• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

• Asia pacific journal of information systems
• /
• v.18 no.3
• /
• pp.91-121
• /
• 2008

Electronic commerce, commonly known as e-commerce or eCommerce, has become a major business trend in these days. The amount of trade conducted electronically has grown extraordinarily by developing the Internet technology. Most electronic commerce has being conducted between businesses to customers; therefore, the researches with respect to e-commerce are to find customer's needs, behaviors through statistical methods. However, the statistical researches, mostly based on a questionnaire, are the static researches, They can tell us the dynamic relationships between initial purchasing and repurchasing. Therefore, this study proposes dynamic research model for analyzing the cause of initial purchasing and repurchasing. This paper is based on the System-Dynamic theory, using the powerful simulation model with some restriction, The restrictions are based on the theory TAM(Technology Acceptance Model), PAM, and TPB(Theory of Planned Behavior). This article investigates not only the customer's purchasing and repurchasing behavior by passing of time but also the interactive effects to one another. This research model has six scenarios and three steps for analyzing customer behaviors. The first step is the research of purchasing situations. The second step is the research of repurchasing situations. Finally, the third step is to study the relationship between initial purchasing and repurchasing. The purpose of six scenarios is to find the customer's purchasing patterns according to the environmental changes. We set six variables in these scenarios by (1) changing the number of products; (2) changing the number of contents in on-line shopping malls; (3) having multimedia files or not in the shopping mall web sites; (4) grading on-line communities; (5) changing the qualities of products; (6) changing the customer's degree of confidence on products. First three variables are applied to study customer's purchasing behavior, and the other variables are applied to repurchasing behavior study. Through the simulation study, this paper presents some inter-relational result about customer purchasing behaviors, For example, Active community actions are not the increasing factor of purchasing but the increasing factor of word of mouth effect, Additionally. The higher products' quality, the more word of mouth effects increase. The number of products and contents on the web sites have same influence on people's buying behaviors. All simulation methods in this paper is not only display the result of each scenario but also find how to affect each other. Hence, electronic commerce firm can make more realistic marketing strategy about consumer behavior through this dynamic simulation research. Moreover, dynamic analysis method can predict the results which help the decision of marketing strategy by using the time-line graph. Consequently, this dynamic simulation analysis could be a useful research model to make firm's competitive advantage. However, this simulation model needs more further study. With respect to reality, this simulation model has some limitations. There are some missing factors which affect customer's buying behaviors in this model. The first missing factor is the customer's degree of recognition of brands. The second factor is the degree of customer satisfaction. The third factor is the power of word of mouth in the specific region. Generally, word of mouth affects significantly on a region's culture, even people's buying behaviors. The last missing factor is the user interface environment in the internet or other on-line shopping tools. In order to get more realistic result, these factors might be essential matters to make better research in the future studies.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Progress in Medical Physics
• /
• v.10 no.2
• /
• pp.63-71
• /
• 1999

For the purpose of utilization in 3-D conformal radiotherapy and whole body radiosurgery, the Whole Body 3-Dimensional Topographic Radiation Therapy System has been developed. Whole body frame was constructed in order to be installed on the couch. Radiopaque catheters were engraved on it for the dedicated coordinate system and a MeV-Green immobilizer was used for the patient setup by the help of side panels and plastic rods. By designing and constructing the whole body frame in this way, geometrical limitation to the gantry rotation in 3-D conformal radiotherapy could be minimized and problem which radiation transmission may be altered in particular incident angles was solved. By analyzing CT images containing information of patient setup with respect to the whole body frame, localization and coordination of the target is performed so that patient setup error may be eliminated between simulation and treatment. For the verification of setup, the change of patient positioning is detected and adjusted in order to minimize the setup error by means of comparison of the body outlines using 3 CCTV cameras. To enhance efficiency of treatment procedure, this work can be done in real time by watching the change of patient setup through the monitor. The method of image subtraction in IDL (Interactive Data Language) was used to visualize the change of patient setup. Rotating X-ray system was constructed for detecting target movement due to internal organ motion. Landmark screws were implanted either on the bones around target or inside target, and variation of target location with respect to markers may be visualized in order to minimize internal setup error through the anterior and the lateral image information taken from rotating X-ray system. For CT simulation, simulation software was developed using IDL on GUI(Graphic User Interface) basis for PC and includes functions of graphic handling, editing and data acquisition of images of internal organs as well as target for the preparation of treatment planning.

