LabVIEW coding for video dehazing was developed. The dark channel prior proposed by K. He was applied to remove fog based on a single image, and K. B. Gibson's median dark channel prior was applied, and implemented in LabVIEW. In other words, we improved the image processing speed by converting the existing fog removal algorithm, dark channel prior, to the LabVIEW system. As a result, we have developed a real-time fog removal system that can be commercialized. Although the existing algorithm has been utilized, since the performance has been verified real - time, it will be highly applicable in academic and industrial fields. In addition, fog removal is performed not only in the entire image but also in the selected area of the partial region. As an application example, we have developed a system that acquires clear video from the long distance by connecting a laptop equipped with LabVIEW SW that was developed in this paper to a 100~300 times zoom telescope.

Lip reading is a field of image processing to assist the process of sound recognition. In some environment, the capture of sound signal usually has significant noise and therefore, the recognition rate of sound signal decreases. Lip reading can be a good feature for the increase of recognition rates. Conventional lip extraction methods have been proposed widely. Maia et. al. proposed a method by the sum of Cr and Cb. However, there are two problems as follows: the point with maximum saturation is not always regarded as lips region and the inner part of lips such as oral cavity and teeth can be classified as lips. To solve these problems, this paper proposes a method which adopts the histogram-based classifier for the extraction of lips region. The proposed method consists of two stages, learning and test. The amount of computation is minimized because this method has no color conversion. The performance of proposed method gives 66.8% of detection rate compared to 28% of conventional ones.

For many stroke patients undergoing rehabilitation therapy, there is a need for indicator for evaluating the body function in paretic and non-paretic regions of stroke patients quantitatively. In this paper, the function of muscles and cells in paretic and non-paretic regions of severe and mild hemiplegic stroke patients was evaluated using multi-channel bioelectrical impedance spectroscopy. The paretic and non-paretic regions of severe and mild stroke patients were quantitatively assessed by using bioelectrical impedance parameters such as prediction marker (PM), phase angle (${\theta}$), characteristic frequency ($f_c$), and bioelectrical impedance vector analysis (BIVA). The mean values of impedance vector were significantly discriminated in all comparisons (severe-paretic, severe-non-paretic, mild-paretic, and mild-non-paretic). The bioelectrical impedance parameters were proved to be a very valuable tool for quantitatively evaluating the paretic and non-paretic regions of hemiplegic stroke patients.

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines. Generally, it is very difficult to diagnose a machine fault by conventional methods based on mathematical models because of the complexity of the real world systems and the obvious existence of nonlinear factors. This study develops an automatic machine fault diagnosis system that uses pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The sounds emitted by the operating machine, a drill in this case, are obtained and analyzed for the different operating conditions. The specific machine conditions considered in this research are the undamaged drill and the defected drill with wear. Principal component analysis is first used to reduce the dimensionality of the original sound data. The first principal components are then used as the inputs of a neural network based classifier to separate normal and defected drill sound data. The results show that the proposed PCA-ANN method can be used for the sounds based automated diagnosis system.

Among the technologies for implementing autonomous vehicles, advanced driver assistance system is a key technology to support driver's safe driving. In the technology using the vision sensor having a high utility, various preprocessing methods are used prior to feature extraction for lane detection. However, in the existing methods, the unnecessary lane candidates such as cars, lawns, and road separator in the road area are false positive. In addition, there are cases where the lane candidate itself can not be extracted in the area under the overpass, the lane within the dark shadow, the center lane of yellow, and weak lane. In this paper, we propose an efficient preprocessing method using k-means clustering for image division and the HSV color model. When the proposed preprocessing method is applied, the true positive region is maximally maintained during the lane detection and many false positive regions are removed.

Today, weather radar is used as a key tool for modern high-tech weather observations and forecasts, along with a wide variety of ground gauges and weather satellites. In this paper, we propose a frequency transform based weather radar image processing technique to improve the weather radar image damaged by beam blocking and clutter removal in order to minimize the uncertainty of the weather radar observation. In the proposed method, DCT based mean energy correction is performed to improve damage caused by beam shielding, and DWT based morphological image processing and high frequency cancellation are performed to improve damage caused by clutter removal. Experimental results show that the application of the proposed method to the damaged original weather radar image improves the quality of weather radar image adaptively to the weather echo feature around the damaged area. In addition, radar QPE calculated from the improved weather radar image was also qualitatively confirmed to be improved by the damage. In the future, we will develop quantitative evaluation scales through continuous research and develop an improved algorithm of the proposed method through numerical comparison.

