This paper presents an evaluation system to determine the completeness of a space map obtained by a visual SLAM(Simultaneous Localization And Mapping) algorithm. The proposed system consists of three parts. First, the proposed system detects the occurrence of loop closing to confirm that users acquired the information from all directions. Thereafter, the acquired map is divided with regular intervals and is verified whether each area has enough map points to successfully estimate users' position. Finally, to check the effectiveness of each map point, the system checks whether the map points are identifiable even at the location where there is a large distance difference from the acquisition position. Experimental results show that space maps whose completeness is proven by the proposed system has higher stability and accuracy in terms of position estimation than other maps that are not proven.

In this paper, we propose a real-time hand gesture recognition algorithm to eliminate the inconvenience of using hand controllers in VR applications. The user's 3D hand coordinate information is detected by leap motion sensor and then the coordinates are generated into two dimensional image. We classify hand gestures in real-time by learning the imaged 3D hand coordinate information through SSD(Single Shot multibox Detector) model which is one of CNN(Convolutional Neural Networks) models. We propose to use all 3 channels rather than only one channel. A sliding window technique is also proposed to recognize the gesture in real time when the user actually makes a gesture. An experiment was conducted to measure the recognition rate and learning performance of the proposed model. Our proposed model showed 99.88% recognition accuracy and showed higher usability than the existing algorithm.

Most current human action recognition methods based on deep learning methods. It is required, however, a very high computational cost. In this paper, we propose an action change detection method to reduce repetitive human action recognition tasks. In reality, simple actions are often repeated and it is time consuming process to apply high cost action recognition methods on repeated actions. The proposed method decides whether action has changed. The action recognition is executed only when it has detected action change. The action change detection process is as follows. First, extract the number of non-zero pixel from motion history image and generate one-dimensional time-series data. Second, detecting action change by comparison of difference between current time trend and local extremum of time-series data and threshold. Experiments on the proposed method achieved 89% balanced accuracy on action change data and 61% reduced action recognition repetition.

In recent years, there has been active research on a recommender system that considers three or more inputs in addition to users and goods, making it a multi-dimensional array, also known as a tensor. The main issue with using tensor is that there are a lot of missing values, making it sparse. In order to solve this, the tensor can be shrunk using the tensor decomposition algorithm into a lower dimensional array called a factor matrix. Then, the tensor is reconstructed by calculating factor matrices to fill original empty cells with predicted values. This is called tensor reconstruction. In this paper, we propose a user-based Top-K recommender system by normalized PARAFAC tensor reconstruction. This method involves factorization of a tensor into factor matrices and reconstructs the tensor again. Before decomposition, the original tensor is normalized based on each dimension to reduce overfitting. Using the real world dataset, this paper shows the processing of a large amount of data and implements a recommender system based on Apache Spark. In addition, this study has confirmed that the recommender performance is improved through normalization of the tensor.

This paper proposes a method of utilizing convolutional neural network to classify the images of Bender Gestalt Test (BGT), which is a tool to understand and analyze a person's characteristic. The proposed network is composed of 29 layers including 18 convolutional layers and 2 fully connected layers, where the network is to be trained with augmented images. To verify the proposed method, 10 fold validation was adopted. In results, the proposed method classified the images into 9 classes with the mean f1 score of 97.05%, which is 13.71%p higher than a previous method. The analysis of the results shows the classification accuracy of the proposed method is stable over all the patterns as the worst f1 score among all the patterns was 92.11%.

The growth of mobile technology particularly smartphone applications such as ticketing, access control, and making payments are on the increase. Elliptic Curve Cryptography (ECC)-based systems have also become widely available in the market offering various convenient services by bringing smartphones in proximity to ECC-enabled objects. When a system user attempts to establish a connection, the AIK sends hashes to a server that then verifies the values. ECC can be used with various operating systems in conjunction with other technologies such as biometric verification systems, smart cards, anti-virus programs, and firewalls. The use of Elliptic-curve cryptography ensures efficient verification and signing of security status verification reports which allows the system to take advantage of Trusted Computing Technologies. This paper proposes a device payment method based on ECC and Shuffling based on distributed key exchange. Our study focuses on the secure and efficient implementation of ECC in payment device. This novel approach is well secure against intruders and will prevent the unauthorized extraction of information from communication. It converts plaintext into ASCII value that leads to the point of curve, then after, it performs shuffling to encrypt and decrypt the data to generate secret shared key used by both sender and receiver.

