• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.29-37
• /
• 1999

In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.6
• /
• pp.107-116
• /
• 2015

In compliance with digital device growth, the proliferation of high-tech computers, the availability of high quality and inexpensive video cameras, the demands for automated video analysis is increasing, especially in field of intelligent monitor system, video compression and robot vision. That is why object tracking of computer vision comes into the spotlight. Tracking is the process of locating a moving object over time using a camera. The consideration of object's scale, rotation and shape deformation is the most important thing in robust object tracking. In this paper, we propose a robust object tracking scheme using Random Forest. Specifically, an object detection scheme based on region covariance and ZNCC(zeros mean normalized cross correlation) is adopted for estimating accurate object location. Next, the detected region will be divided into five regions for random forest-based learning. The five regions are verified by random forest. The verified regions are put into the model pool. Finally, the input model is updated for the object location correction when the region does not contain the object. The experiments shows that the proposed method produces better accurate performance with respect to object location than the existing methods.

• Korean Journal of Construction Engineering and Management
• /
• v.1 no.1 s.1
• /
• pp.87-94
• /
• 2000

Crack sealing, a routine and necessary part of pavement maintenance, is a dangerous, costly, and labor-intensive operation. Within the North America, about ${\$}200$ million is spent annually on crack sealing, with the Texas Department of Transportation (TxDOT) spending about ${\$}7$ million annually (labor alone accounts for over 50 percent of these costs). Prompted by concerns of safety and cost, the University of Texas at Austin, in cooperation with TxDOT and the Federal Highway Administration (FHWA) has developed a unique computer-guided Automated Road Maintenance Machine (ARMM) for pavement crack sealing. In 1999, successful field tests have been undertaken in 8 States around the U.S. This paper first describes significance of the automated crack sealing and technical advances in automated crack sealers including the ARMM, developed in the U.S. It then discusses the ARMM's field implementation and performance evaluation results, and improvements and modifications suggested through the technology evaluation during the field trials. Current research efforts and future work plans in its further development are also presented in this paper.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.541-551
• /
• 2021

Among the numerous duties of a librarian in a library, the work of arranging books is a job that the librarian has to do one by one. Thus, the cost of labor and time is large. In order to solve this problem, the interest in book-arranging robots based on artificial intelligence has recently increased. In this paper, we propose the K-ACO algorithm, which is the shortest path algorithm for multi-stops that can be applied to the library book arrangement robots. The proposed K-ACO algorithm assumes multiple robots rather than one robot. In addition, the K-ACO improves the ANT algorithm to create K clusters and provides the shortest path for each cluster. In this paper, the performance analysis of the proposed algorithm was carried out from the perspective of book arrangement time. The proposed algorithm, the K-ACO algorithm, was applied to a university library and compared with the current book arrangement algorithm. Through the simulation, we found that the proposed algorithm can allocate fairly, without biasing the work of arranging books, and ultimately significantly reduce the time to complete the entire work. Through the results of this study, we expect to improve quality services in the library by reducing the labor and time costs required for arranging books.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1036-1043
• /
• 2022

This paper discusses about the development of a visual sensor that can be installed in an automatic mooring device to detect the berthing condition of a vessel. Despite controlling the ship's speed and confirming its location to prevent accidents while berthing a vessel, ship collision occurs at the pier every year, causing great economic and environmental damage. Therefore, it is important to develop a visual system that can quickly obtain the information on the speed and location of the vessel to ensure safety of the berthing vessel. In this study, a visual sensor was developed to observe a ship through an image while berthing, and to properly check the ship's status according to the surrounding environment. To obtain the adequacy of the visual sensor to be developed, the sensor characteristics were analyzed in terms of information provided from the existing sensors, that is, detection range, real-timeness, accuracy, and precision. Based on these analysis data, we developed a 3D visual module that can acquire information on objects in real time by conducting conceptual designs of LiDAR (Light Detection And Ranging) type 3D visual system, driving mechanism, and position and force controller for motion tilting system. Finally, performance evaluation of the control system and scan speed test were executed, and the effectiveness of the developed system was confirmed through experiments.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.127-136
• /
• 2022

As manufacturing items have changed in various ways, changes in the mass production of small-scale small-scale production of multiple varieties have become commonplace. As a result, the method of the manufacturing site has also changed, and the "smart factory," which emphasizes the production efficiency aspect using automation lines and big data of factories, is in the spotlight according to the global market economy. The introduction performance of smart factories has a positive effect in terms of production efficiency and is drawing a steep upward curve. In addition to the positive aspects, the aspect that needs to be supplemented in the future is the support and cooperation of specialized smart equipment suppliers, but education on standardized smart factories and the relocation of existing manpower, education, evaluation, and creative production that robots cannot replace Various support measures are also needed for activities. In addition, continuous management and systematic education are required to enter the upper stage. Through the case of companies that have built smart factories, it is intended to emphasize the need for proper use of manpower and support management for settlement and maintenance after introduction and continuous on-the-job training through the comparison of productivity before and after introduction to ensure the effect continues.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.665-672
• /
• 2023

Purpose: Underground utility tunnel is facility that is jointly house infrastructure such as electricity, water and gas in city, causing condensation problems due to lack of airflow. This paper aims to prevent electricity leakage fires caused by condensation by detecting whether the control panel door in the underground utility tunnel is open using a deep learning model. Method: YOLO, a deep learning object recognition model, is trained to recognize the opening and closing of the control panel door using video data taken by a robot patrolling the underground utility tunnel. To improve the recognition rate, image augmentation is used. Result: Among the image enhancement techniques, we compared the performance of the YOLO model trained using mosaic with that of the YOLO model without mosaic, and found that the mosaic technique performed better. The mAP for all classes were 0.994, which is high evaluation result. Conclusion: It was able to detect the control panel even when there were lights off or other objects in the underground cavity. This allows you to effectively manage the underground utility tunnel and prevent disasters.

• (The) Research of the performance art and culture
• /
• no.43
• /
• pp.293-322
• /
• 2021

The present study examined the scientific awareness appearing in Korean tokusatsu series by focusing on Vectorman: Warriors of the Earth. As a work representing Korean tokusatsu series, Vectorman: Warriors of the Earth achieved the greatest success among tokusatsu series. This work was released thanks to the continued popularity of Japanese tokusatsu since the mid-1980s and the trend of robot animations. Due to the chronic problems regarding Korean children's programs-the oversupply of imported programs and repeated reruns-the need for domestically produced children's programs has continued to come to the fore. However, as the popularity of Korean animation waned beginning in the mid-1990s, inevitably the burden fr producing animation increased. As a result, Vectorman: Warriors of the Earth was produced as a tokusatsu rather than an animation, and because this was a time when an environment for using special effects technology was being fostered in broadcasting stations, computer visual effects were actively used for the series. The response to the new domestically produced tokusatsu series Vectorman: Warriors of the Earth was explosive. The Vectorman series explained the abilities of cosmic beings by using specific scientific terms such as DNA synthesis, brain cell transformation, and special psychological control device instead of ambiguous words like the scientific technology of space. Although the series is unable to describe in detail about the process and cause, the way it defines technology using concrete terms rather than science fiction shows how scientific imagination is manifesting in specific forms in Korean society. Furthermore, the equal relationship between Vectorman and the aliens shows how the science of space, explained with the scientific terms of earth, is an expression of confidence regarding the advancement of Korean scientific technology which represents earth. However, the female characters fail to gain entry into the domain of science and are portrayed as unscientific beings, revealing limitations in terms of scientific awareness.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.