• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.1
• /
• pp.65-72
• /
• 2010

For developing navigation system of total hip arthroplasty (THA) and evaluating hip joint kinematics, 3-D pose position of the femur and acetabulum in the pelvic coordinate system has been quantified. The pelvic coordinate system is determined by manually indicating pelvic landmarks in multidetector-row computed tomography (MDCT) images. It includes intra- and inter-observer variability, and may result in a variability of THA operation or diagnosis. To reduce the variability of pelvic coordinate system determination, this paper proposes an automated method in MDCT images. The proposed method determines pelvic coordinate system automatically by detecting pelvic landmarks on anterior pelvic plane (APP) from MDCT images. The method calibrates pelvic pose by using silhouette images to suppress the affect of pelvic pose change. As a result of comparing with manual determination, the proposed method determined the coordinate system with a mean displacement of $2.6\;{\pm}\;1.6$ mm and a mean angle error of $0.78\;{\pm}\;0.34$ deg on 5 THA subjects. For changes of pelvic pose position within 10 deg, standard deviation of displacement was 3.7 mm, and of pose was 1.28 deg. We confirmed the proposed method was robust for pelvic pose changes.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.169-181
• /
• 2017

As vehicle supply rate increases, traffic jam-related problems emerge and sharing transportation including carpool, centered on the advanced countries, becomes a major interest. This study aims to analyze benefit generated by carpool during the rush hours of medium and long distance travel, focused on the workers of public Agencies relocated to innovation cities. In order to compute benefit, carpool demand of relocated public Agencies was estimated and travel speed was estimated according to reduced traffic volume through carpool adoption using a traffic flow model. The benefit were computed dividing them into direct benefit and indirect benefit. As a result, 23billion KRW and 56.5billion KRW were annually revealed to be generated in terms of direct benefit and indirect benefit. The study result is expected to be used as part of basic research to adopt carpool for future traffic demand management.

• Journal of the Korea Convergence Society
• /
• v.8 no.9
• /
• pp.271-276
• /
• 2017

This project has been conducted to improve the usability of Chatbot Services such as Google(Allo) and Facebook M(Messenger. Based on the evaluation, this study aims to suggest the solutions to improve the usability of domestic Chatbot services and future directions for their development. It provides the overall understanding of the AI Chatbot service and the feature of Chatbot service through literature search. Furthermore, we summarized the current standing and the prospect of domestic messenger-based assistant Chatbot services. For conducting user evaluation, Peter Morville's honeycomb model is applied to in-depth user interviews. The followings are elements that could be amended to improve the service. The service should be incorporated by intuitive elements for users' understanding its functions and eliminate any elements that interfere with usability. The accuracy should be increased to improve the user satisfaction. This research will provide the future guidelines to improve the usability of Chabot services through continuous evaluation by users.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.6
• /
• pp.571-577
• /
• 2015

In the paper, we propose a method for developing a physical training management module which sends physical data to smart devices using an wireless module attached to physical appliances. In the proposed stick-type physical appliance, the physical amount of data measured from sensors inside the appliance is sent to a smart device via wireless communication. And then the smart device records the physical amount of data categorized in person-based data and shows useful information about the user's physical training on the dedicated display. For the performance evaluation, indoor environment and electro magnetic wave tests are taken from national specialized organizations, and their results was very efficient. The proposed physical training management module is highly extensible since it is easily applicable to other physical appliances and useful to both Android and iOS platforms.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.519-529
• /
• 2019

Nowadays, intelligent Android malware applies anti-analysis techniques to hide malicious behaviors and make it difficult for anti-virus vendors to detect its presence. Malware can use background components to hide harmful operations, use activity-alias to get around with automation script, or wipe the logcat to avoid forensics. During our study, several static analysis tools can not extract these hidden components like main activity, and dynamic analysis tools also have problem with code coverage due to partial execution of android malware. In this paper, we design and implement a system to analyze intelligent malware that uses anti-analysis techniques to improve detection rate of evasive malware. It extracts the hidden components of malware, runs background components like service, and generates all the intent events defined in the app. We also implemented a real-time logging system that uses modified logcat to block deleting logs from malware. As a result, we improve detection rate from 70.9% to 89.6% comparing other container based dynamic analysis platform with proposed system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.74-87
• /
• 2020

Overloaded trucks are the main source that threatens road safety and directly affects the reduction of pavement life. The On-board truck scale is the only equipment that could prevent overloading by measuring and adjusting the loading weight before driving. Legislation is needed to encourage its installation so that the driver can prevent overloading. In this study, an on-board truck scale system was installed on 30 dump trucks for transporting construction waste, such as soil and aggregates, which are major loads of 36.55% for overloading, and the trucks were monitored remotely. The overload prevention effect was analyzed by comparing driving data for 1 month before distribution of the weight display app that can recognize the weight to the driver and 1 month after distribution. After installation, overloading could be 6.1% reduced, and the transportation efficiency could be increased by checking the weight provided from the On-board truck scale system.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.3
• /
• pp.21-29
• /
• 2015

The Internet of Things (IoT) is an Infrastructure which allows to connect with each device in physical world through the Internet. Thus IoT enables to provide meahup services or intelligent services to human user using collected data from those devices. Due to these advantages, IoT is used in divers service domains such as traffic, distribution, healthcare, and smart city. However, current IoT provides restricted services because it only supports monitor and control devices according to collected data from the devices. To resolve this problem, we propose a design and implementation of personalized IoT service base on service orchestration. The proposed service allows to discover specific services and then to combine the services according to a user location. To this end, we develop a service ontology to interpret user information according to meanings and smartphone web app to use the IoT service by human user. We also develop a service platform to work with external IoT platform. Finally, to show feasibility, we evaluate the proposed system via study.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.5
• /
• pp.149-154
• /
• 2013

IoT is emerging topic of the post-smartphone era. But IoT service is actually not easy but due to the absence of the open standard IoT service platform. In this study, We propose and implement IoT services platform using commercial SNS platform like Tweet, Facebook or YouTube. we implement the intelligent control system of the urban farm using our IoT services platform as an example. Our system can save an additional server deployment and management cost using open SNS platform like Tweet or Facebook or Youtube. In addition, there are needs to develop App. for the smartphone because we can take advantage of the user interface which is developed by global enterprises.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1109-1116
• /
• 2018

The purpose of this study is to solve the loss of personal belongings by utilizing monitoring function of IoT platform. The beacon to combined with personal belongings are registered with the application server, the trigger processing function according to the occurrence of the lost event is performed intelligently through the device, the app, the IoT network, and the application server.