There are various algorithms evaluating a threshold for image segmentation. Among them, Otsu's algorithm sets a threshold based on the histogram. It finds the between-class variance for all over gray levels and then sets the largest one as Otsu's optimal threshold, so we can see that Otsu's algorithm requires a lot of the computation. In this paper, we improved the amount of computational needs by using estimated Otsu's threshold rather than computing for all the threshold candidates. The proposed algorithm is compared with the original one in computation amount and accuracy. we confirm that the proposed algorithm is about 29 times faster than conventional method on single processor and about 4 times faster than on parallel processing architecture machine.

Biometric recognition is one of the major challenging topics which needs high performance of recognition accuracy. Most of existing methods rely on a single source of biometric to achieve recognition. The recognition accuracy in biometrics is affected by the variability of effects, including illumination and appearance variations. In this paper, we propose a new multimodal biometrics recognition using convolutional neural network. We focus on multimodal biometrics from face and periocular regions. Through experiments, we have demonstrated that facial multimodal biometrics features deep learning framework is helpful for achieving high recognition performance.

The fourth industrial revolution is a phenomenon where productivity is improved in each field by the convergence of IT technology and existing industries. In the dental treatment process, prosthetic treatment time is drastically shortened through AI and expert software. Oral imaging, prosthesis design, and prosthesis manufacturing are performed continuously, so the treatment can be completed in a few hours. In this paper, we introduce the research trend of multimedia technology in the prosthetic process. We also propose a new method for accelerating the fusion of surface data during the optical impression. Proposed method enables high-speed optical impression and accelerates the overall automated production process of dental prosthesis.

The paper presents a histogram equalization method using the edge information of an image to be processed. The basic idea of this method is to carry out histogram equalization with edge information, which is important and essential for object conformation. In the proposed method, the edge information is used to generate histogram for the equalization process. It is found to be effective to suppress the histogram spikes that cause quantum jumps in mapping function for the equalization process. The proposed method is tested for randomly selected 30 images and compared to conventional approaches with a quantitative measure to check it preserves the structural similarity. Experimental results show that the proposed method has better performance and no artifacts caused by histogram spikes.

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

The brain magnetic resonance images (MRI) is an important imaging biomarker in Alzheimer's disease (AD) as the cerebral atrophy has been shown to strongly associate with cognitive symptoms. The decrease of volume estimates in different structures of the medial temporal lobe related to memory correlates with the decline of cognitive functions in neurodegenerative diseases. During the past decades several methods have been developed for quantifying the disease related atrophy of hippocampus from MRI. Special effort has been dedicated to separate AD and mild cognitive impairment (MCI) related modifications from normal aging for the purpose of early detection and prediction. We trained a multi-class support vector machine (SVM) with probabilistic outputs on a sample (n = 58) of 20 normal controls (NC), 19 individuals with MCI, and 19 individuals with AD. The model was then applied to the cross-validation of same data set which no labels were known and the predictions. This study presents data on the association between MRI quantitative parameters of hippocampus and its quantitative structural changes examination use on the classification of the diseases.

Abnormal situation caused by aggressive behavior of pigs adversely affects the growth of pigs, and comes with an economic loss in intensive pigsties. Therefore, IT-based video surveillance system is needed to monitor the abnormal situations in pigsty continuously in order to minimize the economic demage. Recently, some advances have been made in pig monitoring; however, detecting each pig is still challenging problem. In this paper, we propose a new color image-based monitoring system for the detection of the individual pig using a fast region-based convolution neural network with consideration of detecting touching pigs in a crowed pigsty. The experimental results with the color images obtained from a pig farm located in Sejong city illustrate the efficiency of the proposed method.

Line-laser beams are used for accurate measurement of 3D shape, which is robust to external illumination. For depth measurement, we project a line-laser beam across an object from the face and take an image of the beam on the object surface using a CCD camera at some angle with respect to the face. For shape measurement, we project parallel line-laser beams with narrow line to line distance. When a layer of thin materials attached to a cylinder is long narrow along its circumference, we can measure the shape of the layer with a small number of parallel line beams if we project line beams along the circumference of the cylinder. Measurement of the depth of the attached materials on a line-laser beam is based on the number of pixels between an imaginary line along the imaginary cylinder without the attached materials and the beam line along the materials attached to the cylinder. For this we need to localize the imaginary line in the captured image. In this paper, we model the shape of the line as an ellipse and localize the line with least square estimate. The proposed method results in smaller error (maximum 0.24mm) than a popular 3D depth camera (maximum 1mm).

