Shin Jin Kang

Procedural Synthesis using Vortex Particle Method for Fluid Simulation

We propose a fast and effective technique to improve sub‐grid visual details of the grid based fluid simulation. Our method procedurally synthesizes the flow fields coming from the incompressible Navier‐Stokes solver and the vorticity fields generated by vortex particle method for sub‐grid turbulence. We are able to efficiently animate smoke which is highly turbulent and swirling with small scale details. Since this technique does not solve the linear system in high‐resolution grids, it can perform fluid simulation more rapidly. We can easily estimate the influence of turbulent and swirling effect to the fluid flow.

Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies.

This paper proposes a method to predict fluctuations in the prices of cryptocurrencies, which are increasingly used for online transactions worldwide. Little research has been conducted on predicting fluctuations in the price and number of transactions of a variety of cryptocurrencies. Moreover, the few methods proposed to predict fluctuation in currency prices are inefficient because they fail to take into account the differences in attributes between real currencies and cryptocurrencies. This paper analyzes user comments in online cryptocurrency communities to predict fluctuations in the prices of cryptocurrencies and the number of transactions. By focusing on three cryptocurrencies, each with a large market size and user base, this paper attempts to predict such fluctuations by using a simple and efficient method.

Automatic player behavior analysis system using trajectory data in a massive multiplayer online game

This paper presents a new automated behavior analysis system using a trajectory clustering method for massive multiplayer online games (MMOGs). The description of a player’s behavior is useful information in MMOG development, but the monitoring and evaluation cost of player behavior is expensive. In this paper, we suggest an automated behavior analysis system using simple trajectory data with few monitoring and evaluation costs. We used hierarchical classification first, then applied an extended density based clustering algorithm for behavior analysis. We show the usefulness of our system using trajectory data from the commercial MMOG World of Warcraft (WOW). The results show that the proposed system can analyze player behavior and automatically generate insights on players’ experience from simple trajectory data.

Virtual World Currency Value Fluctuation Prediction System Based on User Sentiment Analysis

In this paper, we present a method for predicting the value of virtual currencies used in virtual gaming environments that support multiple users, such as massively multiplayer online role-playing games (MMORPGs). Predicting virtual currency values in a virtual gaming environment has rarely been explored; it is difficult to apply real-world methods for predicting fluctuating currency values or shares to the virtual gaming world on account of differences in domains between the two worlds. To address this issue, we herein predict virtual currency value fluctuations by collecting user opinion data from a virtual community and analyzing user sentiments or emotions from the opinion data. The proposed method is straightforward and applicable to predicting virtual currencies as well as to gaming environments, including MMORPGs. We test the proposed method using large-scale MMORPGs and demonstrate that virtual currencies can be effectively and efficiently predicted with it.

Erratum to: Development of a low-cost wearable sensing glove with multiple inertial sensors and a light and fast orientation estimation algorithm

Correct capturing the movement of hands and fingers provides natural ways of interacting with computers. However, developing a glove-based device for such interaction has been very expensive and there were technical problems such as a complicate motion measurement algorithm in limited embedded resources and a complicate calibration process. We present a practical development of a low-cost and lightweight wearable sensing glove using only one CPU and seventeen IMUs. It transmits the captured movement data of seventeen joints of hand and wrist to a host machine via Bluetooth communication. We also propose a light and fast orientation estimation algorithm for the glove system, which should compute orientations and calibrations for seventeen inertia measurement units (IMUs) in real time. The seventeen individual IMUs are composed of an accelerometer, a gyroscope and a magnetometer based on micro electro-mechanical system technology. The magnetometer has sensor bias and scale factor errors, which vary with temperatures and places. Moreover, as the wearable sensing glove has a limited battery life and a cheap embedded processor, it can only utilize limited memory and computation power. Therefore, the algorithm should compute the attitude of the IMUs and calibrate the magnetic sensor in real time with very low computational load, by maintaining only a valid subset of data points. Our experimental results indicate that the algorithm achieves sufficient levels of real-time computation and accuracy.

Predicting Virtual World User Population Fluctuations with Deep Learning.

This paper proposes a system for predicting increases in virtual world user actions. The virtual world user population is a very important aspect of these worlds; however, methods for predicting fluctuations in these populations have not been well documented. Therefore, we attempt to predict changes in virtual world user populations with deep learning, using easily accessible online data, including formal datasets from Google Trends, Wikipedia, and online communities, as well as informal datasets collected from online forums. We use the proposed system to analyze the user population of EVE Online, one of the largest virtual worlds.

Efficiently detecting outlying behavior in video-game players

In this paper, we propose a method for automatically detecting the times during which game players exhibit specific behavior, such as when players commonly show excitement, concentration, immersion, and surprise. The proposed method detects such outlying behavior based on the game players’ characteristics. These characteristics are captured non-invasively in a general game environment. In this paper, cameras were used to analyze observed data such as facial expressions and player movements. Moreover, multimodal data from the game players (i.e., data regarding adjustments to the volume and the use of the keyboard and mouse) was used to analyze high-dimensional game-player data. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70%. The proposed method can also be used for feedback analysis of various interactive content provided in PC environments.

Line recognition algorithm for 3D polygonal model using a parallel computing platform

Line recognition-based rendering technique has been used effectively for shape transmission of 3D polygon model. Line recognition is defined by multifarious forms and characteristics of lines, and has been a fundamental key point in expressing shape of 3D polygon model in non-photorealistic rendering technique. Line recognition, however, requires a long period of calculation time and thus, various methods have been studied to accelerate the speed of the operation. This paper presents a new method that will accelerate the overall operation compared to the standard CPU-based method of extracting ink line. The new method will enhance the efficiency of the calculation speed by applying the parallel processing technique CUDA (Compute Unified Device Architecture) to the complex processes that consume a lot of time such as implicit surface calculation and feature point extraction. The overall performance will be tested and verified through various types of experiments with 3D polygon model.

Analyzing repetitive action in game based on sequence pattern matching

As games become more popular, procedures which can support the analysis and understanding of players’ behaviors are necessary for success of commercial games. This paper presents a log-based usability evaluation system to analyze user behavior in a gaming environment. We explore the potential of input log data for automated usability evaluation and visualization of player behavior in a game. We traced the keyboard input value and mouse movement of users using a sequence data mining technique in a gaming environment. And we also constructed 3D body meshes for the behavior analysis using Kinect interface. We visualized the data obtained by tracing and automatically searched repetitive patterns in the game and analyzed them. The result obtained from the analysis can be used for user interface optimization, fun evaluation, and the bot-detection field.

Virtual ball player

It is very difficult and tedious work to synthesize an animation in which a character skillfully controls several balls. This is because all the virtual balls need to be synchronized with the motion of the character temporally and spatially as following the laws of physics. Moreover, a skillful actor is needed for capturing the motion. We introduce a simple but interesting method such that anyone can synthesize an animation of skillful ball-handling motion using interaction patterns without any actual ball. Interaction patterns involve regularly repeated human motions to control the virtual ball. We first capture the motion that mimics controlling a ball using various interaction patterns. Then we synthesize the trajectory of a virtual ball by analyzing the captured motion and correct the character motion to be fitted to the synthesized trajectory of a virtual ball. Experiments convincingly show the usefulness of proposed technique by synthesizing various ball-handling animations.