• Journal of Korean Society on Water Environment
• /
• v.37 no.4
• /
• pp.275-285
• /
• 2021

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.77-90
• /
• 2024

Waste foundry sand (WFS) is the waste product that cause environmental hazards. WFS can be used as a partial replacement of cement or fine aggregates in concrete. A database comprising 234 compressive strength tests of concrete fabricated with WFS is used. To construct the machine learning-based prediction models, the water-to-cement ratio, WFS replacement percentage, WFS-to-cement content ratio, and fineness modulus of WFS were considered as the model's inputs, and the compressive strength of concrete is set as the model's output. A base extreme gradient boosting (XGBoost) model together with two hybrid XGBoost models mixed with the tunicate swarm algorithm (TSA) and the salp swarm algorithm (SSA) were applied. The role of TSA and SSA is to identify the optimum values of XGBoost hyperparameters to obtain the higher performance. The results of these hybrid techniques were compared with the results of the base XGBoost model in order to investigate and justify the implementation of optimisation algorithms. The results showed that the hybrid XGBoost models are faster and more accurate compared to the base XGBoost technique. The XGBoost-SSA model shows superior performance compared to previously published works in the literature, offering a reduced system error rate. Although the WFS-to-cement ratio is significant, the WFS replacement percentage has a smaller influence on the compressive strength of concrete. To improve the compressive strength of concrete fabricated with WFS, the simultaneous consideration of the water-to-cement ratio and fineness modulus of WFS is recommended.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1479-1495
• /
• 2012

Spectrum scarcity seems to be the most challenging issue to be solved in new wireless telecommunication services. It is shown that spectrum unavailability is mainly due to spectrum inefficient utilization and inappropriate physical layer execution rather than spectrum shortage. Daily increasing demand for new wireless services with higher data rate and QoS level makes the upgrade of the physical layer modulation techniques inevitable. Orthogonal Frequency Division Multiple Access (OFDMA) which utilizes multicarrier modulation to provide higher data rates with the capability of flexible resource allocation, although has widely been used in current wireless systems and standards, seems not to be the best candidate for cognitive radio systems. Filter Bank based Multi-Carrier (FBMC) is an evolutionary scheme with some advantages over the widely-used OFDM multicarrier technique. In this paper, we focus on the total throughput improvement of a cognitive radio network using FBMC modulation. Along with this modulation scheme, we propose a novel uplink radio resource allocation algorithm in which fairness issue is also considered. Moreover, the average throughput of the proposed FBMC based cognitive radio is compared to a conventional OFDM system in order to illustrate the efficiency of using FBMC in future cognitive radio systems. Simulation results show that in comparison with the state of the art two algorithms (namely, Shaat and Wang) our proposed algorithm achieves higher throughputs and a better fairness for cognitive radio applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.4
• /
• pp.855-869
• /
• 1997

In this paper, we proposed two kids of dynamic priority control mechanisms controlling the cell service ratio in order to improve the QOS(Quality of Service). We also analyse theoretically the characteristics of cell loss probability and mean cell delay time by applying the proposed priority control mechanisms to ATM switch with output buffer. The proposed priority control mechanisms have the same principles of storing cells into buffer but the different principles of serving cells from buffer. The one is the control mechanism controlling the cell service ratio according to the relative cell occupancy ratio of buffer, the other is the control mechanism controlling the cell service ratio according to both the relative cell occupancy ratio of buffer and the average arrival rate. The two service classes of our concern are the delay sensitive class and the loss sensitive class. The analytical results show that the proposed control mechanisms are able to improve the QOS, the characteristics of cell loss probability and mean cell delay time, by selecting properly the relative cell occupancy ratio of buffer and the average arrival rate. conventional DLB algorithm does not support synchronous cells, but the proposed algorithm gives higher priority to synchronous cells. To reduce synchronous cell loss rate, the synchronous cell detector is used in the proposed algorithm. Synchronous cell detector detects synchronous cells, and passes them cells to the 2nd Leaky-Bucket. So it is similar to give higher priority to synchronous cells. In this paper, the proposed algorithm used audio/video traffic modeled by On/Off and Two-state MMPP, and simulated by SLAM II package. As simulation results, the proposed algorithm gets lower synchronous cell loss rate than the conventional DLB algorithms. The improved DLB algorithm for multimedia synchronization can be extended to any other cells which require higher priority.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.7
• /
• pp.674-684
• /
• 2011

More and more elderly and disabled people are using electric scooters instead of electric wheelchairs because of higher mobility. However, people with high levels of impairment or the elderly still have difficulties in driving the electric scooters safely. Semi-autonomous electric scooter system is one of the solutions for the safety: Either manual driving or autonomous driving can be used selectively. In this paper, we implement a semi-autonomous electric scooter system with functions of localization and path following. In order to recognize the pose of electric scooter in outdoor environments, we design an outdoor localization system based on the extended Kalman filter using DGPS (Differential Global Positioning System) and wheel encoders. We added an accelerometer to make the localization system adaptable to road condition. Also we propose a path following algorithm using two arcs with current pose of the electric scooter and a given path in the map. Simulation results are described to show that the proposed algorithms provide the ability to drive an electric scooter semi-autonomously. Finally, we conduct outdoor experiments to reveal the practicality of the proposed system.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.204-207
• /
• 2002

The current paper proposes a new multispectral image data compression algorithm that can efficiently reduce spatial and spectral redundancies by applying classified prediction, a Karhunen-Loeve transform (KLT), and the three-dimensional set partitioning in hierarchical trees (3-D SPIHT) algorithm In the wavelet transform (WT) domain. The classification is performed in the WT domain to exploit the interband classified dependency, while the resulting class information is used for the interband prediction. The residual image data on the prediction errors between the original image data and the predicted image data is decorrelated by a KLT. Finally, the 3D-SPIHT algorithm is used to encode the transformed coefficients listed in a descending order spatially and spectrally as a result of the WT and KLT. Simulation results showed that the reconstructed images after using the proposed algorithm exhibited a better quality and higher compression ratio than those using conventional algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2658-2679
• /
• 2018

This paper proposes a novel Random Scheduling Algorithm based on Subregion Coverage (RSASC), to solve the SET K-cover problem (an NP-complete problem). SET K-cover problem distributes the set of sensors into the maximum number of mutually exclusive subsets (MESSs) in such a way that each of them can be scheduled for lifetime extension of WSN. Sensor coverage divides the target region into different subregions. RSASC first sorts the subregions in the ascending order concerning their sensor coverage. Then, it forms the subregion groups according to their similar sensor coverage. Lastly, RSASC ensures the K-coverage of each subregion from every group by randomly scheduling the sensors. We consider the target-coverage and area-coverage applications of WSN to analyze the usefulness of our proposed RSASC algorithm. The distinct quality of RSASC is that it utilizes less number of deployed sensors (33% less) to form the optimum number of MESSs with the higher computational speed (saves more than 93% of the time) as compared to the existing three algorithms.