• The Journal of Bigdata
• /
• 제4권1호
• /
• pp.63-72
• /
• 2019

For power energy, optimal generation and distribution plans based on accurate demand forecasts are necessary because it is not recoverable after they have been delivered to users through power generation and transmission processes. Failure to predict power demand can cause various social and economic problems, such as a massive power outage in September 2011. In previous studies on forecasting power demand, ARIMA, neural network models, and other methods were developed. However, limitations such as the use of the national average ambient air temperature and the application of uniform criteria to distinguish seasonality are causing distortion of data or performance degradation of the predictive model. In order to improve the performance of the power demand prediction model, we divided Korea into five major regions, and the power demand prediction model of the linear regression model and the neural network model were developed, reflecting seasonal characteristics through regional characteristics and migration period learning techniques. With the proposed approach, it seems possible to forecast the future demand in short term as well as in long term. Also, it is possible to consider various events and exceptional cases during a certain period.

• KIPS Transactions on Software and Data Engineering
• /
• 제11권12호
• /
• pp.489-498
• /
• 2022

Recently, the textile industry, which is labor-intensive, is attempting to reduce process costs and optimize quality through artificial intelligence. However, the fiber spinning process has a high cost for data collection and lacks a systematic data collection and processing system, so the amount of accumulated data is small. In addition, data imbalance occurs by preferentially collecting only data with changes in specific variables according to the purpose of fiber spinning, and there is an error even between samples collected under the same fiber spinning conditions due to difference in the measurement environment of physical properties. If these data characteristics are not taken into account and used for AI models, problems such as overfitting and performance degradation may occur. Therefore, in this paper, we propose an outlier handling technique and data augmentation technique considering the characteristics of the spinning process data. And, by comparing it with the existing outlier handling technique and data augmentation technique, it is shown that the proposed technique is more suitable for spinning process data. In addition, by comparing the original data and the data processed with the proposed method to various models, it is shown that the performance of the tensile tenacity and elongation prediction model is improved in the models using the proposed methods compared to the models not using the proposed methods.

• The KIPS Transactions:PartD
• /
• 제15D권4호
• /
• pp.451-462
• /
• 2008

Recently, with the advent of applications using locations of moving objects, it becomes crucial to develop efficient index schemes for spatio-temporal databases. The $TPR^*$-tree is most popularly accepted as an index structure for processing future-time queries. In the $TPR^*$-tree, the future locations of moving objects are predicted based on the CBR(Conservative Bounding Rectangle). Since the areas predicted from CBRs tend to grow rapidly over time, CBRs thus enlarged lead to serious performance degradation in query processing. Against the problem, we propose a new method to adjust CBRs to be tight, thereby improving the performance of query processing. Our method examines whether the adjustment of a CBR is necessary when accessing a leaf node for processing a user query. Thus, it does not incur extra disk I/Os in this examination. Also, in order to make a correct decision, we devise a cost model that considers both the I/O overhead for the CBR adjustment and the performance gain in the future-time owing to the CBR adjustment. With the cost model, we can prevent unusual expansions of BRs even when updates on nodes are infrequent and also avoid unnecessary execution of the CBR adjustment. For performance evaluation, we conducted a variety of experiments. The results show that our method improves the performance of the original $TPR^*$-tree significantly.

• Journal of Intelligence and Information Systems
• /
• 제24권2호
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.

• Asian-Australasian Journal of Animal Sciences
• /
• 제25권9호
• /
• pp.1237-1247
• /
• 2012

The objective of this study was to evaluate the predictions of dry matter intake (DMI) and average daily gain (ADG) of Vietnamese Yellow (Vang) purebred and crossbred (Vang with Red Sindhi or Brahman) bulls fed under Vietnamese conditions using two levels of solution (1 and 2) of the large ruminant nutrition system (LRNS) model. Animal information and feed chemical characterization were obtained from five studies. The initial mean body weight (BW) of the animals was 186, with standard deviation ${\pm}33.2$ kg. Animals were fed ad libitum commonly available feedstuffs, including cassava powder, corn grain, Napier grass, rice straw and bran, and minerals and vitamins, for 50 to 80 d. Adequacy of the predictions was assessed with the Model Evaluation System using the root of mean square error of prediction (RMSEP), accuracy (Cb), coefficient of determination ($r^2$), and mean bias (MB). When all treatment means were used, both levels of solution predicted DMI similarly with low precision ($r^2$ of 0.389 and 0.45 for level 1 and 2, respectively) and medium accuracy (Cb of 0.827 and 0.859, respectively). The LRNS clearly over-predicted the intake of one study. When this study was removed from the comparison, the precision and accuracy considerably increased for the level 1 solution. Metabolisable protein was limiting ADG for more than 68% of the treatment averages. Both levels differed regarding precision and accuracy. While level 1 solution had the least MB compared with level 2 (0.058 and 0.159 kg/d, respectively), the precision was greater for level 2 than level 1 (0.89 and 0.70, respectively). The accuracy (Cb) was similar between level 1 and level 2 (p = 0.8997; 0.977 and 0.871, respectively). The RMSEP indicated that both levels were on average under-or over-predicted by about 190 g/d, suggesting that even though the accuracy (Cb) was greater for level 1 compared to level 2, both levels are likely to wrongly predict ADG by the same amount. Our analyses indicated that the level 1 solution can predict DMI reasonably well for this type of animal, but it was not entirely clear if animals consumed at their voluntary intake and/or if the roughness of the diet decreased DMI. A deficit of ruminally-undegradable protein and/or a lack of microbial protein may have limited the performance of these animals. Based on these evaluations, the LRNS level 1 solution may be an alternative to predict animal performance when, under specific circumstances, the fractional degradation rates of the carbohydrate and protein fractions are not known.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제22권1호
• /
• pp.568-574
• /
• 2021

