• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.15-20
• /
• 2022

With the arrival of the fourth industrial era, demand for agriculture is increasing day by day, and smart farm technology, in which computers manage agriculture in line with the current situation, is developing. However, agricultural workers who use it find it difficult to set up and use a management system for smart farms. This paper aims to establish a Lab-View smart farm management system to facilitate the use of a control program for ICT technology farms (hereinafter referred to as smart farms), one of the promising projects of the next industrial revolution. Based on Lab-View, users simply set the type of crops they want to grow, set appropriate temperature/humidity data for each set crop, and collect data in real time through sensors and store it in DB. This functionality maximizes convenience and usability in terms of users.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.1-8
• /
• 2022

Recently, Google MedeiaPipe presents a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Though neural network related to hair segmentation is relatively small size, it produces a high-quality hair segmentation mask that is well suited for AR effects such as a realistic hair recoloring. However, it has undesirable segmentation effects according to hair styles or in case of containing noises and holes. In this study, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood function. It is further optimized according to graph cuts algorithm and initial hair region is obtained. Finally, clustering algorithm and image post-processing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. The proposed method is applied to MediaPipe hair segmentation pipeline.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.139-147
• /
• 2023

The compact tracking radar system is a pulsed radar tracking system that searches, detects, and tracks targets in real time against aircraft targets with a small RCS(Radar Cross Section) maneuvering at high speed. This paper describes the development of comprehensive performance test equipment to verify the performance of the radar system in a anechoic chamber environment. Describes the design and manufacture of comprehensive performance test equipment to meet requirements, including the generation of simulated target signals to simulate aircraft target signals to verify performance in the laboratory environment of radar systems. It also describes a GUI(Graphic User Interface) program to check performance through a test in conjunction with the tracking radar system. Verify the comprehensive performance test equipment implemented through the performance test.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.115-119
• /
• 2023

The natural language processing models used in current artificial intelligence are huge, causing various difficulties in processing and analyzing data in real time. In order to solve these difficulties, we proposed a method to improve the efficiency of processing by using less memory and checked the performance of the proposed model. The technique applied in this paper to evaluate the performance of the proposed model is to divide the large corpus by adjusting the number of attention heads and embedding size of the BERT[1] model to be small, and the results are calculated by averaging the output values of each forward. In this process, a random offset was assigned to the sentences at every epoch to provide diversity in the input data. The model was then fine-tuned for classification. We found that the split processing model was about 12% less accurate than the unsplit model, but the number of parameters in the model was reduced by 56%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.9-14
• /
• 2023

The purpose of information system audit is to proactively identify and efficiently manage all risk factors that may arise during the process of constructing an information system, in order to assist in achieving the objectives of information system development. However, there is currently significant dissatisfaction with the quality and effectiveness of the auditing process, leading to ongoing research aimed at finding effective solutions. In this paper, we propose a multi-level evaluation model to enhance mutual understanding between auditors and evaluators and present a model that undergoes a maturity process, improving its levels and stages. We introduce a maturity-based evaluation model platform, enabling efficient communication between auditors and evaluators, allowing for real-time feedback, and supplementing it through continuous search. By presenting this multi-level model aimed at maturing the entire system, we aim to efficiently manage the system development process.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.83-88
• /
• 2023

In this paper, we developed a workout and diet assistance application to meet the growing demand for workout and dietary support services due to the increase in the home training population. The application analyzes the user's workout posture in real-time through the camera and guides the correct posture using guiding lines and voice feedback. It also classifies the foods included in the captured photos, estimates the amount of each food, and calculates and provides nutritional information such as calories. Nutritional information calculations are executed on the server, which then transmits the results back to the application. Once received, this data is presented visually to the user. Additionally, workout results and nutritional information are saved and organized by date for users to review.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.63-70
• /
• 2023

In this paper, we propose a Mixed Reality based rehabilitation exercise solution with the goal of mitigating one of the most common chronic conditions among the elderly, musculoskeletal disorders. In modern society, as the number of elderly increases, more people engage in office work and engage in more sedentary activities. Due to repetitive work in the office, muscle strength decreases and this causes many difficulties in daily life. In this study, we developed a mixed reality based exercise platform to solve these chronic musculoskeletal diseases. VR is not appropriate for elderly because of dizziness. In addition, we developed a wearable sensor based on IMU and attached it to important parts of the upper body to motion tracking. We developed a algorithm synchronize to raw data from wearable sensor with in a vr avatar. Ederly can check in real time whether rehabilitation exercises are being performed accurately through the avatar.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.55-58
• /
• 2024

In this paper, we propose a design and implementation of big data-based fine dust anomaly detection machine learning system. The proposed is system that classifies the fine dust air quality index through meteorological information composed of fine dust and big data. This system classifies fine dust through the design of an anomaly detection algorithm according to the outliers for each air quality index classification categories based on machine learning. Depth data of the image collected from the camera collects images according to the level of fine dust, and then creates a fine dust visibility mask. And, with a learning-based fingerprinting technique through a mono depth estimation algorithm, the fine dust level is derived by inferring the visibility distance of fine dust collected from the monoscope camera. For experimentation and analysis of this method, after creating learning data by matching the fine dust level data and CCTV image data by region and time, a model is created and tested in a real environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.65-74
• /
• 2024

In recent years, image processing technology has played a critical role in the field of autonomous driving. Among them, image recognition technology is essential for the safety and performance of autonomous vehicles. Therefore, this paper aims to develop a hybrid image recognition system to enhance the safety and performance of autonomous vehicles. In this paper, various image recognition technologies are utilized to construct a system that recognizes and tracks objects in the vehicle's surroundings. Machine learning and deep learning algorithms are employed for this purpose, and objects are identified and classified in real-time through image processing and analysis. Furthermore, this study aims to fuse image processing technology with vehicle control systems to improve the safety and performance of autonomous vehicles. To achieve this, the identified object's information is transmitted to the vehicle control system to enable appropriate autonomous driving responses. The developed hybrid image recognition system in this paper is expected to significantly improve the safety and performance of autonomous vehicles. This is expected to accelerate the commercialization of autonomous vehicles.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.177-182
• /
• 2024

In this paper, the purpose of this paper is to predict and prevent the risk of crowd concentration in advance for possible future crowd accidents based on the Itaewon crush accident in Korea on October 29, 2022. In the case of a single CCTV, the administrator can determine the current situation in real time, but since the screen cannot be seen throughout the day, objects are detected using YOLOv4, which learns images taken with CCTV angle, and safety accidents due to crowd concentration are prevented by notification when the number of clusters exceeds. The reason for using the YOLO v4 model is that it improves with higher accuracy and faster speed than the previous YOLO model, making object detection techniques easier. This service will go through the process of testing with CCTV image data registered on the AI-Hub site. Currently, CCTVs have increased exponentially in Korea, and if they are applied to actual CCTVs, it is expected that various accidents, including accidents caused by crowd concentration in the future, can be prevented.