• Convergence Security Journal
• /
• v.21 no.3
• /
• pp.57-66
• /
• 2021

As the detection performance using deep learning and machine learning of the intrusion detection field has been verified, the cases of using it are increasing day by day. However, it is difficult to collect the data required for learning, and it is difficult to apply the machine learning performance to reality due to the imbalance of the collected data. Therefore, in this paper, A mixed sampling technique using t-SNE visualization for imbalanced data processing is proposed as a solution to this problem. To do this, separate fields according to characteristics for intrusion detection events, including payload. Extracts TF-IDF-based features for separated fields. After applying the mixed sampling technique based on the extracted features, a data set optimized for intrusion detection with imbalanced data is obtained through data visualization using t-SNE. Nine sampling techniques were applied through the open intrusion detection dataset CSIC2012, and it was verified that the proposed sampling technique improves detection performance through F-score and G-mean evaluation indicators.

• Industry Promotion Research
• /
• v.6 no.1
• /
• pp.1-7
• /
• 2021

We investigated multi-layer perceptrons and supervised learning algorithms, and also examined how to model functional relationships between covariates and response variables using a package called neuralnet. The algorithm applied in this paper is characterized by continuous adjustment of the weights, which are parameters to minimize the error function based on the comparison between the actual and predicted values of the response variable. In the neuralnet package, the activation and error functions can be appropriately selected according to the given situation, and the remaining parameters can be set as default values. As a result of using the neuralnet package for the infertility data, we found that age has little influence on infertility among the four independent variables. In addition, the weight of the neural network takes various values from -751.6 to 7.25, and the intercepts of the first hidden layer are -92.6 and 7.25, and the weights for the covariates age, parity, induced, and spontaneous to the first hidden neuron are identified as 3.17, -5.20, -36.82, and -751.6.

• The Southeast Asian review
• /
• v.28 no.4
• /
• pp.1-29
• /
• 2018

The purpose of this study is to review the Southeast Asian studies in Korea in a comprehensive way and to set a new task for our academic community. To do this, I tried to analyze the total amount and trends of scholarly achievement (thesis, journal articles, and academic books). The content is divided into research history, research accumulation, and researcher scale. The history of research dates back more than we thought and was decentralized. Research accumulation is becoming more and more pluralistic. The number of researchers from various academic fields was higher than expected. The newly discovered Southeast Asian studies of Korea suggests the task of increasing the inclusiveness of our academic community. The KASEAS (Korean Association of Southeast Asian Studies) seems to be narrow and stagnant compared to the trend of Southeast Asian studies in Korea, which is constantly growing quantitatively, academically spreading, and transcending nationality. In order to increase the inclusiveness of the KASEAS, efforts should be made to open a variety of decentralized and autonomous study groups, to invite domestic graduate students from Southeast Asia, and to spread the university's foothold as a point of contact between pluralistic disciplines.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.2
• /
• pp.115-125
• /
• 2003

As Web services are generally open for external uses and not filtered by Firewall, these result in attacker's target. Web attacks which exploit vulnerable web-applications and malicious users' requests cause economical and social problems. In this paper, we are modelling general web service usages based on user-web-session and detect anomal usages with Bayesian estimation method. Finally we propose SAD(Session Anomaly Detection) for detection unknown web attacks. To evaluate SAD, we made an experiment on attack simulation with web vulnerability scanner, whisker. The results show that the detection rate of SAD is over 90%, which is influenced by several features such as size of window or training set, detection filter method and web topology.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.4
• /
• pp.183-194
• /
• 2020

Recently, the number of hip dysplasia (DDH) that occurs during infant and child growth has been increasing. DDH should be detected and treated as early as possible because it hinders infant growth and causes many other side effects In this study, two modelling techniques were used for multiple training techniques. Based on the results after the first transformation, the training was designed to be possible even with a small amount of data. The vertical flip, rotation, width and height shift functions were used to improve the efficiency of the model. Adam optimization was applied for parameter learning with the learning parameter initially set at 2.0 x 10e-4. Training was stopped when the validation loss was at the minimum. respectively A novel image overlay system using 3D laser scanner and a non-rigid registration method is implemented and its accuracy is evaluated. By using the proposed system, we successfully related the preoperative images with an open organ in the operating room

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.567-591
• /
• 2021

This study examined the curriculum of 23 graduate schools of archival sciences in the United States, Canada, the United Kingdom, and Australia and 25 graduate schools of archival sciences in Korea, and compared core knowledge categories. The average number of courses in Korea and other countries was similar, but each university in other countries set required courses, and few in Korea. As a result of comparison by knowledge category, all knowledge categories in North America were opened as individual courses, while the UK and Australia did not open knowledge categories of outreach, instruction, advocacy, and knowledge categories of professionalism separately. In Korea, the category of outreach, instruction, advocacy, the knowledge category of professionalism, and the knowledge category of information technology have not been established separately, while courses related to history and administration are subdivided. In order to reform the archival science education in Korea, the knowledge categories for archival professionals should be prepared and the guidelines and certification standards for the education should be established.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1223-1230
• /
• 2021

