• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.117-124
• /
• 2021

Livestock behavioral analysis is a factor that has a great influence on livestock health management and agricultural productivity increase. However, most digital devices introduced for behavioral analysis of livestock do not provide raw data and also provide limited analysis results. Such a closed system makes it more difficult to integrate data and build big data, which are essential for the introduction of advanced IT technologies. Therefore, it is necessary to supply farm-scale data collection devices that can be easily used at low cost. This study presents a data collection system for analyzing the behavior of livestock. The system consists of a number of miniature computing units that operate wirelessly, and collects livestock body temperature and acceleration data, location information, and livestock environment data. In addition, this study presents an algorithm for estimating the behavior of livestock based on the collected acceleration data. For the experiment, a system was built in a Korean cattle farm in Icheon, Gyeonggi-do, and data were collected for 20 Korean cattle, and based on this, the empirical and analysis results were presented.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.36 no.4
• /
• pp.105-112
• /
• 2022

Dongje school (同濟學校), alternately Dongje medical school, is generally recognized as the first modern school for Korean medicine. However, there is very limited information concerning its establishment, duration period, governance, location, and contents for teaching. We found several points which are different from popular opinions through investigating news articles of those days and maps. Dongje school has established on June 1, 1906 and the time of its discontinuance is not clear. The school was founded with the cooperation of three former government officials of the Korean Empire, Eungse Lee (李應世), Piljoo Kang (姜弼周), and Dongho Cho (趙東浩) and many people donated fund for supporting Dongje school. However, there is no evidence of national or royal expenditures for operating the school. Dongje school has been established in 76-6, Seohak hill (西學峴), Yeogyeong-bang (餘慶坊), West county (西署), Seoul and moved to Naesum-si (內贍寺) located in Bongsangsi front village (奉常寺前門洞), Indal-bang (仁達坊), West county, at September 1906. The curriculum of the school comprehends several disciplines including literature in Korean and Chinese, mathematics, foreign language, physics, and Western medicine, as well as Korean medicine. Particularly at that time, they thought both of women and men. To elucidate the issue of the governance of Dongje school regarding the national or royal establishment, more information and extensive studies should be needed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.312-318
• /
• 2022

This paper proposes a model which classifies the type of guns and information about sound source location using deep neural network. The proposed classification model is composed of convolutional neural networks (CNN) and long short-term memory (LSTM). For training and test the model, we use the Gunshot Audio Forensic Dataset generated by the project supported by the National Institute of Justice (NIJ). The acoustic signals are transformed to Mel-Spectrogram and they are provided as learning and test data for the proposed model. The model is compared with the control model consisting of convolutional neural networks only. The proposed model shows high accuracy more than 90 %.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.39-44
• /
• 2023

Renewable energy such as solar and wind power is a resource that is sensitive to weather conditions and environmental changes. Since the amount of power generated by a facility can vary depending on the installation location and structure, it is important to accurately predict the amount of power generation. Using meteorological data, a data preprocessing process based on principal component analysis was conducted to monitor the relationship between features that affect energy production prediction. In addition, in this study, the prediction was tested by reconstructing the dataset according to the sensitivity and applying it to the machine learning model. Using the proposed model, the performance of energy production prediction using random forest regression was confirmed by predicting energy production according to the meteorological environment for new and renewable energy, and comparing it with the actual production value at that time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.219-230
• /
• 2023

Marine waste is classified according to its location into coastal waste, floating waste, and submerged waste. As awareness of environmental issues increases, research on marine submerged waste in addition to visible trash is needed. In Korea, which is surrounded by the sea on three sides, this is a study on the distribution of marine sedimentary waste by type in the West Sea of Korea. Through the study, waste synthetic resin, scrap metal, waste tires, and others appeared in the order of large amounts. As a result showing the seriousness of waste synthetic resin among sediments deposited in the West Sea, it is expected to have a huge impact not only on the marine ecosystem but also on our lives in the near future. Through this study, it is judged that it will be helpful for future collection activities by recognizing marine submerged waste that was not known because it was invisible.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.626-643
• /
• 2023

As mobile forensics has emerged as an essential technique, the demand for technology development, education and training is increasing, wherein images are used. Academic societies in South Korea and national institutions in the US and the UK are leading the Mobile Forensic Image development. However, compared with disks, images developed in a mobile environment are few cases and have less active research, causing a waste of time, money, and manpower. Mobile Forensic Images are also difficult to trust owing to insufficient verification processes. Additionally, in South Korea, there are legal issues involving the Telecommunications Business Act and the Act on the Protection and Use of Location Information. Therefore, in this study, we requested a review of a standard model for the development of Mobile Forensic Image from experts and designed an 11-step development model. The steps of the model are as follows: a. setting of design directions, b. scenario design, c. selection of analysis techniques, d. review of legal issues, e. creation of virtual information, f. configuring system settings, g. performing imaging as per scenarios, h. Developing a checklist, i. internal verification, j. external verification, and k. confirmation of validity. Finally, we identified the differences between the mobile and disk environments and discussed the institutional efforts of South Korea. This study will also provide a guideline for the development of professional quality verification and proficiency tests as well as technology and talent-nurturing tools. We propose a method that can be used as a guide to secure pan-national trust in forensic examiners and tools. We expect this study to strengthen the mobile forensics capabilities of forensic examiners and researchers. This research will be used for the verification and evaluation of individuals and institutions, contributing to national security, eventually.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.54-57
• /
• 1998

As the physical layer on telecommunication network is replaced fiber optic lines, it is increased the need of systematic maintenance for fiber optic lines. Korea Telecom has developed FLOMS in order to establish maintenance processes for optical fiber lines. FLOMS has functions which manages optical facilities and tests optical fiber lines automatically. As a resuls, this system can check and/or report a fault. Operator, who is reponsible for management of optical fiber lines, can test the characteristics of optical fiber lines remotely using FLOMS. As interpoerable with Digital Transmission Management System, FLOMS provides efficient management for optical fiber lines. This system improves the work process to find fault location fast, detect the degradation of fiber quality, and make database of optical facilities efficiently.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.41-46
• /
• 2023

UWB is a type of technology used for indoor positioning and is characterized by higher accuracy than RSSI-based schemes. Mobile equipment operating based on ROS can monitor the environment around the equipment using lidar and cameras. When applying the loop closing technique to determine the starting position in this monitoring process, the existing method has a problem of low accuracy because the closing operation occurs only when there are feature points on the image. In this paper, to solve this problem, we designed a system that increases the accuracy of loop closing work by providing location information by mounting a UWB tag on a mobile device. In addition, the accuracy of the UWB-based indoor positioning system was evaluated through experiments, and it was verified that it could be used for loop closing techniques.