• Korean Journal of Artificial Intelligence
• /
• v.11 no.1
• /
• pp.25-29
• /
• 2023

In this paper, the purpose is to create a standard of AI training dataset type for commercial space design. As the market size of the field of space design continues to increase and the time spent increases indoors after COVID-19, interest in space is expanding throughout society. In addition, more and more consumers are getting used to the digital environment. Therefore, If you identify trends and preemptively propose the atmosphere and specifications that customers require quickly and easily, you can increase customer trust and conduct effective sales. As for the data set type, commercial districts were divided into a total of 8 categories, and images that could be processed were derived by refining 4,009,30MB JPG format images collected through web crawling. Then, by performing bounding and labeling operations, we developed a 'Dataset for AI Training' of 3,356 commercial space image data in CSV format with a size of 2.08MB. Through this study, elements of spatial images such as place type, space classification, and furniture can be extracted and used when developing AI algorithms, and it is expected that images requested by clients can be easily and quickly collected through spatial image input information.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.531-536
• /
• 2023

This paper proposes a sliding window method with frame feature insertion for immediate attack detection on in-vehicle networks. This method guarantees real-time attack detection by labeling based on the attack status of the current frame. Experiments show that the proposed method improves detection performance by giving more weight to the current frame in CNN computation. The proposed model was designed based on a lightweight LeNet-5 architecture and it achieves 100% detection for DoS attacks. Additionally, by comparing the complexity with conventional models, the proposed model has been proven to be more suitable for resource-constrained devices like ECUs.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.2_2
• /
• pp.445-456
• /
• 2024

This study aims to suggest service improvement opportunities by analyzing user review data of the top three OTT service apps(Netflix, Coupang Play, and TVING) on Google Play Store. To achieve this objective, we proposed a framework for uncovering service opportunities through the analysis of negative user reviews from OTT service providers. The framework involves automating the labeling of identified topics and generating service improvement opportunities using topic modeling and prompt engineering, leveraging GPT-4, a generative AI model. Consequently, we pinpointed five dissatisfaction topics for Netflix and TVING, and nine for Coupang Play. Common issues include "video playback errors", "app installation and update errors", "subscription and payment" problems, and concerns regarding "content quality". The commonly identified service enhancement opportunities include "enhancing and diversifying content quality". "optimizing video quality and data usage", "ensuring compatibility with external devices", and "streamlining payment and cancellation processes". In contrast to prior research, this study introduces a novel research framework leveraging generative AI to label topics and propose improvement strategies based on the derived topics. This is noteworthy as it identifies actionable service opportunities aimed at enhancing service competitiveness and satisfaction, instead of merely outlining topics.

• Journal of Sensor Science and Technology
• /
• v.33 no.5
• /
• pp.298-304
• /
• 2024

In Korea, fires are the second most common type of disaster, causing large-scale damages. The installation of fire detectors is legislated to prevent fires and minimize damage. Conventional fire detectors have limitations in initial suppression of failures because they detect fires when large amounts of smoke and heat are generated. Additionally, frequent malfunctions in fire detectors may cause users to turn them off. To address these issues, recent studies focus on accurately detecting even small-scale fires using multi-sensor and deep-learning technologies. They also aim at quick fire detection and thermal decomposition using gas. However, these studies are not practical because they overlook the heavy computations involved. Therefore, we propose a fast and accurate fire detection system based on multi-sensor and deep-learning technologies. In addition, we propose a computation-reduction method for selecting sensors suitable for detection using the Pearson correlation coefficient. Specifically, we use a moving average to handle outliers and two-stage labeling to reduce false detections during preprocessing. Subsequently, a deep-learning model is selected as LSTM for analyzing the temporal sequence. Then, we analyze the data using a correlation analysis. Consequently, the model using a small data group with low correlation achieves an accuracy of 99.88% and a false detection rate of 0.12%.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.315-321
• /
• 2023

Long-span bridges are flexible structures with low natural frequencies and damping ratios, making them susceptible to vibrational serviceability problems. However, the current design guideline of South Korea assumes a uniform threshold of wind speed or vibrational amplitude to assess the occurrence of harmful vibrations, potentially overlooking the complex vibrational patterns observed in long-span bridges. In this study, we propose a pointwise vortex-induced vibration (VIV) detection method using a deep-learning-based signalsegmentation model. Departing from conventional supervised methods of data acquisition and manual labeling, we synthesize training data by generating sinusoidal waves with an envelope to accurately represent VIV. A Fourier synchrosqueezed transform is leveraged to extract time-frequency features, which serve as input data for training a bidirectional long short-term memory model. The effectiveness of the model trained on synthetic VIV data is demonstrated through a comparison with its counterpart trained on manually labeled real datasets from an actual cable-supported bridge.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.31 no.1
• /
• pp.170-176
• /
• 2002

