Multiple Sclerosis (MS) can be early diagnosed by detecting lesions in brain magnetic resonance images (MRI). Unsupervised anomaly detection methods based on autoencoder have been recently proposed for automated detection of MS lesions. However, these autoencoder-based methods were developed only for 2D images (e.g. 2D cross-sectional slices) of MRI, so do not utilize the full 3D information of MRI. In this paper, therefore, we propose a novel 3D autoencoder-based framework for detection of the lesion volume of MS in MRI. We first define a 3D convolutional neural network (CNN) for full MRI volumes, and build each encoder and decoder layer of the 3D autoencoder based on 3D CNN. We also add a skip connection between the encoder and decoder layer for effective data reconstruction. In the experimental results, we compare the 3D autoencoder-based method with the 2D autoencoder models using the training datasets of 80 healthy subjects from the Human Connectome Project (HCP) and the testing datasets of 25 MS patients from the Longitudinal multiple sclerosis lesion segmentation challenge, and show that the proposed method achieves superior performance in prediction of MS lesion by up to 15%.

AOI (Automatic Optical Inspection) of PCB (Printed Circuit Board) is a very important step to guarantee the product performance. The process of registering components called teaching mode is first perform, and AOI is then carried out in a testing mode that checks defects, such as recognizing and comparing the component mounted on the PCB to the stored components. Since most of registration of the components on the PCB is done manually, it takes a lot of time and there are many problems caused by mistakes or misjudgement. In this paper, A components classifier is proposed using YOLO (You Only Look Once) v2's object detection model that can automatically register components in teaching modes to reduce dramatically time and mistakes. The network of YOLO is modified to classify small objects, and the number of anchor boxes was increased from 9 to 15 to classify various types and sizes. Experimental results show that the proposed method has a good performance with 99.86% accuracy.

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

Currently, since the black-white QR (Quick Response) codes have limited storage capacity, color QR codes have been actively being studied. By multiplexing 3 colors, the color QR codes can allow the code capacity to be increased by three times, however, the color multiplexing brings about the possibility of crosstalk and noises in the acquisition process of the final image, incurring the decrease of bit-recognition rate. In order to improve the bit recognition rate, while keeping the storage capacity high, this paper proposes a new type of color QR code which uses the pattern information as well as the color information, and then analyzes how to increase the bit recognition rate. For this aim, the paper presents an efficient system which extracts embedded information from color QR code and then, through practical experiments, it is shown that the proposed color QR codes improves the bit recognition rate and are useful for commercial applications, compared to the conventional color codes.

Facial alignment is very important task for human life. And facial landmark detection is one of the instrumental methods in face alignment. We introduce the stacked hourglass networks with transposed convolutional layers for facial landmark detection. our method substitutes nearest neighbor upsampling for transposed convolutional layer. Our method returns better accuracy in facial landmark detection compared to stacked hourglass networks with nearest neighbor upsampling.

Tire wear and defect are important factors for safe driving condition. These defects are generally inspected by some specialized experts or very expensive equipments such as stereo depth camera and depth gauge. In this paper, we propose tire safety vision inspector based on deep neural network (DNN). The status of tire wear is categorized into three: 'safety', 'warning', and 'danger' based on depth of tire tread. We propose an attention mechanism for emphasizing the feature of tread area. The attention-based feature is concatenated to output feature maps of the last convolution layer of ResNet-101 to extract more robust feature. Through experiments, the proposed tire wear classification model improves 1.8% of accuracy compared to the existing ResNet-101 model. For detecting the tire defections, the developed tire defect detection model shows up-to 91% of accuracy using the Mask R-CNN model. From these results, we can see that the suggested models are useful for checking on the safety condition of working tire in real environment.

The shoulder is less stable than other joints, making it easier to onset of various shoulder disorders. In addition, limited range of motion and pain in the shoulder due to shoulder disorders restricts daily life and social activities. The problem with exercise therapy can be reduced in exercise effect by causing boredom through simple repetition of motion, thus reducing the patient's willingness to participate. Therefore, this paper aims to provide a treatment method that can induce active participation of patients by developing devices capable of passive, active, and resistance exercise and serious game contents using them. Furthermore, sEMG was used to verify whether the rotational exercise in the horizontal and vertical using serious game contents helps the shoulder movement actually. The measured sEMG signal was classified as 5 phases according to the angle of rotation and calculated the mean integrated EMG. The mean integrated EMG for the experimental results was higher in all phases when rotational was performed compared to those when both horizontal and vertical rotational exercise remained initial posture, indicating an increase in muscle activity.

