• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.76-83
• /
• 2022

With the recent development of IT technology, research and interest in various biosignal measuring devices is increasing. As an aging society is in full swing, research on the elderly population using IT-related technologies is continuously developing. This study is about the development of life pattern detection and fall detection algorithm, which is one of the medical service areas for the elderly, who are rapidly developing as they enter a super-aged society. This study consisted of a system using a 3-axis accelerometer and an electrocardiogram sensor, collected data, and then analyzed the data. It was confirmed that behavioral patterns could be classified from the actual research results. In order to evaluate the usefulness of the human activity monitoring system implemented in this study, experiments were performed under various conditions, such as changes in posture and walking speed, and signal magnitude range and signal vector magnitude parameters reflecting the acceleration of gravity of the human body and the degree of human activity. was extracted. And the possibility of discrimination according to the condition of the subject was examined by these parameter values.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.303-314
• /
• 2023

Voice conversion, a technology that allows an individual's speech data to be regenerated with the acoustic properties(tone, cadence, gender) of another, has countless applications in education, communication, and entertainment. This paper proposes an approach based on the StarGAN-VC model that generates realistic-sounding speech without requiring parallel utterances. To overcome the constraints of the existing StarGAN-VC model that utilizes one-hot vectors of original and target speaker information, this paper extracts feature vectors of target speakers using a pre-trained version of Rawnet3. This results in a latent space where voice conversion can be performed without direct speaker-to-speaker mappings, enabling an any-to-any structure. In addition to the loss terms used in the original StarGAN-VC model, Wasserstein distance is used as a loss term to ensure that generated voice segments match the acoustic properties of the target voice. Two Time-Scale Update Rule (TTUR) is also used to facilitate stable training. Experimental results show that the proposed method outperforms previous methods, including the StarGAN-VC network on which it was based.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.199-208
• /
• 2023

Taguchi method is one of the most popular approaches for design optimization such that performance characteristics become robust to uncontrollable noise variables. However, most previous Taguchi method applications have addressed a single-characteristic problem. Problems with multiple characteristics are more common in practice. The multi-criteria decision making(MCDM) problem is to select the optimal one among multiple alternatives by integrating a number of criteria that may conflict with each other. Representative MCDM methods include TOPSIS(Technique for Order of Preference by Similarity to Ideal Solution), GRA(Grey Relational Analysis), PCA(Principal Component Analysis), fuzzy logic system, and so on. Therefore, numerous approaches have been conducted to deal with the multi-characteristic design problem by combining original Taguchi method and MCDM methods. In the MCDM problem, multiple criteria generally have different measurement units, which means that there may be a large difference in the physical value of the criteria and ultimately makes it difficult to integrate the measurements for the criteria. Therefore, the normalization technique is usually utilized to convert different units of criteria into one identical unit. There are four normalization techniques commonly used in MCDM problems, including vector normalization, linear scale transformation(max-min, max, or sum). However, the normalization techniques have several shortcomings and do not adequately incorporate the practical matters. For example, if certain alternative has maximum value of data for certain criterion, this alternative is considered as the solution in original process. However, if the maximum value of data does not satisfy the required degree of fulfillment of designer or customer, the alternative may not be considered as the solution. To solve this problem, this paper employs the desirability function that has been proposed in our previous research. The desirability function uses upper limit and lower limit in normalization process. The threshold points for establishing upper or lower limits let us know what degree of fulfillment of designer or customer is. This paper proposes a new design optimization technique for multi-characteristic design problem by integrating the Taguchi method and our desirability functions. Finally, the proposed technique is able to obtain the optimal solution that is robust to multi-characteristic performances.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.1
• /
• pp.229-249
• /
• 2022

This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.2
• /
• pp.245-256
• /
• 2024

Since 2020, quantitative easing and easy money policies have been implemented for the purpose of economic stimulus. As a result, real estate prices have skyrocketed. In this study, the relationship between sales and rental prices by housing type during the period of soaring real estate prices in Busan was analyzed spatio-temporally. Based on the actual transaction price data, housing type, transaction type, and monthly data of district units were constructed. Among the spatio-temporal analysis models, the SpVAR, which is used to understand the temporal and spatial effects of variables, and the GSTAR, which is used to understand the effects of each region on those variables, were used. As a result, the sales price of apartment had positive effect on the sale price of apartment, row house, and detached house in the surrounding area, including the target area. On the other hand, it was confirmed that demand was converted to apartment rental due to an increase in apartment sales prices, and the sale price fell again over time. The spatio-temporal spillover effect of apartments was positive, but the positive effect of row house and detached house were concentrated in the original downtown area.

