• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.65-70
• /
• 2023

The "information roadway" will give us an impact of new PC based assignments and administrations, yet the unusualness of this new condition will ask for another style of human-PC association, where the PC transforms into a sharp, dynamic and customized partner. Interface administrators are PC programs that use Artificial Intelligence frameworks to give dynamic help to a customer with PC based errands. Operators drastically change the present client encounter, through the similitude that a specialist can go about as an individual collaborator. The operator procures its capability by gaining from the client and from specialists helping different clients. A couple of model administrators have been gathered using this methodology, including authorities that give customized help with meeting planning, electronic mail taking care of, Smart Personal Assistant and choice of diversion. Operators help clients in a scope of various ways: they perform assignments for the client's sake; they can prepare or educate the client, they enable diverse clients to work together and they screen occasions and methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.74-83
• /
• 2024

The threat of North Korea's long-range firepower is recognized as a typical asymmetric threat, and South Korea is prioritizing the development of a Korean-style missile defense system to defend against it. To address this, previous research modeled North Korean long-range artillery attacks as a Markov Decision Process (MDP) and used Approximate Dynamic Programming as an algorithm for missile defense, but due to its limitations, there is an intention to apply deep reinforcement learning techniques that incorporate deep learning. In this paper, we aim to develop a missile defense system algorithm by applying a modified DQN with multi-agent-based deep reinforcement learning techniques. Through this, we have researched to ensure an efficient missile defense system can be implemented considering the style of attacks in recent wars, such as how effectively it can respond to enemy missile attacks, and have proven that the results learned through deep reinforcement learning show superior outcomes.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.606-612
• /
• 2024

The modeling and simulation of built environments are crucial preliminary steps for their design, planning, and management. Among various simulation methods, agent-based modeling (ABM) has recently gained traction for simulating built environments due to its ability to effectively model and capture complex interactions between simulated entities. The increasing applications of ABM for the simulation of built environments necessitate a comprehensive review of past scientific endeavors with positive accomplishments and those that remain unsolved. This study seeks to address this gap by reviewing ABM and its applications in the simulation of built environments, with a specific focus on the planning and design phases. First, the research introduces ABM and its unique features concerning the simulation of built environments. Second, it conducts a systematic review of past studies in the planning (e.g., feasibility analysis, risk management, and scheduling under constraints) and design (e.g., automated design, collaborative design, improving operations, and facilitating evacuation) aspects of built environments. Finally, following the in-depth review and subsequent analysis, the study identifies the strengths and weaknesses of using ABM for simulating the built environments. The study concludes with a remark on potential future research directions to overcome the limitations of the existing studies.

• Journal of Digital Contents Society
• /
• v.8 no.3
• /
• pp.309-314
• /
• 2007

A decision tree algorithm should be modified to be suitable in distributed and collaborative environments for distributed data mining. The distributed data mining system proposed in this paper consists of several agents and a mediator. Each agent deals with a local data mining for data in each local site and communicates with one another to build the global decision tree model. The mediator helps several agents to efficiently communicate among them. One of advantages in distributed data mining is to save much time to analyze huge data with several agents. The paper focuses on a transfer technique among agents dealing with each local decision tree model to reduce huge overhead in communication among them.

• Advances in robotics research
• /
• v.2 no.2
• /
• pp.161-182
• /
• 2018

This paper proposes a novel receding horizon control (RHC) algorithm for formation control of a swarm of unmanned surface vehicles (USVs) using particle swarm optimization (PSO). The proposed control algorithm provides the coordinated path tracking of multi-agent USVs while preventing collisions and considering external disturbances such as ocean currents. A three degrees-of-freedom kinematic model of the USV is used for the RHC with guaranteed stability and convergence by incorporating a sequential Monte Carlo (SMC)-based particle initialization. An ocean current model-based estimator is designed to compensate for the effect of ocean currents on the USVs. This method is compared with the PSO-based RHC algorithms to demonstrate the performance of the formation control and the collision avoidance in the presence of ocean currents through numerical simulations.