With the development of smartphone technologies enable photoplethysmogram (PPG) acquisition by camera and heart rate (HR) measurement. This papers presents improved algorithm to extract HR from PPG signal recorded by smartphone camera and to develop real-time PPG signal processing Android application. 400 video samples recorded by Samsung smartphone camera are imported as input data for further processing and evaluating algorithm on MATLAB. An optimized algorithm is developed and tested on Android platform with different kind of Samsung smartphones. To assess algorithm's performance, medical device Beurer BC08 is used as reference. According to related works, accuracy parameters includes 90% number of samples that has relative errors less than 5%, Person correlation (r) more than 0.9, and standard estimated error (SEE) less than 5 beats-per-minutes (bpm).

Reversible DNA watermarking is capable of continuous DNA storage and forgery prevention, and has the advantage of being able to analyze biological mutation processes by external watermarking by iterative process of concealment and restoration. In this paper, we propose a reversible DNA watermarking method based on histogram multiple shifting of noncoding DNA sequence that can prevent false start codon, maintain original sequence length, maintain high watermark capacity without biologic mutation. The proposed method transforms the non-coding region DNA sequence to the n-th code coefficients and embeds the multiple bits of the n-th code coefficients by the non-recursive histogram multiple shifting method. The multi-bit embedding process prevents the false start codon generation through comparison search between adjacent concealed nucleotide sequences. From the experimental results, it was confirmed that the proposed method has higher watermark capacity of 0.004-0.382 bpn than the conventional method and has higher watermark capacity than the additional data. Also, it was confirmed that false start codon was not generated unlike the conventional method.

Data packets from sensor nodes scattered over measuring fields are generally forwarding to the sink node, which may be connected to the wired networks, in a wireless sensor network. So many data packets are gathered near the sink node, resulting in significant data packet collisions and severe transmission latency. In an event detection application such as object tracking and military, bursty data is generated when an event occurs. So many data packet should be transmitted in a limited time to the sink node. In this paper, we present a delay efficient and bursty traffic friendly MAC protocol called DEBF-MAC protocol for wireless sensor networks. The DEBF-MAC uses a slot-reserved mechanism and sleep period control method to send multiple data packets efficiently in an operational cycle time. Our simulation results show that DEBF-MAC outperforms DW-MAC and SR-MAC in terms of energy consumption and transmission delay.

Data hiding is a way to hide the information in multimedia media such as images or video. The scheme proposed by Nguyen and Chang, was able to embed, extract, and restore the cover image and the secret data using Sudoku. But in the extracting phase, the occurrence of duplicate values in the reference matrix was found to decrease the embedding capacity of secret data. This paper has proposed a reversible data hiding scheme while maintaining the quality of the image to provide high embedding capacity using $7{\times}7$ Sudoku and Shamir's secret sharing scheme.

This paper introduces a user-friendly PLC (programmable logic controller) monitoring and control system of heavy machinery using Android based smartphone. The proposed system will control diesel generator and many such like machine without a dedicated PC with respect to similar system and offers a new communication protocol for handling it. The smartphone controls the generator via Wi-Fi, through which it connects to the Raspberry pi which will be installed in the PLC panel to setup the communication between them. Furthermore, Raspberry pi connects to two devices, one is PLC which gives the status and current information of the machine and to ON/OFF the machine. This proposed system used RS485 as a key mediator for data exchanging between Raspberry PI(master) and PLC(slave). RS485 allows multiple devices (up to 32) to communicate at half duplex on single pair of wires and provides a long connectivity area (up to 1200 meters) as compared to another device. This proposed system specially focused on accurate data flow between smartphone and PLC panel.

Nowadays, nations cyber security capabilities play an important role in a nation's defense. Security-critical infrastructures such as national defenses, public services, and financial services are now exposed to Advanced Persistent Threats (APT) and their resistance to such attacks effects the nations stability. Currently Cyber Threat Intelligence (CTI) is widely used by organizations to mitigate and deter APT for its ability to proactively protect their assets by using evidence-based knowledge. The evidence-based knowledge information can be exchanged among organizations and used by the receiving party to strengthen their cyber security management. This paper will discuss on the business process reengineering of the CTI information exchange management for a nationwide scaled control and governance by the government to better protect their national information security assets.

When implementing a hardware elliptic curve cryptosystem (ECC) module, the efficient design of Modular Inverse (MI) algorithm is especially important since it requires much more computation than other finite field operations in ECC. Among the MI algorithms, binary Right-Shift modular inverse (RS) algorithm has good performance when implemented in hardware, but Montgomery Modular Inverse (MMI) algorithm is not considered in [1, 2]. Since MMI has a similar structure to that of RS, we show that the area-improvement idea that is applied to RS is applicable to MMI, and that we can improve the speed of MMI. We designed area- and speed-improved MMI variants as hardware modules and analyzed their performance.

