• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.73-82
• /
• 2023

Optimization of Construction Site Layout Planning (CSLP) heavily relies on workers' travel paths. However, traditional path generation approaches predominantly focus on the shortest path, often neglecting critical variables such as individual wayfinding tendencies, the spatial arrangement of site objects, and potential hazards. These oversights can lead to compromised path simulations, resulting in less reliable site layout plans. While Deep Reinforcement Learning (DRL) has been proposed as a potential alternative to address these issues, it has shown limitations. Despite presenting more realistic travel paths by considering these variables, DRL often struggles with efficiency in complex environments, leading to extended learning times and potential failures. To overcome these challenges, this study introduces a refined model that enhances spatial navigation capabilities and learning performance by integrating workers' visibility into the reward functions. The proposed model demonstrated a 12.47% increase in the pathfinding success rate and notable improvements in the other two performance measures compared to the existing DRL framework. The adoption of this model could greatly enhance the reliability of the results, ultimately improving site operational efficiency and safety management such as by reducing site congestion and accidents. Future research could expand this study by simulating travel paths in dynamic, multi-agent environments that represent different stages of construction.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1085-1092
• /
• 2022

Travel distance is a parameter mainly used in the objective function of Construction Site Layout Planning (CSLP) automation models. To obtain travel distance, common approaches, such as linear distance, shortest-distance algorithm, visibility graph, and access road path, concentrate only on identifying the shortest path. However, humans do not necessarily follow one shortest path but can choose a safer and more comfortable path according to their situation within a reasonable range. Thus, paths generated by these approaches may be different from the actual paths of the workers, which may cause a decrease in the reliability of the optimized construction site layout. To solve this problem, this paper adopts reinforcement learning (RL) inspired by various concepts of cognitive science and behavioral psychology to generate a realistic path that mimics the decision-making and behavioral processes of wayfinding of workers on the construction site. To do so, in this paper, the collection of human wayfinding tendencies and the characteristics of the walking environment of construction sites are investigated and the importance of taking these into account in simulating the actual path of workers is emphasized. Furthermore, a simulation developed by mapping the identified tendencies to the reward design shows that the RL agent behaves like a real construction worker. Based on the research findings, some opportunities and challenges were proposed. This study contributes to simulating the potential path of workers based on deep RL, which can be utilized to calculate the travel distance of CSLP automation models, contributing to providing more reliable solutions.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.189-198
• /
• 2009

Unstructured peer-to-peer systems are most commonly used in today's internet. But file placement is random in these systems and no correlation exists between peers and their contents. There is no guarantee that flooding queries will find the desired data. In this paper, we propose to cluster nodes in unstructured P2P systems using the agglomerative hierarchical clustering algorithm to improve the search method. We compared the delay time of clustering the nodes between our proposed algorithm and the k-means clustering algorithm. We also simulated the delay time of locating data in a network topology and recorded the overhead of the system using our proposed algorithm, k-means clustering, and without clustering. Simulation results show that the delay time of our proposed algorithm is shorter compared to other methods and resource overhead is also reduced.

• Journal of the Korean Geographical Society
• /
• v.46 no.3
• /
• pp.291-303
• /
• 2011

It has actively advanced to study the impact of climate change on ecosystem. This study addresses ABMS (Agent Based Modeling and Simulation) as a methodology of ecosystem research. ABMS would suggest the possibility of practical use in this sector. This study would investigate how the melting speed of glacier in the arctic influences the extinction period of polar bears. The Polar Bears and Glacier Model in this study is expected to contribute to accurate prediction of the polar bear's extinction period. The suggested ABMS could also be applied to the study of various factors of ecosystem in general.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.2
• /
• pp.209-216
• /
• 2002

World Wide Web has potential possibility of infrastructure for parallel computing environment connecting massive computing resources, not just platform to provide and share information via browser. The approach of Web-based parallel computing has many advantages of the ease of accessibility, scalability, cost-effectiveness, and utilization of existing networks. Applet has the possibility of decomposing the independent/parallel task, moving over network, and executing in computers connected in Web, but it lacks in the flexibility due to strict security semantic model. Therefore, in this paper, Web-based parallel computing environment using mobile agent, Aglet (Agile applet) was designed and possible implementation technologies and architecture were analyzed. And simple simulation and analysis was done compared with applet-based approach.

• Journal of Internet Computing and Services
• /
• v.13 no.2
• /
• pp.99-108
• /
• 2012

Many methods had been developed to improve the accuracy of extracting information from a vast amount of data. This paper combined a number of natural language processing methods such as NER (named entity recognition), sentence extraction, and part of speech tagging to carry out text analysis. The data source is comprised of texts obtained from the web using a domain-specific data extraction agent. A framework for the extraction of information from unstructured data was developed using the aforementioned natural language processing methods. We simulated the performance of our work in the extraction and analysis of texts for the detection of organizational structures. Simulation shows that our study outperformed other NER classifiers such as MUC and CoNLL on information extraction.

• Fire Science and Engineering
• /
• v.18 no.4
• /
• pp.27-34
• /
• 2004

We have conducted a numerical simulation under three-dimensional unsteady conditions in order to analyze the effect of flow and CO₂ mass transfer according to the distance between the CO₂ nozzle of CO₂ fire fighting system and the rear wall in a protection space. Flow fields and CO₂ concentration fields were measured. The different recirculation flow form and wall jet was developed according to increasing the distance between CO₂ nozzles and rear wall. In all the case, CO₂ mass transfer was generated toward the center of a protection space from each walls, but the CO₂ mass fraction of front and rear areas based on CO₂ nozzles showed higher or lower by increasing the distance between CO₂ nozzle and rear wall.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.3
• /
• pp.169-175
• /
• 2010

Recently, to improve operating efficiency with the higher in-line rate in automated production lines, a lot of cases of grouping machines and material handling system together to form a cluster has shown frequently. This article addresses the job allocation and operation method of automated material handling for cluster-type production systems. First of all, the control problems of the automated material handling systems are classified into the control problem of inter-cluster material handling system and that of intra-cluster material handling system. Then, a distributed agent-based control scheme is proposed for the former, and an operational control procedure for the latter. Simulation experiment shows that the proposed method is efficient in reducing cycle times and improving utilization of material handling vehicles.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.4 no.1
• /
• pp.14-19
• /
• 2009

In Mobile Ad-hoc Network, link failure and packet loss may occur frequently due to its nature of mobility and limited battery life. In this paper, an enhanced robust routing protocol based on AODV(Ad hoc On-demand Distance Vector routing) by monitoring variation of receiving signal strength is proposed. New metric function that consists of node mobility and hops of path is used for routing decision. For preventing route failure by node movement during data transmission, a new route maintenance is presented. If the node movement is detected, the routing agent switches local path to its neighbor node. Simulation results show that the performance of the proposed routing scheme is superior to previous AODV protocol.