The objective of this study was to investigate the current status of calcium fortification in processed foods for obtaining basic data on nutrition fortification policy and nutrition labeling, Surveyed samples were the products fortified wish calcium among processed products sold in department store and large mart in Seoul from Aug. 1998 to Aug. 1999. But supplementary health food or special nutritious food and weaning food and infant formula were excluded from them. We examined the kinds and numbers of added nutrients except calcium and the amounts of calcium per 100 g product and nutrient labeling of calcium-fortified foods. Surveyed products were 81 foods and they were grouped in grain products, milk and milk products, processed meat and fishes, ramyuns, retort pouch foods, fruit juice and drinks. and others. Calcium fortification was found in wide food groups, especially in snack foods and carbonated beverages. In relation to surveyed products, most of them were fortified with only calcium. The number of added nutrients in the product were relatively various in comparison with each food groups. In addition to calcium, the most frequently added nutrient was DHA, and were followed vitamin, mineral, oligosacchride, fiber, etc. This result showed that the kind(s) and the number(s) of nutrient added to product did not consider nutrition balance of calcium-fortified foods. Units of calcium content were decided by companies, therefore consumers confused labelled content with mouth dose of calcium and the comparison of the amounts added calcium among products was difficult. The amounts of calcium in products were from 16.4 to 1226 mg Per 100 and from 2.5 to 27.6% RDA (recommended daily allowance) per serving size. The amounts of calcium in many products were less than 10% RDA per serving size, whole appraisal about fortified content was needed. And for nutrient labeling on calcium, they used various term whether it is approved by law or not.

• Journal of radiological science and technology
• /
• v.34 no.4
• /
• pp.323-331
• /
• 2011

We evaluated clinical usefulness of Arterial spin labeling perfusion MR imaging on the acute ischemic cerebral infarction patients through this study. We compared 22 patients who were done with DSC imaging and ASL imaging in admitted emergency room with acute ischemic cerebral infarction, with 36 normal comparison persons (DSC image on 21persons, ASL images on 15persons). Siemens Magnetom Verio 3.0T with 12 channel head coil was used for this study. DSC image obtained 4 maps(rCBV, rCBF, rMTT, TTP) through post-processing. For qualitative analysis we compared the area of lesion macro-diagonal with the size of diffusion weighted MR image for rMTT, TTP, rCBF, rCBV, ASL maps. For Quantitative analysis we analyzed significant correlations between less than 3 cm infarction group and normal comparison group using mean relative value of flowing image with Mann-Whitney U test. TTP(95.5%) and rCBF(95.5%) maps showed high recognition rate in qualitative analysis for >3cm infarction group. The rCBF and rCBV map tests were highly related with final stage stroke areas. Mean relative value of infarction group showed a significant correlations in quantitative analysis(p<0.05). As a conclusion, arterial spin labeling image showed high lesion recognition rate in the >3cm infarction group. Mean relative values in quantitative evaluation were used for reference data. If we do more sustainable researches, ASL image will be useful for an early diagnosis of cerebral infarction, determination of the range of ischemic pneumbra and effective treatments.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.5 no.2
• /
• pp.207-224
• /
• 1998

The purposes of this study were to identify nurse's recognition and performance and to represent the factors of hindrance in the IV therapy management. The subjects were 420 nurses who worked at five general hospitals in Pusan. Tha data were collected using a questionnaire and the period of data collection was from January 1 to January 31, 1998. The instrument for this study was made by author oneself on the basis of guidelines Simmons et al', CDC' Stanley' and Kurdi' guideline, Cllinical Nurse's Association' that consist of 68 items for 5 fields ; pre-injection, just before-injection, needle-injection, during injection, post-injection field. Cron-bach Alpha coefficient of recognition and performance in the IV therapy management was .93 and .87. The datas were analized by a SPSS program using frequency, percent, paired t-test, t-test and oneway ANOVA. The results obtained were as follows : 1. The mean score of recognition in IV therapy management was significantly higher than that of performance(t=5.86, P<.001). 2. The items of lower than mean score of each fields in performance were the identification of drugs, hands washing, patient teaching about medication, disinfectional methods of the injection site and the rubber stopper in bottle, the use of disposable gloves, mask and eye goggles at the chemotherapy preparation, use of tape and armboard, changing the IV tubing, labeling the dressing over the injection site, observation and recordings of patient's condition after medication and confirmation of the needle length at the needle removal. 3. The factors of hindrance in IV therapy were 'having no time', 'insufficiency of goods', 'unknowing of methods', 'no disadvantage', and 'factors of doctor's doing'. The most important factor was 'have no time', especially item of hands washing. The other factors of hindrance showed high frequency in the following items ; 'insufficiency of goods' in the use of disposable gloves, mask and eye goggles at the chemotherapy preparation, 'unknowing of methods' in the certification of drugs compatibility, 'no disadvantage' in the labeling the dressing over the injection site, and 'factors of doctor's doing' in the changing the subclavian catheter dressing and checking the glucose level during the TPN infusion. In conclusion, there is necessity of educational program which can improve the nurse's knowledge of drugs, disinfection methods, comfort of patient and recordings in IV therapy management and alternative plan which are political and financial aids such as setting up the sink, giving of paper towels and necessary goods in the IV therapy for reducing the factors of hindrance for IV therapy management.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1291-1300
• /
• 2020

Recently, a deep learning-based non-profiling side-channel analysis was proposed. The deep learning-based non-profiling analysis is a technique that trains a neural network model for all guessed keys and then finds the correct secret key through the difference in the training metrics. As the performance of non-profiling analysis varies greatly depending on the neural network training model design, a correct model design criterion is required. This paper describes the two types of loss functions and eight labeling methods used in the training model design. It predicts the analysis performance of each labeling method in terms of non-profiling analysis and power consumption model. Considering the characteristics of non-profiling analysis and the HW (Hamming Weight) power consumption model is assumed, we predict that the learning model applying the HW label without One-hot encoding and the Correlation Optimization (CO) loss will have the best analysis performance. And we performed actual analysis on three data sets that are Subbytes operation part of AES-128 1 round. We verified our prediction by non-profiling analyzing two data sets with a total 16 of MLP-based model, which we describe.