• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.169-171
• /
• 1999

This paper presents a new demand control technique using fuzzy logic. Generally, predictive demand control method often brings about a large number of control actions and undesirable alarm during the beginning stage of the demand period. To solve this problem, a fuzzy predictive algorithm is proposed. The main idea of the method is the determination of sensitivity factor by using fuzzy logic. The performance of the proposed algorithm is tested through a case study.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.9
• /
• pp.11-20
• /
• 2015

In order to prevent the elderly people from committing suicide attempts, it is necessary to verify attributes that affect the suicide attempts. It is noted that previous studies have focused on qualitative approaches, and simple correlation analyses to determine the attributes related to the suicide attempts in the elderly people. However, such previous approaches had led to insufficient performance when facing with complicated data sets. In this sense, this study suggests an alternative method in which attribute selection techniques are adopted to determine more relevant attributes of the suicide attempts occurring in Korean elderly people. To verify empirical validity of our proposed method, we used Korea National Health and Nutrition Examination Survey (KNHANES) from January 2007 to December 2012. Empirical results proved that the proposed attribute selection techniques showed better predictive effectiveness; 94.4% compared to the simple statistical methods. This study proposes a way to determining the elderly suicide and preventing it to happen.

• ETRI Journal
• /
• v.35 no.2
• /
• pp.321-331
• /
• 2013

High-tech markets are unpredictable owing to rapid technology innovation, diverse customer needs, high competition, and other elements. Many scholars have attempted to explain the uncertainty in high-tech markets using their own various approaches. However, sufficiently clear ways to predict diverse changes and trends in high-tech markets have yet to be presented. Thus, this paper proposes a new approach model, that is, systematic market segmentation, to give more accurate information. Using an empirical dataset from the mobile handset market in the Republic of Korea, we conduct our research model consisting of three steps. First, we categorize nine basic segments. Second, we test the stability of these segments. Finally, we profile the characteristics of the customers and products. We conclude that the approach is able to offer more diagnostic information to both practitioners and scholars. It is expected to provide rich information for an appropriate marketing mix in practice.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.798-800
• /
• 1995

The neural network predictive controller(NNPC) is proposed for the attempt to mimic the function of brain that forecasts the future. It consists of two loops, one is for the prediction of output(Neural Network Predictor) and the other one is for control the plant(Neural Network Controller). The output of NNC makes the control input of plant, which is followed by the variation of both plant error and prediction error. The NNP forecasts the future output based upon the current control input and the estimated control output. The method is applied to the control of temperature in boiler systems. The proposed NNPC is compared with the other conventional control methods such as PID controller, neural network controller with specialized learning architecture, and one-step-ahead controller. The computer simulation and experimental results show that the proposed method has better performances than the other methods.

• Honam Mathematical Journal
• /
• v.43 no.4
• /
• pp.717-739
• /
• 2021

We used blood data to predict obesity by complementing the BMI risk, because some blood factors are significantly associated with obesity. For the sampling method, a two-step stratified colony sampling method was used based on sixteen blood factors collected by the Korea National Health and Nutrition Examination Survey(KNHANES). We identify the number of effective blood data of obesity in the final model as 6 ~ 8 factors that differ somewhat depending on age and gender. Also, the coefficient of determination that represents the predictive power of obesity in the regression model is the highest for both men and women of aged 19 and in their 20s and 30s, and the predictive power decreases with increasing age.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.5
• /
• pp.139-147
• /
• 1996

PID control has been widely used for real control systems. Particularly, there are many researches on control schemes of tuning PID gains. However, to the best of our knowledge, there is no result for discrete-time systems with unknown time-delay and unknown system parameters. On the other hand, Generalized predictive control has been reported as a useful self-tuning control technique for systems with unknown time-delay. So, in this study, based on minimization of a GPC criterion, we present a self-tuning PID control algorithm for unknown papameters and unknown time-delay system. A numerical simulation was presented to illustrate the effectiveness of this method.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.16-26
• /
• 2024

