• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2991-3007
• /
• 2022

Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2023

This paper developed a training model to classify normal roads and flooded roads using artificial intelligence technology. We expanded the diversity of learning data using various data augmentation techniques and implemented a model that shows good performance in various environments. Transfer learning was performed using the CNN-based Resnet152v2 model as a pre-learning model. During the model learning process, the performance of the final model was improved through various parameter tuning and optimization processes. Learning was implemented in Python using Google Colab NVIDIA Tesla T4 GPU, and the test results showed that flooding situations were detected with very high accuracy in the test dataset.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.113-120
• /
• 2024

The population sparseness index(PSI) is being utilized to describe the functioning of internal layers in artificial neural networks from the perspective of neurons, shedding light on the black-box nature of the network's internal operations. There is research indicating a positive correlation between the PSI and performance in each layer of convolutional neural network models for image classification. In this study, we observed the internal operations of a convolutional neural network when adversarial examples were applied. The results of the experiments revealed a similar pattern of positive correlation for adversarial examples, which were modified to maintain 5% accuracy compared to applying benign data. Thus, while there may be differences in each adversarial attack, the observed PSI for adversarial examples demonstrated consistent positive correlations with benign data across layers.

• Nutrition Research and Practice
• /
• v.8 no.6
• /
• pp.713-718
• /
• 2014

BACKGROUND/OBJECTIVES: Studies have indicated that university students majoring in nutrition and dietetics or sport sciences may have more obsessions associated with eating attitudes and body shape perception compared to other disciplines i.e. social sciences. Therefore, this study aimed to assess and compare the risk of eating disorders and body shape perception. MATERIALS/METHODS: Data was collected from 773 undergraduate students at the Departments of Nutrition and Dietetics (NDD) (n = 254), Physical Education and Sports (PESD) (n = 263), and Social Sciences (SOC) (n = 256).A socio-demographic and personal information questionnaire, Eating Attitudes Test (EAT-40), Body Shape Questionnaire (BSQ-34), Perceived Figure Rating Scale (FRS) were applied; and body weights and heights were measured. RESULTS: Mean EAT-40 scores showed that, both male and female students of PESD had the highest scores ($7.4{\pm}11.6$) compared with NDD ($14.3{\pm}8.3$) and SOC ($13.0{\pm}6.2$) (P < 0.05). According to EAT-40 classification, high risk in abnormal eating behavior was more in PESD (10.7%) compared to NDD (2.9%) and SOC (0.4%) students (P < 0.05). Students of PESD, who skipped meal, had higher tendency to the risk of eating disorders (P < 0.05). In parallel, body shape perception was found to be marked with higher scores in NDD ($72.0{\pm}28.7$) and PESD ($71.5{\pm}32.8$) compared with SOC ($64.2{\pm}27.5$) students (P < 0.05). Considering BSQ-34 classification, high concern (moderate and marked) for body shape were more in PESD (7.4 %) compared to NDD (5.2%) and SOC (1.9%) students (P < 0.05). The body size judgement via obtained by the FRS scale were generally correlated with BMI. The Body Mass Index levels were in normal range (Mean BMI: $21.9{\pm}2.8kg/m^2$) and generally consistent with FRS data. CONCLUSIONS: Tendency to the abnormal eating behavior and substantial body shape perception were higher in PESD students who have more concern on body shape and were not well-educated about nutrition. In conclusion, substantial concern on physical appearance might affect eating behavior disorders in PESD students.

• Journal of Korea Water Resources Association
• /
• v.49 no.4
• /
• pp.305-314
• /
• 2016

In this study, a quantitative assessment was carried out in order to identify the agricultural drought in time and space using the Terra MODIS remote sensing data for the agricultural drought. The Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) were selected by MOD13A3 image which shows the changes in vegetation conditions. The land cover classification was made to show only vegetation excluding water and urbanized areas in order to collect the land information efficiently by Type1 of MCD12Q1 images. NDVI and EVI index calculated using land cover classification indicates the strong seasonal tendency. Therefore, standardized Vegetation Stress Index Anomaly (VSIA) of EVI were used to estimated the medium-scale regions in Korea during the extreme drought year 2001. In addition, the agricultural drought damages were investigated in the country's past, and it was calculated based on the Standardized Precipitation Index (SPI) using the data of the ground stations. The VSIA were compared with SPI based on historical drought in Korea and application for drought assessment was made by temporal and spatial correlation analysis to diagnose the properties of agricultural droughts in Korea.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.661-672
• /
• 2022

