• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.2
• /
• pp.171-177
• /
• 2002

In this paper, we propose a new data fusion method to improve the performance of individual prediction models for time series data. Individual models used are ARIMA and neural network and their results are combined based on the weight reflecting the inverse of EWMA of squared prediction error of each individual model. Monte Carlo simulation is used to identify the situation where the proposed approach can take a vintage point over typical fusion methods which utilize MSE for weight. Study results indicate the following: EWMA performs better than MSE fusion when the data size is large with a relatively big amplitude, which is often observed in intra-cranial pressure data. Additionally, EWMA turns out to be a best choice among MSE fusion and the two individual prediction models when the data size is large with relatively small random noises, often appearing in tax revenue data.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.157-168
• /
• 2016

In image processing and computer vision fields, mean squared error (MSE) has popularly been used as an objective metric in image quality optimization problems due to its desirable mathematical properties such as metricability, differentiability and convexity. However, as known that MSE is not highly correlated with perceived visual quality, much effort has been made to develop new image quality assessment (IQA) metrics having both the desirable mathematical properties aforementioned and high prediction performances for subjective visual quality scores. Although recent IQA metrics having the desirable mathematical properties have shown to give some promising results in prediction performance for visual quality scores, they also have high computation complexities. In order to alleviate this problem, we propose a new fast IQA metric using a simple Laplace operator. Since the Laplace operator used in our IQA metric can not only effectively mimic operations of receptive fields in retina for luminance stimulus but also be simply computed, our IQA metric can yield both very fast processing speed and high prediction performance. In order to verify the effectiveness of the proposed IQA metric, our method is compared to some state-of-the-art IQA metrics. The experimental results showed that the proposed IQA metric has the fastest running speed compared the IQA methods except MSE under comparison. Moreover, our IQA metric achieves the best prediction performance for subjective image quality scores among the state-of-the-art IQA metrics under test.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.323-325
• /
• 2021

In this article, we have improved the prediction of hypertension detection using the feature selection method for the Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. The paper is divided into two modules. The first of these is a data pre-processing step that uses a factor analysis (FA) based feature selection method from the dataset. The next module applies a predictive analysis step to detect and predict hypertension risk prediction. In this study, we compare the mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed FIFA-OE-NB algorithm has an MSE, F1-score, and AUC outcomes 0.259, 0.460, and 64.70%, respectively. These results demonstrate that the proposed FIFA-OE method outperforms other models for hypertension risk predictions.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.149-159
• /
• 2016

With the success of the genome-wide association studies (GWASs), many candidate loci for complex human diseases have been reported in the GWAS catalog. Recently, many disease prediction models based on penalized regression or statistical learning methods were proposed using candidate causal variants from significant single-nucleotide polymorphisms of GWASs. However, there have been only a few systematic studies comparing existing methods. In this study, we first constructed risk prediction models, such as stepwise linear regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN), using a GWAS chip and GWAS catalog. We then compared the prediction accuracy by calculating the mean square error (MSE) value on data from the Korea Association Resource (KARE) with body mass index. Our results show that SLR provides a smaller MSE value than the other methods, while the numbers of selected variables in each model were similar.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7A
• /
• pp.762-769
• /
• 2007

Adaptive MIMO-OFDM (Orthogonal Frequency Division Multiplexing) system adaptively changes modulation scheme depending on feedback channel state information (CSI). The CSI feedback channel which is the reverse link channel has multiple symbol delays including propagation delay, processing delay, frame delay, etc. The unreliable CSI due to feedback delay degrades adaptive modulation system performance. This paper compares the MSE and data capacity with respect to delay and channel signal to noise ratio for the two multi-step channel prediction schemes, CTSBP and BTSBP, such that robust adaptive SISO-OFDM/MIMO-OFDM is designed over severe mobile multipath channel conditions. This paper presents an interpolation method to reduce feedback overhead for adaptive MIMO-OFDM and shows MSE with respect to interpolation interval.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.3
• /
• pp.28-37
• /
• 2020

This study developed a deep learning model that predicts rental demand for public bicycles. For this, public bicycle rental data, weather data, and subway usage data were collected. After building an exponential smoothing model, ARIMA model and LSTM-based deep learning model, forecasting errors were compared and evaluated using MSE and MAE evaluation indicators. Based on the analysis results, MSE 348.74 and MAE 14.15 were calculated using the exponential smoothing model. The ARIMA model produced MSE 170.10 and MAE 9.30 values. In addition, MSE 120.22 and MAE 6.76 values were calculated using the deep learning model. Compared to the value of the exponential smoothing model, the MSE of the ARIMA model decreased by 51% and the MAE by 34%. In addition, the MSE of the deep learning model decreased by 66% and the MAE by 52%, which was found to have the least error in the deep learning model. These results show that the prediction error in public bicycle rental demand forecasting can be greatly reduced by applying the deep learning model.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.109-123
• /
• 2008

Many small area estimation methods have been suggested. Also for the comparison of the estimation methods, model diagnostic checking techniques have been studied. Almost all of the small area estimators were developed by minimizing MSE(Mean square error) and so the MSE is the well-known comparison criterion for superiority. In this paper we suggested a new small area estimator based on minimizing MSPE(Mean square percentage error) which is recently re-highlighted. Also we compared the new suggested estimator with the estimators explained in Shin et al. (2007) using MSE, MSPE and other diagnostic checking criteria.

• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.1
• /
• pp.111-115
• /
• 2024

This study builds a machine learning model optimized for clocks among various techniques in the field of artificial intelligence and applies it to clock stabilization or synchronization technology based on atomic clock noise characteristics. In addition, the possibility of providing stable source clock data is confirmed through the characteristics of machine learning predicted values during holdover of atomic clocks. The proposed machine learning model is evaluated by comparing its performance with the AutoRegressive Integrated Moving Average (ARIMA) model, an existing statistical clock prediction model. From the results of the analysis, the prediction model proposed in this study (MSE: 9.47476) has a lower MSE value than the ARIMA model (MSE: 221.2622), which means that it provides more accurate predictions. The prediction accuracy is based on understanding the complex nature of data that changes over time and how well the model reflects this. The application of a machine learning prediction model can be seen as a way to overcome the limitations of the statistical-based ARIMA model in time series prediction and achieve improved prediction performance.

• Journal of Korea Water Resources Association
• /
• v.56 no.1
• /
• pp.63-74
• /
• 2023

High-reliability prediction of dam inflow is necessary for efficient dam operation. Recently, studies were conducted to predict the inflow of dams using Multi Layer Perceptron (MLP). Existing studies used the Gradient Descent (GD)-based optimizer as the optimizer among MLP operators to find the optimal correlation between data. However, the GD-based optimizers have disadvantages in that the prediction performance is deteriorated due to the possibility of convergence to the local optimal value and the absence of storage space. This study improved the shortcomings of the GD-based optimizer by developing Adaptive moments combined with Improved Harmony Search (AdamIHS), which combines Adaptive moments among GD-based optimizers and Improved Harmony Search (IHS). In order to evaluate the learning and prediction performance of MLP using AdamIHS, Daecheong Dam inflow was learned and predicted and compared with the learning and prediction performance of MLP using GD-based optimizer. Comparing the learning results, the Mean Squared Error (MSE) of MLP, which is 5 hidden layers using AdamIHS, was the lowest at 11,577. Comparing the prediction results, the average MSE of MLP, which is one hidden layer using AdamIHS, was the lowest at 413,262. Using AdamIHS developed in this study, it will be possible to show improved prediction performance in various fields.