• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.526-538
• /
• 2021

Machine and deep learning-based models are emerging techniques that are being used to address prediction problems in biomedical data analysis. DNA sequence prediction is a critical problem that has attracted a great deal of attention in the biomedical domain. Machine and deep learning-based models have been shown to provide more accurate results when compared to conventional regression-based models. The prediction of the gene sequence that leads to cancerous diseases, such as prostate cancer, is crucial. Identifying the most important features in a gene sequence is a challenging task. Extracting the components of the gene sequence that can provide an insight into the types of mutation in the gene is of great importance as it will lead to effective drug design and the promotion of the new concept of personalised medicine. In this work, we extracted the exons in the prostate gene sequences that were used in the experiment. We built a Deep Neural Network (DNN) and Bi-directional Long-Short Term Memory (Bi-LSTM) model using a k-mer encoding for the DNA sequence and one-hot encoding for the class label. The models were evaluated using different classification metrics. Our experimental results show that DNN model prediction offers a training accuracy of 99 percent and validation accuracy of 96 percent. The bi-LSTM model also has a training accuracy of 95 percent and validation accuracy of 91 percent.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.18-25
• /
• 2023

In these days, high dimensional data prediction technology based on neural network shows compelling results in many different kind of field including engineering. Especially, a lot of variants of convolution neural network are widely utilized to develop pixel level prediction model for high dimensional data such as picture, or physical field value from the sensors. In this study, velocity vector field of ideal flow on ship surface is estimated on pixel level by Unet. First, potential flow analysis was conducted for the set of hull form data which are generated by hull form transformation method. Thereafter, four different neural network with a U-shape structure were conFig.d to train velocity vectors at the node position of pre-processed hull form data. As a result, for the test hull forms, it was confirmed that the network with short skip-connection gives the most accurate prediction results of streamlines and velocity magnitude. And the results also have a good agreement with potential flow analysis results. However, in some cases which don't have nothing in common with training data in terms of speed or shape, the network has relatively high error at the region of large curvature.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.183-183
• /
• 2021

Deep learning methods and their application have become an essential part of prediction and modeling in water-related research areas, including hydrological processes, climate change, etc. It is known that application of deep learning leads to high availability of data sources in hydrology, which shows its usefulness in analysis of precipitation, runoff, groundwater level, evapotranspiration, and so on. However, there is still a limitation on microclimate analysis and prediction with deep learning methods because of deficiency of gauge-based data and shortcomings of existing technologies. In this study, a real-time rainfall prediction model was developed from a sky image data set with convolutional neural networks (CNNs). These daily image data were collected at Chung-Ang University and Korea University. For high accuracy of the proposed model, it considers data classification, image processing, ratio adjustment of no-rain data. Rainfall prediction data were compared with minutely rainfall data at rain gauge stations close to image sensors. It indicates that the proposed model could offer an interpolation of current rainfall observation system and have large potential to fill an observation gap. Information from small-scaled areas leads to advance in accurate weather forecasting and hydrological modeling at a micro scale.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7A
• /
• pp.778-784
• /
• 2007

Predictive channel reservation techniques have widely been studied in mobile cellular networks in order to meet the desired quality-of-service requirements. Those efforts are mostly concentrated on predicting the target cell that a mobile will move to and reserving the channel before the actual handoff, and subsequently reducing handoff-dropping probability and improving bandwidth utilization. In this paper, we propose adaptive reporting schemes that a mobile reports its mobility status information such as position, speed, and direction in an appropriate moment based on the user's mobility pattern characteristics and, hence the network can make a more-accurate prediction on the user's mobility. We show from the simulations that the proposed scheme is capable of keeping target cell prediction more accurate and required number of reporting through the wireless up-link channel lower.

• Journal of the Korean Society of Tobacco Science
• /
• v.35 no.1
• /
• pp.1-6
• /
• 2013

