• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.73-80
• /
• 2023

The recent steep increase in the minimum hourly wage has increased the burden of labor costs, and the share of unmanned stores is increasing in the aftermath of COVID-19. As a result, theft crimes targeting unmanned stores are also increasing, and the "Just Walk Out" system is introduced to prevent such thefts, and LiDAR sensors, weight sensors, etc. are used or manually checked through continuous CCTV monitoring. However, the more expensive sensors are used, the higher the initial cost of operating the store and the higher the cost in many ways, and CCTV verification is difficult for managers to monitor around the clock and is limited in use. In this paper, we would like to propose an AI image processing fusion algorithm that can solve these sensors or human-dependent parts and detect customers who perform abnormal behaviors such as theft at low costs that can be used in unmanned stores and provide cloud-based notifications. In addition, this paper verifies the accuracy of each algorithm based on behavior pattern data collected from unmanned stores through motion capture using mediapipe, object detection using YOLO, and fusion algorithm and proves the performance of the convergence algorithm through various scenario designs.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.27-34
• /
• 2024

The direct and indirect damages caused by fires in underground utility tunnels have a great impact on society as a whole, so efforts are needed to prevent and manage them in advance. To this end, research is ongoing to prevent disasters such as fire flooding by applying digital twin technology to underground utility tunnels. A network is required to transmit the sensed signals from each sensor to the platform. In essence, it is necessary to analyze the application of wireless networks in the underground utility tunnel environments because the tunnel lacks the reception range of external wireless communication systems. Within the underground utility tunnels, electromagnetic interference caused by transmission and distribution cables, and diffuse reflection of signals from internal structures, obstacles, and metallic pipes such as water pipes can cause distortion or size reduction of wireless signals. To ensure real-time connectivity for remote surveillance and monitoring tasks through sensing, it is necessary to measure and analyze the wireless coverage in underground utility tunnels. Therefore, in order to build a wireless network environment in the underground utility tunnels. this study minimized the shaded area and measured the actual cavity environment so that there is no problem in connecting to the wireless environment inside the underground utility tunnels. We analyzed the data transmission rate, signal strength, and signal-to-noise ratio for each section of the terrain of the underground utility tunnels. The obtained results provide an appropriate wireless planning approach for installing wireless networks in underground utility tunnels.

• Journal of the Korean Geographical Society
• /
• v.47 no.4
• /
• pp.592-605
• /
• 2012

This article reviewed issues in Korean geographical journals: web GIS and National GIS. Web GIS in Korea is now evolving to mobile GIS, which requires portable hardware, wireless Internet, and GPS receiver. The new trend of mobile GIS is using a smart phone. Recently, a variety of studies for the mobile App and mobile Web in Korea has been developed. With explosive information on the Web 2.0, the Korean government has built the Human-Oriented Geographic Information System (HOGIS) in which Ontology was implemented for semantic query on the Web. On the government side, Korean government has produced various nationwide data through 4-phase NGIS project. Current NGIS ($4^{th}$ phase: 2011-2015) moves toward a Korean Green Geospatial Society using geospatial information as a new growth engine for the future.

• Progress in Medical Physics
• /
• v.14 no.1
• /
• pp.43-50
• /
• 2003

PACS mostly has been used in large scaled hospital due to expensive initial cost to set up the system. The network of PACS is independent of the others: network. The user's PC has to be connected physically to the network of PACS as well as the image viewer has to be installed. The web based mini-PACS can store, manage and search inexpensively a large quantity of radiologic image acquired in a hospital. The certificated user can search and diagnose the radiologic image using web browser anywhere Internet connected. The implemented Image viewer is a viewer to diagnose the radiologic image. Which support the DICOM standard and was implemented to use JAVA programming technology. The JAVA program language is cross-platform which makes easier upgrade the system than others. The image filter was added to the viewer so as to diagnose the radiologic image in detail. In order to access to the database, the user activates his web browser to specify the URL of the web based PACS. Thus, The invoked PERL script generates an HTML file, which displays a query form with two fields: Patient name and Patient ID. The user fills out the form and submits his request via the PERL script that enters the search into the relational database to determine the patient who is corresponding to the input criteria. The user selects a patient and obtains a display list of the patient's personal study and images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.8
• /
• pp.1443-1448
• /
• 2006

