• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.6
• /
• pp.639-646
• /
• 2022

Energy harvesting technologies that can convert wasted various energy into usable electrical energy have been widely investigated to overcome the limitation of batteries for the powering of IoT sensors and small electronic devices. Hybrid energy harvesting is known as a technology that enhances the output power of single energy harvesting device by housing two or more various energy harvesting mechanisms. In this study, we introduce a hybrid MME (Magneto-Mechano-Electric) generator coupled with the triboelectric effect. Through FEA modeling, four triboelectric materials, including PI (Polyimide), PFA(Teflon), Cu, and Al, were selected and compared with the expected triboelectric potentials. The effect of surface morphology was investigated as well. Among various combination of triboelectric materials and surface morphologies, PFA-Al combination with the surface morphology having nano-scale square projections showed highest output potential under triboelectrification. It is also experimentally confirmed that output voltage and power of the hybrid MME generator with triboelectric material combinations.

• Journal of Animal Science and Technology
• /
• v.64 no.3
• /
• pp.564-573
• /
• 2022

In this study, considering the difficulties for all farms to convert farm styles to animal welfare-based housing, an experiment was performed to observe the changes in the behavior and welfare of sows when the slat floor was changed to a collective breeding ground. Twenty-eight sows used in this study were between the second and fifth parities to minimize the influence of parity. Using a flats floor cover, the flattening rates were treated as 0%, 20%, 30%, 40%, and 50%. Data collection was the behavior of sows visually observed using a camera (e.g., standing, lying, fighting and excessive biting behaviors, and abnormal behaviors) and the animal welfare level measured through field visits. Lying behavior was found to be higher (p < 0.01) as the flattening rate increased, and sows lying on the slatted cover also increased as the flattening rate increased (p < 0.01). Fighting behavior wasincreased when the flattening rate was increased to 20%, and chewing behavior was increased (p < 0.05) as the flattening rate increased. The animal welfare level of sows, 'good feeding', it was found that all treatment groups for body condition score and water were good at 100 (p < 0.05). 'Good housing' was the maximum value (100) in each treatment group. As the percentage of floor increased, the minimum good housing was increased from 78 in 0% flattening rate to 96 in 50% flattening rate. The maximum (100) 'good health' was achieved in the 0% and 20% flattening rates, and it was 98, 98, and 99 in the 30%, 50%, and 40% flattening rate, respectively. 'Appropriate behavior' score was significantly lower than that of other paremeters, but when the flattening ratio was 0% and 20%, the maximum and minimum values were 10. At 40% and 50%, the maximum values were 39 and 49, respectively, and the minimum values were analyzed as 19 for both 40% and 50%. These results will be used as basic data about sow welfare for farmers to successfully transition to group housing and flat floors.

• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.24-31
• /
• 2023

Recently, interest in UAM (Urban Air Mobility, UAM), which can take off and land vertically in the operation of urban air transportation systems, has been increasing. Therefore, various start-up companies are developing related technologies as eco-friendly future transportation with advanced technology. However, studies on ways to increase safety in the operation of UAM are still insignificant. In particular, efforts are more urgent to improve the safety of risks generated in the process of attempting to land in the city center by UAM equipped with autonomous driving. Accordingly, this study proposes a plan to safely land by avoiding dangerous region that interfere when autonomous UAM attempts to land in the city center. To this end, first, the latitude and longitude coordinate values of dangerous objects observed by the sense of the UAM are calculated. Based on this, we proposed to convert the coordinates of the distorted planar image from the 3D image to latitude and longitude and then use the calculated latitude and longitude to compare the pre-learned feature descriptor with the HOG (Histogram of Oriented Gradients, HOG) feature descriptor to extract the dangerous Region. Although the dangerous region could not be completely extracted, generally satisfactory results were obtained. Accordingly, the proposed research method reduces the enormous cost of selecting a take-off and landing site for UAM equipped with autonomous driving technology and contribute to basic measures to reduce risk increase safety when attempting to land in complex environments such as urban areas.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• Korean Journal of Optics and Photonics
• /
• v.34 no.2
• /
• pp.53-60
• /
• 2023

We designed a catadioptric objective lens with a 0.6 numerical aperture (NA) for semiconductor inspection at 193 nm. The objective lens meets major requirements such as a spatial resolution of 200 nm and a field of view (FOV) of 0.15 mm or more. We selected a wavelength of 266 nm for autofocus based on the availability of the light source. First, we built the objective lenses of three lens groups: a focusing lens group, a field-lens group, and an NA conversion group. In particular, the NA conversion group is a group of catadioptric lenses that convert the numerical aperture of the beam focused by the prior groups to the required value, i.e., 0.6. The last design comprises 11 optical elements with root-mean-squared (RMS) wavefront aberrations less than λ/80 over the entire field of view. We also achieved the athermalization of the objective lens with focus-shift alone satisfying the performance of RMS wavefront aberration below λ/30 at a temperature range of 20 ± 1.2 ℃.

