In this paper, we propose a system that recognizes weed images using a classifier based on ResNeXt model. On the server of the proposed system, the ResNeXt model extracts the fine features of the weed images sent from the user and classifies it as one of the most similar weeds out of 21 species. And the classification result is delivered to the client and displayed on the smartphone screen through the application. The experimental results show that the proposed weed recognition system based on ResNeXt model is superior to existing methods and can be effectively applied in the real-world agriculture field.

During tensile test, tensile strain of tensile tester is measured by movement distance of upper zig and initial specimen's length. Conventional tensile tester program obtains the tensile strain after the end of the test, however the method is not appropriate in real time because the results are calculated until the test is finished. We suggest a real-time measurement system of tensile strain using ArUco Marker in OpenCV library. The system is designed to detect marker attached on the upper zig and calculate specimen's tensile strain. According to comparison of the calculated data and the results of the tester, errors approximately showed 0.128 mm on 3840×2160 video resolution.

The identity verification is one of the most important technologies in online services. Many services in society are provided online, and the service is provided after confirming the user's identity. Users can do a lot of things online, but they also have side effects. Online digital information is easily manipulated and it is difficult to verify its authenticity, causing social confusion. Accordingly, there has been a movement for individuals to directly manage their identity information using DID. In this paper, we propose a system that can authenticate identity by directly adding own personal information and issuing an identifier using DID technology based on a private blockchain. Then, to verify the proposed system, the scenario is executed and verified.

The reversible data hiding technique safely transmits secret data to the recipient from malicious attacks by third parties. In addition, this technique can completely restore the image used as a transmission medium for secret data. The reversible data hiding schemes have been proposed in various forms, and recently, the reversible data hiding schemes based on interpolation are actively researching. The reversible data hiding scheme based on the interpolation method expands the original image into the cover image and embed secret data. However, the existing interpolation-based reversible data hiding schemes did not embed secret data during the interpolation process. To improve this problem, this paper proposes embedding the first secret data during the image interpolation process and embedding the second secret data into the interpolated cover image. In the embedding process, the original image is divided into blocks without duplicates, and the maximum and minimum values are determined within each block. Three way searching based on the maximum value and two way searching based on the minimum value are performed. And, image interpolation is performed while embedding the first secret data using the PVD scheme. A stego image is created by embedding the second secret data using the maximum difference value and log function in the interpolated cover image. As a result, the proposed scheme embeds secret data twice. In particular, it is possible to embed secret data even during the interpolation process of an image that did not previously embed secret data. Experimental results show that the proposed scheme can transmit more secret data to the receiver while maintaining the image quality similar to other interpolation-based reversible data hiding schemes.

In order to provide useful Internet of Things (IoT) services, the locations of IoT devices should be well managed. However, frequent location updates of lots of IoT devices result in signaling overhead in networks. To solve this problem, this paper utilizes the opportunistic fog node (OFN) which is opportunistically available according to the mobility to perform the location updates as a representative of IoT devices. Therefore, the location updates through OFN can reduce the signaling loads of networks. To show the performance of the proposed scheme, we develop an analytic model for the opportunistic location update offloading probability that the location update can be offloaded to OFN from the IoT device. Then, the extensive simulation results are given to validate the analytic model and to assess the performance of the proposed scheme in terms of the opportunistic location update offloading probability.

In computer vision, visual tracking method addresses the problem of localizing an specific object in video sequence according to the bounding box. In this paper, we propose a tracking method by introducing the feature correlation comparison into the siamese network to increase its matching identification. We propose a way to compute location of object to improve matching performance by a correlation operation, which locates parts for solving the searching problem. The higher layer in the network can extract a lot of object information. The lower layer has many location information. To reduce error rate of the object center point, we built a siamese network that extracts the distribution and location information of target objects. As a result of the experiment, the average center error rate was less than 25%.

Push-ups are one of the body exercises that can be easily measured anytime, anywhere. As one of the most widely used techniques as a test tool for evaluating physical strength, they are broadly used in various fields, especially in fields that require physical ability to estimate, such as military, police, and firefighters. However, social distancing is currently being implemented, and the issue of fairness has been steadily raised due to subtle differences between measurement. Accordingly, in this paper, the correct posture for each individual was photographed and learned by a high-performance computer, and the result was derived by comparing it with the case of performing the incorrect posture of the individual. If method is introduced into the physical fitness evaluation through the proposed method, the individual takes the correct posture and learns the photographed photo, and measures the posture with several images taken during a given time. Through this, it is possible to measure more objectively because it measures with the merit that can be measured even in the present situation and with one's correct posture.

Based on the theory of space perception, this paper concludes that the mixed reality application under the theory of space perception has a three-level definition of visual hierarchy and then analyzes the component elements of interface design and the classification mode of interface windows. Next, carry out case practice research through this theoretical definition, and finally conduct the survey and analysis of questionnaire data, verifying that the mixed reality interface design based on spatial perception theory meets the user experience elements of Usability, Availability, and Attraction. The conclusion is that the constituent elements of interface design and the window classification mode can provide specific and practical design specifications for mixed reality interface design, reduce the interaction cost of completing tasks, reduce users' cognitive load, and make it easier for users to receive interface information

The Bluetooth Low Energy profile has the advantage of continuing wireless communication with very little power consumption compared to the existing Bluetooth, so it is widely applied to smart devices. Most of them are applied to Point-to-Point (1:1) communication between Central (Master) and Peripheral (Slave), but can be applied to Point-to-Multiple (1:N) wireless communication through the use of multiple threads and timers. Therefore, in this paper, a precise timer was designed in the BLE profile to devise an image segmentation transmission/reception structure based on multiple access, and a smart image block device applied to it was designed and verified.

Parents' influence on children's development is generally considered essential. This paper attempts to explore the role of AR in preschool education from the perspective of parents, aiming to help parents better understand the impact of children's use of augmented reality in preschool education. The subjects were parents of children in the preschool age range (3-6 years old), and the experimental equipment was AR cognitive cards. In order to extract parents' views on AR, five parents were invited to conduct an experiment with their children using AR cognition cards, and then an open interview survey was conducted. In the second experiment, the answers obtained from the first experiment were sorted out and formed a questionnaire to conduct a closed-book survey. It shows that parents are satisfied with the characteristics of AR to assist their children's learning. At the same time, parents also value technology, usage management and playing environment. AR can stimulate children's learning initiative. Children like to use AR, AR is suitable for learning, make parents satisfied. But even if AR is suitable for learning, parents will control the time their children use it.