In the field of augmented reality, edge-based methods have been popularly used in tracking textureless 3D objects. However, edge-based methods are inherently vulnerable to cluttered backgrounds. Another way to track textureless or poorly-textured 3D objects is to directly align image intensity of 3D object between consecutive frames. Although the direct methods enable more reliable and stable tracking compared to using local features such as edges, they are more sensitive to occlusion and less accurate than the edge-based methods. Therefore, we propose a method that combines an edge-based method and a direct method to leverage the advantages from each approach. Experimental results show that the proposed method is much robust to both fast camera (or object) movements and occlusion while still working in real time at a frame rate of 18 Hz. The tracking success rate and tracking accuracy were improved by up to 84% and 1.4 pixels, respectively, compared to using the edge-based method or the direct method solely.

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

It is very important to support real-time on the inspection equipment based on Windows. In particular, in the system using MIL-STD-1553B communication, which is widely used in military weapon systems, real-time is required for inspection equipment that uses mostly platforms based on Windows such as Industrial PCs. However, in order to use a complete real-time operating system such as VxWorks, the purchase cost is expensive and the implementation is complicated on the system, so it is not suitable for inspection equipment that requires simple functions to just check go or no-go. Therefore, in this paper, a Real-Time implanted Kernel(RTiK) in the Windows kernel is implanted in order to improve these defects, and real-time performance is implemented for periodically MIL-STD-1553B communication by Deferred Procedure Call(DPC) of Windows. Also, it was verified that the period of up to 2ms was guaranteed with a RDTSC into the EDX:EAX registers for measuring the periodicity.

Since face masks in public were mandated during COVID-19, more people have taken temperature checks, with their masks on. The study has developed a contactless thermal camera that accurately measures temperatures of people wearing different kinds of masks, detect people wearing masks wrong, and record the temperature data. The built-in system that identifies people wearing masks wrong is what masks our contactless thermal camera differentiated from other thermal cameras. Also our contactless thermal camera can keep track of the number of mask wearers in different regions and their temperatures. Thus, the analysis of such regional data can significantly contribute to stemming the spread of the virus.

The agricultural is plagued by agricultural damage from wild boars every year. As a result, research on systems to repelling wild boars continues, and most of the systems are to detect objects with body temperature through sensors and then repelling them with actions such as light and sound. The problems of these system are operating regardless of wild boars and people, which can cause significant accident when using electric fence. In addition, If the same repelling action is repeated, wild boars can be adapted to that repelling action. As a solution to the two problems, Adaptation problem can be solved by random sounds and distinction problem can be solved by YOLO V4.

The power output of solar panels highly depends on environmental situations like weather and air pollution. Due to bad weather or air pollution, it is difficult for solar panels to operate at their full potential. Knowing the power output of solar panels in advance helps set up the solar panels correctly and work their possible potential. This paper presents an approach to predict the power output of solar panels based on weather and air pollution features using machine learning methods. We create machine learning models with three kinds set of features, such as weather, air pollution, and weather and air pollution. Our datasets are collected from the area of Seoul, South Korea, between 2017 and 2019. The experimental results show that the weather and air pollution features can be efficient factors to predict the power output of solar panels.

Recently, several ICT-based cat studies have produced some successful results, according to academic and industry sources. However, research on the level of simply identifying the cat's condition, such as the behavior and sound classification of cats based on images and sound signals, has yet to be found. In this paper, based on the veterinary scientific knowledge of cats, a practical and academic cat monitoring and disease diagnosis system is proposed to monitor the health status of the cat 24 hours a day by automatically categorizing and analyzing the behavior of the cat with location information using LSTM with a beacon sensor and a raspberry pie that can be built at low cost. Validity of the proposed system is verified through experimentation with cats in actual custody (the accuracy of the cat behavior classification and location identification was 96.3% and 92.7% on average, respectively). Furthermore, a rule-based disease analysis system based on the veterinary knowledge was designed and implemented so that owners can check whether or not the cats have diseases at home (or can be used as an auxiliary tool for diagnosis by a pet veterinarian).

