• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.148-155
• /
• 2002

Multithreaded models improve the efficiency of parallel systems by combining inner parallelism, asynchronous data availability and the locality of von Neumann model. This model executes thread code which is generated by compiler and of which quality is given by the method of generation. But multithreaded models have the demerit that execution model is restricted to a specific platform. On the contrary, Java has the platform independency, so if we can translate from threads code to Java bytecode, we can use the advantages of multithreaded models in many platforms. Java executes Java bytecode which is intermediate language format for Java virtual machine. Java bytecode plays a role of an intermediate language in translator and Java virtual machine work as back-end in translator. But, Java bytecode which is translated from multithreaded models have the demerit that it is not secure. This paper, multhithread code whose feature of platform independent can execute in java virtual machine. We design and implement translator which translate from thread code of multithreaded code to Java bytecode and which check secure problems from Java bytecode.

• Journal of Food Hygiene and Safety
• /
• v.29 no.4
• /
• pp.299-304
• /
• 2014

The dose-response models are important for the quantitative microbiological risk assessment (QMRA) because they would enable prediction of infection risk to humans from foodborne pathogens. In this study, we performed a comprehensive literature review and meta-analysis to better quantify this association. The meta-analysis applied a final selection of 193 published papers for total 43 species foodborne disease pathogens (bacteria 26, virus 9, and parasite 8 species) which were identified and classified based on the dose-response models related to QMRA studies from PubMed, ScienceDirect database and internet websites during 1980-2012. The main search keywords used the combination "food", "foodborne disease pathogen", "dose-response model", and "quantitative microbiological risk assessment". The appropriate dose-response models for Campylobacter jejuni, pathogenic E. coli O157:H7 (EHEC / EPEC / ETEC), Listeria monocytogenes, Salmonella spp., Shigella spp., Staphylococcus aureus, Vibrio parahaemolyticus, Vibrio cholera, Rota virus, and Cryptosporidium pavum were beta-poisson (${\alpha}=0.15$, ${\beta}=7.59$, fi = 0.72), beta-poisson (${\alpha}=0.49$, ${\beta}=1.81{\times}10^5$, fi = 0.67) / beta-poisson (${\alpha}=0.22$, ${\beta}=8.70{\times}10^3$, fi = 0.40) / beta-poisson (${\alpha}=0.18$, ${\beta}=8.60{\times}10^7$, fi = 0.60), exponential (r=$1.18{\times}10^{-10}$, fi = 0.14), beta-poisson (${\alpha}=0.11$, ${\beta}=6,097$, fi = 0.09), beta-poisson (${\alpha}=0.21$, ${\beta}=1,120$, fi = 0.15), exponential ($r=7.64{\times}10^{-8}$, fi = 1.00), betapoisson (${\alpha}=0.17$, ${\beta}=1.18{\times}10^5$, fi = 1.00), beta-poisson (${\alpha}=0.25$, ${\beta}=16.2$, fi = 0.57), exponential ($r=1.73{\times}10{-2}$, fi = 1.00), and exponential ($r=1.73{\times}10^{-2}$, fi = 0.17), respectively. Therefore, these results provide the preliminary data necessary for the development of foodborne pathogens QMRA.

• Archives of design research
• /
• v.16 no.1
• /
• pp.181-198
• /
• 2003

The purpose of this study is to develop a on-line design tool for effectively coping with e-Business environment, or product design process into a Cyber model for traditional manufacturers which attempts new product development under such environment. It was finally developed as a model named $\ulcorner$Design Vortal Site; e-BVDS) that was based on the structure and style of internet web site. Results of the study can be described as follows ; \circled1 e-Business is based on the Internet. All processes in the context of e-Business require models whose structure and method of use are on-line styles. \circled2 In case that a traditional manufacturing business is converted into e-Business, it is better to first consider Hybrid Model that combines resources and advantages of both such traditional and digital businesses. \circled3 The product design process appropriate for e-Business environment has to have a structure and style that ensure utilization of the process as an Internet web site, active participation by product developers and interactive communication between participants in designing and designers. \circled4 $\ulcorner$e-BDVS) makes possible the use of designers around the wend like in-house designers, overcoming lack in creativity, ideas and human resources traditional business organizations face. However, the operation of $\ulcorner$e-BDVS$\lrcorner$ requires time and budget investments in securing related elements and conditions. \circled5 Cyber designers under $\ulcorner$e-BDVS$\lrcorner$ can easily perform all design projects in cyber space. But they have some limits in playing a role as designers and they have difficulty in getting rewards if such projects completed by them are not finally accepted. \circled6 $\ulcorner$e-BDVS) ensures the rapid use of a wide range of design information and data, reception of a variety of solutions and ideas and effective design development, all of which are not possible through traditional processes. However, this process may not be suitable to be used routine process or tool. \circled7 $\ulcorner$e-BDVS$\lrcorner$ makes it possible for out-sourcing or partners businesses to overcome restrictions in time and space and improve productivity and effectiveness. But such they may have to continue off-line works that can not be treated on-line.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.85-97
• /
• 2005

