• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.423-432
• /
• 2022

Due to the development of treatments due to COVID-19, the Firm-value of the pharmaceutical industry has increased. However, the development of treatments has been delayed, and the development of overseas markets has become difficult due to COVID-19. Therefore, this study aims to present an efficient management plan for each firm by analyzing the management efficiency of these firms. As for the research method, DEA analysis was conducted for the pharmaceutical industry. Through this method, we propose values of input variables that inefficient companies can benchmark. As a result of the analysis, there was no significant difference in management efficiency before and after COVID-19, but it was confirmed that the management efficiency of certain Firm decreased. Through this study, it is possible to judge a Firm's survival competitiveness and management strategy, and furthermore, a plan to continuously grow and enhance competitiveness was suggested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.120-122
• /
• 2021

Currently, as demand for cars at home and abroad increases, the number of vehicles is decreasing and the number of vehicles is increasing. This is the main cause of the traffic jam. To solve this problem, it operates a high-ocompancy vehicle (HOV) lane, a multi-passenger vehicle, but many people ignore the conditions of use and use it illegally. Since the police visually judge and crack down on such illegal activities, the accuracy of the crackdown is low and inefficient. In this paper, we propose a system design that enables more efficient detection using imaging techniques using computer vision to solve such problems. By improving the existing vehicle detection method that was studied, the trigger was set in the image so that the detection object can be selected and the image analysis can be conducted intensively on the target. Using the YOLO model, a deep learning object recognition model, we propose a method to utilize the shift amount of the center point rather than judging by the bounding box in the image to obtain real-time object detection and accurate signals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.60-68
• /
• 2024

Purpose: When designing plants and workplaces such as handling and using chemicals, a system that can automatically determine whether the design has been made in compliance with domestic safety management laws is established to shorten the review time and increase accuracy. Method: Safety design standards for chemical handling and use workplaces were investigated, and types and systems were derived that could automatically judge design errors by dividing the articles into semantic units. Result: An automatic design review method performed when designing a building was proposed, and a system that can review the safety design requirements required when designing a chemical handling business site through the development of a rule checker was proposed. After confirming whether the law is subject to application, the safety design rules are classified into semantic units through preprocessing. The classified results can be classified into four types, and the specifications, space, conditions, situations, and specific devices and facilities to reinforce safety were analyzed as representative types. It proposes a system that prepares a diagram for the safety design rule and allows it to be reviewed through the rule checker program.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.967-974
• /
• 2024

This paper propose a method for detecting defects in 3D printer outputs using a transmissive photo sensor. The transmissive photo sensor measures the transmittance of the material and is used to detect defects that may occur during the printing process. To this end, the transmissive photo sensor is integrated into the 3D printer platform, and an algorithm that processes the data obtained from the sensor in real time to judge the presence of defects was developed. The results of the experiment confirmed that the propoesd system can quickly detect a variety of defects that occur during the manufacturing process. Not only can these results play a crucial role in quality control and productivity enhancement of 3D printers, but they also have potential for application in the manufacturing industry. In the future, it is expected that the defect detection system based on the proposed method will improve the stability and efficiency fo the manufacturing process.