After the outbreak of the SARS-CoV2 virus that causes COVID-19, it spreads around the world with the number of infections and deaths rising rapidly caused a shortage of medical resources. As a way to solve this problem, chest X-ray diagnosis using Artificial Intelligence(AI) received attention as a primary diagnostic method. The purpose of this study is to comprehensively analyze the detection of COVID-19 via AI. To achieve this purpose, 292 studies were collected through a series of Classification methods. Based on these data, performance measurement information including Accuracy, Precision, Area Under Cover(AUC), Sensitivity, Specificity, F1-score, Recall, K-fold, Architecture and Class were analyzed. As a result, the average Accuracy, Precision, AUC, Sensitivity and Specificity were achieved as 95.2%, 94.81%, 94.01%, 93.5%, and 93.92%, respectively. Although the performance measurement information on a year-on-year basis gradually increased, furthermore, we conducted a study on the rate of change according to the number of Class and image data, the ratio of use of Architecture and about the K-fold. Currently, diagnosis of COVID-19 using AI has several problems to be used independently, however, it is expected that it will be sufficient to be used as a doctor's assistant.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.270-278
• /
• 2022

This study was conducted using deep learning technology to classify for 'Mihwang' peach maturity with RGB images and fruit quality attributes during fruit development and maturation periods. The 730 images of peach were used in the training data set and validation data set at a ratio of 8:2. The remains of 170 images were used to test the deep learning models. In this study, among the fruit quality attributes, firmness, Hue value, and a^* value were adapted to the index with maturity classification, such as immature, mature, and over mature fruit. This study used the CNN (Convolutional Neural Networks) models for image classification; VGG16 and InceptionV3 of GoogLeNet. The performance results show 87.1% and 83.6% with Hue left value in VGG16 and InceptionV3, respectively. In contrast, the performance results show 72.2% and 76.9% with firmness in VGG16 and InceptionV3, respectively. The loss rate shows 54.3% and 62.1% with firmness in VGG16 and InceptionV3, respectively. It considers increasing for adapting a field utilization with firmness index in peach.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.69-79
• /
• 2024

Field geotechnical data are obtained from various field and laboratory tests and are documented in geotechnical investigation reports. For efficient design and construction, digitizing these geotechnical parameters is essential. However, current practices involve manual data entry, which is time-consuming, labor-intensive, and prone to errors. Thus, this study proposes an automatic data extraction method from geotechnical investigation reports using image-based deep learning models and text-mining techniques. A deep-learning-based page classification model and a text-searching algorithm were employed to classify geotechnical investigation report pages with 100% accuracy. Computer vision algorithms were utilized to identify valid data regions within report pages, and text analysis was used to match and extract the corresponding geotechnical data. The proposed model was validated using a dataset of 205 geotechnical investigation reports, achieving an average data extraction accuracy of 93.0%. Finally, a user-interface-based program was developed to enhance the practical application of the extraction model. It allowed users to upload PDF files of geotechnical investigation reports, automatically analyze these reports, and extract and edit data. This approach is expected to improve the efficiency and accuracy of digitizing geotechnical investigation reports and building geotechnical databases.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.1-12
• /
• 2019

As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

• The Journal of Information Systems
• /
• v.27 no.1
• /
• pp.171-191
• /
• 2018

Purpose Corporate technology leakage is not only monetary loss, but also has a negative impact on the corporate image and further deteriorates sustainable growth. In particular, since SMEs are highly dependent on core technologies compared to large corporations, loss of technology leakage threatens corporate survival. Therefore, it is important for SMEs to "prevent and protect technology leakage". With the recent development of data analysis technology and the opening of public data, it has become possible to discover and proactively detect companies with a high probability of technology leakage based on actual company data. In this study, we try to construct profiles of enterprises with and without technology leakage experience through profiling analysis using data mining techniques. Furthermore, based on this, we propose a classification model that distinguishes companies that are likely to leak technology. Design/methodology/approach This study tries to develop the empirical model for prevention and protection of technology leakage through profiling method which analyzes each SME from the viewpoint of individual. Based on the previous research, we tried to classify many characteristics of SMEs into six categories and to identify the factors influencing the technology leakage of SMEs from the enterprise point of view. Specifically, we divided the 29 SME characteristics into the following six categories: 'firm characteristics', 'organizational characteristics', 'technical characteristics', 'relational characteristics', 'financial characteristics', and 'enterprise core competencies'. Each characteristic was extracted from the questionnaire data of 'Survey of Small and Medium Enterprises Technology' carried out annually by the Government of the Republic of Korea. Since the number of SMEs with experience of technology leakage in questionnaire data was significantly smaller than the other, we made a 1: 1 correspondence with each sample through mixed sampling. We conducted profiling of companies with and without technology leakage experience using decision-tree technique for research data, and derived meaningful variables that can distinguish the two. Then, empirical model for prevention and protection of technology leakage was developed through discriminant analysis and logistic regression analysis. Findings Profiling analysis shows that technology novelty, enterprise technology group, number of intellectual property registrations, product life cycle, technology development infrastructure level(absence of dedicated organization), enterprise core competency(design) and enterprise core competency(process design) help us find SME's technology leakage. We developed the two empirical model for prevention and protection of technology leakage in SMEs using discriminant analysis and logistic regression analysis, and each hit ratio is 65%(discriminant analysis) and 67%(logistic regression analysis).