• Progress in Medical Physics
• /
• v.14 no.1
• /
• pp.34-42
• /
• 2003

In medical imaging, three-dimensional (3D) display using Virtual Reality Modeling Language (VRML) as a portable file format can give intuitive information more efficiently on the World Wide Web (WWW). The web-based 3D visualization of functional images combined with anatomical images has not studied much in systematic ways. The goal of this study was to achieve a simultaneous observation of 3D anatomic and functional models with planar images on the WWW, providing their locational information in 3D space with a measuring implement using VRML. MRI and ictal-interictal SPECT images were obtained from one epileptic patient. Subtraction ictal SPECT co-registered to MRI (SISCOM) was performed to improve identification of a seizure focus. SISCOM image volumes were held by thresholds above one standard deviation (1-SD) and two standard deviations (2-SD). SISCOM foci and boundaries of gray matter, white matter, and cerebrospinal fluid (CSF) in the MRI volume were segmented and rendered to VRML polygonal surfaces by marching cube algorithm. Line profiles of x and y-axis that represent real lengths on an image were acquired and their maximum lengths were the same as 211.67 mm. The real size vs. the rendered VRML surface size was approximately the ratio of 1 to 605.9. A VRML measuring tool was made and merged with previous VRML surfaces. User interface tools were embedded with Java Script routines to display MRI planar images as cross sections of 3D surface models and to set transparencies of 3D surface models. When transparencies of 3D surface models were properly controlled, a fused display of the brain geometry with 3D distributions of focal activated regions provided intuitively spatial correlations among three 3D surface models. The epileptic seizure focus was in the right temporal lobe of the brain. The real position of the seizure focus could be verified by the VRML measuring tool and the anatomy corresponding to the seizure focus could be confirmed by MRI planar images crossing 3D surface models. The VRML application developed in this study may have several advantages. Firstly, 3D fused display and control of anatomic and functional image were achieved on the m. Secondly, the vector analysis of a 3D surface model was defined by the VRML measuring tool based on the real size. Finally, the anatomy corresponding to the seizure focus was intuitively detected by correlations with MRI images. Our web based visualization of 3-D fusion image and its localization will be a help to online research and education in diagnostic radiology, therapeutic radiology, and surgery applications.

• Journal of Internet Computing and Services
• /
• v.17 no.4
• /
• pp.145-159
• /
• 2016

This study points out the problems of absence of the legislation for standard regulation on Video on Demand(VoD) advertisement which grows so fast lately, for this it recommends making legal references, which have the definition of non-linear broadcasting & VoD advertisement and VoD advertisement standard regulation in the merged Broadcasting Act, and adopting co-regulation system. Pay TV operators providing VoD service have the opportunities to make money as subscribers uses it increasingly. In case of linear service, the Broadcasting Act regulates the advertisement strictly, but not the VoD ads. The reason why is that Korean legislation including the Broadcasting Act does not have legal reference to regulate it, instead of that, it rely on the self-regulation system which is operated by pay-tv players who provide the VoD ads. So, there is the limitation to protect the minors such as children and youth from the harmful VoD ads, to be invulnerable for advertisers to influence to advertising agents, and to ensure the regulatory effectiveness under player-centric self-regulatory regime. In this context, this study analyses the how to regulate VoD ads standard with a three-pronged approach. First, it analyses the VoD ads regulation system in overseas countries, UK, Canada, EU and Ireland. Each country has the legal reference to regulate it in the Broadcasting Act or lower statures and adopts the co-regulatory regime the NRA and the 3rd entity operate together. Second, it reviews the objectives and scope of VoD ads standard. This study recommends that the objective of it is users protection and the scope of it is standard regulation not commercial practice. Third, this study researches how to legislate for regulation of VoD ads standard. Considering VoD service's characteristics(non-linear service) and legal position of Ads agency(i.e. pay tv operators), it suggest that legal reference will be in the integrated Broadcasting bill, which is the general law, not individual. If it is available to regulate VoD ads standard with co-regulatory regime, it expects the enhancement of user protection from the harmful VoD ads and make up sustainability of the pay-tv players' self-regulation.