• Asia pacific journal of information systems
• /
• v.24 no.2
• /
• pp.233-253
• /
• 2014

Can the stock market really be predicted? Stock market prediction has attracted much attention from many fields including business, economics, statistics, and mathematics. Early research on stock market prediction was based on random walk theory (RWT) and the efficient market hypothesis (EMH). According to the EMH, stock market are largely driven by new information rather than present and past prices. Since it is unpredictable, stock market will follow a random walk. Even though these theories, Schumaker [2010] asserted that people keep trying to predict the stock market by using artificial intelligence, statistical estimates, and mathematical models. Mathematical approaches include Percolation Methods, Log-Periodic Oscillations and Wavelet Transforms to model future prices. Examples of artificial intelligence approaches that deals with optimization and machine learning are Genetic Algorithms, Support Vector Machines (SVM) and Neural Networks. Statistical approaches typically predicts the future by using past stock market data. Recently, financial engineers have started to predict the stock prices movement pattern by using the SNS data. SNS is the place where peoples opinions and ideas are freely flow and affect others' beliefs on certain things. Through word-of-mouth in SNS, people share product usage experiences, subjective feelings, and commonly accompanying sentiment or mood with others. An increasing number of empirical analyses of sentiment and mood are based on textual collections of public user generated data on the web. The Opinion mining is one domain of the data mining fields extracting public opinions exposed in SNS by utilizing data mining. There have been many studies on the issues of opinion mining from Web sources such as product reviews, forum posts and blogs. In relation to this literatures, we are trying to understand the effects of SNS exposures of firms on stock prices in Korea. Similarly to Bollen et al. [2011], we empirically analyze the impact of SNS exposures on stock return rates. We use Social Metrics by Daum Soft, an SNS big data analysis company in Korea. Social Metrics provides trends and public opinions in Twitter and blogs by using natural language process and analysis tools. It collects the sentences circulated in the Twitter in real time, and breaks down these sentences into the word units and then extracts keywords. In this study, we classify firms' exposures in SNS into two groups: positive and negative. To test the correlation and causation relationship between SNS exposures and stock price returns, we first collect 252 firms' stock prices and KRX100 index in the Korea Stock Exchange (KRX) from May 25, 2012 to September 1, 2012. We also gather the public attitudes (positive, negative) about these firms from Social Metrics over the same period of time. We conduct regression analysis between stock prices and the number of SNS exposures. Having checked the correlation between the two variables, we perform Granger causality test to see the causation direction between the two variables. The research result is that the number of total SNS exposures is positively related with stock market returns. The number of positive mentions of has also positive relationship with stock market returns. Contrarily, the number of negative mentions has negative relationship with stock market returns, but this relationship is statistically not significant. This means that the impact of positive mentions is statistically bigger than the impact of negative mentions. We also investigate whether the impacts are moderated by industry type and firm's size. We find that the SNS exposures impacts are bigger for IT firms than for non-IT firms, and bigger for small sized firms than for large sized firms. The results of Granger causality test shows change of stock price return is caused by SNS exposures, while the causation of the other way round is not significant. Therefore the correlation relationship between SNS exposures and stock prices has uni-direction causality. The more a firm is exposed in SNS, the more is the stock price likely to increase, while stock price changes may not cause more SNS mentions.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.191-201
• /
• 2011