The fourth industrial revolution is expected to show technological innovation that develops among different fields beyond boundaries through the convergence and integration of fields. With the development and convergence of digital technology, users can receive information anywhere in the world. In this paper, we propose an adaptive interaction concept in a various environment by using a mobile robot based on projection augmented reality (AR). Most previous studies have aimed fixed projector or projection for a pre-designed environment. Thus, they provide only limited information. To overcome the abovementioned problem, we provide the adaptive information by implementing a projection AR system that can be mounted on the mobile robot. For that, the mobile robot based on the projection system was defined as Pervasive AR. Pervasive AR is configured with a pervasive display, a pervasive interface, and seamless interaction. The Pervasive AR technology enables the user to access information immediately by expanding the display area into real space, which implies an environment of intuitive and convenient interaction by expanding the user interface. This system can be applied to various areas, such as a home environment and a public space.

The emergence of E-book have allowed readers to interact with other readers and to actively participate (e.g. social reading). Furthermore, there is a growing demand in writer's community to take the advantage of the feedback from their readers to update the content of E-book. To do that, they require the service that utilizes the user feedback while creating or updating the e-book content. This study aims to let authors collect and to apply the reader's feedback on E-book content. However, in order to apply the user feedback, users first need to explicitly type the feedback, and even if they do, authors need to develop the software to automatically analyze and to apply the user feedback. This makes difficult for authors without programming background to produce E-book with automatic content adaptation. In this paper, we propose Feedback Clue Model to generate, analyze and apply the user feedback into E-book content. Based on this model, we develop the block editor which allows easy implementation of E-book that can be dynamically updated.

Recently, the importance of personalized healthcare(wellness) services is increasing in the era of the 4th Industrial Revolution. However, the authoring of wellness contents fused with variety of contents and the study of the system which provides the customized recommendation are insufficient. In this paper, we proposes the recommendation service system for the customized convergence wellness contents. The proposed system makes to the wellness contents by the existing cultural/tourism/leisure contents and recommends the customized wellness contents based on a user's profile and the situation information such as location and weather. The proposed systems is expected to contribute to designing the innovative and new service models for the tailored wellness content.

We have heard about several keywords of the fourth industrial revolution such as automation, artificial intelligence and connectivity. And electronic publishing systems and ebooks will enable us to experience a new industrial revolution without discrimination. On that level, it is necessary to study a method of automatic accessibility tool for electronic publishing. There are some studies on accessibility standard specifications, accessibility guidelines, and accessibility certificate criteria. but there is little research about automatic inspection tools in electronic publishing area. This paper proposed a library for accessibility inspector of EPUB and its components based on IDPF EPUB accessiblity guidelines and TTA accessibility certificate criteria for reading disabled people. After implementing the library that can be connected to SIGIL, which is the most widely used in Korea, we verified its functionality and its coverage with Korean commercial EPUB files.

We propose a real time personalized recommendation algorithm on the mobile device. We use a unified collaborative filtering with reduced data. We use Fuzzy C-means clustering to obtain the reduced data and Konohen SOM is applied to get initial values of the cluster centers. The proposed algorithm overcomes data sparsity since it extends data to the similar users and similar items. Also, it enables real time service on the mobile device since it reduces computing time by data clustering. Applying the suggested algorithm to the MovieLens data, we show that the suggested algorithm has reasonable performance in comparison with collaborative filtering. We developed Android-based smart-phone application, which recommends restaurants with coupons and restaurant information.

In this paper, we propose the obstacle database management module for obstacle estimation and clustering. The proposed G-eye manager system can create customized walking route for blind people using the UI manager and verify the coordinates of the path. Especially, G-eye management system designed a regional information module. The regional information module can improve the loading speed of the obstacle data by classifying the local information by clustering the coordinates of the obstacle. In this paper, we evaluate the reliability of the walking route generated from the obstacle map. We obtain the coordinate value of the path avoiding the virtual obstacle from the proposed system and analyze the error rate of the path avoiding the obstacle according to the size of the obstacle. And we analyze the correlation between obstacle size and route by classifying virtual obstacles into sizes.