Tempered electronic contents have multiplied in last few years, thanks to the emergence of sophisticated artificial intelligence(AI) algorithms. Deepfakes (fake footage, photos, speech, and videos) can be a frightening and destructive phenomenon that has the capacity to distort the facts and hamper reputation by presenting a fake reality. Evidence of ownership or authentication of digital material is crucial for combating the fabricated content influx we are facing today. Current solutions lack the capacity to track digital media's history and provenance. Due to the rise of misrepresentation created by technologies like deepfake, detection algorithms are required to verify the integrity of digital content. Many real-world scenarios have been claimed to benefit from blockchain's authentication capabilities. Despite the scattered efforts surrounding such remedies, relatively little research has been undertaken to discover where blockchain technology can be used to tackle the deepfake problem. Latest blockchain based innovations such as Smart Contract, Hyperledger fabric can play a vital role against the manipulation of digital content. The goal of this paper is to summarize and discuss the ongoing researches related to blockchain's capabilities to protect digital content authentication. We have also suggested a blockchain (smart contract) dependent framework that can keep the data integrity of original content and thus prevent deepfake. This study also aims at discussing how blockchain technology can be used more effectively in deepfake prevention as well as highlight the current state of deepfake video detection research, including the generating process, various detection algorithms, and existing benchmarks.

In this paper, a HDR algorithm for a single image is proposed using the exposure fusion, that adaptively calculates gamma correction coefficients according to the image distribution. Since typical HDR methods should use at least three images with different exposure values at the same scene, the main problem was that they could not be applied at the single shot image. Thus, HDR enhancements based on a single image using tone mapping and histogram modifications were recently presented, but these created some location-specific noises due to improper corrections. Therefore, the proposed algorithm calculates proper gamma coefficients according to the distribution of the input image and generates different exposure images which are corrected by the dark and the bright region stretching. A HDR image reproduction controlling exposure fusion weights among the gamma corrected and the original pixels is presented. As the result, the proposed algorithm can reduce certain noises at both the flat and the edge areas and obtain subjectively superior image quality to that of conventional methods.

Wireless sensor network (WSN) can be usefully used in battlefields requiring rapid installation and operation by enabling surveillance and reconnaissance using small sensors in areas where any existing network infrastructure is not formed. As WSN uses battery, energy efficiency acts as a very important issue in network survivability. Layer-based routing protocols have been studied a lot in the aspect of energy efficiency. Many research selected LEACH and PEGASIS protocols as their comparison targets. This study examines the two protocols and LECEEP, a protocol designed by combining their advantages, and proposes a new protocol, A-LECEEP, which is more energy efficient than the others. The proposed protocol can increase energy efficiency compared to the existing ones by eliminating unnecessary transmissions with multiple chains configuration.

Among the currently used knowledge-based authentication methods for smartphones, text and graphic-based authentication methods, such as PIN and pattern methods, use a display unit and a touch function of the display unit for input/output of secret information. Recently released smartphone form factors are trying to transform into various forms, away from the conventional bar and slate types because of the material change of the display unit used in the existing smartphone and the increased flexibility of the display unit. However, as mentioned in the study of D. Choi [1], the structural change of the display unit may directly or indirectly affect the authentication method using the display unit as the main input/output device for confidential information, resulting in unexpected security vulnerabilities. In this paper, we analyze the security vulnerabilities of the current mobile user authentication methods that is applied atypical form factor. According to the analysis results, it seems that the existing display-dependent mobile user authentication methods do not consider emerging security threats at all. Furthermore, it is easily affected by changes in the form factor of smartphones. Finally, we propose countermeasures for security vulnerabilities expected when applying conventional authentication methods to atypical form factor-based smartphones.

