Kwan-Hee Yoo

Chungbuk National University · Department of Software Engineering

In the domain of agricultural product sales and consumption forecasting, the presence of infrequent yet impactful events such as livestock epidemics and mass media influences poses substantial challenges. These rare occurrences, termed Sparse Critical Events (SCEs), often lead to predictions converging towards average values due to their omission f...

This code is an implementation of this paper (Jong-Sung Ha and Kwan-Hee Yoo, Approximating Centroids for the Maximum Intersection of Spherical Polygons, Computer-Aided Design, Vol. 37(8), 2005). Especially, the member function "void S2::IntersectTwoVM(int i, int j)" js just an implementation of the spherical edge advancing rules of the reference [1...

Ensuring the quality of color contact lenses is vital, particularly in detecting defects during their production since they are directly worn on the eyes. One significant defect is the “center deviation (CD) defect”, where the colored area (CA) deviates from the center point. Measuring the extent of deviation of the CA from the center point is nece...

Object detection is a constantly evolving field of interest in the field of computer vision. As image-processing technologies continue to advance, detecting small objects has emerged as a critical challenge. However, currently available algorithms still struggle with this task owing to the small flaws in detection and complex backgrounds. This pape...

Big data have become a core technology to provide innovative solutions in numerical applications and services in many fields [...]

In the manufacturing industry, the process capability index (Cpk) measures the level and capability required to improve the processes. However, the Cpk is not enough to represent the process capability and performance of the manufacturing processes. In other words, considering that the smart manufacturing environment can accommodate the big data co...

Power is essential in nonferrous arc furnace plants for burning and melting scraps, as well as for the composition of raw materials to produce the furnace product. To ensure high-quality operation, the electric energy is controlled by changing the tap positions. However, there is no standard working pattern to determine the most effective option fo...

Product quality is a major concern in manufacturing. In the metal processing industry, low-quality products must be remanufactured, which requires additional labor, money, and time. Therefore, user-controllable variables for machines and raw material compositions are key factors for ensuring product quality. In this study, we propose a method for g...

Our research intends to distinguish the variety of soiling on PV panels for solar energy systems based on natural and environmental factors. A convolutional neural network (CNN), a powerful method for image classification in computer vision, is set out with a nine-layer to classify panel images in the training. The dataset splits into categories th...

In this paper we demonstrate the threshold effects of infectious diseases on livestock prices. Daily retail prices of pork and chicken were used as structured data; news and SNS mentions of African Swine Fever (ASF) and Avian Influenza (AI) were used as unstructured data. Models were tested for the threshold effects of disease-related news and SNS...

Knowing the prices of agricultural commodities in advance can provide governments, farmers, and consumers with various advantages, including a clearer understanding of the market, planning business strategies, and adjusting personal finances. Thus, there have been many efforts to predict the future prices of agricultural commodities in the past. Fo...

In modern manufacturing, the detection and prediction of machine anomalies, i.e., the inactive state of the machine during operation, is an important issue. Accurate inactive state detection models for factory machines can result in increased productivity. Moreover, they can guide engineers in implementing appropriate maintenance actions, which can...

In data mining or machine learning, one of the most commonly used feature extraction techniques is principal component analysis (PCA). However, it performs poorly on a large dataset. In this paper, we propose a new method of accelerating conventional PCA, named hash-tree PCA. It samples the objects that are similar to each other without losing the...

This paper is concerned with techniques for directly embedding moving objects in the real world into 360° virtual reality scenes captured by 360° camera, DSLR camera, smartphone, and others. For more natural embedding, we present a cylindrical mapping methodology based on a proposed international standard model for mixed and augmented reality, in w...

OPTICS is a state-of-the-art algorithm for visualizing density-based clustering structures of multi-dimensional datasets. However, OPTICS requires iterative distance computations for all objects and is thus computed in O ( n 2 ) time, making it unsuitable for massive datasets. In this paper, we propose constrained OPTICS (C-OPTICS) to quickly creat...

This paper presents a web-based three-dimensional (3D) navigation system for a spinal disease ontology using a 3D virtual human spine. The 3D navigation system consists of three main modules: a query module for finding spinal diseases and their causes and treatments from the spinal disease ontology via a web page, a 3D rendering module for renderin...

A methodical modeling of human respiratory organ is created by using the respiratory modeling architecture (RMA) of the scene-graph of H-Anim structure. H-Anim follows an X3D file format to construct the modeling features for the level of detail of a complex human respiratory organs including structures, inner surfaces, and the lungs. The respirato...