Recently, energy resource management is a major concern around the world. Energy management activities minimize environmental impacts of the energy production. This paper presents design and prototyping of a home electric energy monitoring system that provides residential consumers with real time information about their electricity use. The developed system is composed of an in-house sensing system and a server system. The in-home sensing system is a set of wireless smart plug which have an AC power socket, a relay to switch the socket ON/OFF, a CT sensor to sense current of load appliance and a Kmote. The Kmote is a wireless communication interface based on TinyOS. Each sensing node sends its detection signal to a home gateway via wireless link. The home gateway stores the received signals into a remote database. The server system is composed of a database server and a web server, which provides web-based monitoring system to residential consumers. We analyzed and presented energy consumption data from electrical appliances for 3 months in home. The experimental results show the promising possibilities to estimate the energy consumption patterns and the current status.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.201-206
• /
• 2022

In this paper, a flushing system with automatic opening and closing function of the toilet cover was studied. It works by an infrared sensor attached to the cover is detected or not. When the infrared sensor of the open function detects it, the servomotor is driven on the toilet cover to raise the cover, and when the infrared sensor with the close function detects the infrared sensor, the cover is set to be lowered. A tilt sensor is attached to the inside of the cover to operate when the cover goes down, and when this is activated, the servomotor connected to the toilet lever opens the stopper of the supply port and sends water down. In addition, we minimized the inconveniences for the next user when they use the toilet by using the non-contact water level sensor and LED function to notice the water is clogged during the flushing process. Also, we implemented UV-LED function to prevent bacterial growth while the toilet is closed.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.4
• /
• pp.23-31
• /
• 2021

PURPOSE: This study compared the effect of training ankle joint and hip joint thera-band exercise on balance. METHODS: The participants were divided into two groups of 11 each. Group A performed hip exercise after ankle exercise, and Group B performed ankle exercise after hip exercise. Using a green thera-band, the dorsiflexion and plantarflexion and hip flexion and hip extension were exercised repeatedly for 15 seconds three times with a five-second rest between each set. After the exercise and measurement of one area were complete, the exercise and measurement of the other area were performed at one-day intervals. The balance ability was assessed using a Tetrax and Y-balance test and repeated three times; the best values were taken. RESULTS: In the stability index (ST) of the static balance, the hip joint exercise group (HTG) during the follow-up of normal eye open (NO) revealed notable improvement over the ankle joint exercise group (ATG), and in the follow-up of the normal eye closed (NC), the ATG showed significant improvement over the HTG. In the pillow with eye closed (PC) follow-up, the ATG showed significant improvements over the HTG. At the left (Lt) and Y-balance test (YBT), the ATG showed significant improvements in the follow-up over the HTG (p <.05). CONCLUSION: In static balance, the ATG showed significant improvement in the follow-up of NC and PC over the HTG. In the dynamic balance, the Lt. dynamic balance on the non-dominant side in the ATG showed significant improvement in the follow-up over the HTG.

• International Journal of Advanced Culture Technology
• /
• v.10 no.3
• /
• pp.146-155
• /
• 2022

The purpose of this study is to investigate the recyclability of Shenlong in China using SWOT. The main analysis results are as follows. First, provided that the company's current capacity utilization rate is seriously insufficient, reducing staff is one among the effective ways. Second, Shenlong should open a web store to cater to young people's online shopping behavior, and further expand the brand visibility using national mainstream media and online shopping platforms like Taobao and JingDong to market Dongfeng Peugeot and Dongfeng Citroen on the whole network. Third, under the premise of maintaining the present best-selling models, Shenlong should appropriately reduce the amount of models, adjust the assembly capacity ratio of every model and every displacement in real time per the newest market trends, increase the agility of auto companies' production, and timely meet the wants of domestic consumers. Fourth, dual-brand coordination and channel integration are very necessary, and also the profitability and profitability of dealers are going to be further improved, thereby increasing sales. Fifth, target building new energy leading products of Shenlong, strive to attain the forefront of the industry within the sales of recent energy vehicles within 5 years, and gradually expand new energy vehicle products from passenger vehicles to passenger vehicles and commercial vehicles. Finally, the marketing field of Shenlong Automobile should achieve "three major changes", that is, change from a goal-driven type to a demand-driven type, cancel the bundling of outlet invoicing goals and delivery incentive tiers; start from basic capabilities, and set pragmatic and challenging goals; focus Channels, to realize following the activation of outlets, and single store sales increase.