• The KIPS Transactions:PartD
• /
• v.14D no.6
• /
• pp.649-656
• /
• 2007

Today, controller area network(CAN) is a field bus that is nowadays widespread in distributed embedded systems due to its electrical robustness, low price, and deterministic access delay. However, its use safety-critical applications has been controversial due to dependability limitation, such as those arising from its bus topology. Thus it is important to analyze the performance of the network in terms of load of data bus, maximum time delay, communication contention, and others during the design phase of the controller area network. In this paper, a simulation algorithm is introduced to evaluate the communication performance of the vehicle network and apply software base fault injection techniques. This can not only reduce any erratic implementation of the vehicle network but it also improves the reliability of the system.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.705-709
• /
• 1995

The objective of this study is to design a multi-layer neural network which controls the position of excavator's attachment. In this paper, a dynamic controller has been developed based on an error back-propagation(BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it was used as a commanded feedforward input generator. A PD feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the excavator as well as the PD feedback error. By using the BP network as a feedforward controller, no a priori knowledge on system dynamics is need. Computer simulation results demonstrate such powerful characteristics of the proposed controller as adaptation to changing environment, robustness to disturbancen and performance improvement with the on-line learning in the position control of excavator attachment.

• The KIPS Transactions:PartC
• /
• v.15C no.5
• /
• pp.329-342
• /
• 2008

The Sensor Networks have limitations in utilizing energies, developing energy-efficient routing protocol and secure routing protocol are important issues in Sensor Network. In the field of data management, Tributaries and Deltas(TD) which incorporates tree topology and multi-path topology effectively have been suggested to provide efficiency and robustness in data aggregation. And our research rendered hierarchical property to TD and proposed Clustering-based Tributaries-Deltas. Through this new structure, we integrated efficiency and robustness of TD structure and advantages of hierarchical Sensor Network. Clustering-based Tributaries-Deltas was proven to perform better than TD in two situations through our research. The first is when a Base Station (BS) notices received information as wrong and requests the network's sensing data retransmission and aggregation. And the second is when the BS is mobile agent with mobility. In addition, we proposed key establishment mechanism proper for the newly proposed structure which resulted in new Sensor Network structure with improved security and energy efficiency as well. We demonstrated that the new mechanism is more energy-efficient than previous one by analyzing consumed amount of energy, and realized the mechanism on TmoteSKY sensor board using TinyOS 2.0. Through this we proved that the new mechanism could be actually utilized in network design.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12B
• /
• pp.1359-1370
• /
• 2009

In wireless sensor networks, data dissemination is based on data-centric routing that well matches the publish/subscribe communication paradigm. The publish/subscribe paradigm requires decoupling properties: space, time, and synchronization decoupling. For large-scale applications, the three decoupling properties provide scalability and robust communication. However, existing data dissemination schemes for wireless sensor networks do not achieve full decoupling. Therefore, we propose a novel data dissemination scheme that fully accomplishes the three decoupling, called ARBIETER. ARBITER constructs an independent network structure as a logical software bus. Information interworking between publishers and subscribers is indirectly and asynchronously performed via the network structure. ARBITER also manages storage and mapping of queries and data on the structure because of supporting different time connection of publishers and subscribers. Our simulation proves ARBITER show better performance in terms of scalability, network robustness, data responsibility, mobility support, and energy efficiency.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.149-158
• /
• 2005

This paper proposed a blind watermarking method for video contents which satisfies both the invisibility and the robustness to attacks to prohibit counterfeiting, modification, illegal usage and illegal re-production of video contents. This watermarking algorithm targets MPEG compression system and was designed to control the amount of watermarking to be inserted according to the adaptive quantization scale code to follow the adaptive quantization of the compression system. The inserting positions of the watermark were chosen by considering the frequency property of an image and horizontal, vertical and diagonal property of a $8{\times}8$ image block. Also the amount of watermarking for each watermark bit was decided by considering the quantization step. This algorithm was implemented by C++ and experimented for invisibility and robustness with MPEG-2 system. The experiment results showed that the method satisfied enough the invisibility of the inserted watermark and robustness against attacks. For the general attacks, the error rate of the extracted watermark was less than $10\%$, which is enough in robustness against the attacks. Therefore, this algorithm is expected to be used effectively as a part in many MPEG systems for real-time watermarking, especially in the sensitive applications to the network environments.

• Journal of Power Electronics
• /
• v.6 no.4
• /
• pp.340-346
• /
• 2006

A high efficiency drive technique for synchronous reluctance motors (SynRM) using a neural network (NN) is presented in this paper. High efficiency drive condition depends on the mathematical model of SynRM. A NN is employed as an adaptive model of SynRM. The proposed high efficiency drive technique does not require an accurate mathematical model of SynRM. Moreover, the proposed method shows robustness against machine parameter variations because the training algorithm of the NN is executed on-line. The usefulness of the proposed method is confirmed through experimentation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1033-1039
• /
• 2007

In this paper, we design a terminal sliding mode controller based on self-recurrent wavelet neural network (SRWNN) for the second-order nonlinear systems with model uncertainties. The terminal sliding mode control (TSMC) method can drive the tracking errors to zero within finite time in comparison with the classical sliding mode control (CSMC) method. In addition, the TSMC method has advantages such as the improved performance, robustness, reliability and precision. We employ the SRWNN to approximate model uncertainties. The weights of SRWNN are trained by adaptation laws induced from Lyapunov stability theorem. Finally, we carry out simulations for Duffing system and the wing rock phenomena to illustrate the effectiveness of the proposed control scheme.

• Journal of information and communication convergence engineering
• /
• v.12 no.4
• /
• pp.237-245
• /
• 2014

In this study, software-based countermeasures against a side-channel cryptanalysis of the Rabbit stream cipher were developed using Moteiv's Tmote Sky, a popular wireless sensor mote based on the Berkeley TelosB, as the target platform. The countermeasures build upon previous work by improving mask generation, masking and hiding other components of the algorithm, and introducing a key refreshment scheme. Our contribution brings improvements to previous countermeasures making the implementation resistant to higher-order attacks. Four functional metrics, namely resiliency, robustness, resistance, and scalability, were used for the assessment. Finally, performance costs were measured using memory usage and execution time. In this work, it was demonstrated that although attacks can be feasibly carried out on unprotected systems, the proposed countermeasures can also be feasibly developed and deployed on resource-constrained devices, such as wireless sensors.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.58-60
• /
• 2019

Double JPEG compression detection is one of the most important ways of exposing the integrity of the JPEG image in image forensics. Several methods have been proposed for discriminating against the double JPEG image. In this paper, we propose a new method for restoring the JPEG compressed image and making the detector confused by introducing a Generative Adversarial Network (GAN). First, a generator network is designed for restoring the JPEG compressed image and analyzed the quality. Then, the restored image is tested with the double compression detector for evaluating the robustness of the proposed GAN model. The detection accuracy reduces from 98% to 58%.