• Korean Journal of Computational Design and Engineering
• /
• v.18 no.4
• /
• pp.258-266
• /
• 2013

In shipbuilding, 2D manufacturing drawings are crucial for building a ship. Even various types of 3D models are being utilized for supporting ship manufacturing, which does not reduce the importance of 2D drawings. Recently things are changing in the shipbuilding industry. To reduce the number of 2D drawings or to reduce the quantity of information contained in 2D drawings, some attempts that can substitute for 2D drawings are being made. One of the attempts is to visualize lightweight 3D manufacturing models in a mobile device. In this paper, a method for displaying lightweight 3D models of a ship in an Android based device is introduced. To overcome the problem with parsing JT files in Android system, JT files are parsed in a Windows based server and as-simple-as-possible visualization data are transmitted to an Android based viewer. A comparison result with a commercial system is also given.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.1-8
• /
• 2024

On-device AI technology, which can operate AI models at the edge devices to support real-time processing and privacy enhancement, is attracting attention. As intelligent IoT is applied to various industries, services utilizing the on-device AI technology are increasing significantly. However, general deep learning models require a lot of computational resources for inference and learning. Therefore, various lightweighting methods such as quantization and pruning have been suggested to operate deep learning models in embedded edge devices. Among the lightweighting methods, we analyze how to lightweight and apply deep learning models to edge computing devices, focusing on pruning technology in this paper. In particular, we utilize dynamic and static pruning techniques to evaluate the inference speed, accuracy, and memory usage of a lightweight AI vision model. The content analyzed in this paper can be used for intelligent video control systems or video security systems in autonomous vehicles, where real-time processing are highly required. In addition, it is expected that the content can be used more effectively in various IoT services and industries.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2015

The IoT(Internet of things) technology enable objects around user to be connected with each other for sharing information. To support security is the mandatory requirement in IoT because it is related to the disclosure of private information but also directly related to the human safety. However, it is difficult to apply traditional security mechanism into lightweight devices. This is owing to the fact that many IoT devices are generally resource constrained and powered by battery. PSK(Pre-Shared Key) based approach, which share secret key in advance between communication entities thereafter operate security functions, is suitable for light-weight device. That is because PSK is costly efficient than a session key establishment approach based on public key algorithm. However, how to safely set a PSK of the lightweight device in advance is a difficult issue because input/output interfaces such as keyboard or display are constrained in general lightweight devices. To solve the problem, we propose and develop a secure PSK configuration scheme for resource constrained devices in IoT.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.16 no.12S
• /
• pp.1237-1241
• /
• 2003

In this paper, we report a novel RF-MEMS packaging technology with lightweight, small size, and short electric path length. To achieve this goal, we used the ultra thin silicon substrate as a packaging substrate. The via holes lot vortical feed-through were fabricated on the thin silicon wafer by wet chemical processing. Then, via holes were filled and micro-bumps were fabricated by electroplating. The packaged RF device has a reflection loss under 22 〔㏈〕 and a insertion loss of -0.04∼-0.08 〔㏈〕. These measurements show that we could package the RF device without loss and interference by using the vertical feed-through. Specially, with the ultra thin silicon wafer we can realize of a device package that has low-cost, lightweight and small size. Also, we can extend a 3-D packaging structure by stacking assembled thin packages.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.12
• /
• pp.48-53
• /
• 2005

In this paper, we present our recent progress in the LIPCA (Lightweight Piezo-Composite Actuator) application for actuation of a flapping wing device. The flapping device uses linkage system that can amplify the actuation displacement of LIPCA. The feathering mechanism is also designed and implemented such that the wing can rotate during flapping. The natural flapping-frequency of the device was about 9 Hz, where the maximum flapping angle was achieved. The flapping test under 4 Hz to 15 Hz flapping frequency was performed to investigate the flapping performance by measuring the produced lift and thrust. Maximum lift and thrust were produced when the flapping device was actuated at about the natural flapping-frequency.

• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.1014-1028
• /
• 2012

Recently, N-screen service and secondary device have gotten an attention from public. Also, we can experience N-screen service through various digital devices. N-screen means multimedia technology which can seamlessly consume multimedia content. Secondary device means auxiliary multimedia device which can consume content related to main content through adjunct connection to main device. Not only be electronic manufactures interested in N-screen technology and services but also digital devices applied for N-screen have been released. But it has limitation that user can only consume content to be purchased from content company server not device of user. This paper proposes the system that composes effective and various N-screen multimedia service through MPEG-4 LASeR (Lightweight Application Scene Representation) PMSI (Presentation and Modification of Structured Information) as international standard technology which can provide scene description including many instruction for dynamic update of scene.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1323-1324
• /
• 2011

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.11
• /
• pp.12-17
• /
• 2004

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.