This paper proposes an algorithm for automatically converting and displaying rainfall radar data on a 3D GIS platform. The weather information displayed like rainfall radar data is updated frequently and large-scale. Thus, in order to efficiently display the data, an algorithm to convert and output the data automatically, rather than manually, is required. In addition, since rainfall data is extracted from the space, the use of the display image fused with the 3D GIS data representing the space enhances the visibility of the user. To meet these requirements, this study developed the Auto Data Converter application that analyzes the raw data of the rainfall radar and convert them into a universal format. In addition, Unity 3D, which has good development accessibility, was used for dynamic 3D implementation of the converted rainfall radar data. The software applications developed in this study could automatically convert a large volume of rainfall data into a universal format in a short time and perform 3D modeling effectively according to the data conversion on the 3D platform. Furthermore, the rainfall radar data could be merged with other GIS data for effective visualization.

Data assimilation is an initializing method for air quality forecasting such as PM10. It is very important to enhance the forecasting accuracy. Optimal interpolation is one of the data assimilation techniques. It is very effective and widely used in air quality forecasting fields. The technique, however, requires too much memory space and long execution time. It makes the PM10 air quality forecasting difficult in real time. We propose a fast optimal interpolation data assimilation method for PM10 air quality forecasting using a new kernel tridiagonal sparse matrix and CUDA massively parallel processing architecture. Experimental results show the proposed method is 5~56 times faster than conventional ones.

The performance of the statistical context-sensitive spelling error correction depends on the quality and quantity of the data for statistical language model. In general, the size and quality of data in a statistical language model are proportional. However, as the amount of data increases, the processing speed becomes slower and storage space also takes up a lot. We suggest the improved statistical language model to solve this problem. And we propose an effective spelling error candidate generation method based on a new statistical language model. The proposed statistical model and the correction method based on it improve the performance of the spelling error correction and processing speed.

Learning computational thinking is very important in programming education. Computational thinking refers to the problem solving ability based on the theories of computer science, indicating the importance of algorithm thinking. That is the reason for focusing on promoting creativity and improving the problem solving ability of the students in programming education. This paper commented the elements to consider for teachers when teaching computational thinking to elementary school students with online coding education website 'code.org' that helps beginners have easy programming experiences based on the characteristics of the website, and proposed the appropriate teaching methods.

In recent years, the use of touch screens has expanded, and devices such as remote controllers have been developed in various ways to control and access contents at long range. The wireless-based touch screen is used in classroom, seminar room, and remote video conversation in addition to the TV remote control. The purpose of the study is to design a smart phone-based intuitive interface that can perform the role of a wireless mouse and a wireless keyboard at range using Bluetooth and to develop an application that integrates functions of a mouse and a keyboard. Firstly, touch interaction model for controlling software such as PowerPoint by connecting to a general PC on a smart phone has been studied. The most simple touch operation interface is used to reproduce the function of existing devices and design more simply. The studies of the extension of interfaces with various functions are important, but development of optimized interfaces for users will become more important in the future. In this sense, this study is valuable.

This study is to examine how middle and high school students vary in terms of good and bad usage of online games and how these factors have varying effects on their use of the internet as a whole. My focus is to study their behavioral patterns individually while playing internet-based online games. The results are as follows: First, 260 out of 390 subjects used the internet. Male students who are high school students with siblings, or preschool time game users were revealed to play online games more often rather than female students who are middle school students with no siblings, or non-preschool time game users. Secondly, the analysis of differences of good and bad usage of online games revealed that there is a significant correlation between gender and beginning age. Lastly, a thorough analysis of the average difference in terms of following the online game shutdown found that there is no significant correlation among the sub-groups. However, an analysis of the difference of the problematic game usage has shown that there is a significant difference in the heavy user group. This findings means that the students who don't follow the online game shutdown spend more time than those who do.

In recent trends, the first age of digital device usage has been significantly getting low and the using frequencies for younger generation have been gradually increasing. Also, while there were more negative opinions of this trend in the past, the new idea is changing to more needs of training and approaches for children's sound using guidelines for digital device. In fact, people believe the new generation will face more advanced future, called the Fourth Industrial Revolution. The purpose of the paper is first to explain about the Jacques Lacan's concept of desire theory in order to understand the human's unconscious level through His desire theory. Second, the paper identifies how this unconscious level is affected to ethical aspects of new generations whose unconscious level are frequently and early exposed to digital media. Lastly, the paper will present the necessity of digital literacy education as well as future direction. Furthermore, the paper review for what is the ethics and positive guidelines of digital media for children who will become the future citizens in the era of the Fourth Industrial Revolution.

This study was attempted to improve the utilization of kiosk DID and to establish the production direction of the kiosk DID to be developed in the future, through analysis of kiosk DID user satisfaction at bus stop. This study showed that the satisfaction of the usability of the bus stop kiosk DID was high but in order to enhance the active use of kiosk DID and user satisfaction, unique and interesting content needs to be added and switched, not just simple information but content that users will immerse.