• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1176-1182
• /
• 2021

Recently, with the development of artificial intelligence and IoT technology, automation, and unmanned work are progressing in various fields, and the importance of image processing, which is the basis of AI object recognition, is increasing. In particular, in systems that require detailed data processing, noise removal is used as a preprocessing step, but the existing algorithm does not consider the noise level of the image, so it has the disadvantage of blurring in the filtering process. Therefore, in this paper, we propose a modified Gaussian filter that determines the weight by determining the noise level of the image. The proposed algorithm obtains the noise estimate for the AWGN of the image using quadtree segmentation, determines the Gaussian weight and the pixel weight, and obtains the final output by convolution with the local mask. To evaluate the proposed algorithm, it was simulated compared to the existing method, and superior performance was confirmed compared to the existing method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1373-1378
• /
• 2018

In order to solve the problems such as reduction of agriculture population, aging and declining of grain self sufficiency rate, agriculture ICT convergence technology utilizing IoT technology is actively being developed. Agricultural ICT technology only concentrates on facility houses, and there is no automated control system in the field of cultivation. In this paper, we propose an irrigation control system that automatically controls the solenoid valves and water pumps in a large area with Lora wireless communication. The proposed system does not require a separate power source by using a small solar panel, and it is very convenient to install and operate supporting wireless auto setup by plug-and-play method. Therefore, it is expected that it will contribute to the reduction of labor force, quality of agricultural products, and productivity improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1310-1316
• /
• 2021

Recently, with the development of artificial intelligence and IoT technology, the importance of video processing such as object tracking, medical imaging, and object recognition is increasing. In particular, the noise reduction technology used in the preprocessing process demands the ability to effectively remove noise and maintain detailed features as the importance of system images increases. In this paper, we provide a modified weight filter based on pixel matching in an AWGN environment. The proposed algorithm uses a pixel matching method to maintain high-frequency components in which the pixel value of the image changes significantly, detects areas with highly relevant patterns in the peripheral area, and matches pixels required for output calculation. Classify the values. The final output is obtained by calculating the weight according to the similarity and spatial distance between the matching pixels with the center pixel in order to consider the edge component in the filtering process.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.109-115
• /
• 2019

Currently, LPWA(Low Power Wide Area) communication technology is widely used due to the development of IoT(Internet of Things) technology. Among the LPWA technologies, LoRaWAN(Long Range Wide Area Network) is widely used in many fields due to its wide coverage, stable communication speed, and low-cost modem module prices. In particular, LoRa(Long Range) can easily construct LoRaWAN with a dedicated gateway. So many organizations are building their own LoRaWAN-based networks. The LoRaWAN Gateway receives the LoRa packet transmitted from an End-device installed in the adjacent location, converts it into the Internet protocol, and sends the packet to the final destination server. Current LoRa Gateway uses a single-hop method, and each gateway must include a communication network capable of the Internet. If it is the mobile communication(i.e., WCDMA, LTE, etc.) network, it is required to pay the internet usage fee which is installed in each gateway. If the LoRa communication is frequent, the user has to spend a lot of money. We propose an idea on how to design a multi-hop protocol which enables packet routing between gateways by analyzing the LoRaWAN communication method implemented in its existing single-hop way in this paper. For this purpose, this paper provides an analysis of the standard specification of LoRaWAN and explains what was considered when such protocol was designed. In this paper, two gateways have been placed based on the functional role so as to make the multi-hop protocol realized: (i) hopping gateway which receives packets from the end-device and forwards them to another gateway; and (ii) main gateway which finally transmits packets forwarded from the hopping gateway to the server via internet. Moreover, taking into account that LoRaWAN is wireless mobile communication, a level-based routing method is also included. If the protocol proposed by this paper is applied to the LoRaWAN network, the monthly internet fee incurred for the gateway will be reduced and the reliability of data transmission will be increased.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1625-1631
• /
• 2020

With the development of IoT technology, various digital equipment is being spread, and accordingly, the importance of data processing is increasing. The importance of data processing is increasing as it greatly affects the reliability of equipment, and various studies are being conducted. In this paper, we propose an algorithm to remove AWGN according to the characteristics of the fuzzy membership function. The proposed algorithm calculates the estimated value according to the correlation between the value of the fuzzy membership function between the input image and the pixel value inside the filtering mask, and obtains the final output by adding or subtracting the output of the spatial weight filter. In order to evaluate the proposed algorithm, it was simulated with existing AWGN removal algorithms, and analyzed using difference image and PSNR comparison. The proposed algorithm minimizes the effect of noise, preserves the important characteristics of the image, and shows the performance of efficiently removing noise.

