• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.1
• /
• pp.27-32
• /
• 2024

Recently, in the era of the 4th industry, the era of smart agriculture is progressing with the use of related core technologies in the agricultural sector. As a representative example, the use of drones for pest control is increasing, and the use in the agricultural sector is increasing, and the existing control method is being changed by replacing the aging population. However, the importance of control management is increasing due to the increase in agricultural control drones. In this study, various civil complaints are occurring due to the non-standardization of the control operator's work instructions, control area allocation, and control settlement. In this study, we try to resolve civil complaints by computerizing various tasks that occur from the drone control manager's point of view and computerizing them so that they can be managed. Through this, it is intended to manage the control area for large areas and use it as basic data for the development of control management system.

• Korean Journal of Food Science and Technology
• /
• v.24 no.4
• /
• pp.320-325
• /
• 1992

For natural antioxidant test, the Rhus javanica $Linn\'{e}$ was extracted by 75% ethyl alcohol and fractionated it by chloroform and ethyl acetate using separatory funnel and column chromatography. In the Rhus javanica L. extract, the effective material was disolved easily in ethyl acetate and chloroform. When 600 ppm of ethyl acetate fraction of the extract was added to palm oil and lard, AI(antioxidant index) of each oil was 1.60 and 3.90 respectively. The $CHCl_3$ and EtOAc fractions were more effective than whole extract of Rhus javanica L. The palm oil, lard and soybean oil containing different levels of the Rhus javanica L. extract were stored at $60^{\circ}C$ to compare their antioxidative activity. Peroxide value, acid value and TBA value of each oil were monitored. The Rhus javanica L. extract was very effective to retard oxidation of palm oil and lard. This result coincided with Ranimat test.

• Proceedings of KOSOMES biannual meeting
• /
• 2005.05a
• /
• pp.129-134
• /
• 2005

Currently AIS needs high efficiency and safety in terms of operational management and, in the aspect of service range, it is time to minimize shadow regions through conductivity evaluation of AIS transmitter. Thus this study analyzes shadow regions and the reach of waves from stations through AIS conductivity evaluation. First, this study examines the characteristics of AIS wave and draws up methods to analyze the reach of waves according to the characteristics. Second, this study finds out service regions and shadow regions of the 22 stations across the nation by analyzing the actual data based on climate and topography. Lastly, this study summarizes the results of wave conductivity evaluation and conductivity problems and proposes improvement measures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1486-1494
• /
• 2021

Character recognition is a technology required in various platforms, such as smart parking and text to speech, and many studies are being conducted to improve its performance through new attempts. However, with low-quality image used for character recognition, a difference in resolution of the training image and test image for character recognition occurs, resulting in poor accuracy. To solve this problem, this paper designed an end-to-end learning neural network that combines image super-resolution and character recognition so that the character recognition model performance is robust against various quality data, and implemented an alternative whole learning algorithm to learn the whole neural network. An alternative end-to-end learning and recognition performance test was conducted using the license plate image among various text images, and the effectiveness of the proposed algorithm was verified with the performance test.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.37-47
• /
• 2022

Autonomous delivery operation data is the key to driving a paradigm shift for last-mile delivery in the Corona era. To bridge the technological gap between domestic autonomous delivery robots and overseas technology-leading countries, large-scale data collection and verification that can be used for artificial intelligence training is required as the top priority. Therefore, overseas technology-leading countries are contributing to verification and technological development by opening AI training data in public data that anyone can use. In this paper, 326 objects were collected to trainn autonomous delivery robots, and artificial intelligence models such as Mask r-CNN and Yolo v3 were trained and verified. In addition, the two models were compared based on comparison and the elements required for future autonomous delivery robot research were considered.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.37-53
• /
• 2023