According to the Framework Act on Sustainable Infrastructure Management, which has been enforced since 2020, reservoirs should be managed to minimize life cycle costs caused by aging through preemptive management such as systematic maintenance and performance improvement. For maintenance in consideration of the life cycle, it is essential to derive the end of life due to continuous performance degradation as the common period increases. For this purpose, it is necessary to develop a performance-predicting model for reservoirs. In this study, a reservoir was divided into main complex facilities to develop a model for the maintenance of the life cycle. A model was developed for each facility. For model development, maintenance information data were collected under management by the Rural Community Corporation. The data available for model development were selected by analyzing the collected data. The developed model was used to predict the expected life expectancy of the reservoir in the current maintenance system and the expected life expectancy in the case of no action. By using the developed model, it is expected that it will be possible to support decision making in operation management and maintenance while considering the life cycle of the reservoir.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권4호
• /
• pp.1730-1747
• /
• 2018

Multi-view video plus depth (MVD) is a mainstream format of 3D scene representation in free viewpoint video systems. The advanced 3D extension of the high efficiency video coding (3D-HEVC) standard introduces new prediction tools to improve the coding performance of depth video. However, the depth video in 3D-HEVC is time consuming. To reduce the complexity of the depth video inter coding, we propose a fast coding unit (CU) size and mode decision algorithm. First, an off-line trained Bayesian model is built which the feature vector contains the depth levels of the corresponding spatial, temporal, and inter-component (texture-depth) neighboring largest CUs (LCUs). Then, the model is used to predict the depth level of the current LCU, and terminate the CU recursive splitting process. Finally, the CU mode search process is early terminated by making use of the mode correlation of spatial, inter-component (texture-depth), and inter-view neighboring CUs. Compared to the 3D-HEVC reference software HTM-10.0, the proposed algorithm reduces the encoding time of depth video and the total encoding time by 65.03% and 41.04% on average, respectively, with negligible quality degradation of the synthesized virtual view.

• The KIPS Transactions:PartC
• /
• 제13C권5호
• /
• pp.607-612
• /
• 2006

Universal Mobile Telecommunications System (UMTS) and Wireless Local Area Network (WLAN) have been developed independently. Then, many researchers have studied UMTS-WLAN interworking architecture for the efficiency. However, the transmission capacity difference of two networks causes the transmission quality degradation. Therefore, this paper proposes a UMTS-WLAN interworking architecture for Quality of Service (QoS). The proposed architecture is based on tight coupling and dynamically guarantees QoS by the mobility prediction method. The proposed architecture is simulated by ns-2. Performance experimental results show that the proposed architecture reduces the handover dropping probability comparing with the existing method and enhances the amount of receiving packets comparing with the method without guaranteeing QoS.

• Journal of the Korea Society of Computer and Information
• /
• 제19권3호
• /
• pp.11-16
• /
• 2014

In this paper, the two-wheels robot using a predictive controller to maintain the balance of the posture control in real time have been examined. A reaction wheel pendulum control method is adopted to maintain the balance while the bicycle robot is driving. The objective of this research was to design and implement a self-balancing algorithm using the dsPIC30F4013 embedded processor. To calculate the attitude in ARS using 2 axis gyro(roll, pitch) and 3 axis accelerometers (x, y, z). In this study, the disturbance of the posture for the asymmetrical propose to overcome the predictive controller which was a problem in the control of a remote system by introducing the two wheels of the robot controller and the linear prediction of the system controller combines the simulation was performed. Also, the robust characteristic for realizing the goal of designing a loop filter too robust controller is designed so that satisfactory stability of the control system to improve stability of the system to minimize degradation of performance was confirmed.

• Applied Chemistry for Engineering
• /
• 제28권1호
• /
• pp.35-41
• /
• 2017

Materials exposed to outside will deteriorate due to various weathering factors such as sunlight, heat, temperature, humidity and so on. Therefore, predicting speed of degradation and life time is a very important issue. This research uses retro-reflective sheets with white and green which are most commonly used colors to conduct the outdoor exposure test and acceleration test of xenon arc in Arizona state in the United States, Chennai in India, Sanary in France and Seosan in Korea to measure the reflective performance of retro-reflection. The accelerated factor was obtained by using regression analysis through reflective values obtained from the acceleration test of xenon arc from Seosan area. Also, by using solar uv program, the accelerated factor of various climate regions were obtained and it was confirmed that the accelerated factor of Senary was 1.04, Arizona 1.82, Chennai 1.92 times higher than that of Seosan.