We proposed the research on an analysis and prediction model that allows the identification of outliers or abnormality in the data followed by effective and rapid imputation of missing values was conducted. This model is expected to analyze efficiently the problems in the data based on the calibrated raw data. As a result, a system that can adequately utilize the data was constructed by using the introduced KNN + MLE algorithm. With this algorithm, the problems in some of the existing KNN-based missing data imputation algorithms such as ignoring the missing values in some data sections or discarding normal observations were effectively addressed. A comparative evaluation was performed between the existing imputation approaches such as K-means, KNN, MEI, and MI as well as the data missing mechanisms including MCAR, MAR, and NI to check the effectiveness/efficiency of the proposed algorithm, and its superiority in all aspects was confirmed.

Most common web or application system architectures have central network. As a result, central network can be supervised and controlled in all situation. And It has the advantage of easy to manage and fast to work. However, central network have a disadvantage of weak to security and unclear. In particular, many institutions used by web system be has many problems by central network. In this paper, we proposed blokchain technology based on ethereum to resolve of problem and trading structure that arise in cental network. We propose a decentralized application based on points including cryptocurrency functions and smart contract to the advantages of blockchain with a decentralized structure. The results of the performance experiment are as follows; It has shown the advantages of reliable use and security in a variety of environments(Windows, Ubuntu, Mac).

Recently, the small-size mobile robots with remote-control are rapidly growth which market of mobile is increased in the world. Especially, the smart-phones are widely used for interface device in the small size of a mobile robot. The research goal is control system design which is applied to miniaturization of a mobile robot using smart-phone and it can be confirmed performance for designed system. Meanwhile, the fabrication of mini-mobile robot can also be remote-control operation through the WIFI performance of a smart-phone. The smart-phone is used to remote-control for robot operation which control data transmit to robot via the WIFI network. To drive the robot, we can observe by the smart-phone screen and it can easily adjust the robot drive condition and direction by smart-phone button. Consequentially, there was no malfunction and images were printed out well. However, in drive, because of blind spot, robot was bumped into obstacle. Therefore, the additional test is necessary to sensor for blind spot which sensor can be equipment to mobile robot. In addition, the experiment with robot object recognition is needed.

Customized services to a sleep induction for better sleepcare are more effective because of different satisfaction levels to users. The EOG data measured at the frontal lobe when a person blinks his eyes can be used as biometric data because it has different values for each person. The accuracy of measurement is degraded by a noise source, such as toss and turn. Therefore, it is necessary to analyze the noisy data and remove them from normal EOG by filtering. There are low-pass filtering and high-pass filtering as filtering using a frequency band. However, since filtering within a frequency band range is also required for more effective performance, we propose a machine learning model for the filtering of EOG data in this paper as the second filtering method. In addition, optimal values of parameters such as the depth of the hidden layer, the number of nodes of the hidden layer, the activation function, and the dropout were found through experiments, to improve the performance of the machine learning filtering model, and the filtering performance of 95.7% was obtained. Eventually, it is expected that it can be used for effective user identification services by using filtering model for EOG data.

This study developed a responsive healthcare system that users can easily use in real life to prevent turtle neck syndrome by posture correction. We propose a system that naturally induces direct posture improvement by adjusting the height with a responsive cradle through a turtle neck discrimination algorithm detecting the turtle neck posture in real time using a webcam. The turtle neck algorithm was developed based on machine learning, using the points that the distance relationship between the jaw line and the shoulder varies depending on the posture. For the younger age group, which is particularly problematic due to the increase in the use of IT devices, image data in different situations according to the height and posture of the cradle was collected and learned as a support vector machine classifier. In addition, a height-adjustable cradle that can support a laptop has been created and expanded into a responsive cradle that can be controlled with software by interlocking with the Arduino. Therefore, this service enables posture correction of many modern people suffering from turtle neck syndrome and will become an essential platform in the increasing online environment in the non-contact era.