• Journal of Internet of Things and Convergence
• /
• v.7 no.1
• /
• pp.55-62
• /
• 2021

The world is changing rapidly as the Internet spreads and various smart devices appear. High-performance PCs and high-speed communication networks are rapidly spreading in every home, and all kinds of the internet sites are emerging. In particular, the high education enthusiasm of Korean parents adds to this, and the ratio of the internet users among teenagers is exploding every day. In the case of adolescents, most of them use the Internet for online games, indicating that online games are the main cause of the internet addiction. This study was conducted using a questionnaire for male and female high school students using the Internet, and demographic and sociological characteristics were used only as basic data. In this study, as much as parents, students and teachers think, the results of the internet addiction type analysis according to academic achievement in humanities high school students are to be investigated to determine whether internet use has an effect on academic achievement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.207-213
• /
• 2022

Recently, with the improvement of the performance of IoT technology and AI, automation and unmanned work are progressing in a wide range of fields, and interest in image processing, which is the basis of automation such as object recognition and object classification, is increasing. Image noise removal is an important process used as a preprocessing step in an image processing system, and various studies have been conducted. However, in most cases, it is difficult to preserve detailed information due to the smoothing effect in high-frequency components such as edges. In this paper, we propose an algorithm to restore damaged images in AWGN(additive white Gaussian noise) using fuzzy weights based on Gaussian distribution. The proposed algorithm switched the filtering process by comparing the filtering mask and the noise estimate with each other, and reconstructed the image by calculating the fuzzy weights according to the low-frequency and high-frequency components of the image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1846-1852
• /
• 2021

In modern society, various digital devices are being distributed in a wide range of fields due to the fourth industrial revolution and the development of IoT technology. However, noise is generated in the process of acquiring or transmitting an image, and not only damages the information, but also affects the system, causing errors and incorrect operation. AWGN is a representative noise among image noise. As a method for removing noise, prior research has been conducted, and among them, AF, A-TMF, and MF are the representative methods. Existing filters have a disadvantage that smoothing occurs in areas with high frequency components because it is difficult to consider the characteristics of images. Therefore, the proposed algorithm calculates the standard deviation distribution to effectively eliminate noise even in the high frequency domain, and then calculates the final output by applying the probability density function weight of the Laplace distribution using the curve fitting method.

• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.13-19
• /
• 2023

In this paper, we investigated the implementation of a hairstyle recommendation system based on big data and deepfake technology. The proposed hairstyle recommendation system recognizes the facial shapes based on the user's photo (image). Facial shapes are classified into oval, round, and square shapes, and hairstyles that suit each facial shape are synthesized using deepfake technology and provided as videos. Hairstyles are recommended based on big data by applying the latest trends and styles that suit the facial shape. With the image segmentation map and the Motion Supervised Co-Part Segmentation algorithm, it is possible to synthesize elements between images belonging to the same category (such as hair, face, etc.). Next, the synthesized image with the hairstyle and a pre-defined video are applied to the Motion Representations for Articulated Animation algorithm to generate a video animation. The proposed system is expected to be used in various aspects of the beauty industry, including virtual fitting and other related areas. In future research, we plan to study the development of a smart mirror that recommends hairstyles and incorporates features such as Internet of Things (IoT) functionality.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.27-33
• /
• 2024

As of 2023, the number of accident victims in the domestic construction industry is 26,829, ranking second only to other businesses (service industries). The accident types of casualties in all industries were falls (29,229 people), followed by falls (14,357 people). Based on the above data, this study attaches sensors to hard hats and insoles to predict fall accidents that frequently occur at construction sites, and proposes smart safety equipment that applies a random forest algorithm based on the data collected through this. The random forest model can determine fall accidents in real time with high accuracy by generating multiple decision trees and combining the predictions of each tree. This model classifies whether a worker has had a fall accident and the type of behavior through data collected from the MPU-6050 sensor attached to the hard hat. Fall accidents that are primarily determined from hard hats are secondarily predicted through sensors attached to the insole, thereby increasing prediction accuracy. It is expected that this will enable rapid response in the event of an accident, thereby reducing worker deaths and accidents.