• Journal of Distribution Science
• /
• v.14 no.5
• /
• pp.107-114
• /
• 2016

Purpose - Loading can decrease the productivity due to the possibility of carrying out with the opposite order of storage in container terminal. When the container is to be taken out, it is needed to move the container stacked upon the container to be carried out to other place temporarily. It is called as rehandling. Remarshalling, with the loading plan, is the arranging the containers before the ship arrives in order to avoid the rehandling during the carrying out. The present study tried to find out the factors affecting the efficiency when building the remarshalling plan with the utilization of neighboring storage space as a outer slot, and analyzed the efficiency of several remarshalling algorithms with the combination of those factors. Research design, data and methodology - The present study used, when the remarshalling plan is prepared for utilizing the outer slot, the simulation methods in order to compare the efficiency of the remarshalling algorithms which made with the factors affecting the efficiency. The factors affecting the efficiency are the method of making the child node, method of arrangement, and possibility of application of FIX. In order to analyze the affecting factors on the efficiency, several algorithms are prepared with the combination of production of the child node and the arrangement method with the availability of FIX application. With this algorithm, the effect of the factors on the efficiency after building up of remarshalling plan with the target on the bay with 10 rows, 8 columns, and 10 indices. Results - The method of rearrangement and making of a child node as the factor affecting the efficiency of remarshalling utilization of the outer bay were studied. It is efficient to combine the method of making a child node with MCS in order to reduce the number of moving the containers. For reducing the time in carrying out, it was found that all arrangement methods should be combined with RCS for the efficiency. The result of experiment shows the application of FIX with good result in case of succession ratio. In addition, when FIX was not applied, all of the most combinations resulted in short time in remarshalling. As a result, it can be concluded that the algorithm with proper combination of making the child node and the arrangement can increase the job efficiency based on the importance. Conclusion - The present study suggested and analyzed the algorithms with the combination of the arrangement method, the making of child node, and FIX. It is needed to develop the algorithm to judge the possibility whether the best remarshalling plan can be built or not within the bay in order to find a better method between the two cases such as within the bay and outer the bay. As a method for extending the study on the factors affecting the efficiency, it is possible to find out the way to build the remarshalling plan within the permitted time under any storage situation.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.896-906
• /
• 2014

In this paper, a real-time dual-mode temporal synchronization and compensation method based on a new reliability measure in stereoscopic video is proposed. The goal of temporal alignment is to detect the temporal asynchrony and recover synchronization of the two video streams. The accuracy of the temporal synchronization algorithm depends on the 3DTV contents. In order to compensate the temporal synchronization error, it is necessary to judge whether the result of the temporal synchronization is reliable or not. Based on our recently developed temporal synchronization method[1], we define a new reliability measure for the result of the temporal synchronization method. Furthermore, we developed a dual-mode temporal synchronization method, which uses a usual texture matching method and the temporal spatiogram method[1]. The new reliability measure is based on two distinctive features, a dynamic feature for scene change and a matching distinction feature. Various experimental results show the effectiveness of the proposed method. The proposed algorithms are evaluated and verified through an experimental system implemented for 3DTV.

• Journal of the Korean GEO-environmental Society
• /
• v.14 no.8
• /
• pp.53-60
• /
• 2013

The compaction control method of national road substructure is using field density test to determine the relative compaction and plate bearing test to check the load bearing capacity. However, these two tests digitize a construction site manager's judgment based on his experience, so mechanical basis is weak. Resilient modulus method, which is recently being used to resolve such problem, is evaluated as a rational design method of pavement structure that can rationally reflect the stress-strain state of pavement materials that is caused by the condition of load repetition of vehicle load. However, the method of measuring the resilient modulus is difficult and lengthy, and it has many problems. To replace it, light falling weight test is recently being proposed as a simple test method. Therefore, this research uses dynamic plate loading test, which quickly and simply measures the elastic modulus of the subgrade and sub-base construction and site of maintenance, to judge the possibility of compaction control of the stratum under the road, and it proposes relation formula by analyzing the result of static load test.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.3
• /
• pp.1203-1213
• /
• 2013

Governmental accounting system has changed from budgetary accounting on the basis of cash and bookkeeping by single entry to financial accounting on the basis of accrual and bookkeeping by double entry. In the context of this transition, infrastructure becomes considered an asset in accounting, and resulting accounting methods also take different approaches from conventional budgetary accounting. Financial accounting system defines expenditures into two categories, i.e. capital expenditure(CAPEX) and operational expenditure(OPEX), and stipulates that the expenditure shall be divided into those two categories before accounting. The construction and expansion of infrastructure must be considered a CAPEX because it means a sort of asset acquisition, but with regard to applications in practical accounting, it is actually challenging to judge whether any expenditure associated with maintenance works (including repair and service) during use of infrastructure acquired shall be considered CAPEX or OPEX. This paper suggested an asset management based accounting method for sewer maintenance expenditure. And it applied the method to actual accounting cases and analyzed them in comparison with conventional financial information. As a case study result, Sewer asset value of S city increased approximately 700 hundred won because sewer maintenance expenditure are classified between OPEX and CAPEX according to the proposed accounting method. It is expected that the proposed accounting method will contribute significantly to providing any proper sewer asset value information.