• Land and Housing Review
• /
• v.8 no.1
• /
• pp.1-11
• /
• 2017

The government has been constructing and supplying public rental housing to ordinary people in order to stabilize housing since 1989. However, the public rental houses initially supplied to ordinary people are at high risk for safety accidents due to the deterioration of the facilities. Therefore, this study is aimed to propose a solution to solve the life safety hazards of the old rental housing complex as a follow-up study of Analysis of Accident Patterns and Hazard Factor for Life Safety in Rental Housing Complex. Types of life safety accidents that occur in public rental housing complexes are sliding, falling, crash, falling objects, breakage, fire accidents, traffic accidents and criminal accidents. The types of safety accidents that occur in rental housing complexes analyzed in this study are sliding, crashes, falling objects, and fire accidents. Although the incidence of safety accidents such as falling, breakage, traffic accidents and crime accidents in public rental housing complexes is low, these types are likely to cause safety accidents. The method of this study utilized interviews and seminar results, and it suggested ways to solve the life safety hazards in rental housing complexes. Interviews were conducted with residents and managers of rental housing complexes. Seminars were conducted twice with experts in construction, maintenance, asset management, housing welfare and safety. Through interviews and seminars, this study categorizes the life safety hazards that occur in rental housing complexes by types of accidents and suggests ways to resolve them as follows. (1) sliding ; use of flooring materials with high friction coefficient, installation of safety devices such as safety handles, implementation of maintenance, safety inspections and safety education, etc. (2) falling ; supplementation of safety facilities, Improvement of the design method of the falling parts, Safety education, etc. (3) crash ; increase the effective width of the elevator door, increase the effective width of the lamp, improve the lamp type (U type ${\rightarrow}$ I type), etc. (4) falling objects and breakage ; design of furniture considering the usability of residents, replacement of old facilities, enhancement of safety consciousness of residents, safety education, etc. (5) fire accidents ; installation of fire safety equipment, improvement by emergency evacuation, safety inspection and safety education, etc. (6) traffic accidents ; securing parking spaces, installing safety facilities, conducting safety education, etc. (7) criminal accidents; improvement of CCTV pixels, installation of street lights, removal of blind spots in the complex, securing of security, etc. The roles of suppliers, administrators and users of public rental housing proposed in this study are summarized as follows. Suppliers of rental housing should take into consideration the risk factors that may arise not only in the design and construction but also in the maintenance phase and should consider the possibility of easily repairing old facilities considering the life cycle of rental housing. Next, Administrators of rental housing should consider the safety of the users of the rental housing, conduct safety checks from time to time, and immediately remove any hazardous elements within the apartment complex. Finally, the users of the rental housing needs to form a sense of ownership of all the facilities in the rental housing complex, and efforts should be made not to cause safety accidents caused by the user's carelessness. The results of this study can provide the necessary information to enable residents of rental housing complexes to live a safe and comfortable residential life. It is also expected that this information will be used to reduce the incidence of safety accidents in rental housing complexes.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.05a
• /
• pp.234-245
• /
• 2007

The empirical studies on the implementation of data warehousing systems (DWS) are lacking while there exist a number of studies on the implementation of IS. This study intends to examine the factors affecting the implementation success of DWS. The study adopts the empirical analysis of the sample of 112 responses from DWS practitioners. The study results suggest several implications for researchers and practitioners. First, when the support from top management becomes great, the implementation success of DWS in organizational aspects is more likely. When the support from top management exists, users are more likely to be encouraged to use DWS, and organizational resistance to use DWS is well coped with increasing the possibility of implementation success of DWS. The support of resource increases the implementation success of DWS in project aspects while it is not significantly related to the implementation success of DWS in organizational aspects. The support of funds, human resources, and other efforts enhances the possibility of successful implementation of project; the project does not exceed the time and resource budgets and meet the functional requirements. The effect of resource support, however, is not significantly related to the organizational success. The user involvement in systems implementation affects the implementation success of DWS in organizational and project aspects. The success of DWS implementation is significantly related to the users' commitment to the project and the proactive involvement in the implementation tasks. users' task. The observation of the behaviors of competitors which possibly increases data quality does not affect the implementation success of DWS. This indicates that the quality of data such as data consistency and accuracy is not ensured through the understanding of the behaviors of competitors, and this does not affect the data integration and the successful implementation of DWS projects. The prototyping for the DWS implementation positively affects the implementation success of DWS. This indicates that the extent of understanding requirements and the communication among project members increases the implementation success of DWS. Developing the prototypes for DWS ensures the acquirement of accurate or integrated data, the flexible processing of data, and the adaptation into new organizational conditions. The extent of consulting activities in DWS projects increases the implementation success of DWS in project aspects. The continuous support for consulting activities and technology transfer enhances the adherence to the project schedule preventing the exceeding use of project budget and ensuring the implementation of intended system functions; this ultimately leads to the successful implementation of DWS projects. The research hypothesis that the capability of project teams affects the implementation success of DWS is rejected. The technical ability of team members and human relationship skills themselves do not affect the successful implementation of DWS projects. The quality of the system which provided data to DWS affects the implementation success of DWS in technical aspects. The standardization of data definition and the commitment to the technical standard increase the possibility of overcoming the technical problems of DWS. Further, the development technology of DWS affects the implementation success of DWS. The hardware, software, implementation methodology, and implementation tools contribute to effective integration and classification of data in various forms. In addition, the implementation success of DWS in organizational and project aspects increases the data quality and system quality of DWS while the implementation success of DWS in technical aspects does not affect the data quality and system quality of DWS. The data and systems quality increases the effective processing of individual tasks, and reduces the decision making times and efforts enhancing the perceived benefits of DWS.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.3
• /
• pp.322-331
• /
• 2003

