• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.373-384
• /
• 2014

Data mining is to clarify pattern or correlation of mass data of complicated structure and to predict the diverse outcomes. This technique is used in the fields of finance, telecommunication, circulation, medicine and so on. In this paper, we selected risk factors of respiratory diseases in the field of medicine. The data we used was divided into respiratory diseases group and health group from the Gyeongsangbuk-do database of Community Health Survey conducted in 2012. In order to select major risk factors, we applied data mining techniques such as neural network, logistic regression, Bayesian network, C5.0 and CART. We divided total data into training and testing data, and applied model which was designed by training data to testing data. By the comparison of prediction accuracy, CART was identified as best model. Depression, smoking and stress were proved as the major risk factors of respiratory disease.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.59-73
• /
• 2016

The demand for subsurface transport is increasing. The users and the operators of road tunnels are exposed to risks with different causes. One main cause, however, is the traffic situation in the event of accidents. The importance of a Quantified Risk Assessment is increasing to quantify the safety of road tunnels and to balance the requirements (capacity, reliability, availability, maintainability and safety) of various stakeholders. Although there are classical methods for risk assessments, such as ETA and FTA. These methods are used for relatively simple cases because it could not relevantly reflect the diversity and relationship of the parameters. Therefore, a quantitative risk assessment based on Bayesian Probabilistic Networks considering interdependence between the parameters of a complex underground system as a double deck tunnel is provided.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.190-202
• /
• 2015

Much research has been conducted on location-based intelligent personal assistants that can understand a user's intention by learning the user's route model and then inferring the user's destinations and routes using data of GPS and other sensors in a smartphone. The intelligence of the location-based personal assistant is contingent on the accuracy and efficiency of the real-time predictions of the user's intended destinations and routes by processing movement information based on uncertain sensor data. We propose a robust particle filter based on Dynamic Bayesian Network model to infer the user's routes. The proposed robust particle filter includes a particle generator to supplement the incorrect and incomplete sensor information, an efficient switching function and an weight function to reduce the computation complexity as well as a resampler to enhance the accuracy of the particles. The proposed method improves the accuracy and efficiency of determining a user's routes and destinations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.86-99
• /
• 2011

Due to the uncertainty of intention recognition for behaviors of users, the intention is differently recognized according to the situation for the same behavior by the same user, the accuracy of user intention recognition by minimizing the uncertainty is able to be improved. This paper suggests a novel ontology-based method to recognize user intentions, and able to minimize the uncertainties that are the obstacles against the precise recognition of user intention. This approach creates ontology for user intention, makes a hierarchy and relationship among user intentions by using RuleML as well as Dynamic Bayesian Network, and improves the accuracy of user intention recognition by using the defined RuleML as well as the gathered sensor data such as temperature, humidity, vision, and auditory. To evaluate the performance of robot proactive planning mechanism, we developed a simulator, carried out some experiments to measure the accuracy of user intention recognition for all possible situations, and analyzed and detailed described the results. The result of our experiments represented relatively high level the accuracy of user intention recognition. On the other hand, the result of experiments tells us the fact that the actions including the uncertainty get in the way the precise user intention recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.512-517
• /
• 2008

It is show that increasing of aged and handicapped people requires development of Ubiquitous computing technique to offer the specialized service for handicapped-people. For this, we need a development of Context Awareness and Service Reasoning Technique that the technique is supplied interaction between user and U-environment instead of the old unilateral relation. The old research of context awareness needed probabilistic presentation model like a Bayesian Network based on expert Systems for recognize given circumstance by a domain of uncertain real world. In this article, we define a domain of disorder activity assistant service application and context model based on ontology in diversified environment and minimized intervention of user and developer. By use this context model, we apply the structure learning of Bayesian Network and decide the service and activity to development of application service for handicapped people. Finally, we define the proper Conditional Probability Table of the structured Bayesian Network and if random situation is given to user, then present state variable of Activity and Service by given Causal relation of Bayesian Network based on Conditional Probability Table and it can be result of context awareness.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.795-800
• /
• 2016

In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.333-340
• /
• 2019

A combat system performs a given mission enduring various threats. It is important to analyze the reliability of combat systems in order to increase their ability to perform a given mission. Most of studies considered no threat or on threat and didn't analyze all the dependent relationships among the components. In this paper, we analyze the loss probability of the function of the combat system and use it to analyze the reliability. The proposed method is divided into two layers, A lower layer and a upper layer. In lower layer, the failure probability of each components is derived by using FTA to consider various threats. In the upper layer, The loss probability of function is analyzed using the failure probability of the component derived from lower layer and BBN in order to consider the dependent relationships among the components. Using the proposed method, it is possible to analyze considering various threats and the dependency between components.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.6A
• /
• pp.129-137
• /
• 2008

As the use of the internet increases, the distribution of spam mail has also vastly increased. The email's main use was for the exchange of information, however, currently it is being more frequently used for advertisement and malware distribution. This is a serious problem because it consumes a large amount of the limited internet resources. Furthermore, an extensive amount of computer, network and human resources are consumed to prevent it. As a result much research is being done to prevent and filter spam. Currently, research is being done on readable sentences which do not use proper grammar. This type of spam can not be classified by previous vocabulary analysis or document classification methods. This paper proposes a method to filter spam by using the subject of the mail and N-GRAM for indexing and Bayesian, SVM algorithms for classification.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.3
• /
• pp.255-263
• /
• 2014

Today, a number of CCTV on the highway is to observe the flow of traffics. There have been a number of studies where traffic data (e.g., the speed of vehicles and the amount of traffic on the road) are transferred back to the centralized server so that an appropriate action can be taken. This paper introduces a system that detects the changes of traffic flows caused by an accident or unexpected stopping (i.e., vehicle remains idle) by monitoring each lane separately. The traffic flows of each lane are level spacing curve that shows Wigner distribution for location vector. Applying calogero-moser system and Hamiltonian system, probability equation for each level-spacing curve is derived. The high level of modification of the signal means that the lane is in accident situation. This is different from previous studies in that it does more than looking for the signal from only one lane, now it is able to detect an accident in entire flow of traffic. In process of monitoring traffic flow of each lane, when camera recognizes a shadow of vehicle as a vehicle, it will affect the accident detecting capability. To prevent this from happening, the study introduces how to get rid of such shadow. The system using Basian network method is being compared for capability evaluation of the system of the study. As a result, the system of the study appeared to be better in performance in detecting the modification of traffic flow caused by idle vehicle.