In this paper, we construct the traffic information database by using the acquired data from the traffic information devices installed in road network, and, by referring to this database, propose the intersection simulation system which can dynamically manage the real-time traffic flow for each section of road from the intersections, This system consists of hierarchical 3 parts, The lower layer is the physical layer where the traffic information is acquired on an actual road. The traffic flow control framework exists in the middle layer. The framework supports the grouping of intersection, the collection of real-time traffic flow information, and the remote monitoring and control by using the traffic information of the lower layer, This layer is designed by extending the distributed object group framework we developed. In upper layer, the intersection simulator applications controlling the traffic flow by grouping the intersections exist. The components of the intersection application in our system are composed of the implementing objects based on the Time-triggered Message-triggered Object(TMO) scheme, The intersection simulation system considers the each intersection on road as an application group, and can apply the control models of dynamic traffic flow by the road's status. At this time, we use the real-time traffic information collected through inter-communication among intersections. For constructing this system, we defined the system architecture and the interaction of components on the traffic flow control framework which supports the TMO scheme and the TMO Support Middleware(TMOSM), and designed the application simulator and the user interface to the monitoring and the controlling of traffic flow.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.155-161
• /
• 2020

In general, optimization problems are difficult to solve simply. The reason is that the given problem is solved as soon as it is simple, but the more complex it is, the very large number of cases. This study is about the optimization of AI neural network. What we are dealing with here is the relief method for constructing AI network. The main topics deal with non-deterministic issues such as the stability and unstability of the overall network state, cost down and energy down. For this one, we discuss associative memory models, that is, a method in which local minimum memory information does not select fake information. The simulated annealing, this is a method of estimating the direction with the lowest possible value and combining it with the previous one to modify it to a lower value. And nonlinear planning problems, it is a method of checking and correcting the input / output by applying the appropriate gradient descent method to minimize the very large number of objective functions. This research suggests a useful approach to relief method as a theoretical approach to solving optimization problems. Therefore, this research will be a good proposal to apply efficiently when constructing a new AI neural network.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.

• Journal of Internet Computing and Services
• /
• v.16 no.3
• /
• pp.117-126
• /
• 2015

The concept of Creating Shared Value (CSV) has emerged as a solution for companies' sustainable growth and social problems through collaboration of business activities and social demand. Therefore, studies on shared value creativity and measurement of companies' performances are required. However, most recent studies have applied the CSV concept to existing business models or measure shared value considering only economic value. Few studies have considered the appropriateness of applying the CSV or discussed performance measurement with respect to industry characteristics. This study selects the industry expected to have the greatest created value with applying the CSV, and then suggests measurement of performance in this industry. First, through the expert interview, the study selects one from among South Korea's 10 main industries, which is expected to solve social demand through convergence with the IT industry, and to create new value for a traditional industry. The Home Appliance industry was selected as appropriate, because it has industrial growth stagnation under the smart environment. Moreover, it is facing problems such as energy savings and environmental issues. The study goes on to suggest, based on Michael Porter's three strategic levels, measurement variables of the value creation process and performance. This study has limitations from an empirical perspective. However, as the interest of applying CSV to business is growing, it is meaningful to explore the CSV strategies activities and measurement performance based on industry-specific characteristics.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.113-129
• /
• 2009

Abstract Corporate activities are composed of numerous working processes and during the working flow, various business processes are being created and completed simultaneously. Enterprise Resources Planning (ERP) makes the working process simple, yet creates more complicated work structure and therefore, there is an absolute need of efficient management for business processes. The workflow literature has been looking for efficient and effective ways of rediscovering and mining workflow intelligence and knowledge from their enactment histories and event logs. As part of studies to analyze and improve the process, the concepts of 'Process Mining', 'Process re-discovery', 'BPR (Business Process Reengineering)' have appeared and the studies for practical implementation are proactively being done. However, these studies normally follow the approach throughout data warehousing for log data of process instances. It is very hard for these approaches to reflect user's intention to the rediscovering and mining activities. The process instances designed based on the consideration of analysis can make groupings effectively and when the analysis demand of user changes within the analysis domain can also reduce the cost of analysis. Therefore, the thesis proposes a special type of workflow model, which is called a colored workflow model, that is extended from the ICN (information control net) modeling methodology by reinforcing the concept of colored token. The colored tokens represent the conceptual types of constraints and criteria that can be used to classifying and grouping the workflow intelligence and knowledge extracted from the corresponding workflow models' enactment histories and event logs. Through the runtime information of process instances, it makes possible to analyze proactive and user-oriented process with the goal of deriving business knowledge from the beginning of process definition.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.133-144
• /
• 2020

The number of elderly people with dementia is increasing as fast as the proportion of older people due to aging, which creates a social and economic burden. In particular, dementia care costs, including indirect costs such as increased care costs due to lost caregiver hours and caregivers, have grown exponentially over the years. In order to reduce these costs, it is urgent to introduce a management system to care for dementia patients. Therefore, this study proposes a sensor-based abnormal behavior detection system to manage dementia patients who live alone or in an environment where they cannot always take care of dementia patients. Existing studies were merely evaluating behavior or evaluating normal behavior, and there were studies that perceived behavior by processing images, not data from sensors. In this study, we recognized the limitation of real data collection and used both the auto-encoder, the unsupervised learning model, and the LSTM, the supervised learning model. Autoencoder, an unsupervised learning model, trained normal behavioral data to learn patterns for normal behavior, and LSTM further refined classification by learning behaviors that could be perceived by sensors. The test results show that each model has about 96% and 98% accuracy and is designed to pass the LSTM model when the autoencoder outlier has more than 3%. The system is expected to effectively manage the elderly and dementia patients who live alone and reduce the cost of caring.