Recently, as indoor activities increase due to the spread of infectious diseases, the metaverse is attracting attention. Metaverse refers to content in which the virtual world and the real world are closely related, and its representative platform technology is VR(Virtual Reality). However, since VR hardware is difficult to access in terms of cost, the concept of streaming-based cloud VR has emerged. This study proposes a server configuration and deployment method in an edge network when metaverse content involving multiple users operates based on cloud VR. The proposed algorithm deploys the edge server in consideration of the network and computing resources and client location for cloud VR, which requires a high level of computing resources while at the same time is very sensitive to latency. Based on simulation, it is confirmed that the proposed algorithm can effectively reduce the total network traffic load regardless of the number of applications or the number of users through comparison with the existing deployment method.

The rapid growth of sense-and-respond applications and the emerging cloud computing model present a new challenge: providing publish/subscribe middleware as a scalable and elastic cloud service. The publish/subscribe interaction model is a promising solution for scalable data dissemination over wide-area networks. In addition, there have been some work on the publish/subscribe messaging paradigm that guarantees reliability and availability in the face of node and link failures. These publish/subscribe systems are commonly used in information-centric networks and edge-fog-cloud infrastructures for IoT. The IoT has an edge-fog cloud infrastructure to efficiently process massive amounts of sensing data collected from the surrounding environment. In this paper. we propose a quorum-based hierarchical fault-tolerant publish/subscribe systems (QHFPS) to enable reliable delivery of messages in the presence of link and node failures. The QHFPS efficiently distributes IoT messages to the publish/subscribe brokers in fog overlay layers on the basis of proposing extended stepped grid (xS-grid) quorum for providing tolerance when faced with node failures and network partitions. We evaluate the performance of QHFPS in three aspects: number of transmitted Pub/Sub messages, average subscription delay, and subscritpion delivery rate with an analytical model.

In this paper, we implement a recipe recommendation system using ingredient harmonization analysis based on recipe data. The proposed system receives an image of a food ingredient purchase receipt to recommend ingredients and recipes to the user. Moreover, it performs preprocessing of the receipt images and text extraction using the OCR algorithm. The proposed system can recommend recipes based on the combined data of ingredients. It collects recipe data to calculate the combination for each food ingredient and extracts the food ingredients of the collected recipe as training data. And then, it acquires vector data by learning with a natural language processing algorithm. Moreover, it can recommend recipes based on ingredients with high similarity. Also, the proposed system can recommend recipes using replaceable ingredients to improve the accuracy of the result through preprocessing and postprocessing. For our evaluation, we created a random input dataset to evaluate the proposed recipe recommendation system's performance and calculated the accuracy for each algorithm. As a result of performance evaluation, the accuracy of the Word2Vec algorithm was the highest.

PM_2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.

In this study, we developed a 'shared-use mobility'-mounted local particulate matter monitoring terminal technology to measure the actual particulate matter concentration around me. As a mobile terminal device in the form of an IoT sensor platform, it is designed to be separated into a control module and a sensor module to minimize interference between sensors and to consider the optimal observation position of each sensor. As a result of the field test, it was confirmed that particulate matter was locally different depending on time and space even within the same area. In addition, it was confirmed that the concentration of particulate matter in the relevant section differed by up to 100 times compared to the surrounding area due to specific sources of particulate matter such as unpaved roads. In addition, we positively reviewed the applicability of the service in the real-time metaverse environment using this result. Through technological advancement and application of multiple shared-use mobilities, we expect to be able to provide new services for practical smart city air environment monitoring, such as localized particulate matter information, air pollution event information, and identification of causes of particulate matter.

Lack of sleep time increases risks of fatigue, hypomnesis, decreased emotional stability, indigestion, and dementia. The risks can be reduced by providing eyelid-warming, inducing sleep and improving sleep quality. However, effective warming temperature to an person varies depending on physical condition and the individual. The various types of frequencies can be identified in brain wave from a person and amount of frequencies is also changed continuously before and after sleep. Therefore we can identify the user's sleep stage with brain wave, namely EEG. Effective sleep induction is possible if warming temperature to a person is controlled based on EEG. In this paper, we propose customized warming control techniques based on EEG for a efficient and effective sleep induction. As an experiment, sleep induction effects of standard sleep mask and customized temperature control techniques sleep mask are compared. EEG data and warming temperature were measured in 100 experiments. At customized warming control techniques, experiments showed that the ratio of alpha and theta waves increased by 3.21%p and the time to sleep decreased by 85 seconds. It will contribute to effective sleep induction and performance verification methods in customized sleep mask systems.

