• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.162-177
• /
• 2020

The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.44-57
• /
• 2019

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

• Journal of The Korean Association of Information Education
• /
• v.24 no.5
• /
• pp.495-509
• /
• 2020

This study is a theoretical research to explore ways to effectively learn AI in the age of intelligent information driven by artificial intelligence (hereinafter referred to as AI). The emphasis is on presenting a teaching method to make AI education accessible not only to students majoring in mathematics, statistics, or computer science, but also to other majors such as humanities and social sciences and the general public. Given the need for 'Explainable AI(XAI: eXplainable AI)' and 'the importance of storytelling for a sensible and intelligent machine(AI)' by Patrick Winston at the MIT AI Institute [33], we can find the significance of research on AI storytelling learning model. To this end, we discuss the possibility through a pilot study targeting general students of an university in Daegu. First, we introduce the AI storytelling(AI+ST) learning method[30], and review the educational goals, the system of contents, the learning methodology and the use of new AI tools in the method. Then, the results of the learners are compared and analyzed, focusing on research questions: 1) Can the AI+ST learning method complement algorithm-driven or developer-centered learning methods? 2) Whether the AI+ST learning method is effective for students and thus help them to develop their AI comprehension, interest and application skills.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6D
• /
• pp.859-869
• /
• 2008

These days, almost every industry's production line has become automatic and this phenomenon brought a lot of benefits such as increase in productivity and economical effect, assurance in industrial safety, better quality and compatibility. However, unlike industrial production line, in construction industry, automation has number of barriers like uncertainty incidents and intellectual judgment to make ability to make solution out of it. Therefore construction industry is still demanding use of construction machine through labor. Due to this matter operational labor in construction industry is aging and fading. To solve these problem, in developed nations like Europe, US or Japan are keep researching for the automation in construction and road pavement, strengthening and some other simple operations have been worked through automation but in civil engineering site, automation research is still low despite of its importance in constructional site. For automating civil engineering operation, effective operational plan have to be set by analyzing ground information acquainted. If skillful worker apply heuristics, trial & error can be reduced with increased safety and the effective work plan can be established. Hence, this research will introduce Intellectual Task Planning System for Intelligent Excavating System's effective work plan and heuristics applied in each steps.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.32-48
• /
• 2023

Autonomous driving technology is shaping the future of personalized travel, encouraging personalized travel, and traffic impact could be influenced by individualized travel behavior during the transition of driving entity from human to machine. In order to evaluate traffic impact, it is necessary to estimate the total number of trips based on an understanding of individual travel characteristics. The Activity-based model(ABM), which allows for the reflection of individual travel characteristics, deals with all travel sequences of an individual. Understanding the relationship between travel and travel must be important for assessing traffic impact using ABM. However, the ABM has a limitation in the data hunger model. It is difficult to adjust in the actual demand forecasting. Therefore, we utilized a Tour-based model that can explain the relationship between travels based on household travel survey data instead. After that, vehicle registration and population data were used for correction. The result showed that, compared to the KTDB one, the traffic generation exhibited a 13% increase in total trips and approximately 9% reduction in working trips, valid within an acceptable margin of error. As a result, it can be used as a generation correction method based on Tour, which can reflect individual travel characteristics, prior to building an activity-based model to predict demand due to the introduction of autonomous vehicles in terms of road operation, which is the ultimate goal of this study.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.117-127
• /
• 2001

The Main object of this research is directed to LG Oil company harbor in kwangyang-hang, where various ships ranging from 300 ton to 48000ton DWT use seven berths in the harbor. This harbor suffered from inefficient and unsafe management procedures since it is difficult to set guidelines for arrival and departure of ships according to the weather conditions and the current guidelines dose not offer clear basis of its implications. Therefore, it has long been suggested that these guidelines should be improved. This paper proposes a decision-support system, which can quantitatively decide the possibility of entry or departure on a harbor by analyzing the weather conditions (wind, current, and wave) and taking account of factors such as harbor characteristics, ship characteristics, weight condition, and operator characteristics. This system has been verified using 5$_{th}$ and 7$_{th}$ berth in Kwangyang-hang harbor. Machine learning technique using genetic programming(GP) is introduced to the system to quantitatively decide and produce results about the possibility of entry or arrival, and weighted linear associative memory (WLAM) method is also used to reduce the amount of calculation the GP has to perform. Group of additive genetic programming trees (GAGPT) is also used to improve learning performance by making it easy to find global optimum.mum.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.237-246
• /
• 2020

this paper, a data modeling method based on decision-making conditions is proposed for making combat and battlefield management systems to be intelligent, which are also a decision-making support system. A picture of a robot seeing and perceiving like humans and arriving a point it wanted can be understood and be felt in body. However, we can't find an example of implementing a decision-making which is the most important element in human cognitive action. Although the agent arrives at a designated office instead of human, it doesn't support a decision of whether raising the market price is appropriate or doing a counter-attack is smart. After we reviewed a current situation and problem in control & command of military, in order to collect a big data for making a machine staff's advice to be possible, we propose a data modeling prototype based on decision-making conditions as a method to change a current control & command system. In addition, a decision-making tree method is applied as an example of the decision making that the reformed control & command system equipped with the proposed data modeling will do. This paper can contribute in giving us an insight of how a future AI decision-making staff approaches to us.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.255-265
• /
• 2007

In this paper, we propose a new illumination-robust drowsy driver monitoring system with single CCD(Charge Coupled Device) camera for intelligent vehicle in the day and night. For this system that is monitoring driver's eyes during a driving, the eye detection and the measure of eyelid movement are the important preprocesses. Therefore, we propose efficient illumination compensation algorithm to improve the performance of eye detection and also eyelid movement measuring method for efficient drowsy detection in various illumination. For real-time application, Cascaded SVM (Cascaded Support Vector Machine) is applied as an efficient eye verification method in this system. Furthermore, in order to estimate the performance of the proposed algorithm, we collect video data about drivers under various illuminations in the day and night. Finally, we acquired average eye detection rate of over 98% about these own data, and PERCLOS(The percentage of eye-closed time during a period) are represented as drowsy detection results of the proposed system for the collected video data.