The large amount of programmable logic controller (PLC) sensing data has rapidly increased in the manufacturing environment. Therefore, a large data store is necessary for Big Data platforms. In this paper, we propose a Hadoop ecosystem for the support of many features in the manufacturing industry. In this ecosystem, Apache Hadoop and HBase are us...

Clustering is a typical data mining technique that partitions a dataset into multiple subsets of similar objects according to similarity metrics. In particular, density-based algorithms can find clusters of different shapes and sizes while remaining robust to noise objects. DBSCAN, a representative density-based algorithm, finds clusters by definin...

In this paper, we propose a visualizing method that facilitates the 3D model representation using menu with level categories. With the implementation of the organs modeling method, the 3D internal respiratory tracts are incredibly separated into the various organs of both upper and lower regions based on function or anatomy. These regions are appli...

In modern society, various forms of crime are constantly occurring. Accordingly, several safe-return systems for the socially vulnerable are being developed. However, those systems are mainly focused on responding to dangerous situations that have already occurred, and they do not predict the possibility of crime reflected by information about the...

Digital textbooks (DTs) have been established as the major media for future and smart education in South Korea. In general, DTs are implemented using two-dimensional (2D) web-based platforms with embedded 3D content, including images, motion graphics, animations, and video and audio. Recently, these 2D-based DTs have evolved into a 3D-based interfa...

This proposed method aims to facilitate the current problem in the manufacturing industry of data streaming and processing of sensing data. In our implementation, Apache Kafka cluster is carried out as real-time data transmission from PLCs (Programmable Logic Controllers) to a database server which Apache Kafka performed multiple tasks simultaneous...

In this paper, we present an interactive pseudo-holographic rendering of 3D scanned model with respect to a physical object by using the 3D scanner, pyramid pseudo-holographic projector, and Leap Motion sensor. The pseudo-holographic rendering is referred to a technique for projecting 3D objects to display in mid-air by using the pseudo-holographic...

A 3D scanner can be used to analyze a real-world object and collect the spatial location of points of its shape that can be used for constructing a 3D model. In this paper, we propose a system for a physical object in the real world to reconstruct as a 3D model and use it for interactive pseudo-holographic rendering. We use a pocket 3D scanner for...

Live actor and entity refers to a representation of a living physical object such as human being who portrays a character in a performance that can move and interact with virtual objects in virtual reality. Most systems have used the method for embedding objects especially live actor and entity into virtual reality scene by mapping with a bounding...

A mobile three-dimensional image acquisition and reconstruction system using a computer-generated integral imaging technique is proposed. A depth camera connected to the mobile device acquires the color and depth data of a real object simultaneously, and an elemental image array is generated based on the original three-dimensional information for t...

Virtual reality (VR) walking tour refers to a virtual tour which means feeling imaginary world rather than the real one. The imaginary world is a simulation running on high-end devices such as computer or smartphone. VR technology continues to increase and involve in many applications. In this paper, we discuss and propose a navigation control of v...

R-tree is index structure which is frequently used for handling spatial data. However, if the number of dimensions increases, or if only partial dimensions are used for searching the certain data according to user preference, the time for indexing is greatly increased and the efficiency of the generated R-tree is greatly reduced. Hence, it is not s...

Most existing authoring tool for virtual reality are related to the virtual objects and the 3D environment. Different from various authoring tools, our research is focusing on virtual reality walking tour. The virtual reality walking tour refers to a virtual tour which means feeling an imaginary world of the real place rather than the real one. The...

In the image handling and image processing areas, most operations can be executed in a pixel-by-pixel or cluster-by-cluster manner. These parallel and simultaneous executions have many benefits, and many researchers showed remarkable improvements. In this paper, we started from a specific and practical image handling and feature extraction sequence...

An integral imaging system using a polygon model for a real object is proposed. After depth and color data of the real object are acquired by a depth camera, the grid of the polygon model is converted from the initially reconstructed point cloud model. The elemental image array is generated from the polygon model and directly reconstructed. The pol...

Web 3D technology can be used to simulate the experiments of scientific, medical, engineering and multimedia visualization. On the web environment, 3D virtual reality can be accessed well without strictly on operating system, location and time. Virtual Reality (VR) is used to depict a three-dimensional, computer generated realistic images, sound an...

Mixed and augmented reality (MAR) refers to a spatially coordinated combination of media/information components that represent on the real world and its objects, and on the other those that are virtual, synthetic and computer generated including any combination of aural, visual and touch. The extensible 3D (X3D) is the ISO standard for defining 3D...

This paper investigates the relation between Chief Executive Officers (CEO) career concerns and voluntary disclosures using listed firm (KOSPI) data in Korea. Prior research suggests that explicit incentives in the form of CEO stock-based compensation or CEO’s equity ownership mitigate the agency problems of reluctance to make voluntary disclosure....