As computers and networks become popular, distributing information on the Internet is common in our daily life. In the past, e-mail has been the primary choice of exchanging information but messengers are gaining popularity abroad and domestically because of their nature of getting immediate responses. Information leakage by invasion that is enemy of evil in communication of communications division Server and Agent between each agents that become burden of communication for effective administration of data for most of existing messenger is becoming an issue. In this paper, we design a secure messenger system that could be obtained maximum security. It use ECC based on ElGamal methodology using PKI for secure communication. For the message encryption and decryption between the same group non, each group is kept distinct by drawing an elliptic curve and an arbitrary point is chosen on the curve.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1393-1400
• /
• 2017

As the number of smartphone users increases, vulnerability to privacy protection is increasing. This is because personal information is stored on various servers connected to the Internet and the user is authenticated using the same ID and password. Authentication methods such as OTP, FIDO, and PIN codes have been introduced to solve traditional authentication methods, but their use is limited for authentication that requires sharing with other users. In this paper, we propose the authentication method that is needed for the management of shared information such as hospitals and corporations. The proposed algorithm is an algorithm that can authenticate users in the same place in real time using smart phone IMEI, QR code, BLE, push message. We propose an authentication algorithm that can perform user authentication through mutual cooperation using a smart phone and can cancel realtime authentication. And we designed and implemented a mutual authentication system using proposed algorithm.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.35-49
• /
• 2001

Over the years, cluster analysis has become a popular tool for marketing and segmentation researchers. There are various methods for cluster analysis. Among them, K-means partitioning cluster analysis is the most popular segmentation method. However, because the cluster analysis is very sensitive to the initial configurations of the data set at hand, it becomes an important issue to select an appropriate starting configuration that is comparable with the clustering of the whole data so as to improve the reliability of the clustering results. Many programs for K-mean cluster analysis employ various methods to choose the initial seeds and compute the centroids of clusters. In this paper, we suggest a methodology to evaluate various clustering programs. Furthermore, to explore the usability of the methodology, we evaluate four clustering programs by using the methodology.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.1-18
• /
• 2020

Fine dust is one of the top ten causes of deaths globally. More than 95% of the world's population are endangered by it. However, as the fine dust problem is difficult to address immediately, people should be informed of its risk and prepared to deal with it. This study explores the methods used to define, efficiently provide, and manage the complementary relationships between various types of media providing risk information utilizing the competitive characteristics of media in niche theory. A survey consisting of 348 Korean university students was conducted over 12 days, to analyze three factors: consumer perception of fine dust, media usage, and media use gratification. The response value for media gratification was substituted in the equation to derive the niche breadth, niche overlap, and competitive superiority. It was found that 1) for providing fine dust forecast and fine dust response guidance information, a smartphone application was the most effective; 2) smartphone applications were limited in providing additional information such as the severity and origin of fine dust, and hence, it is necessary to establish the functionality of the Internet and TV to complement smartphone applications. Thus, a system considering the above should be developed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2167-2175
• /
• 2017

In recent years, an IoT is dramatically developing according to the enhancement of AI, the increase of connected devices, and the high-performance cloud systems. Huge data produced by many devices and sensors is expanding the scope of services, such as an intelligent diagnostics, a recommendation service, as well as a smart monitoring service. The studies of edge computing are limited as a role of small server system with high quality HW resources. However, there are specialized requirements in a smart factory domain needed edge computing. The edges are needed to pre-process containing tiny filtering, pre-formatting, as well as merging of group contexts and manage the regional rules. So, in this paper, we extract the features and requirements in a scope of efficiency and robustness. Our edge offers to decrease a network resource consumption and update rules and learning models. Moreover, we propose architecture of edge computing based on learning factors sharing with a cloud system in a smart factory.