• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.1
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.1
• /
• pp.1-9
• /
• 2013

This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.

• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.166-173
• /
• 2014

Recently, human action recognition have been developed for various broadcasting and video process. Since a video can consist of various scenes, keypoint approaches have been more attracted than template based methods for real application. Keypoint approahces tried to find regions having motion in video, and made 3-dimensional patches. Then, descriptors using histograms were computed from the patches, and a classifier based on machine learning method was applied to detect actions in video. However, a single classifier was difficult to handle various human actions. In order to improve this problem, approaches using multi classifiers were used to detect and to recognize objects. Thus, we propose a new human action recognition using decision-level fusion with support vector machine and sparse representation. The proposed method extracted descriptors based on keypoint approach from a video, and acquired results from each classifier for human action recognition. Then, we applied weights which were acquired by training stage to fuse each results from two classifiers. The experiment results in this paper show better result than a previous fusion method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3075-3093
• /
• 2014

In this paper, we consider an advanced wireless user, called primary-secondary user (PSU) who is capable of harvesting renewable energy and connecting to both the primary network and cognitive radio networks simultaneously. Recently, energy harvesting has received a great deal of attention from the research community and is a promising approach for maintaining long lifetime of users. On the other hand, the cognitive radio function allows the wireless user to access other primary networks in an opportunistic manner as secondary users in order to receive more throughput in the current time slot. Subsequently, in the paper we propose the channel access policy for a PSU with consideration of the energy harvesting, based on a Partially Observable Markov decision process (POMDP) in which the optimal action from the action set will be selected to maximize expected long-term throughput. The simulation results show that the proposed POMDP-based channel access scheme improves the throughput of PSU, but it requires more computations to make an action decision regarding channel access.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1820-1831
• /
• 2010

When interacting with unknown environments, an autonomous agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. The traditional multiple sequential learning model requires predefined probability of the states' transition. This paper proposes a multiple sequential learning and prediction system with definition of autonomous states to enhance the automatic performance of existing AI algorithms. In sequence learning process, the sensed states are classified into several group by a set of proposed motivation filters to reduce the learning computation. In prediction process, the learning agent makes a decision based on the estimation of each state's cost to get a high payoff from the given environment. The proposed learning and prediction algorithms heightens the automatic planning of the autonomous agent for interacting with the dynamic unknown environment. This model was tested in a virtual library.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.8 no.1
• /
• pp.31-40
• /
• 1983

An uncertain dynamic evolving process has been a continuing challenge to decision problems. The dynamic random variable (drv) changes which characterize such a process are very important for the decision-maker in selecting a course of action in a world that is perceived as uncertain, complex, and dynamic. Using this subjective point prediction algorithm based on a modified recursive filter, the decision-maker becomes to have periodically changing plausible points with the passage of time.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.12
• /
• pp.51-58
• /
• 1993

This paper presents a design of the fuzzy decision maker which infers set value for fuel rate in the rotary kiln of making CaO. The fuzzy decision maker proposed are divided into two groups whose functions are different each other. The one operates when production demand is constant. The other deals with the status of varying production demand. We have chosen several variables used for composing condition and action part by investigating ingerent features of the rotary kiln and skilled operators`manual method of inferring fuel rate. Membership function of each variable was designed by analyzing experimental data and field data collected during two months. On-line operation with fuzzy rules suggested was done safely like human operators' action.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.21-28
• /
• 2019

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.127-130
• /
• 2002

Human's brain action can divide by recognition and intelligence. recognition is sensing voice, image and smell and Intelligence is logical judgment, inference, decision. To this concept, Define function of cerebral cortex, and apply the result. Current expert system is lack, that reasoning by cerebral cortex and thalamus, hoppocampal and so on. In this paper, With human's brain action, wish to embody human's action artificially Embody brain mechanism using Modular Neural Network, Applied this result to snake robot.

• Asia pacific journal of information systems
• /
• v.2 no.2
• /
• pp.31-54
• /
• 1992

Generating an action plan and obtaining commitment to achieve it is desired in organizations, but not always achieved. Whatever the reason, there is a room for an improved approach to decision making, so that people can arrive at a common understanding of a problem and commitment to action. Those are the purposes of a Decision Conferencing(DC). A DC, one example of single workstation-based GDSSs, is a two-day session attended by a group of people who attempt to resolve important issues of concern to their organization with the help of group facilitation techniques and decision analytic computer modelling. The interchange of differing perspectives on the issues is encouraged by the facilitator who attends to group processes but does not contribute to the content of discussions. Decision analysis provides a variety of structures for modelling the differing perspectives. Information and value judgements are incorporated in these models, whose results usually reveal new, higher-level perspectives on the issues. Information technology is needed to combine the part of the model and to facilitate on-the-spot replay of results. The experimental case study in this paper shows that how a DC can help a Korea's trading company to develop new, corporate level resource allocation strategies which are based on improved consensus among competing participants.