The MOBA game is updated every year with a new season, the new season update brings fun to the game users and also makes them feel unfamiliar with the new gameplay. In order to let game users better adapt to the new season, this study will extract the new season balance evaluation factors. Firstly, we used one-on-one review to collect the unbalanced factors that game users had encountered at the beginning of the new season of the MOBA game, and secondly, we organized the collected review data into a questionnaire and conducted a survey. The first step of the experiment was to filter out the lower factors through exploratory factor analysis and extract the balance evaluation factors of the MOBA game new season. The second step of the experiment was to examine the correlation between the factors through confirmatory factor analysis, as well as to confirm the appropriateness and explanatory value of the factors. The analysis resulted in "Game character experience", "Game view's expression", "Game level", and "Composition of the game setting" are the four factors. Finally, through correlation analysis, the most relevant factor for game satisfaction is the "Game character experience", and each factor is correlated with each other.

Measuring and evaluation of audience's visual message perception are crucial process for scientific production of visual content. This study tried to evaluate the difference of viewer's awareness of visual object depends on his or her inherent characteristics like conservatism using an eye tracker system. Especially, this experiment tested research questions about positive correlation between conservatism and peoples' eye movements following the sound visual messages. 57 subjects participated in the test. Two different groups were exposed to two visual elements representing 'the conservative' and 'the liberal'. The results showed that people tended to have different way of seeing visual objects according to their inherent characteristics. Also by comparing the gaze time at the object and area of interest(AOI) in visual, this study is able to verify the existence of 'positive way of seeing' and 'negative way of seeing'. The two different ways of seeing have their own trail of eye movement.

Based on the camera movement on image expression and grammar, this study intended to analyze the characteristics of image expression filmed and broadcasted by drones. This study analyzed drone images using the movement characteristics of existing video cameras as a coding nomenclature. These were intended to examine the differences from existing video grammar and their implications. This study conducted a content analysis using the entire population of drone news footage broadcast for four years in 2015, 2016, 2017 and 2018 by TV Chosun. The size of the screen, camera work, duration of the shot, camera angle, etc. were selected and analyzed. As a result, the drone camera work showed that it uses the most dolly shots in the case of camera movement, followed by the drone camera movement in the order of pan and tilt shots. For zoom, the frequency of use was the smallest. In addition, this study analyzed the size of the screen, duration of the shot, and camera angle of drone. Analysis shows that drones use certain camera movements most frequently, and unlike grandiose modifiers such as "extension of human gaze," drone remains as a supplementary means to enhance the traditional media expression.

In a pop song, the creator's intention is communicated to the user through music and lyrics. Lyric meaning is as important as music, but in most cases lyrics are delivered to users in a static form without non-verbal cues. Providing lyrics in a static text format is inefficient in conveying the emotions of a music. Recently, lyrics video with kinetic typography are increasingly provided, but producing them requires expertise and a lot of time. Therefore, in this system, the emotions of the lyrics are found through the analysis of the text of the lyrics, and the deep learning model is trained with the data obtained by converting the melody into a Mel-spectrogram format to find the appropriate emotions for the music. It sets properties such as motion, font, and color using the emotions found in the music, and automatically creates a kinetic typography video. In this study, we tried to enhance the effect of conveying the meaning of music through this system.

This study focused on how to analyze the ICT policy formation process using social big data. Specifically, in this study, a method for quantifying variables that influenced policy formation using the concept of a policy triggering mechanism and elements necessary to present the analysis results were proposed. For the analysis of the ICT policy triggering mechanism, variables such as 'Scope', 'Duration', 'Interactivity', 'Diversity', 'Attention', 'Preference', 'Transmutability' were proposed. In addition, 'interpretation of results according to data level', 'presentation of differences between collection and analysis time points', and 'setting of garbage level' were suggested as elements necessary to present the analysis results.