• Proceedings of the KOR-KST Conference
• /
• 1999.10a
• /
• pp.217-222
• /
• 1999

• Journal of Navigation and Port Research
• /
• v.47 no.4
• /
• pp.212-219
• /
• 2023

Vessel Traffic Service (VTS) area presents a complex traffic pattern due to ships entering or leaving the port to utilize port facilities, as well as ships passing through the coastal area. To ensure safe and efficient management of maritime traffic, VTS operators continuously monitor and control vessels in real time. However, during periods of high traffic congestion, the workload of VTS operators increases, which can result in delayed or inadequate VTS services. Therefore, it would be beneficial to predict traffic congestion and congested areas to enable more efficient traffic control. Currently, such prediction relies on the experience of VTS operators. In this paper, we defined vessel traffic congestion from the perspective of a VTS operator. We proposed a method to generate traffic networks using historical navigational data and predict traffic congestion and congested areas. Experiments were performed to compare prediction results with real maritime data (Daesan port VTS) and examine whether the proposed method could support VTS operators.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.1-16
• /
• 2023

Accurate traffic information prediction is considered to be one of the most important aspects of intelligent transport systems(ITS), as it can be used to guide users of transportation facilities to avoid congested routes. Various deep learning models have been developed for accurate traffic prediction. Recently, ensemble techniques have been utilized to combine the strengths and weaknesses of various models in various ways to improve prediction accuracy and stability. Therefore, in this study, we developed and evaluated a traffic information prediction model using various deep learning models, and evaluated the performance of the developed deep learning models as a stacking ensemble. The individual models showed error rates within 10% for traffic volume prediction and 3% for speed prediction. The ensemble model showed higher accuracy compared to other models when no cross-validation was performed, and when cross-validation was performed, it showed a uniform error rate in long-term forecasting.

• International Journal of Highway Engineering
• /
• v.14 no.5
• /
• pp.133-143
• /
• 2012

PURPOSES: Using the collected data for crash, traffic volume, and design elements on ramps between 2007 and 2009, this research effort was initiated to develop traffic crash prediction models for expressway ramps. METHODS: Three negative binomial regression models and three zero-inflated negative binomial regression models were developed for individual ramp types, including direct, semi-direct and loop, respectively. For validating the developed models, authors compared the estimated crash frequencies with actual crash frequencies of twelve randomly selected interchanges, the ramps of which have not been used for model developing. RESULTS: The results show that the negative binomial regression models for direct, semi-direct and loop ramps showed 60.3%, 63.8% and 48.7% error rates on average whereas the zero-inflated negative binomial regression models showed 82.1%, 120.4% and 57.3%, respectively. CONCLUSIONS: Conclusively, the negative binomial regression models worked better in traffic crash prediction than the zero-inflated negative binomial regression models for estimating the frequency of traffic accidents on expressway ramps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3635-3654
• /
• 2015

With the rapid development of smart devices and mobile Internet, the video application plays an increasingly important role on mobile devices. Understanding user behavior patterns is critical for optimized operation of mobile live streaming systems. On the other hand, volume based billing models on cloud services make it easier for video service providers to scale their services as well as to reduce the waste from oversized service capacities. In this paper, the watching behaviors of a commercial mobile live streaming system are studied in a content-centric manner. Our analysis captures the intrinsic correlation existing between popularity and watching intensity of programs due to the synchronized watching behaviors with program schedule. The watching pattern is further used to estimate traffic volume generated by the program, which is useful on data volume capacity reservation and billing strategy selection in cloud services. The traffic range of programs is estimated based on a naive popularity prediction. In cross validation, the traffic ranges of around 94% of programs are successfully estimated. In high popularity programs (>20000 viewers), the overestimated traffic is less than 15% of real happened traffic when using upper bound to estimate program traffic.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.119-126
• /
• 2018

