• Smart Media Journal
• /
• v.11 no.5
• /
• pp.75-81
• /
• 2022

In order to respond to carbon neutrality and climate change in agriculture, agricultural machinery, which has been developed centered on internal combustion engines, needs to be converted to an electric-based technology that does not emit greenhouse gases. In this study, simulations for electric UTV suspension design were performed to reduce vibration and shock of electric UTV for agricultural use and to improve driving stability and control performance of the vehicle. The simulation was performed by dividing the tolerance load of the vehicle body and the loaded load state. The range of motion of the suspension spring of UTV is within 30% of the range of motion under condition B under tolerance, the displacement of the UTV suspension with full load is reduced from 264mm to 121mm, and the damping speed is 260mm/s to 300mm/s that it can be seen that the range of motion is within 60%. Suspension design of electric UTV for multi-purpose agricultural work is a very important factor for maintaining agricultural work ability in towing work such as tillage as well as driving and terrain adaptation. The results of this study can be usefully used to determine the spring parameters with the appropriate damping range so that the electric UTV can be used for various agricultural tasks.

• Therapeutic Science for Rehabilitation
• /
• v.11 no.2
• /
• pp.63-76
• /
• 2022

Objective : The purpose of this study is to examine the relationship with employment of the disabled considering the severity and the type of disability. Methods : Data from the 4th data of the 2nd wave Panel Survey of Employment for the Disabled (PSED) by Korea Employment Agency for Persons with Disabilities (KEAD) were used. The odds ratio of employment in disability types according to severity of disability was calculated by logistic regression analysis. Results : When the related variables were adjusted, the employment of internal disability type was significantly lower than that of external disability type by 0.413(95% CI:0.271-0.629) times in the group with severe disability. On the other hand, in the group with less severe disability, internal disability was 0.475(95% CI:0.327-0.690) times lower than that of external disability (p=<.001). Conclusions : Employment may vary depending on the type of disability, even if the disability severity level is the same. It is necessary to prepare judgment criteria that can reduce the variation in employment by considering both the type and severity of the disability.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.2
• /
• pp.256-265
• /
• 2021

Ground, sea and air mobility, such as vehicles, ships, and airplanes, are generally operated by people. Based on the innovative development of autonomous decision-making systems and artificial intelligence (AI) following the recent fourth industrial revolution, research and development on maritime autonomous surface ships (MASS) is been actively performed around the world. Before the realization of the commercialization of MASS in international maritime transport, it is urgent to clarify the characteristics of this ship and its international legal status. This paper aims to analyze the concern of whether a ship without crew members will eventually be operated as a fully unmanned ship or can be recognized as a ship under international law as the number of crew members is gradually reduced owing to the development stage of autonomous ships. Consequently, based on the United Nations Convention on the Law of the Sea (UNCLOS) and the regulations of the International Maritime Organization (IMO), it was found that MASS has the same international legal status as general ships. In addition this paper presents the working principles of enacting and revising the IMO Conventions and international legal measures necessary for the safe operation of MASS.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.105-118
• /
• 2022

The demand for information related to 3D spatial objects model in metaverse, smart cities, digital twins, autonomous vehicles, urban air mobility will be increased. 3D model construction for spatial objects is possible with various equipments such as satellite-, aerial-, ground platforms and technologies such as modeling, artificial intelligence, image matching. However, it is not easy to quickly detect and convert spatial objects that need updating. In this study, based on spatial information (features) and attributes, using matching elements such as address code, number of floors, building name, and area, the converged building DB and the detected building DB are constructed. Both to support above and to verify the suitability of object selection that needs to be updated, one system prototype was developed. When constructing the converged building DB, the convergence of spatial information and attributes was impossible or failed in some buildings, and the matching rate was low at about 80%. It is believed that this is due to omitting of attributes about many building objects, especially in the pilot test area. This system prototype will support the establishment of an efficient drone shooting plan for the rapid update of 3D spatial objects, thereby preventing duplication and unnecessary construction of spatial objects, thereby greatly contributing to object improvement and cost reduction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

Recently, the image processing industry has been activated as deep learning-based technology is introduced in the image recognition and detection field. With the development of deep learning technology, learning model vulnerabilities for adversarial attacks continue to be reported. However, studies on countermeasures against poisoning attacks that inject malicious data during learning are insufficient. The conventional countermeasure against poisoning attacks has a limitation in that it is necessary to perform a separate detection and removal operation by examining the training data each time. Therefore, in this paper, we propose a technique for reducing the attack success rate by applying modifications to the training data and inference data without a separate detection and removal process for the poison data. The One-shot kill poison attack, a clean label poison attack proposed in previous studies, was used as an attack model. The attack performance was confirmed by dividing it into a general attacker and an intelligent attacker according to the attacker's attack strategy. According to the experimental results, when the proposed defense mechanism is applied, the attack success rate can be reduced by up to 65% compared to the conventional method.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.99-109
• /
• 2023

Recently, not only in Korea but also around the world, we have been experiencing constant disasters such as typhoons, wildfires, and heavy rains. The property damage caused by typhoons and heavy rain in South Korea alone has exceeded 1 trillion won. These disasters have resulted in significant loss of life and property damage, and the recovery process will also take a considerable amount of time. In addition, the government's contingency funds are insufficient for the current situation. To prevent and effectively respond to these issues, it is necessary to collect and analyze accurate data in real-time. However, delays and data loss can occur depending on the environment where the sensors are located, the status of the communication network, and the receiving servers. In this paper, we propose a two-stage hybrid situation analysis and prediction algorithm that can accurately analyze even in such communication network conditions. In the first step, data on river and stream levels are collected, filtered, and refined from diverse sensors of different types and stored in a bigdata. An AI rule-based inference algorithm is applied to analyze the crisis alert levels. If the rainfall exceeds a certain threshold, but it remains below the desired level of interest, the second step of deep learning image analysis is performed to determine the final crisis alert level.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.967-971
• /
• 2023

Recently, a variety of AI-based platform services are available, and one of them is ChatGPT that processes a large quantity of data in the natural language and generates an answer after self-learning. ChatGPT can perform various tasks including software programming in the IT sector. Particularly, it may help generate a simple program and correct errors using C Language, which is a major programming language. Accordingly, it is expected that ChatGPT is capable of effectively using Verilog HDL, which is a hardware language created in C Language. Verilog HDL synthesis, however, is to generate imperative sentences in a logical circuit form and thus it needs to be verified whether the products are executed properly. In this paper, we aim to select small-scale logical circuits for ease of experimentation and to verify the results of circuits generated by ChatGPT and human-designed circuits. As to experimental environments, Xilinx ISE 14.7 was used for module modeling, and the xc3s1000 FPGA chip was used for module embodiment. Comparative analysis was performed on the use area and processing time of FPGA to compare the performance of ChatGPT products and Verilog HDL products.