Virtual Reality (VR) is used to describe a three-dimensional, computer generated realistic images, sound and other sensations to replicate a real environment or an imaginary setting which can be explored and interacted with by a person. That person is immersed within virtual environment and is able to manipulate objects or perform a series of actio...

We produced an adaptive lens array composed of multiple flat lens arrays arranged in a curved shape with an adjustable radius of curvature, in order to overcome the hardware problem of the conventional flat or curved lens array-based systems. The manufactured adaptive lens array is applied to an integral imaging system. The gap mismatch that occurs...

Mobile three-dimensional image acquisition and reconstruction system is proposed. When the server transmits the real scene’s depth and color data to the mobile device, the elemental images are generated, and directly reconstructed as three-dimensional images through a lens array or computer-generated reconstruction.

This paper presents a new method for detecting tool breakages at CNC machines in real time. Corruptions of CNC tools in the manufacturing industry are a major impact on production management and quality control in the factories maintaining large quantities of CNC machines. Accordingly, from the viewpoint of an equipment management, monitoring damag...

The continuous optimization of manufacturing processes is important to achieve a success on the market. Once analyzed, the data, collected from various manufacturing resources, can reveal the useful knowledge. We can use this knowledge for the optimization of manufacturing process. However, due to the massive amount of data, discovering the knowled...

Action recognition technology has many application fields including gaming, human-computer interaction, security, virtual reality, etc. The technology has recently advanced and simplified by the introduction of real time depth cameras. The most famous depth camera, Kinect, has shown its success in human action recognitions by supervised learning me...

Extensible 3D (X3D) is the ISO standard for defining 3D interactive web- and broadcast-based 3D content integrated with multimedia. With the advent of this integration of interactive 3D graphics into the web, users can easily produce 3D scenes within web contents. Even though there are diverse texture nodes in X3D, projective textures are not provi...

We present efficient algorithms for computing centroid directions for each of the three types of monotonicity in a polyhedron: strong, weak, and directional monotonicity, which can be used for optimizing directions in many 3D manufacturing processes. Strongly- and directionally-monotone directions are the poles of great circles separating a set of...

Mixed and augmented reality technique deals with mixing content between real world and virtual world containing augmented reality and augmented virtuality excluding of pure real and pure virtual world. In mixed and augmented reality, if a live actor and entity moving in real world can be embedded more naturally in 3D virtual world, various advanced...

Road safety is main concern of South Korean government, as in 2010–2015, car accidents took around 25,000 people lives. It is important to understand the reasons behind these accidents in order to prevent them from happening. In this short paper, we propose to statistically measure the factors that influence on road accidents in South Korea. Specif...

The growing availability of information technologies has enabled law enforcement agencies to collect detailed data about various crimes. However, the volume of crime has made the process of searching and finding the useful information from the crime data difficult. In this paper, we propose an ontology-based approach for searching the knowledge in...

Recently, several accidents have occurred in South Korean military barracks that caused a social concern. In this paper, we argue that these accidents can be prevented. Specifically, we describe an ongoing project that applies well-known data mining techniques to predict accidents in military barracks in South Korea. For this, we first collect vari...

Recently, Image processing has been used in many areas. In the image processing techniques that a lot of research is tracking of moving object in real time. There are a number of popular methods for tracking an object such as HOG(Histogram of Oriented Gradients) to track pedestrians, and Codebook to subtract background. However, object extraction h...

The adoption of manufacturing big data system (MBDS) is anticipated to enhance the competitiveness of small and medium-sized manufacturing firms (SMMFs), as massive amount of big data proliferate in the field of manufacturing industries. Several professionals argue that it is necessary to take an attentive approach in designing appropriate MBDS for...

This paper designs a flexible method for modeling manufacturing processes in big data environment. The purpose of the study is to design a modeling tool broadly used in various manufacture industry areas. To support the functionalities, we provide types of the process symbols, which can be used to facilitate convenient design for process modeling,...

In this paper we introduce a digital hologram generation of a real object captured by depth camera. The depth camera is employing a time multiplexed concept for color and depth image acquisition in a single chip sensor. The 3D information, point cloud, corresponding to the real scene, is extracted from taken image pairs, a gray texture and a depth...

In modern society, various forms of crime are constantly occurring. Accordingly, several safe-return systems for the socially vulnerable are being developed. However, those systems are mainly focused on responding to dangerous situations that have already occurred, and they do not predict the possibility of crime reflected by information about the...