• The Korean Journal of Applied Statistics
• /
• v.36 no.1
• /
• pp.33-48
• /
• 2023

In this paper we consider automatic speech recognition (ASR) for Korean speech data in which elderly persons randomly speak a sequence of words such as animals and vegetables for one minute. Most of the speakers are over 60 years old and some of them are dementia patients. The goal is to compare deep-learning based ASR models for such data and to find models with good performance. ASR is a technology that can recognize spoken words and convert them into written text by computers. Recently, many deep-learning models with good performance have been developed for ASR. Training data for such models are mostly composed of the form of sentences. Furthermore, the speakers in the data should be able to pronounce accurately in most cases. However, in our data, most of the speakers are over the age of 60 and often have incorrect pronunciation. Also, it is Korean speech data in which speakers randomly say series of words, not sentences, for one minute. Therefore, pre-trained models based on typical training data may not be suitable for our data, and hence we train deep-learning based ASR models from scratch using our data. We also apply some data augmentation methods due to small data size.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.189-198
• /
• 2023

As crimes frequently occur on the street, the spread of CCTV is increasing. However, due to the shortcomings of passively operated CCTV, the need for intelligent CCTV is attracting attention. Due to the heavy system of such intelligent CCTV, high-performance devices are required, which has a problem in that it is expensive to replace the general CCTV. To solve this problem, an intelligent CCTV system that recognizes low-quality images and operates even on devices with low performance is required. Therefore, this paper proposes a Saying CCTV system that can detect threats in real time by using the AWS cloud platform to lighten the system and convert images into text. Based on the data extracted using YOLO v4 and OpenPose, it is implemented to determine the risk object, threat behavior, and threat situation, and calculate the risk using machine learning. Through this, the system can be operated anytime and anywhere as long as the network is connected, and the system can be used even with devices with minimal performance for video shooting and image upload. Furthermore, it is possible to quickly prevent crime by automating meaningful statistics on crime by analyzing the video and using the data stored as text.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.97-106
• /
• 2022

In this study, H&E staining is necessary to distinguish cells. However, dyeing directly requires a lot of money and time. The purpose is to convert the phase image of unstained cells to the amplitude image of stained cells. Image data taken with FPM was created with Phase image and Amplitude image using Matlab's parameters. Through normalization, a visually identifiable image was obtained. Through normalization, a visually distinguishable image was obtained. Using the GAN algorithm, a Fake Amplitude image similar to the Real Amplitude image was created based on the Phase image, and cells were distinguished by objectification using MASK R-CNN with the Fake Amplitude image As a result of the study, D loss max is 3.3e-1, min is 6.8e-2, G loss max is 6.9e-2, min is 2.9e-2, A loss max is 5.8e-1, min is 1.2e-1, Mask R-CNN max is 1.9e0, and min is 3.2e-1.

• Korean Journal of Materials Research
• /
• v.33 no.1
• /
• pp.15-20
• /
• 2023

'Tracers' are bullets that emit light at the backside so that the shooter can see the trajectory of their flight. These light-emitting bullets allow snipers to hit targets faster and more accurately. Conventional tracers are all combustion type which use the heat generated upon ignition. However, the conventional tracer has a fire risk at the impact site due to the residual flame and has a by-product that can contaminate the inside of the gun and lead to firearm failure. To resolve these problems, it is necessary to develop non-combustion-type tracers that can convert heat to luminance, so-called 'thermoluminescence (TL)'. Here, we highly improve the thermoluminescence properties of MgB₄O₇ through co-doping of Dy³⁺+Ce³⁺ and Dy³⁺+Na⁺. The presence of doping materials (Dy³⁺, Ce³⁺, Na⁺) was confirmed by XPS (X-ray photoelectron spectroscopy). The as-synthesized co-doped MgB₄O₇ was irradiated with a specific radiation dose and heated to 500 ℃under dark conditions. Different thermoluminescence characteristics were exhibited depending on the type or amounts of doping elements, and the highest luminance of 370 cd/m² was obtained when Dy 10 % and Na 5 % were co-doped.