• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2627-2642
• /
• 2023

Parkinson's disease (PD) is a typical, chronic neurodegenerative disease involving the concentration of dopamine, which can disrupt motor activity and cause different degrees of gait disturbance relevant to PD severity in patients. As current clinical PD diagnosis is a complex, time-consuming, and challenging task that relays on physicians' subjective evaluation of visual observations, gait disturbance has been extensively explored to make automatic detection of PD diagnosis and severity rating and provides auxiliary information for physicians' decisions using gait data from various acquisition devices. Among them, wearable sensors have the advantage of flexibility since they do not limit the wearers' activity sphere in this application scenario. In this paper, an attention-based temporal network (ATN) is designed for the time series structure of gait data (vertical ground reaction force signals) from foot sensor systems, to learn the discriminative differences related to PD severity levels hidden in sequential data. The structure of the proposed method is illuminated by Transformer Network for its success in excavating temporal information, containing three modules: a preprocessing module to map intra-moment features, a feature extractor computing complicated gait characteristic of the whole signal sequence in the temporal dimension, and a classifier for the final decision-making about PD severity assessment. The experiment is conducted on the public dataset PDgait of VGRF signals to verify the proposed model's validity and show promising classification performance compared with several existing methods.

• The Korean Journal of Emergency Medical Services
• /
• v.28 no.1
• /
• pp.97-112
• /
• 2024

Purpose: This study compared the relative importance of educational content, teaching methods, and evaluation methods in the patient assessment curricula of 119 emergency medical technicians (EMTs). Methods: First, we identified the educational content, training hours, and teaching and evaluation methods of the existing patient assessment curriculum based on the National Competency Standard learning module. Second, we surveyed 30 EMTs affiliated with 119 services using the Analytic Hierarchy Process (AHP) method. Subsequently, we compared the differences between the current curriculum and the AHP analysis results. Results: Currently in operation, the "Advanced EMT Course" comprises three learning modules: assessment of patient status, scene size-up and triage, and assessment using monitoring devices. Among these, content related to the assessment of patient status received the most allocated time and was deemed the most important according to the AHP survey results. Conversely, while less time was allocated to scene size and triage compared with assessment using monitoring devices, the former was assessed as more important than the latter in the AHP results. Furthermore, scenario-based team training and procedure-focused individual practice were evaluated as relatively important teaching methods, while practical examination using a checklist was deemed the most appropriate evaluation method for all learning content. Conclusion: To improve the patient assessment curriculum, we propose adjusting teaching hours and introducing new teaching and evaluation methods based on the results of relative importance. The proposed improvement plan will contribute to enhancing the competency of 119 EMTs.

• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.215-224
• /
• 2024

In medium- and long-range optical imaging systems, atmospheric turbulence causes blurring and distortion of images, resulting in loss of image information. An image-restoration method based on an adaptive feature-fusion multi-input-multi-output (MIMO) dense U-shaped network (Unet) is proposed, to restore a single image degraded by atmospheric turbulence. The network's model is based on the MIMO-Unet framework and incorporates patch-embedding shallow-convolution modules. These modules help in extracting shallow features of images and facilitate the processing of the multi-input dense encoding modules that follow. The combination of these modules improves the model's ability to analyze and extract features effectively. An asymmetric feature-fusion module is utilized to combine encoded features at varying scales, facilitating the feature reconstruction of the subsequent multi-output decoding modules for restoration of turbulence-degraded images. Based on experimental results, the adaptive feature-fusion MIMO dense U-shaped network outperforms traditional restoration methods, CMFNet network models, and standard MIMO-Unet network models, in terms of image-quality restoration. It effectively minimizes geometric deformation and blurring of images.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.4
• /
• pp.21-28
• /
• 2006

In this paper, the proposed full-bridge high frequency isolated zoo voltage and zero current switching phase shifted pulse width modulation(ZVZCS PS-PWM)DC-DC converter among fuel cell generation system consist of 1.2[kW] fuel cell of Nexa Power Module, full-bridge DC-DC converter to boost the fuel cell low voltage($28{\sim}43[%]$) to 380[VDC] and a single phase full-bridge inverter is implemented to produce AC output(220[VAC], 60[Hz]). A tapped inductor filter with freewheeling diode is newly implemented in the output filter of the proposed full-bridge high frequency isolated ZVZCS PS-PWM DC-DC converter to suppress circulating current under the wide output voltage regulation range, thus to eliminate the switching and transformer turn-on/off over-short voltage or transient phenomena. Besides the efficiency of $93{\sim}97[%]$ is obtained over the wide output voltage regulation ranges and load variations.

