• 대한임베디드공학회논문지
• /
• 제16권1호
• /
• pp.9-15
• /
• 2021

Recently, it is increasingly necessary to run high-end neural network applications with huge computation overhead on top of resource-constrained embedded systems, such as wearable devices. While the huge computational overhead can be alleviated by distributed neural networks running on multiple separate devices, existing distributed neural network techniques suffer from a large traffic between the devices; thus are very vulnerable to communication failures. These drawbacks make the distributed neural network techniques inapplicable to wearable devices, which are connected with each other through unstable and low data rate communication medium like human body communication. Therefore, in this paper, we propose a distributed neural network partitioning technique that is resilient to communication failures. Furthermore, we show that the proposed technique also improves the inference accuracy even in case of no communication failure, thanks to the improved network partitioning. We verify through comparative experiments with a real-life neural network application that the proposed technique outperforms the existing state-of-the-art distributed neural network technique in terms of accuracy and resiliency to communication failures.

• 한국전자파학회논문지
• /
• 제24권2호
• /
• pp.144-151
• /
• 2013

본 논문에서는 무선 인체 통신 중 off-body 채널에서 안테나 편파의 변화에 대한 영향을 알아보기 위한 실험을 수행하였다. 실험은 두 수신 안테나의 편파 조합에 따라 총 4가지로 나누었으며, Line-of-Sight(LOS)와 Non-LOS(NLOS)에 따른 영향도 조사하였다. 그리고 인체의 움직임으로 인하여 생기는 안테나 편파의 변화가 신호에 어떠한 영향을 미치는지 알아보기 위해, 인체를 정지한 상태와 움직이는 상태로 나누어 신호 세기를 측정하여 비교하였다. 본 논문의 결과를 통해 수신 안테나의 편파 및 두 수신 안테나의 편파 조합에 따른 성능을 확인하였다.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.18-25
• /
• 2014

WBAN(Wireless body area network)에서 신체에 삽입된 센서는 신체의 생물학적인 특성에 의해 일반 센서보다 프레임의 오류가 발생 할 확률이 높아진다. 본 논문에서는 신체에 삽입된 센서의 라이프타임을 향상시키기 위해 삽입 된 센서의 재전송을 외부 센서에서 대신 전송해주는 방법으로 삽입된 센서의 전송을 줄이는 방법을 제시한다. 제시된 LI(Lifetime Increment) 프로토콜은 기존의 CSMA/CA 전송방식에서 데이터 프레임에 외부 센서의 ID를 추가하고, 내부 센서가 전송한 프레임이 재전송이 요구 될 시에는 추가 되어있던 ID의 외부 센서에서 재전송을 책임지는 방법이다. 제안하는 프로토콜의 성능 비교를 위해 WBAN CSMA/CA 전송 방식과 비교한 결과 에너지 소모량이 적어져 라이프 타임이 향상되는 것을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.186-203
• /
• 2020

Image-based Virtual Try-On Systems are among the most potential solution for virtual fitting which tries on a target clothes into a model person image and thus have attracted considerable research efforts. In many cases, current solutions for those fails in achieving naturally looking virtual fitted image where a target clothes is transferred into the body area of a model person of any shape and pose while keeping clothes context like texture, text, logo without distortion and artifacts. In this paper, we propose a new improved image-based virtual try-on network system based on keypoints, which we name as KP-VTON. The proposed KP-VTON first detects keypoints in the target clothes and reliably predicts keypoints in the clothes of a model person image by utilizing a dense human pose estimation. Then, through TPS transformation calculated by utilizing the keypoints as control points, the warped target clothes image, which is matched into the body area for wearing the target clothes, is obtained. Finally, a new try-on module adopting Attention U-Net is applied to handle more detailed synthesis of virtual fitted image. Extensive experiments on a well-known dataset show that the proposed KP-VTON performs better the state-of-the-art virtual try-on systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권12호
• /
• pp.4643-4660
• /
• 2014

Integrity authentication of biometric data in Wireless Body Area Network (WBAN) is a critical issue because the sensitive data transmitted over broadcast wireless channels could be attacked easily. However, traditional cryptograph-based integrity authentication schemes are not suitable for WBAN as they consume much computational resource on the sensor nodes with limited memory, computational capability and power. To address this problem, a novel lightweight integrity authentication scheme based on reversible watermark is proposed for WBAN and implemented on a TinyOS-based WBAN test bed in this paper. In the proposed scheme, the data is divided into groups with a fixed size to improve grouping efficiency; the histogram shifting technique is adopted to avoid possible underflow or overflow; local maps are generated to restore the shifted data; and the watermarks are generated and embedded in a chaining way for integrity authentication. Our analytic and experimental results demonstrate that the integrity of biometric data can be reliably authenticated with low cost, and the data can be entirely recovered for healthcare applications by using our proposed scheme.

• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.3043-3050
• /
• 2022

In Korea, all nuclear power plants (NPPs) participate in annual performance tests including in vivo measurements using the FastScan, a stand type whole body counter (WBC), manufactured by Canberra. In 2018, all Korean NPPs satisfied the testing criterion, the root mean square error (RMSE) ≤ 0.25, for the whole body configuration, but three NPPs which participated in an additional lung configuration test in the fission and activation product category did not meet the criterion. Due to the low resolution of the FastScan NaI(Tl) detectors, the conventional peak analysis (PA) method of the FastScan did not show sufficient performance to meet the criterion in the presence of interfering radioisotopes (RIs), ¹³⁴Cs and ¹³⁷Cs. In this study, we developed an artificial neural network (ANN) to improve the performance of the FastScan in the lung configuration. All of the RMSE values derived by the ANN satisfied the criterion, even though the photopeaks of ¹³⁴Cs and ¹³⁷Cs interfered with those of the analytes or the analyte photopeaks were located in a low-energy region below 300 keV. Since the ANN performed better than the PA method, it would be expected to be a promising approach to improve the accuracy and precision of in vivo FastScan measurement for the lung configuration.

• 전기학회논문지
• /
• 제60권6호
• /
• pp.1190-1195
• /
• 2011

This paper presents a waist pressure evaluation method in human sensibility using a electroencephalogram(EEG) signal. For this objective, a size-controllable waist-belt is used. First of all, EEG signals for relaxed state are acquired. Then, the waist-belt of the subject is tightened about 90% of normal state. After a few minutes, the belt of the subject is released. Some necessary preprocessing is performed on the acquired signals, Linear Prediction (LP) coefficients are utilized as the feature parameters extracting the characteristics of EEG signal, and a multi-layer neural network is used for indicating the state of body pressure. The results of the method showed 77.2% of coincidence with body pressure states. This may be compromising results for ssubject-independent sensibility evaluation using EEG signal.

• 한국자동차공학회논문집
• /
• 제10권5호
• /
• pp.114-120
• /
• 2002

In a distributed real-time control system, it is essential to confirm the timing behavior of all tasks because these tasks of each real-time controller have to finish their processes within the specified time intervals called a deadline. In order to satisfy this objective, the timing analysis of a distributed real-time system such as shcedulability test must be performed during the system design phase. In this study, a simple application of CAN fur a vehicle body network system is formulated to apply to a holistic scheduling analysis, and the worst-case execution time (WCET) and the worst-case end-to-end response time (WCRT) are evaluated in the point of holistic system view.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.129.2-129
• /
• 2001

Visual effects are important cues for providing occupant s with virtual reality in a vehicle simulator which imitates real driving. The viewpoint of an occupant is sensitively dependent upon the occupant´s posture, therefore, the total body motion must be considered in a graphic simulator. A real time simulation is required for the dynamic analysis of complex human body motion. This study attempts to apply a neural network to the motion analysis in various driving situations. A full car of medium-sized vehicles was selected and modeled, and then analyzed using ADAMS in such driving conditions as bump-pass and acceleration. A multibody system analysis software, MADYMO, was used in the motion analysis of an adult male dummy in the seated position. Position data of the head were collected as inputs to the viewpoint movement. Based on these data, a back- propagation neural network was ...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.174.2-174
• /
• 2001

Increasing demand for safety features, driving comfort and operational convenience in automobiles requires an intensive use of electronic components such as sensors, actuators and Electronic Control Unit(ECU)'s. These growing number of electronics has given rise to problems concerning the increasing number, size and weight of the wiring harnesses. In order to resolve these problems, multiplexed wiring systems such as Controller Area Network(CAN) serial communication protocol are applied in vehicle. This paper introduces the development of Body Control Module(BCM)s using multiplexed wiring systems. The BCM's were developed and implemented using CAN, the most popular choice of in-vehicle communication protocols.