• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.1
• /
• pp.290-296
• /
• 2019

Head-up displays for vehicles play an important role in displaying various information about the safety and convenience of driving on the windshield of the vehicle. In this study, ultra-precision machining was performed and evaluated as a method for machining a large-area aspheric free-form mirror that is applicable to augmented reality technology. Precision diamond cutting is highly accurate and suitable for the production of advanced parts with excellent surface integrity, low surface roughness, and low residual stress. By using an aspheric free-form mold, it is possible to improve the optical transfer function, reduce the distortion path, and realize a special image field curvature. To make such a mold, the diamond cutting method was used, and the result was evaluated using an aspherical shape-measuring machine. As a result, it was possible to the mold with shape accuracy (PV) below $1{\mu}m$ and surface roughness (Ra) below $0.02{\mu}m$.

• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.100-106
• /
• 2021

Measuring Intima-media thickness (IMT) with ultrasound images can help early detection of coronary artery disease. As a result, numerous machine learning studies have been conducted to measure IMT. However, most of these studies require several steps of pre-treatment to extract the boundary, and some require manual intervention, so they are not suitable for on-site treatment in urgent situations. in this paper, we propose to use deep learning networks U-Net, Attention U-Net, and Pretrained U-Net to automatically segment the intima-media complex. This study also applied the HE, HS, and CLAHE preprocessing technique to wireless portable ultrasound diagnostic device images. As a result, The average dice coefficient of HE applied Models is 71% and CLAHE applied Models is 70%, while the HS applied Models have improved as 72% dice coefficient. Among them, Pretrained U-Net showed the highest performance with an average of 74%. When comparing this with the mean value of IMT measured by Conventional wired ultrasound equipment, the highest correlation coefficient value was shown in the HS applied pretrained U-Net.

• Journal of Animal Science and Technology
• /
• v.65 no.3
• /
• pp.638-651
• /
• 2023

The objective of this study was to quantitatively estimate the level of grazing area damage in outdoor free-range pig production using a Unmanned Aerial Vehicles (UAV) with an RGB image sensor. Ten corn field images were captured by a UAV over approximately two weeks, during which gestating sows were allowed to graze freely on the corn field measuring 100 × 50 m². The images were corrected to a bird's-eye view, and then divided into 32 segments and sequentially inputted into the YOLOv4 detector to detect the corn images according to their condition. The 43 raw training images selected randomly out of 320 segmented images were flipped to create 86 images, and then these images were further augmented by rotating them in 5-degree increments to create a total of 6,192 images. The increased 6,192 images are further augmented by applying three random color transformations to each image, resulting in 24,768 datasets. The occupancy rate of corn in the field was estimated efficiently using You Only Look Once (YOLO). As of the first day of observation (day 2), it was evident that almost all the corn had disappeared by the ninth day. When grazing 20 sows in a 50 × 100 m² cornfield (250 m²/sow), it appears that the animals should be rotated to other grazing areas to protect the cover crop after at least five days. In agricultural technology, most of the research using machine and deep learning is related to the detection of fruits and pests, and research on other application fields is needed. In addition, large-scale image data collected by experts in the field are required as training data to apply deep learning. If the data required for deep learning is insufficient, a large number of data augmentation is required.

• Nuclear Engineering and Technology
• /
• v.56 no.7
• /
• pp.2690-2697
• /
• 2024

With advancements in machine learning technologies, artificial neural networks (ANNs) are being widely used to improve the performance of gamma-ray spectroscopy based on NaI(Tl) scintillation detectors. Typically, the performance of ANNs is evaluated using test datasets composed of actual spectra. However, the generation of such test datasets encompassing a wide range of actual spectra representing various scenarios often proves inefficient and time-consuming. Thus, instead of measuring actual spectra, we generated virtual spectra with diverse spectral features by sampling from categorical distribution functions derived from the base spectra of six radioactive isotopes: ⁵⁴Mn, ⁵⁷Co, ⁶⁰Co, ¹³⁴Cs, ¹³⁷Cs, and ²⁴¹Am. For practical applications, we determined the optimum counting time (OCT) as the point at which the change in the Kullback-Leibler divergence (ΔKLDV) values between the synthetic spectra used for training the ANN and the virtual spectra approaches zero. The accuracies of the actual spectra were significantly improved when measured up to their respective OCTs. The outcomes demonstrated that the proposed method can effectively determine the OCTs for gamma-ray spectroscopy based on ANNs without the need to measure actual spectra.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.51 no.3
• /
• pp.299-309
• /
• 2024