• BMB Reports
• /
• v.50 no.8
• /
• pp.417-422
• /
• 2017

Cisplatin is the most effective and widely used chemotherapeutic agent for many types of cancer. Unfortunately, its clinical use is limited by its adverse effects, notably bone marrow suppression leading to abnormal hematopoiesis. We previously revealed that neuropeptide Y (NPY) is responsible for the maintenance of hematopoietic stem cell (HSC) function by protecting the sympathetic nervous system (SNS) fibers survival from chemotherapy-induced bone marrow impairment. Here, we show the NPY-mediated protective effect against bone marrow dysfunction due to cisplatin in an ovarian cancer mouse model. During chemotherapy, NPY mitigates reduction in HSC abundance and destruction of SNS fibers in the bone marrow without blocking the anticancer efficacy of cisplatin, and it results in the restoration of blood cells and amelioration of sensory neuropathy. Therefore, these results suggest that NPY can be used as a potentially effective agent to improve bone marrow dysfunction during cisplatin-based cancer therapy.

• Journal of Pharmaceutical Investigation
• /
• v.41 no.5
• /
• pp.279-288
• /
• 2011

The Dexamethasone (DEX) loaded chitosan microspheres were prepared by thermal denaturation and chemical cross-linking method using a dierent concentration of glutaraldehyde as chemical cross-linking agent. The prepared microspheres were evaluated for the percentage of Drug Loading (DL), Encapsulation Efficiency (EE) and surface morphology by Scanning Electron Microscopy (SEM). DL and EE were found to be maximum range of 10.0 to 10.79 % and 58.19 to 64.73 % respectively. The SEM Photographs of the resultant microspheres exhibited fairly smooth surfaces and predominantly spherical in appearance. In addition, Fourier Transform Infrared Spectroscopy (FTIR) and Differential Scanning Calorimetry (DSC) shown that there was no interaction between the drug and polymer. In vitro and in vivo release studies revealed that the release of dexamethasone was sustained and extended up to 63 days and effectively controlled by the extent of cross-linking agent. Non-clinical parameters such as paw volume, hematological parameters like Erythrocyte Sedimentation Rate (ESR), Paced Cell Volume (PCV), Total Leucocytes Count (TLC), Hemoglobin (Hb), Differential Cell Count (DCC) were investigated in Fruend's Complete Adjuvant (FCA) induced arthritic rats. Radiology and histopathological studies were also performed in order to evaluate the therapeutic efficacy of the DEX-loaded microspheres in extenuating the rat arthritic model.

• Environmental and Resource Economics Review
• /
• v.26 no.1
• /
• pp.85-101
• /
• 2017

The objective of the Nagoya Protocol is to enhance biodiversity by the mean of economic incentives but there has been yet consistent lack of realized contracts between genetic resource users and holders due to the asymmetric information among the parties. This paper presents a principle-agent model to provide optimal contracts under asymmetric information in order to achieve the sustainable biological resource. The model concludes the royalty contracts over the fixed lump-sum benefit transfer as profit sharing mechanism.

• Journal of Information Processing Systems
• /
• v.3 no.2
• /
• pp.82-88
• /
• 2007

Web services are the new building block of today's Internet, and provides interoperability among heterogeneous distributed systems. Recently in web services environment, security has become one of the most critical issues. The hackers attack one of fragile point and can misuse legitimate user privilege because all of the connected devices provide services for the user control and monitoring in real time. Also, the users of web services must temporarily delegate some or all of their rights to agents in order to perform actions on their behalf. This fact risks the exposure of user privacy information. In this paper, we propose secure delegation model based on SAML that provides confidentiality and integrity about the user information in distributed systems. In order to support privacy protection, service confidentiality, and assertion integrity, encryption and a digital signature mechanism is deployed. We build web service management server based on XACML, in order to manage services and policies of web service providers.