Mobile edge computing (MEC) plays a crucial role in improving the performance of resource-constrained mobile devices by offloading computation-intensive tasks to nearby edge servers. However, existing methods often neglect the critical consideration of future task requirements when making offloading decisions. In this paper, we propose an innovative approach that addresses this limitation. Our method leverages recurrent neural networks (RNNs) to predict task sizes for future time slots. Incorporating this predictive capability enables more informed offloading decisions that account for upcoming computational demands. We employ genetic algorithms (GAs) to fine-tune fitness functions for current and future time slots to optimize offloading decisions. Our objective is twofold: minimizing total processing time and reducing energy consumption. By considering future task requirements, our approach achieves more efficient resource utilization. We validate our method using a real-world dataset from Google-cluster. Experimental results demonstrate that our proposed approach outperforms baseline methods, highlighting its effectiveness in MEC systems.

• Journal of Sensor Science and Technology
• /
• v.33 no.5
• /
• pp.248-254
• /
• 2024

Artificial intelligence techniques have improved fire-detection methods; however, false alarms still occur. Conventional methods detect fires using current sensors, which can lead to detection errors due to temporary environmental changes or noise. Thus, fire-detection methods must include a trend analysis of past information. We propose a deep-learning-based fire detection method using multi-sensor data and Kendall's tau. The proposed system used a BiLSTM model to predict fires using pre-processed multi-sensor data and extracted trend information. Kendall's tau indicates the trend of a time-series data as a score; therefore, it is easy to obtain a target pattern. The experimental results showed that the proposed system with trend values recorded an accuracy of 99.93% for BiLSTM and GRU models in a 20-tap moving average filter and 40% fire threshold. Thus, the proposed trend approach is more accurate than that of conventional approaches.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1212-1222
• /
• 2018

This paper presents a model predictive control (MPC) method to reduce the common-mode voltage (CMV) for inverters connected in parallel, which increase the capacity of energy storage systems (ESSs). The proposed method is based on subdivided voltage vectors, and the resulting algorithm can be applied to control the inverters. Furthermore, we use more voltage vectors than the conventional MPC algorithm; consequently, the quality of grid currents is improved. Several methods were proposed in order to reduce the CMV appearing during operation and its adverse effects. However, those methods have shown to increase the total harmonic distortion of the grid currents. Our method, however, aims to both avoid this drawback and effectively reduce the CMV. By employing phase difference in the carrier signals to control each inverter, we successfully reduced the CMV for inverters connected in parallel, thus outperforming similar methods. In fact, the validity of the proposed method was verified by simulations and experimental results.

• Journal of the Korean GEO-environmental Society
• /
• v.16 no.6
• /
• pp.23-30
• /
• 2015

This study analyzed degree of disturbance, using specimens by laboratory test with large block specimens and piston samplers collected from the Korea's two typical soft ground districts: South coast Gwangyang and Yangsan. To assess the characteristics of compression index of laboratory test incurred by disturbance, the compression index of laboratory test was compared with the back analysis compression index resulting from the analysis of the measured settlement. The analysis of specimen disturbance of the laboratory test results with the piston specimens of the two districts found that the qualities of most specimens were poor and the settlement predicted by the laboratory test compression index was underestimated. The analysis of test material taken from nearby areas proved that the disturbance degrees of large block specimens were lower than that of the piston specimens. The hyperbolic method, Hoshino method, Asaoka method, and ${\sqrt{S}}$ method, all of which are predictive methods using measured settlement, were employed to reach a conclusion that reliabilities of each predictive method except predictive material of a few points were the same. To compensate the disturbance effects on compression index of the piston specimens, we suggested a new modification formula that estimates compression index of piston specimens, using Schmertmann's corrected compression index, and back analysis compression index from the analysis of predictive settlement.