This study aimed to assess the competency of artificial intelligence (AI) in pediatric dentistry and compare it with that of dentists. We used open-source data obtained from the Korea Health Personnel Licensing Examination Institute. A total of 32 item multiple-choice pediatric dentistry exam questions were included. Two AI-based chatbots (ChatGPT 3.5 and Gemini) were evaluated. Each chatbot received the same questions seven times in separate chat sessions initiated on April 25, 2024. The accuracy was assessed by measuring the percentage of correct answers, and consistency was evaluated using Cronbach's alpha coefficient. Both ChatGPT 3.5 and Gemini demonstrated similar accuracy, with no significant differences observed between them. However, neither chatbot achieved the minimum passing score set by the Pediatric Dentistry National Examination. However, both chatbots exhibited acceptable consistency in their responses. Within the limits of this study, both AI-based chatbots did not sufficiently answer the pediatric dentistry exam questions. This finding suggests that pediatric dentists should be aware of the advantages and limitations of this new tool and effectively utilize it to promote patient health.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.255-265
• /
• 2007

In this paper, we propose a new illumination-robust drowsy driver monitoring system with single CCD(Charge Coupled Device) camera for intelligent vehicle in the day and night. For this system that is monitoring driver's eyes during a driving, the eye detection and the measure of eyelid movement are the important preprocesses. Therefore, we propose efficient illumination compensation algorithm to improve the performance of eye detection and also eyelid movement measuring method for efficient drowsy detection in various illumination. For real-time application, Cascaded SVM (Cascaded Support Vector Machine) is applied as an efficient eye verification method in this system. Furthermore, in order to estimate the performance of the proposed algorithm, we collect video data about drivers under various illuminations in the day and night. Finally, we acquired average eye detection rate of over 98% about these own data, and PERCLOS(The percentage of eye-closed time during a period) are represented as drowsy detection results of the proposed system for the collected video data.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.4
• /
• pp.371-376
• /
• 2017

In this paper, we propose an algorithm that can recognize the pattern regardless of the sensor position when performing EMG pattern recognition using circular EMG system equipment. Fourteen features were extracted by using the data obtained by measuring the eight channel EMG signals of six motions for 1 second. In addition, 112 features extracted from 8 channels were analyzed to perform principal component analysis, and only the data with high influence was cut out to 8 input signals. All experiments were performed using k-NN classifier and data was verified using 5-fold cross validation. When learning data in machine learning, the results vary greatly depending on what data is learned. EMG Accuracy of 99.3% was confirmed when using the learning data used in the previous studies. However, even if the position of the sensor was changed by only 22.5 degrees, it was clearly dropped to 67.28% accuracy. The accuracy of the proposed method is 98% and the accuracy of the proposed method is about 98% even if the sensor position is changed. Using these results, it is expected that the convenience of the users using the circular EMG system can be greatly increased.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2935-2940
• /
• 2023