Geographical features, geometric objects, and even moving objects in the spatial database should be interactively represented on the computer screens, typically through spatial data visualization system. In this paper, we assume that the 3D spatial objects, moving objects and their network data are totally stored into the main-memory DBMS (database...

The Korean Institute of Science and Technology Information (KISTI) has recently constructed a spinal disease ontology, in cooperation with the Catholic University of Korea, to establish a simulation model to support the diagnosis of age-related spinal disorders. Here we present a web-based three-dimensional (3D) navigation system for this spinal di...

This paper looks into the chronic-diseases that gradually seek more necessity of management in our society, and let the patient take care of his/her disease by him/herself through analyzing and visualizing the disease-data. We propose a hybrid app service which is provided to the patient with more systematic management and effective service develop...

KISTI is carrying out an e-Spine project for spinal diseases to prepare for the aged society, so-called NAP. The purpose of the study is to build a spine ontology that represents the anatomical structure and disease information which is compatible with simulation model of KISTI. The final use of the ontology includes diagnosis of diseases and setti...

Integral imaging display using an adaptive lens array which provides with the flat and curved lens array-based systems is proposed. GPU parallel processing is applied for the real-time display. By the experiment, adaptive lens array-based novel real-time integral imaging display has been demonstrated.

Integral imaging display using an adaptive lens array which provides with the flat and curved lens array-based systems is proposed. GPU parallel processing is applied for the real-time display. By the experiment, adaptive lens array-based novel real-time integral imaging display has been demonstrated.

With the development of mobile devices and Internet, information exchange has actively been made through SNS and Blogs. Blogs are widely used as a space where people share their experience after their visit to tourist attractions. We propose a method of recommending associated tourist attractions based on tourists` opinions using issue analysis, as...

Due to the limitations of micro lens arrays and camera sensors, images on display devices through the integral imaging microscope systems have been suffering for a low-resolution. In this paper, a resolution-enhanced orthographic-view image display method for integral imaging microscopy is proposed and demonstrated. Iterative intermediate-view reco...

This paper proposes and defines four eXtensible 3-dimensional (X3D) nodes to render real-world characters such as human being and animals in 3D virtual environments, which conform to the X3D standard format for representing and rendering real-world characters in virtual spaces, aiming to make them available as an extension of the X3D core nodes. Se...

A novel 360-degree integral-floating display based on the real object is proposed. The general procedure of the display system is similar with conventional 360-degree integral-floating displays. Unlike previously presented 360-degree displays, the proposed system displays the 3D image generated from the real object in 360-degree viewing zone. In or...

With an increasing number of users having more than one smart device, an environment for delivering the same content through multiple devices has been established via wired and wireless network connections. Consequently, online education services that have provided content on one device screen by dividing it into multi pieces have changed to provid...

The use of smart mobile devices has grown considerably in recent years. A large variety of digital content has entered the market and, in particular, there has been rapid growth in sales of electronic books (e-books). Consequently, demand for more diverse digital content has increased greatly as has the demand, in particular, for smart digital cont...

SETTING: A novel effective treatment is necessary for severe asthma.OBJECTIVE: To review clinical trials examining the role of tiotropium in patients with poorly controlled asthma despite inhaled corticosteroid use with or without long-acting β2-agonists.DESIGN: A computerised search of electronic databases (Medline, EMBASE and Cochrane Central Reg...

An enhanced 360-degree integral-floating three-dimensional display system using a hexagonal lens array and a hidden point removal operator is proposed. Only the visible points of the chosen three-dimensional point cloud model are detected by the hidden point removal operator for each rotating step of the anamorphic optics system and elemental image...

Generally, integral image used for autostereoscopic 3d display is generated for flat lens array, but flat lens array cannot provide a wide range of view for generated integral image because of narrow range of view. To make up for this flat lens array`s weak point, curved lens array has been proposed, and due to technical and cost problem, approxima...

With the reformation of organization and function of local office of education in 2010, consulting-supervision is introduced to schools as a system for education reform to improve the quality of school education. However, a dedicated on-line portal system that can provide integrated management on the functionalities of consulting-supervision has no...

A real-time interactive orthographic-view image display of integral imaging (II) microscopy that includes the generation of intermediate-view elemental images (IVEIs) for resolution enhancement is proposed. Unlike the conventional II microscopes, parallel processing through a graphics processing unit is required for real-time display that generates...

A real-time interactive orthographic-view image display of integral imaging (II) microscopy that includes the generation of intermediate-view elemental images (IVEIs) for resolution enhancement is proposed. Unlike the conventional II microscopes, parallel processing through a graphics processing unit is required for real-time display that generates...