The AI based intelligent command and control system can automatically analyzes the properties of intricate battlefield information and tactical data. In addition, commanders can receive situation analysis results and battlefield awareness through the system to support decision-making. It is necessary to build a battlefield situation analysis dataset similar to the actual battlefield situation for learning AI in order to provide decision-making support to commanders. In this paper, we explain the next step of the dataset construction method of the existing previous research, 'A Virtual Battlefield Situation Dataset Generation for Battlefield Analysis based on Artificial Intelligence'. We proposed a method to build the dataset required for the final battlefield situation analysis results to support the commander's decision-making and recognize the future battlefield. We developed 'Dataset Generator SW', a software tool to build a learning dataset for battlefield situation analysis, and used the SW tool to perform data labeling. The constructed dataset was input into the Siamese Network model. Then, the output results were inferred to verify the dataset construction method using a post-processing ranking algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.186-191
• /
• 2023

Data processing techniques play a critical role in decision-making, including handling missing and outlier data, prediction, and recommendation models. This requires a clear explanation of the validity, reliability, and accuracy of all processes and results. In addition, it is necessary to solve data problems through explainable models using decision trees, inference, etc., and proceed with model lightweight by considering various types of learning. The multi-layer mining classification method that applies the sixth principle is a method that discovers multidimensional relationships between variables and attributes that occur frequently in transactions after data preprocessing. This explains how to discover significant relationships using mining on transactions and model the data through regression analysis. It develops scalable models and logistic regression models and proposes mining techniques to generate class labels through data cleansing, relevance analysis, data transformation, and data augmentation to make explanatory decisions.

• Korean Journal of Materials Research
• /
• v.7 no.2
• /
• pp.145-151
• /
• 1997

Remelting of $A-Si/SiC_{p}$ composites followed by isothermal holding and solidification, leads ro the settling of Sic particles to the bottom of the mold. With the isothermal holding time for molten $A-Si/SiC_{p}$ composites. the particle free zone increases rapidly up to approximately first 30 minutes of the holding time. Experimental resulls of the particle settling confirm that the larger SIC particles sink faster tlun the sniiller particles. An increase in volume fraction of Sic particles decreases the setrling velocity of the particles.

• Journal of Welding and Joining
• /
• v.21 no.2
• /
• pp.57-63
• /
• 2003

Since new types of vehicles or structures made from thin aluminum alloy are under rapid development and some products are already on the market, welding of aluminium sheet is increasing. MIG(Metal Inert Gas), MIG-Pulse, TIG(Tungsten Inert Gas) welding are the typical Ai welding. MIG welding has the advantage of high speed, but it is difficult to apply to the thin plate, because of bum-through by the high heat input and spatter. MIG-Pulse welding can weld without spatter and burn-through, but when the gap exists at the welding joint, there is quite a possibility of bum-through. TIG welding is difficult to weld at a high speed. AC Pulse welding alternates between DCEP(Direct Current Electrode Positive) and DCEN(Direct Current Electrode Negative). DCEN is higher wire melting rate than DCEP, while lower temperature of droplet than DCEP. In AC Pulse welding, far fixed welding current, wire melting rate increases as the EN ratio increases. For fixed wire feed rate, welding current decreases as the EN ratio increases. Because of these features, the temperature of droplet, the depth of penetration, the width of bead decrease and the reinforcement height increases as EN ratio increases, and these are able to weld at a high speed, lower heat input. It is the purpose of this study that design of AC pulse current waveform for MIG welding of Al sheet and estimation of output characteristic.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.194-202
• /
• 2008

In this study, we investigated the tribology behaviour of two different bearing materials. One of these alloys content is Cu(90)-Sn(10) alloy and is widely used in the automotive industry.The other is Al alloy. This bearing content is Al-Sn-Si-Cu. Therefore, it is required to study on the lublicating characteristics of bearing according to different materials. In this study, compressor bearings made by respectively "PTFE solid lubricant" and "AI alloy with superior load carrying capacity, rubbing and impact endurance", have gone through journal bearing test. Lubrication and abrasion characteristics are evaluated by analyzing the material characteristics of a scroll compressor bearing bush. The AI alloy bearing showed the most excellent lubrication and abrasion characteristics than Cu-Sn alloy under high load condition.