• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.668-674
• /
• 2022

Machine learning techniques using visual data have high usability in fields of industry and service such as scene recognition, fault detection, security and user analysis. Among these, user analysis through the videos from CCTV is one of the practical way of using vision data. Also, many studies about lightweight artificial neural network have been published to increase high usability for mobile and embedded environment so far. In this study, we propose the network combining the object detection and classification for mobile graphic processing unit. This network detects pedestrian and face, classifies age and gender from detected face. Proposed network is constructed based on MobileNet, YOLOv2 and skip connection. Both detection and classification models are trained individually and combined as 2-stage structure. Also, attention mechanism is used to improve detection and classification ability. Nvidia Jetson Nano is used to run and evaluate the proposed system.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.77-84
• /
• 2023

This research originated from the need to enhance the security of secure multiparty computation by ensuring that participants involved in multiparty computations provide truthful inputs that have not been manipulated. While malicious participants can be involved, which goes beyond the traditional security models, malicious behaviors through input manipulation often occur in real-world scenarios, leading to privacy infringements or situations where the accuracy of multiparty computation results cannot be guaranteed. Therefore, in this study, we propose a signature scheme applicable to secure multiparty technologies, combining it with secret sharing to strengthen the accuracy of inputs using authentication techniques. We also investigate methods to enhance the efficiency of authentication through the use of batch authentication techniques. To this end, a scheme capable of input certification was designed by applying a commitment scheme and zero-knowledge proof of knowledge to the CL signature scheme, which is a lightweight signature scheme, and batch verification was applied to improve efficiency during authentication.

• Journal of Aerospace System Engineering
• /
• v.17 no.2
• /
• pp.1-8
• /
• 2023

Power transmission shafts in rotary wing aircraft use a hollow shaft to reduce weight. We can apply linear elastic fracture mechanics to predict crack propagation behavior. This paper predicted crack growth life of a hollow shaft with a circumferential through-type crack by finite element analysis. A 2D finite element model was created by applying a torsion and forming elements considering cracks. We defined the initial crack length and performed the finite element analysis by increasing the crack length to derive stress intensity factor at crack tips. We defined the length just prior to the stress intensity factor exceeding the fracture toughness as the crack limit length. We calculated the crack limit length using a handbook and numerically integrated the crack growth rate equation to derive growth life of each crack. The growth life of each crack was compared to verify the proposed finite element analysis method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3A
• /
• pp.457-464
• /
• 2006

Fiber-reinforced composite materials due to their high specific strength, high stiffness and light weight are becoming increasingly used in many engineering industry, especially in the aerospace, marin and civil, etc. In this paper, the buckling load and mode shapes of composite laminates with elliptical cross-section including transverse shear deformations are analyzed. For solving this problems, a versatile flat shell element has been developed by combining a membrane element with drilling degree-of-freedom and a plate bending element. Also, an improved shell element has been established by the combined use of the addition of enhanced assumed strain and the substitute shear strain fields. The combined influence of shell geometry and elliptical cross-sectional parameter, fiber angle, and lay-up on the buckling loads of elliptical cylinder is examined. The critical buckling loads and mode shapes analyzed here may serve as a benchmark for future investigations.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.464-473
• /
• 2022

In this paper, about a lightweight design that satisfies the performance of UHF-GPS Antenna used in autonomous underwater vehicle is proposed. Structural analysis, watertight external pressure test and non-destructive testing used in the design process are decided in consideration of structural safety for operating external forces in the underwater environment. First, the material of radome is selected for the performance of the UHF-GPS Antenna for communication with the carrier on the underwater operation in consideration of the 20 bar pressure generated. And the material of radome as PA-GF is selected by conducting electromagnetic field analysis and structural analysis and by considering high strength, rigidity and high dielectric constant. Electromagnetic field analysis and structural analysis by the thickness of radome are additionally performed in order to satisfy the required weight of UHF-GPS antenna. After selecting the final model, its structural safety is verified through watertight external pressure test and non-destructive testing.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.6
• /
• pp.140-146
• /
• 2011