A polystyrene phantom was developed following the guidance of the International Atomic Energy Association (IAEA) for gamma knife (GK) quality assurance. Its performance was assessed by measuring the absorbed dose rate to water and dose distributions. The phantom was made of polystyrene, which has an electron density (1.0156) similar to that of water. The phantom included one outer phantom and four inner phantoms. Two inner phantoms held PTW T31010 and Exradin A16 ion chambers. One inner phantom held a film in the XY plane of the Leksell coordinate system, and another inner phantom held a film in the YZ or ZX planes. The absorbed dose rate to water and beam profiles of the machine-specific reference (msr) field, namely, the 16 mm collimator field of a GK Perfexion^TM or Icon^TM, were measured at seven GK sites. The measured results were compared to those of an IAEA-recommended solid water (SW) phantom. The radius of the polystyrene phantom was determined to be 7.88 cm by converting the electron density of the plastic, considering a water depth of 8 g/cm². The absorbed dose rates to water measured in both phantoms differed from the treatment planning program by less than 1.1%. Before msr correction, the PTW T31010 dose rates (PTW Freiberg GmbH, New York, NY, USA) in the polystyrene phantom were 0.70 (0.29)% higher on average than those in the SW phantom. The Exradin A16 (Standard Imaging, Middleton, WI, USA) dose rates were 0.76 (0.32)% higher in the polystyrene phantom. After msr correction factors were applied, there were no statistically significant differences in the A16 dose rates measured in the two phantoms; however, the T31010 dose rates were 0.72 (0.29)% higher in the polystyrene phantom. When the full widths at half maximum and penumbras of the msr field were compared, no significant differences between the two phantoms were observed, except for the penumbra in the Y-axis. However, the difference in the penumbra was smaller than variations among different sites. A polystyrene phantom developed for gamma knife dosimetry showed dosimetric performance comparable to that of a commercial SW phantom. In addition to its cost effectiveness, the polystyrene phantom removes air space around the detector. Additional simulations of the msr correction factors of the polystyrene phantom should be performed.

• The Journal of Korean Academy of Prosthodontics
• /
• v.48 no.4
• /
• pp.294-300
• /
• 2010

Purpose: The template-guided implant surgery offers several advantages over the traditional approach. The purpose of this study was to evaluate the accuracy of coordinate synchronization procedure with 5-axis milling machine for surgical template fabrication by means of reverse engineering through universal CAD software. Materials and methods: The study was performed on ten edentulous models with imbedded gutta percha stoppings which were hidden under silicon gingival form. The platform for synchordination was formed on the bottom side of models and these casts were imaged in Cone beam CT. Vectors of stoppings were extracted and transferred to those of planned implant on virtual planning software. Depth of milling process was set to the level of one half of stoppings and the coordinate of the data was synchronized to the model image. Synchronization of milling coordinate was done by the conversion process for the platform for the synchordination located on the bottom of the model. The models were fixed on the synchordination plate of 5-axis milling machine and drilling was done as the planned vector and depth based on the synchronized data with twist drill of the same diameter as GP stopping. For the 3D rendering and image merging, the impression tray was set on the conbeam CT and pre- and post- CT acquiring was done with the model fixed on the impression body. The accuracy analysis was done with Solidworks (Dassault systems, Concord, USA) by measuring vector of stopping’s top and bottom centers of experimental model through merging and reverse engineering the planned and post-drilling CT image. Correlations among the parameters were tested by means of Pearson correlation coefficient and calculated with SPSS (release 14.0, SPSS Inc. Chicago, USA) ($\alpha$ = 0.05). Results: Due to the declination, GP remnant on upper half of stoppings was observed for every drilled bores. The deviation between planned image and drilled bore that was reverse engineered was 0.31 (0.15 - 0.42) mm at the entrance, 0.36 (0.24 - 0.51) mm at the apex, and angular deviation was 1.62 (0.54 - 2.27)$^{\circ}$. There was positive correlation between the deviation at the entrance and that at the apex (Pearson Correlation Coefficient = 0.904, P = .013). Conclusion: The coordinate synchronization 5-axis milling procedure has adequate accuracy for the production of the guided surgical template.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.3
• /
• pp.86-92
• /
• 2001

Position controls are very important in semiconductor manufacturing devices, machine tools, precision measuring instruments, etc. to measure the distance of movement of moving objects in minute units and the accuracy of measurement for the moving distance in these devices affect the performance of the whole devices. Therefore, in those precision instruments, a sensing device that can measure the distance of movement with high-precision resolution is required. Thus an optical encoder that has such advantages as easy digital interface, economical price, and a resolution similar to that of laser interferometers can be used. In this paper, a interferometer-type linear scale with easy digital interface and high-resolution has been set up and measured the distance of movement based on the diffraction principle. Interference signals produced in this optical setup of the linear scale have beers digitalized through fabricated photodetectors and designed signal processing circuits. A resolution of 0.5${\mu}{\textrm}{m}$ is acquired from the experimental interferometer-type linear scale without for the movement of scales any additional dividing circuits. It is shown that from this experiment a high-resolution distance measurement device can be designed by a simple optical setup.