• The Journal of the Convergence on Culture Technology
• /
• v.5 no.4
• /
• pp.361-366
• /
• 2019

Exchanging sheets for patients is one of the worst and one of the factors that makes the nursing environment difficult. Many beds with various functions for the patient have already been developed, but there is no device for automatically changing the sheets. In this study, we developed and tested the first automatic sheet changer for a medical bed and verified its performance. The developed automatic seat changer uses a torque limiter to properly adjust tension and exchange a dirty sheet and a new seat at the same time. The designed automatic sheet changer was experimentally confirmed to be properly operated and installed in a integrated multi-functional bed with bed sores prevention and automatic patient transfer functions.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.52 no.6
• /
• pp.9-17
• /
• 2010

In this paper, an automatic cruise system of unmanned boat was developed for surveying water depth in reservoir using GIS (geographic information system)-GPS (global positioning system) Technologies. the automatic cruise system consisted of an automatic path generation program (APGP) and an automatic boat control program (ABCP). A grid processing method with $3{\times}3$ roving window in GIS function was used to develop the APGP. For development of the ABCP, GPS and its coordinate calculation technique were introduced. The developed system was tested to verify the applicability for a sample reservoir, Misan reservoir located on Ansan city of Kyunggi province. From the test results, this study found the APGP generated cruise path automatically according to input condition on grid size of 5 m, 10 m, and 20 m, as well as, the ABCP also tracked well the cruise paths with high position accuracy. Another verification result on surveying time for 20 ha of water area also showed that the new system could survey water depth of reservoir quickly, including very high quality of spatial resolution.

• Language and Information
• /
• v.15 no.2
• /
• pp.23-45
• /
• 2011

This paper proposes a statistical-based linguistic methodology for automatic mapping between large-scale heterogeneous languages resources for NLP applications in general. As a particular case, it treats automatic mapping between two large-scale heterogeneous Korean language resources: Sejong Semantic Classes (SJSC) in the Sejong Electronic Dictionary (SJD) and nouns in KorLex. KorLex is a large-scale Korean WordNet, but it lacks syntactic information. SJD contains refined semantic-syntactic information, with semantic labels depending on SJSC, but the list of its entry words is much smaller than that of KorLex. The goal of our study is to build a rich language resource by integrating useful information within SJD into KorLex. In this paper, we use both linguistic and statistical methods for constructing an automatic mapping methodology. The linguistic aspect of the methodology focuses on the following three linguistic clues: monosemy/polysemy of word forms, instances (example words), and semantically related words. The statistical aspect of the methodology uses the three statistical formulae ${\chi}^2$, Mutual Information and Information Gain to obtain candidate synsets. Compared with the performance of manual mapping, the automatic mapping based on our proposed statistical linguistic methods shows good performance rates in terms of correctness, specifically giving recall 0.838, precision 0.718, and F1 0.774.

• Journal of the Korean Society for information Management
• /
• v.27 no.3
• /
• pp.265-281
• /
• 2010

The proposed method in this study is the Maximal Concept-Strength Recognition Method(MCR). In case that we don't know which database is the most suitable for automatic-classification when new database is imported, MCR method can support to select the most similar database among many databases in the legacy system. For experiments, we constructed four heterogeneous scholarly databases and measured the best performance with MCR method. In result, we retrieved the exact database expected and the precision value of MCR based automatic-classification was close to the best performance.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.2
• /
• pp.227-233
• /
• 2019

In recent years, vehicle fires account for the second highest rate after residential fires. It accounts for more than 10.7% of the total fire occurrence rate. Vehicle fires are very difficult to evolve at an early stage. Most of the vehicles are burned down in the event of a fire, resulting in a lot of physical and personal damage. In the EU and other countries, efforts are being made to install automatic fire extinguishing systems in preparation for vehicle fires. In addition, since the automatic fire extinguishing system applied to a vehicle must operate in a moving state of a car, a method for detecting a fire is needed. Therefore, this paper proposes a structure of an automatic fire extinguishing system that can evolve a fire when a fire occurs in a commercial vehicle among various vehicles. Especially, it confirms the feasibility of the automatic fire extinguishing system simulated in the laboratory environment and confirms its applicability.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.87-94
• /
• 2024

Children with speech sound disorders (SSDs) face various challenges in producing speech sounds, which often lead to significant social and educational barriers. Detecting and treating SSDs in children is complex due to the variability in disorder severity and diagnostic boundaries. This study aims to develop an automated SSD detection system using deep learning models, leveraging their ability to transcribe audio, efficiently capture sound patterns on a vast scale, and address the limitations of traditional methods involving speech-language pathologists. For this study, we collected audio recordings from 573 children aged two to nine using standardized prompts from the Assessment of Phonology and Articulation for Children. Speech-language pathologists analyzed the recordings and identified 92 children with SSDs. To build an automatic SSD detection system, we used a dataset to train neural network models for automatic speech recognition and audio classification. Five different methods are studied, with the best method achieving 73.9% unweighted average recall. While the results show the potential of using deep learning models for the automatic detection of SSDs in children, further research is needed to improve the reliability of the models widely used in practice.

• Spatial Information Research
• /
• v.15 no.2
• /
• pp.181-187
• /
• 2007

To make digital terrain data, automatic correlation matching by stereo airborne/satellite images has been researched. The result of automatic correlation matching has a limit on extracting exact ground height because of angle of sensor, tree of height. Therefore, the amount of editing works depend on the distribution of spatial feature in images as well as image quality. This paper shows that the automatic correlation matching result was affected by density and height of tree.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.1179-1186
• /
• 2003

This study is described about development method and application of developed automatic design program. Automatic design program is the object-oriented program which based on mathematical algorithm. Automatic design program can do mathematic operation according to program contents. Also it can do modeling of shape. Shape modeling method is based on mathematical and geometrical algorithm. And created models can generate NC manufacturing program from CAM software. Also STL file format that is changed form created models can do RP manufacturing.

• Proceedings of the Korean Magnestics Society Conference
• /
• 2007.05a
• /
• pp.310.1-310.1
• /
• 2007