• The KIPS Transactions:PartD
• /
• v.8D no.2
• /
• pp.154-165
• /
• 2001

A number of attempts to develop methods for measuring software effort have been focused on the area of software engineering and many models have also been suggested to estimate the effort of software projects. Almost all current models use algorithmic or statistical mechanisms, but the existing algorithmic effort estimation models have failed to produce accurate estimates. Furthermore, they are unable to reflect the rapidly changing technical environment of software development such as module reuse, 4GL, CASE tool, etc. In addition, these models do not consider the paradigm shift of software engineering and information systems(i.e., Object Oriented system, Client-Server architecture, Internet/Intranet based system etc.). Thus, a new approach to software effort estimation is needed. After reviewing and analyzing the problems of the current estimation models, we have developed a model and a system architecture that will improve estimation performance. In this paper, we have adopted a neural network model to overcome some drawbacks and to increase estimation performance. We will also address the efficient system architecture and estimation procedure by a similar case-based approach and finally suggest the heuristic search method to find the best estimate of target project through empirical experiments. According to our experiment with the optimally parsimonious neural network model the mean error rate was significantly reduced to 14.3%.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.15 no.4
• /
• pp.321-332
• /
• 2017

In order to build a general model of a high-throughput uranium electrorefining process according to the electrode configuration, numerical analysis was conducted using the COMSOL Multiphysics V5.3 electrodeposition module with Ordinary Differential Equation (ODE) interfaces. The generated model was validated by comparing a current density-potential curve according to the distance between the anode and cathode and the electrode array, using a lab-scale (1kg U/day) multi-electrode electrorefiner made by the Korea Atomic Energy Research Institute (KAERI). The operating temperature was $500^{\circ}C$ and LiCl-KCl eutectic with 3.5wt% $UCl_3$ was used for molten salt. The efficiency of the uranium electrorefining apparatus was improved by lowering the cell potential as the distance between the electrodes decreased and the anode/cathode area ratio increased. This approach will be useful for constructing database for safety design of high throughput spent nuclear fuel electrorefiners.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.437-446
• /
• 2017

70 percent of Korea's territory is covered with mountains, whose difficult conditions can cause damage to facilities. Recently, the demand for facilities related to outdoor activities including monorails has been on the rise, and such facilities are much more likely to become damaged. For this reason, a monitoring system applying IoT to mountainous areas was developed and its applicability is evaluated in this study. The current status of the existing mountainous facilities and monitoring systems were reviewed, and the current wired monitoring technology was analyzed. A scenario for IoT-based monitoring was developed, and then sensor nodes were developed, which include an RF-communication module and interface, power-supply and solar-cell. A testbed was set up at K University. The same data was collected by the wireless system as had been collected by the wired one. The study findings are as follows. Firstly, by using the wireless system, it is estimated that the construction duration can be reduced by about 25 percent, while the construction costs can be reduced by about 3~52 percent. Secondly, the safety of the construction workers can be improved by making the working conditions less dangerous, such as by eliminating the need to transport cables.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.499-506
• /
• 2019

An intelligent robot should decide its behavior accordingly to the dynamic changes in the environment and user's requirements by evaluating options to choose the best one for the current situation. Many intelligent robot systems that use the Procedural Reasoning System (PRS) accomplishes such task management functions by defining the priority functions in the task model and evaluating the priority functions of the applicable tasks in the current situation. The priority functions, however, are defined locally inside of the plan, which exhibits limitation for the tasks for multi-domain services because global contexts for overall prioritization are hard to be expressed in the local priority functions. Furthermore, since the prioritization functions are not defined as an explicit module, reuse or extension of the them for general context is limited. In order to remove such limitations, we propose a policy-based meta-planning for general task management for multi-domain services, which provides the ability to explicitly define the utility of a task in the meta-planning process and thus the ability to evaluate task priorities for general context combining the modular priority functions. The ontological specification of the model also enhances the scalability of the policy model. In the experiments, adaptive behavior of a robot according to the policy model are confirmed by observing the appropriate tasks are selected in dynamic service environments.

• Current Industrial and Technological Trends in Aerospace
• /
• v.6 no.1
• /
• pp.3-13
• /
• 2008

The year 2007 marked two important anniversaries for space. The Soviet Union launched Sputnik 50 years ago on October 4. 1957. The 40th anniversary of the United Nations treaty on outer space was also marked in 2007. 2008 and 2007 were full of dramatic events of space activity as well : Success of Japan's first large lunar explorer 'KAGUYA'(SELENE) and China's 'Chang'e 1', launch of ISS laboratory module, 'Colombus' and 'Kibo', test of China's ASAT, and success of Korea's first astronaut program and so on. International government space budgets reached $78.3 billion in 2007, a strong growth rate of 36% over 2006, and the recently released Global Exploration Strategy, The Framework for Coordination is a set of guidelines for international cooperation among 14 of the world's space agencies. Worldwide space industry revenue grew by 20% over 2005, $106.1 billion in 2006 and $173.9 billion expected in 2007. This paper discusses the issues related to the Earth observation R&D trend and market in detail. Korea's 2008 government space spending is \316.4 billion, 2007 space industry revenue was $106 million. Several research projects are now underway and STSAT 2 will be launched by KSLV-1 at the Naro Space Center within this year.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1778-1785
• /
• 2014

In order to construct offshore structures safely, geotechnical investigation should be carried out with high accuracy. Up to now, onshore geotechnical investigation equipments installed on the barge are used for offshore geotechnical investigation. In this case, many limitations can be confronted such as deep water depth, high wave, strong current, severe wind and so on. For the safe and economic offshore geotechnical investigation with high precision, a seabed type unmanned automated site investigation equipment is developed. It can be operated remotely underwater conditions with 100m water depth and can explore the ground depth of 50m. Also, the standard penetration test (SPT), soil boring, soil sampling and rock coring can be possible using the equipment. Numerical analysis was conducted to secure the stability of the equipment against current of 4 knot. Energy efficiency of SPT apparatus which is attached to the equipment shows 78% in average.