• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.6
• /
• pp.400-412
• /
• 2022

This paper provides the results of numerical and theoretical predictions of oil outflows from damaged single-hull and double-hull ships.Theoretical equations derived from the unsteady Bernoulli equation and a CFD method for multi-phase flow analysis were used to estimate the oil outflow rate from cargo tank. The predicted oil outflow rate from a single-hull cargo tank damaged due to grounding and collision accidents showed a good agreement with the available experimental results in both numerical and theoretical analyses. However, in the case of the double-hull conditions, the time variation of the amount of water and oil mixture inside the ballast tank predicted by the theoretical equation showed some different behavior from the numerical results. The reason was that the interaction of the oil flow with the water inflow in the ballast tank was not reflected in the theoretical equations. In the problems of the initial pressure condition in the cargo and ballast tanks, the oil outflow and water inflow were delayed at the pressure condition that the tanks were sealed. When the flow interaction between the oil and water in the ballast tank was less complicated, the theoretical and the numerical results showed a good agreement with each other.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.344-352
• /
• 2022

Accurate indoor localization of construction workers and mobile assets is essential in safety management. Existing positioning methods based on GPS, wireless, vision, or sensor based RTLS are erroneous or expensive in large-scale indoor environments. Tightly coupled sensor fusion mitigates these limitations. This research paper proposes a state-of-the-art positioning methodology, addressing the existing limitations, by integrating Stereo Visual Inertial Odometry (SVIO) with fiducial landmarks called AprilTags. SVIO determines the relative position of the moving assets or workers from the initial starting point. This relative position is transformed to an absolute position when AprilTag placed at various entry points is decoded. The proposed solution is tested on the NVIDIA ISAAC SIM virtual environment, where the trajectory of the indoor moving forklift is estimated. The results show accurate localization of the moving asset within any indoor or underground environment. The system can be utilized in various use cases to increase productivity and improve safety at construction sites, contributing towards 1) indoor monitoring of man machinery coactivity for collision avoidance and 2) precise real-time knowledge of who is doing what and where.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.4
• /
• pp.1-10
• /
• 2024

In the fields of computer animation and robotics, reaching a destination while avoiding obstacles has always been a difficult task. Moreover, generating appropriate motions while planning a route is even more challenging. Recently, academic circles are actively conducting research to generate character motions by modifying and utilizing VAE (Variational Auto-Encoder), a data-based generation model. Based on this, in this study, the latent space of the MVAE model is learned using a reinforcement learning method[1]. With the policy learned in this way, the character can arrive its destination while avoiding both static and dynamic obstacles with natural motions. The character can easily avoid obstacles moving in random directions, and it is experimentally shown that the performance is improved, and the learning time is greatly reduced compared to existing approach.

• Journal of Ginseng Research
• /
• v.44 no.1
• /
• pp.105-114
• /
• 2020

Background: Exploring the pharmacokinetic (PK) changes of various active components of single herbs and their combinations is necessary to elucidate the compatibility mechanism. However, the lack of chemical standards and low concentrations of multiple active ingredients in the biological matrix restrict PK studies. Methods: A putative multiple reaction monitoring strategy based on liquid chromatography coupled with mass spectrometry (LC-MS) was developed to extend the PK scopes of quantification without resorting to the use of chemical standards. First, the compounds studied, including components with available reference standard (ARS) and components lacking reference standard (LRS), were preclassified to several groups according to their chemical structures. Herb decoctions were then subjected to ultrahigh-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry analysis with appropriate collision energy (CE) in MS² mode. Finally, multiple reaction monitoring transitions transformed from MS² of ultrahigh-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry were used for ultrahigh-performance liquid chromatography coupled with triple quadrupole mass spectrometry to obtain the mass responses of LRS components. LRS components quantification was further performed by developing an assistive group-dependent semiquantitative method. Results: The developed method was exemplified by the comparative PK process of single herbs Radix Ginseng (RG), Radix Polygala (RP), and their combinations (RG-RP). Significant changes in PK parameters were observed before and after combination. Conclusion: Results indicated that Traditional Chinese Medicine combinations can produce synergistic effects and diminish possible toxic effects, thereby reflecting the advantages of compatibility. The proposed strategy can solve the quantitative problem of LRS and extend the scopes of PK studies.