Near InfraRed Spectroscopy(NIRS) is a quick and accurate analytical method to measure multiple components in tobacco manufacturing process. This study was carried out to develop calibration equation of near infrared spectroscopy for the prediction of the amount of chemical components and hot water solubles(HWS) of reconstituted tobacco leaf. Calibration samples of reconstituted tobacco leaf were collected from every lot produced during one year. The calibration equation was formulated as modified partial least square regression method (MPLS) by analyzing laboratory actual values and mathematically pre-treated spectra. The accuracy of the acquired equation was confirmed with the standard error of prediction(SEP) of chemical components in reconstituted tobacco leaf samples, indicated as coefficient of determination($R^2$) and prediction error of sample unacquainted, followed by the verification of model equation of laboratory actual values and these predicted results. As a result of monitoring, the standard error of prediction(SEP) were 0.25 % for total sugar, 0.03 % for nicotine, 0.03 % for chlorine, 0.16 % for nitrate, and 0.38 % for hot water solubles. The coefficient of determination($R^2$) were 0.98 for total sugar, 0.97 for nicotine, 0.96 for chlorine, 0.98 for nitrate and 0.92 for hot water solubles. Therefore, the NIRS calibration equation can be applicable and reliable for determination of chemical components of reconstituted tobacco leaf, and NIRS analytical method could be used as a rapid and accurate quality control method.

• Journal of Korean Society of Steel Construction
• /
• v.25 no.6
• /
• pp.587-599
• /
• 2013

A simple but accurate analytical method to evaluate the fire resistance of unprotected concrete filled tubular (CFT) columns under standard fire condition is proposed based on the fire design framework of EC4. To this end, the accuracy of the current tabulation method for the temperature prediction proposed by Lawson et al. was first critically evaluated, and a new prediction equation for the temperature gradient across the CFT section was then proposed based on available test and finite element analysis results. Overall, the axial strength predicted by using the proposed equation under the general fire design framework of EC4 was more accurate than that based on existing methods and appeared reasonable for design purposes. The results of this study are directly usable for the more rational fire analysis and design of unprotected CFT columns.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.6
• /
• pp.8-22
• /
• 2011

Investigations on modeling methods of a CFD wind resource prediction program, WindSim for a ccurate predictions of wind speeds were performed with the field measurements. Meteorological Masts having heights of 40m and 50m were installed at two different sites in complex terrain. The wind speeds and direction were monitored from sensors installed on the masts and recorded for one year. Modeling parameters of WindSim input variables for accurate predictions of wind speeds were investigated by performing cross predictions of wind speeds at the masts using the measured data. Four parameters that most affect the wind speed prediction in WindSim including the size of a topographical map, cell sizes in x and y direction, height distribution factors, and the roughness lengths were studied to find out more suitable input parameters for better wind speed predictions. The parameters were then applied to WindSim to predict the wind speed of another location in complex terrain in Korea for validation. The predicted annual wind speeds were compared with the averaged measured data for one year from meteorological masts installed for this study, and the errors were within 6.9%. The results of the proposed practical study are believed to be very useful to give guidelines to wind engineers for more accurate prediction results and time-saving in predicting wind speed of complex terrain that will be used to predict annual energy production of a virtual wind farm in complex terrain.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.57-64
• /
• 2021

This study presents a method for realtime fuel consumption prediction using real data collected from OBDII. With the advent of the era of self-driving cars, electronic control units(ECU) are getting more complex, and various studies are being attempted to extract and analyze more accurate data from vehicles. But since ECU is getting more complex, it is getting harder to get the data from ECU. To solve this problem, the firmware was developed for acquiring accurate vehicle data in this study, which extracted 53,580 actual driving data sets from vehicles from January to February 2019. Using these data, the ensemble stacking technique was used to increase the accuracy of the realtime fuel consumption prediction model. In this study, Ridge, Lasso, XGBoost, and LightGBM were used as base models, and Ridge was used for meta model, and the predicted performance was MAE 0.011, RMSE 0.017.

• The korean journal of orthodontics
• /
• v.37 no.1 s.120
• /
• pp.16-28
• /
• 2007

Objective: Evaluation of individual growth is important in orthodontics. The aim of this study was to develop a convenient software that can evaluate current growth status and predict further growth. Methods: Stature data of 2 to 20 year-old Koreans (4893 boys and 4987 girls) were extracted from a nationwide data. Age-sex-specific continuous functions describing percentile growth curves were constructed using natural cubic spline function (NCSF). Then, final stature prediction algorithm was developed and its validity was tested using longitudinal series of stature measurements on randomly selected 200 samples. Various accuracy measurements and analyses of errors between observed and predicted stature using NCSF growth curves were performed. Results: NCSF growth curves were shown to be excellent models in describing reference percentile stature growth curie over age. The prediction accuracy compared favorably with previous prediction models, even more accurate. The current prediction models gave more accurate results in girls than boys. Although the prediction accuracy was high, the error pattern of the validation data showed that in most cases, there were a lot of residuals with the same sign, suggestive of autocorrelation among them. Conclusion: More sophisticated growth prediction algorithm is warranted to enhance a more appropriate goodness of model fit for individual growth.