiments with network models, where the performance and validity of each alternative approach can be analyzed, we showed the applicability and strengths of our approach. The weight tuning processes for the links of these network models enabled us to control the experiment errors form the link weight differences and compare the implementation easiness of alternatives. An additional example of how to enter the content scores of commercial or spam posts into the graph-based method is suggested on a small network model as well. This research, as a starting point of the study on identifying influential users in SNS, is distinctive from the previous researches in the following points. First, various influence-related properties that are deemed important but are disregarded, such as scraping, commenting, subscribing to RSS feeds, and trusting friends, can be considered simultaneously. Second, the framework reflects the general phenomenon where objects interacting with more influential objects increase their influence. Third, regarding the extent to which a bloggers causes other bloggers to act after him or her as the most important factor of influence, we treated sequential referencing relationships with a viewpoint from that of PageRank or HITS (Hypertext Induced Topic Selection).

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.1-12
• /
• 2005

Image registration is a process to establish the spatial correspondence between images of the same scene, which are acquired at different view points, at different times, or by different sensors. This paper presents a new algorithm for robust registration of the images acquired by multiple sensors having different modalities; the EO (electro-optic) and IR(infrared) ones in the paper. The two feature-based and intensity-based approaches are usually possible for image registration. In the former selection of accurate common features is crucial for high performance, but features in the EO image are often not the same as those in the R image. Hence, this approach is inadequate to register the E0/IR images. In the latter normalized mutual Information (nHr) has been widely used as a similarity measure due to its high accuracy and robustness, and NMI-based image registration methods assume that statistical correlation between two images should be global. Unfortunately, since we find out that EO and IR images don't often satisfy this assumption, registration accuracy is not high enough to apply to some applications. In this paper, we propose a two-stage NMI-based registration method based on the analysis of statistical correlation between E0/1R images. In the first stage, for robust registration, we propose two preprocessing schemes: extraction of statistically correlated regions (ESCR) and enhancement of statistical correlation by filtering (ESCF). For each image, ESCR automatically extracts the regions that are highly correlated to the corresponding regions in the other image. And ESCF adaptively filters out each image to enhance statistical correlation between them. In the second stage, two output images are registered by using NMI-based algorithm. The proposed method provides prospective results for various E0/1R sensor image pairs in terms of accuracy, robustness, and speed.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.