As the complexity of a 3D game is increased by various factors of the game scenario, it has a problem for controlling the interrelation of the game objects. Therefore, a game system has a necessity of the coordination of the responses of the game objects. Also, it is necessary to control the behaviors of animations of the game objects in terms of the game scenario. To produce realistic game simulations, a system has to include a structure for designing the interactions among the game objects. This paper presents a method that designs the dynamic control mechanism for the interaction of the game objects in the game scenario. For the method, we suggest a game agent system as a framework that is based on intelligent agents who can make decisions using specific rules. Game agent systems are used in order to manage environment data, to simulate the game objects, to control interactions among game objects, and to support visual authoring interface that ran define a various interrelations of the game objects. These techniques can process the autonomy level of the game objects and the associated collision avoidance method, etc. Also, it is possible to make the coherent decision-making ability of the game objects about a change of the scene. In this paper, the rule-based behavior control was designed to guide the simulation of the game objects. The rules are pre-defined by the user using visual interface for designing their interaction. The Agent State Decision Network, which is composed of the visual elements, is able to pass the information and infers the current state of the game objects. All of such methods can monitor and check a variation of motion state between game objects in real time. Finally, we present a validation of the control method together with a simple case-study example. In this paper, we design and implement the supervised classification systems for high resolution satellite images. The systems support various interfaces and statistical data of training samples so that we can select the most effective training data. In addition, the efficient extension of new classification algorithms and satellite image formats are applied easily through the modularized systems. The classifiers are considered the characteristics of spectral bands from the selected training data. They provide various supervised classification algorithms which include Parallelepiped, Minimum distance, Mahalanobis distance, Maximum likelihood and Fuzzy theory. We used IKONOS images for the input and verified the systems for the classification of high resolution satellite images.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.135-155
• /
• 2018

The purpose of this study is to analyze the difference of interpretation level and intention to use message framing when autonomous vehicle, which is emerging as the product of 4th industrial revolution, is used as taxi, Interpretation level refers to the interpretation of a product or service, assuming that it will happen in the near future or in the distant future. Message framing refers to the formation of positive or negative expressions or messages at the extremes of benefits and losses. In other words, previous studies interpret the value of a product or service differently according to these two concepts. The purpose of this study is to investigate whether there are differences in intention to use when two concepts are applied when an autonomous vehicle is launched as a taxi. The results are summarized as follows: First, the message format explaining the gain and why should be used when using the autonomous taxi in the message framing configuration, and the loss and how when the autonomous taxi is not used. Messages were constructed and compared. The two message framing differed (t = 3.063), and the message type describing the benefits and reasons showed a higher intention to use. In addition, the results according to interpretation level are summarized as follows. There was a difference in intentions to use when assuming that it would occur in the near future and in the near future with respect to the gain and loss, Respectively. In summary, in order to increase the intention of using autonomous taxis, it is concluded that messages should be given to people assuming positive messages (Gain) and what can happen in the distant future. In addition, this study will be able to utilize the research method in studying intention to use new technology. However, this study has the following limitations. First, it assumes message framing and time without user experience of autonomous taxi. This will be different from the actual experience of using an autonomous taxi in the future. Second, self-driving cars should technical progress is continuing, but laws and institutions must be established in order to commercialize it and build the infrastructure to operate the autonomous car. Considering this fact, the results of this study can not reflect a more realistic aspect. However, there is a practical limit to search for users with sufficient experience in new technologies such as autonomous vehicles. In fact, although the autonomous car to take advantage of the public transportation by taxi is now ready for the road infrastructure, and technical and legal public may not be willing to choose to not have enough knowledge to use the Autonomous cab. Therefore, the main purpose of this study is that by assuming that autonomous cars will be commercialized by taxi you can do to take advantage of the autonomous car, it is necessary to frame the message, why can most effectively be used to find how to deliver. In addition, the research methodology should be improved and future research should be done as follows. First, most students responded in this study. It is also true that it is difficult to generalize the hypotheses to be tested in this study. Therefore, in future studies, it would be reasonable to investigate the population of various distribution considering the age, area, occupation, education level, etc. Where autonomous taxi can be used rather than those who can drive. Second, it is desirable to construct various message framing of the questionnaire, but it is necessary to learn various message framing in advance and to prevent errors in response to the next message framing. Therefore, it is desirable to measure the message framing with a certain amount of time when the questionnaire is designed.