• Advanced Industrial SCIence
• /
• v.3 no.1
• /
• pp.23-29
• /
• 2024

In this scholarly investigation, the focus is placed on the transformative potential of edge computing in enhancing Intelligent Transportation Systems (ITS) for the facilitation of autonomous driving. The intrinsic capability of edge computing to process voluminous datasets locally and in a real-time manner is identified as paramount in meeting the exigent requirements of autonomous vehicles, encompassing expedited decision-making processes and the bolstering of safety protocols. This inquiry delves into the synergy between edge computing and extant ITS infrastructures, elucidating the manner in which localized data processing can substantially diminish latency, thereby augmenting the responsiveness of autonomous vehicles. Further, the study scrutinizes the deployment of edge servers, an array of sensors, and Vehicle-to-Everything (V2X) communication technologies, positing these elements as constituents of a robust framework designed to support instantaneous traffic management, collision avoidance mechanisms, and the dynamic optimization of vehicular routes. Moreover, this research addresses the principal challenges encountered in the incorporation of edge computing within ITS, including issues related to security, the integration of data, and the scalability of systems. It proffers insights into viable solutions and delineates directions for future scholarly inquiry.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.196-201
• /
• 2013

In this paper, we propose an asynchronous and adaptive message passing scheme based on S-MAC for handling with the problem on energy efficiency in wireless sensor networks. The proposed scheme consists of a policy that differentiate transmission errors caused by packet collision or radio interference from congestion errors caused by buffer overflow and a method that adaptively controls the size of a fragment according to the variance of traffic loads. Especially, it presents a method that highly reduce the energy consumption by keeping the size of fragment not being excessively smaller than the one that may result in rapid increment of the total transfer time. Finally, with the simulation results we show that network throughput and delay are improved by using the proposed message passing scheme.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1483-1490
• /
• 2009

This parer is presented multiple path-planning of unmanned autonomous forklift using modified genetic algorithm and fuzzy inference system. There are a task-level feedback method and a method that path is dynamically replaned in realtime while the autonomous vehicles are moving by means of an optimal algorithm for existing multiple path-planning. However, such methods cause malfunctions and inefficiency in the sense of time and energy, and path-planning should be dynamically replanned in realtime. To solve these problems, we propose multiple path-planning using modified genetic algorithm and fuzzy inference system and show the performance with autonomous vehicles. For experiment, we designed and built two autonomous mobile vehicles that equipped with the same driving control part used in actual autonomous forklift, and test the proposed multiple path-planning algorithm. Experimental result that actual autonomous mobile vehicle, we verified that fast optimized path-planning and efficient collision avoidance are possible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.6
• /
• pp.151-158
• /
• 2010

In line with the requirement of appropriate protocol support for such mission-critical wireless sensor network (WSN) applications as patient monitoring, we investigate the framework for designing medium access control (MAC) schemes. The data traffic in medical systems comes with inherent traffic heterogeneity as well as strict requirement of reliability according to the varied extents of devise-wise criticality in separate cases. This implies that the quality-of-Service (QoS) issues are very distinctly delicate requiring specialized consideration. Besides, there are features in such systems that can be exploited during the design of a MAC scheme. In a monitoring or routine surveillance application, there are degrees of regularity or predictability in traffic as coordinated from a node of central control. The coordinator thus takes on the role of marshaling the resources in a neighborhood of nodes deployed mostly for upstream traffic; in a collision-free scheme, it schedules the time slots for each superframe based on the QoS specifications. In this preliminary study, we identify the key artifacts of such a MAC scheme. We also present basic performance issues like the impact of superframe length on delay incurred, energy efficiency achieved in the network operation as obtained in a typical simulation setup based on this framework.

• Korean Journal of Food Science and Technology
• /
• v.9 no.1
• /
• pp.61-67
• /
• 1977

Seed separation from half-cut red pepper were investigated with free falling, up-and-down shaking and rotating collision methods. The separation rates were related with impact appiied and the rotating case was distinguished from the other two methods. Beside the impact effect, velocity of the pod and tumbling factors were involved. Momentum effectiveness of seed separation were calculated as $2.50{\times}10^{-6}$, $2.09{\times}10^{-6}$, and $3.94{\times}10^{-8}$ for free falling, shaking and rotating method on the same velocity basis, respectively. The tendency of separation rate was similar to that of red pepper drying rate against time.