PURPOSES : The purpose of this study is to develop a crash prediction model at signalized intersections, which can capture the randomness and uncertainty of traffic accident forecasting in order to provide more precise results. METHODS : The authors propose a random parameter (RP) approach to overcome the limitation of the Count model that cannot consider the heterogeneity of the assigned locations or road sections. For the model's development, 55 intersections located in the Daejeon metropolitan area were selected as the scope of the study, and panel data such as the number of crashes, traffic volume, and intersection geometry at each intersection were collected for the analysis. RESULTS : Based on the results of the RP negative binomial crash prediction model developed in this study, it was found that the independent variables such as the log form of average annual traffic volume, presence or absence of left-turn lanes on major roads, presence or absence of right-turn lanes on minor roads, and the number of crosswalks were statistically significant random parameters, and this showed that the variables have a heterogeneous influence on individual intersections. CONCLUSIONS : It was found that the RP model had a better fit to the data than the fixed parameters (FP) model since the RP model reflects the heterogeneity of the individual observations and captures the inconsistent and biased effects.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.15-20
• /
• 2023

This study aims to enhance the accuracy of fine dust predictions by analyzing various factors within the local environment, in addition to atmospheric conditions. In the atmospheric environment, meteorological and air pollution data were utilized, and additional factors contributing to fine dust generation within the region, such as traffic volume and electricity transaction data, were sequentially incorporated for analysis. XGBoost, Random Forest, and ANN (Artificial Neural Network) were employed for the analysis. As variables were added, all algorithms demonstrated improved performance. Particularly noteworthy was the Artificial Neural Network, which, when using atmospheric conditions as a variable, resulted in an MAE of 6.25. Upon the addition of traffic volume, the MAE decreased to 5.49, and further inclusion of power transaction data led to a notable improvement, resulting in an MAE of 4.61. This research provides valuable insights for proactive measures against air pollution by predicting future fine dust levels.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.1
• /
• pp.101-110
• /
• 2010

In this study, a prediction model for incident reaction time was developed so that we can cope with the increasing demand for information related to the accident reaction time. For this, the time for dealing with accidents and dependent variables were classified into incident grade, A, B, and C. Then, fifteen independent variables including traffic volume, number of accident-related vehicles and the accidents time zone were utilized. As a result, traffic volume, possibility of including heavy vehicles, and an accident time zone were found as important variables. The results showed that the model has some degree of explanatory power. In addition, when the CHAID Technique was applied, the Answer Tree was constructed based on the variables included in the prediction model for incident reaction time. Using the developed Answer Tree model, accidents firstly were classified into grades A, B, and C. In the secondary classification, they were grouped according to the traffic volume. This study is expected to make a contribution to provide expressway users with quicker and more effective traffic information through the prediction model for incident reaction time and the Answer Tree, when incidents happen on expressway

• Journal of the Korea Society for Simulation
• /
• v.29 no.3
• /
• pp.41-48
• /
• 2020

In this paper, a dynamic prediction algorithm using the cumulative distribution function for traffic volume is presented as a new method for predicting highway traffic rate more accurately, where an approximation function of the cumulative distribution function is obtained through numerical methods such as natural cubic spline interpolation and Levenberg-Marquardt method. This algorithm is a new structure of random number generation algorithm using the cumulative distribution function used in financial mathematics to be suitable for predicting traffic flow. It can be confirmed that if the highway traffic rate is simulated with this algorithm, the result is very similar to the actual traffic volume. Therefore, this algorithm is a new one that can be used in a variety of areas that require traffic forecasting as well as highways.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.351-360
• /
• 2010

In 2010, the number of registered vehicles reached almost at 17.48 millions in Korea. This dramatic increase of vehicles influenced to increase the number of traffic accidents which is one of the serious social problems and also to soar the personal and economic losses in Korea. Through this research, an enhanced intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network will be developed in order to obtain the important data for developing the countermeasures of traffic accidents and eventually to reduce the traffic accidents in Korea. Firstly, this research has investigated the influencing factors of road geometric features on the traffic volume of each approaching for the intersections where traffic accidents and congestions frequently take place and, a linear regression model of traffic accidents and traffic conflicts were developed by examining the relationship between traffic accidents and traffic conflicts through the statistical significance tests. Secondly, this research also developed an intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network through applying the intersection traffic volume, the road geometric features and the specific variables of traffic conflicts. Lastly, this research found out that the developed model is better than the existed forecasting models in terms of the reliability and accuracy by comparing the actual number of traffic accidents and the predicted number of accidents from the developed model. In conclusion, it is expect that the cost/effectiveness of any traffic safety improvement projects can be maximized if this developed intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network use practically at field in the future.