Soybean has widely grown for its edible bean which has numerous uses. Microwave remote sensing has a great potential over the conventional remote sensing with the visible and infrared spectra due to its all-weather day-and-night imaging capabilities. In this investigation, a ground-based polarimetric scatterometer operating at multiple frequencies was used to continuously monitor the crop conditions of a soybean field. Polarimetric backscatter data at L, C, and X-bands were acquired every 10 minutes on the microwave observations at various soybean stages. The polarimetric scatterometer consists of a vector network analyzer, a microwave switch, radio frequency cables, power unit and a personal computer. The polarimetric scatterometer components were installed inside an air-conditioned shelter to maintain constant temperature and humidity during the data acquisition period. The backscattering coefficients were calculated from the measured data at incidence angle $40^{\circ}$ and full polarization (HH, VV, HV, VH) by applying the radar equation. The soybean growth data such as leaf area index (LAI), plant height, fresh and dry weight, vegetation water content and pod weight were measured periodically throughout the growth season. We measured the temporal variations of backscattering coefficients of the soybean crop at L, C, and X-bands during a soybean growth period. In the three bands, VV-polarized backscattering coefficients were higher than HH-polarized backscattering coefficients until mid-June, and thereafter HH-polarized backscattering coefficients were higher than VV-, HV-polarized back scattering coefficients. However, the cross-over stage (HH > VV) was different for each frequency: DOY 200 for L-band and DOY 210 for both C and X-bands. The temporal trend of the backscattering coefficients for all bands agreed with the soybean growth data such as LAI, dry weight and plant height; i.e., increased until about DOY 271 and decreased afterward. We plotted the relationship between the backscattering coefficients with three bands and soybean growth parameters. The growth parameters were highly correlated with HH-polarization at L-band (over r=0.92).

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.187-201
• /
• 2011

KOSPI200 index is the Korean stock price index consisting of actively traded 200 stocks in the Korean stock market. Its base value of 100 was set on January 3, 1990. The Korea Exchange (KRX) developed derivatives markets on the KOSPI200 index. KOSPI200 index futures market, introduced in 1996, has become one of the most actively traded indexes markets in the world. Traders can make profit by entering a long position on the KOSPI200 index futures contract if the KOSPI200 index will rise in the future. Likewise, they can make profit by entering a short position if the KOSPI200 index will decline in the future. Basically, KOSPI200 index futures trading is a short-term zero-sum game and therefore most futures traders are using technical indicators. Advanced traders make stable profits by using system trading technique, also known as algorithm trading. Algorithm trading uses computer programs for receiving real-time stock market data, analyzing stock price movements with various technical indicators and automatically entering trading orders such as timing, price or quantity of the order without any human intervention. Recent studies have shown the usefulness of artificial intelligent systems in forecasting stock prices or investment risk. KOSPI200 index data is numerical time-series data which is a sequence of data points measured at successive uniform time intervals such as minute, day, week or month. KOSPI200 index futures traders use technical analysis to find out some patterns on the time-series chart. Although there are many technical indicators, their results indicate the market states among bull, bear and flat. Most strategies based on technical analysis are divided into trend following strategy and non-trend following strategy. Both strategies decide the market states based on the patterns of the KOSPI200 index time-series data. This goes well with Markov model (MM). Everybody knows that the next price is upper or lower than the last price or similar to the last price, and knows that the next price is influenced by the last price. However, nobody knows the exact status of the next price whether it goes up or down or flat. So, hidden Markov model (HMM) is better fitted than MM. HMM is divided into discrete HMM (DHMM) and continuous HMM (CHMM). The only difference between DHMM and CHMM is in their representation of state probabilities. DHMM uses discrete probability density function and CHMM uses continuous probability density function such as Gaussian Mixture Model. KOSPI200 index values are real number and these follow a continuous probability density function, so CHMM is proper than DHMM for the KOSPI200 index. In this paper, we present an artificial intelligent trading system based on CHMM for the KOSPI200 index futures system traders. Traders have experienced on technical trading for the KOSPI200 index futures market ever since the introduction of the KOSPI200 index futures market. They have applied many strategies to make profit in trading the KOSPI200 index futures. Some strategies are based on technical indicators such as moving averages or stochastics, and others are based on candlestick patterns such as three outside up, three outside down, harami or doji star. We show a trading system of moving average cross strategy based on CHMM, and we compare it to a traditional algorithmic trading system. We set the parameter values of moving averages at common values used by market practitioners. Empirical results are presented to compare the simulation performance with the traditional algorithmic trading system using long-term daily KOSPI200 index data of more than 20 years. Our suggested trading system shows higher trading performance than naive system trading.