Today, computational thinking takes an important role in problem solving in software education. As a result, software education as liberal arts for non-CS major students is rapidly expanding. It is necessary to study the effects of computational thinking on software problem solving ability compared to traditional programming language education. In this paper, we propose an evaluation model for analyzing the effects of computational thinking on the overall software development process, and analyze how the problem solving process is different for learners who take computing thinking classes and programming language courses as liberal arts courses. As a result, students who learned computational thinking showed higher ability in problem analysis and design process.

Nowadays, Electronic Medical Record (EMR) has just implemented at few hospitals for Outpatient Department (OPD). OPD is the diversified data, it includes demographic and diseases of patient, so it need to be clustered in order to explore the hidden rules and the relationship of data types of patient's information. In this paper, we propose a novel approach for unsupervised clustering of patient's demographic and diseases in OPD. Firstly, we collect data from a hospital at OPD. Then, we preprocess and transform data by using powerful techniques such as standardization, label encoder, and categorical encoder. After obtaining transformed data, we use some strong experiments, techniques, and evaluation to select the best number of clusters and best clustering algorithm. In addition, we use some tests and measurements to analyze and evaluate cluster tendency, models, and algorithms. Finally, we obtain the results to analyze and discover new knowledge, meanings, and rules. Clusters that are found out in this research provide knowledge to medical managers and doctors. From these information, they can improve the patient management methods, patient arrangement methods, and doctor's ability. In addition, it is a reference for medical data scientist to mine OPD dataset.

Variational methods, which cast deformation as an energy-minimization problem, are known to provide a good trade-off between practicality and speed. However, the time required to deform a fully detailed shape means that these methods are largely unsuitable for real-time applications. We simplify a 2D shape into a curve skeleton, which can be deformed much more rapidly than the original shape. The curve skeleton also provides a simplified control for the user, utilizing a small number of control handles. Our system deforms the curve skeleton using an energy-minimization method and then applies the resulting deformation to the original shape using linear blend skinning. This approach effectively reduces the size of the variational optimization problem while producing deformations of a similar quality to those obtained from full-scale nonlinear variational methods.

Existing user research methods are subject to a variety of research conditions such as the amount and variety of data collected and the expertise of the facilitator of a group research session. In this study, we propose a new user research methodology using an 'Issue-Network' system, which is developed based on the theory and methods of social network analysis. The Issue-Network is designed to define problem spaces from the issues raised by users in a group research session in a form of an interactive network graph. The system helps to break out of ordinary perspectives of looking into problem spaces by enabling an alternative and more creative way to connect issues in the network. In this study, we took a case study of generating the Issue-Network on behalf of the problems raised by users in various driving-related situations. We were able to draw three navigation usage scenarios that cover relatively important problem spaces: safety and being ready for the unexpected, smart navigation and notifications, making use of the spare time. In the future, the Issue-Network system is expected to be used as a tool to identify problems and derive solutions in group research sessions involving a large number of users.

DOOH(Digital Out Of Home) advertising targets for reaching consumers through outdoor digital display medias. Traditionally, scheduling of advertisement contents over DOOH medias is usually done by operator's strategy, but an efficient ad scheduling strategy is not easy to find under various advertising contexts. In this paper, we present a context-aware factorization machine-based recommendation model for the scheduling under various advertising contexts, and provide analysis for understanding of the contexts' effects on advertising based on the recommendation model. Through simulation results on the dataset adapted from a real dataset of RecSys challenge 2015, it is shown that the proposed model and analysis based on the model will be effective for better scheduling of ad contents under advertising contexts over DOOH networks.