As the demand of Variable Message Sign(VMS) has become pervasive in fulfilling the ITS policy, the costs of maintaining the Variable Message Sign operation have also increased. This paper proposes the U-curved figure, the C-curved figure and the ventilated figure type for aerodynamic drag reduction on Variable Message Sign and shows the analysis of aerodynamic drag effects using Flow Analysis. As a results of the flow analysis for right-angled, 45 degrees from side to side and 45 degrees from up or down, the C-curved figure and the ventilated figure type show about 30% aerodynamic drag reduction in all direction. And the U-curved figure type shows vivid aerodynamic drag reduction for right-angled and 45 degree from side to side, but trivial aerodynamic drag reduction for 45 degree from up or down. It is possible to reduce not only the damage on Variable Message Sign due to typhoon because of the aerodynamic drag reduction, but also installation constraints because of lighter Variable Message Sign support structure by appling the proposed structure and analysis in this paper.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.25 no.1
• /
• pp.37-49
• /
• 2012

A structural model of the SNF(spent nuclear fuel) disposal canister for the PWR(pressurized water reactor) for about 10,000 years long term deposition at a 500m deep granitic bedrock repository has been developed through various structural safety evaluations. The SNF disposal baskets of this canister model have the array type whose four square cross section baskets stand parallel to each other and symmetrically with respect to the center of the canister section. However, whether this developed structural model of the SNF disposal canister is optimal is not determinable yet. Especially, there is still a problem in weight-reduction of the canister. The cross section shape of the SNF basket should be changed to solve this problem. There are two ways in changing the cross section shape of the SNF basket; the one is to rotate the cross section itself and the other is to change the cross section shape as other shape different from the square cross section. The previous study shows that the canister with $30{\sim}35^{\circ}$ rotated basket array is structurally more stable than the canister with un-rotated parallel basket array. However, whether this canister with rotated basket array is optimal is not either determinable as yet, because it is not revealed that the canister with other cross section different from the square cross section is structurally more stable than other canisters. Therefore, the structural analysis of the SNF disposal canister with other cross section shape which is also symmetric with respect to the canister center planes is very necessary. The structural analysis of the canister with various cross section shape basket array in which each basket is arrayed symmetrically with respect to the center planes is carried out in this paper. The structural analysis result shows that the SNF disposal canister with circular cross section shape baskets located symmetrically with respect to the center of the canister section is structurally more stable than the previously developed SNF disposal canister with the parallel basket array.

• Spatial Information Research
• /
• v.23 no.5
• /
• pp.41-52
• /
• 2015

MOLIT (Minister of Land, Infrastructure and Transport) authorized Indoor Spatial Information as Basic spatial information in 2013. It became a legal evidence for constructing and managing Indoor Spatial Information. Although it has a little advantage to utilize as service level that Indoor Spatial Information by laser scan or measurement, it has a lot of problems such as consuming many resources, requiring additional progresses for inputting Object Information. In conclusion, it is inefficient to utilize for the maintenance and domestic AEC/FM field. The purposes of this study is to output Indoor Spatial Information by operating IFC model which based on open BIM and to improve availability of Indoor Spatial Information with data visualization. The open-sources of IFC Exporter, a inner program of Revit (Autodesk Inc), is used to output Indoor Spatial Information. Directs 3D Library is also operated to visualize Indoor Spatial Information. It is possible to inter-operate between XML format and the objects of Indoor Spatial Information. It can be utilized in various field as well. For example COBie linkage in facility management, construction of geo-database using air-photogrammetry of UAV (Unmaned Areal Vehicle), the simulation of large-scale military operations and the simulation of large-scale evacuation. The method that is purposed in this study has outstanding advantages such as conformance with national spatial information policy, high level of interoperability as indoor spatial information objects based on IFC, convenience of editing information, light level of data and simplifying progress of producing information.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.144-153
• /
• 2009

Recently, as the necessity of a light-weighted video encoding technique has been rising for applications such as UCC(User Created Contents) or Multiview Video, Distributed Video Coding(DVC) where a decoder, not an encoder, performs the motion estimation/compensation taking most of computational complexity has been vigorously investigated. Wyner-Ziv coding reconstructs an image by eliminating the noise on side information which is decoder-side prediction of original image using channel code. Generally the side information of Wyner-Ziv coding is generated by using frame interpolation between key frames. The channel code such as Turbo code or LDPC code which shows a performance close to the Shannon's limit is employed. The noise model of Wyner-Ziv coding for channel decoding is called Virtual Channel Noise and is generally modeled by Laplacian or Gaussian distribution. In this paper, we propose a Wyner-Ziv coding method based on the frequency-adaptive channel noise modeling in transform domain. The experimental results with various sequences prove that the proposed method makes the channel noise model more accurate compared to the conventional scheme, resulting in improvement of the rate-distortion performance by up to 0.52dB.