Learning assistance system that continuously measures user's concentration will be helpful to grasp the concentration pattern and adjust the learning method accordingly to improve the learning efficiency. Although a lot of various learning aids have been proposed, there have been few studies on the concentration monitoring system in real time. Therefore, in this study, we developed an Android-based mobile application that can measure concentration during study by using functional near-infrared spectroscopy, which is used to measure brain activity. First, the task accuracy was predicted at a maximum level of 93.75% from the prefrontal oxygenation characteristics measured while performing the visual Q&A task on 11 college students, and a concentration calculation formula based on a linear regression model was derived. Then, a survey on the usability of the mobile application was conducted, overall high satisfaction and positive opinions were obtained. From these findings, this application can be used as a customized learning aid application for users, and further, it can help educators improve the quality of classes based on the level of concentration of learners.

One of the highly reliable object tracking methods is to trace objects by associating objects detected by deep learning. The detected object is represented by a rectangular box. The box has information such as location and size. Since the tracker has motion information of the object in addition to the location and size, knowing additional information about the motion of the detected box can increase the reliability of object tracking. In this paper, we present a new method of reliably estimating the moving direction of the detected object in underground parking lot. First, the frame difference image is binarized for detecting motion energy, change due to the object motion. Then, a cumulative binary image is generated that shows how the motion energy changes over time. Next, the moving direction of the detected box is estimated from the accumulated image. We use a new cost function to accurately estimate the direction of movement of the detected box. The proposed method proves its performance through comparative experiments of the existing methods.

This study aims to help users to have a more satisfying encounter based on the problems found by comparing and analyzing similar applications. That is, an application that derives intermediate points through the subway, which is a public transportation means, and provides information on nearby convenience facilities was proposed. The middle point calculation process uses the dijkstra algorithm, which stores the minimum number of nodes in the stored path from the first input location to the last location. The stack and arraylist are used to search all paths from the first input position to the last position, and then the path with the smallest number of nodes is selected. After that, the number of stations in the route is divided in half and the resulting station is output. In addition, this study provides information on convenience facilities near intermediate points in order to have differences from similar applications. It categorizes within a 1km radius of the point and provides a function that helps to conveniently identify only facilities around the middle point. In particular, by visualizing the number of convenience facilities with radar charts and numbers, it is possible to grasp the commercial district around the midpoint at a glance.

We aim to investigate the effects of task type and user gender on the expected gender of chatbots. We conducted an online study of 381 participants who selected the gender (female, male, or neutral) for chabots performing six different tasks. Our results indicate that users expect human- gendered chatbots for all tasks and that the expected gender of a chatbot is significantly different depending on the task type. Users expected chatting, counseling, healthcare and clerical work to be done by female chatbots; professional and customer service work were expected to be done by male chatbots. A tendency for participants to prefer chatbots of the same-gendered as themselves is revealed in several tasks for both male and female users. However, this homophily tendency is stronger for female users. We conclude by suggesting practical guidelines for designing chatbot services that reflect user expectations.

In the era of 'Untact', virtual reality-based job training platforms are actively being used as part of non-face-to-face education for students with developmental disabilities. Because the people with developmental disabilities may lack sufficient cognitive abilities, it is difficult to conduct untact training seamlessly without the help of a third party. Therefore, it is necessary for training programs to identify the right timing to provide help so that the training can be continued. This research analyzed the visual attention of students with developmental disabilities in virtual reality-based job training program in order to determine the point of time when an intervention is required by the trainee. Results showed that students who completed the mission tended to have intense visual attention on a small number of objects for a certain period of time; the visual attention of the students who failed tended to shift erratically among multiple objects.

AI technology is spreading not only to industrial fields, but also to culture, art, and content fields. In this paper, we proposed a system based on AI technology that can automate the process of reproducing contents using characters for movie contents. After creating the basic appearance of the character by using the StyleGAN2 model from the video extracted from the movie contents, analyzing the character's personality and propensity using the extracted dialogue data, it was determined from the contemplative appearance based on the yin-yang and five elements to the character's propensity. Accordingly, the external characteristics are reflected in the character. Using the OpenPose model, a character's motion is created, and the finally generated data is integrated to reproduce the content. It is expected that many movie contents can be reproduced through the study of the proposed system.