• Transactions on Electrical and Electronic Materials
• /
• v.9 no.2
• /
• pp.62-66
• /
• 2008

We report on the growth mechanism of vertically aligned carbon nanotubes (VACNTs) using ultra thin Ni catalysts and direct current plasma enhanced chemical vapor deposition (PECVD) system. The CNTs were grown with -600 V bias to substrate electrode and catalyst thickness variation of 0.07 nm to 3 nm. The CNT density was reduced with catalyst thickness reduction and increased growth time. Cone like CNTs were grown with ultra thin Ni thickness, and it results from an etch of carbon network by reactive etchant species and continuous carbon precipitation on CNT walls. Vertically aligned sparse CNTs can be grown with ultra thin Ni catalyst.

• ETRI Journal
• /
• v.33 no.6
• /
• pp.924-934
• /
• 2011

Sensor networks play an important role in making the dream of ubiquitous computing a reality. With a variety of applications, sensor networks have the potential to influence everyone's life in the near future. However, there are a number of issues in deployment and exploitation of these networks that must be dealt with for sensor network applications to realize such potential. Localization of the sensor nodes, which is the subject of this paper, is one of the basic problems that must be solved for sensor networks to be effectively used. This paper proposes a probabilistic support vector machine (SVM)-based method to gain a fairly accurate localization of sensor nodes. As opposed to many existing methods, our method assumes almost no extra equipment on the sensor nodes. Our experiments demonstrate that the probabilistic SVM method (PSVM) provides a significant improvement over existing localization methods, particularly in sparse networks and rough environments. In addition, a post processing step for PSVM, called attractive/repulsive potential field localization, is proposed, which provides even more improvement on the accuracy of the sensor node locations.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.4
• /
• pp.297-305
• /
• 2021

Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learning-based monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense ground-truth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.1
• /
• pp.1-7
• /
• 2021

In this paper, we presented the experimental basis for the theoretical background and robustness of the Convolutional Neural Network for object recognition based on artificial intelligence. An experimental result was performed to visualize the weighting filters and feature maps for each layer to determine what characteristics CNN is automatically generating. experimental results were presented on the trend of learning error and identification error rate by checking the relevance of the weight filter and feature map for learning error and identification error. The weighting filter and characteristic map are presented as experimental results. The automatically generated characteristic quantities presented the results of error rates for moving and rotating robustness to geometric changes.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1350-1352
• /
• 2022

본 논문에서는 희소깊이영상과 컬러영상을 이용해 조밀한 깊이영상을 추정하는 깊이 완성(depth completion)을 수행하기위해 최근접 이웃 커널을 추정하는 방식의 네트워크를 제안한다. 회귀방식의 딥러닝 네트워크는 일반적으로 값을 직접 예측하는 것보다 기본 값에 더해질 잔차를 추정하는 방식이 더욱 효율적이다. 본 논문에서는 최근접 이웃 커널을 입력영상에 적용하여 추정하고자 하는 픽셀의 인근 픽셀에서 값을 가져와 기본 값으로 사용하고, 해당 값의 잔차를 회귀방식으로 추정하는 네트워크를 설계했다. 이러한 방식으로 여러 SOTA 알고리즘 대비 좋은 성능을 나타냈고, 특히 이와 유사한 방식인 Plane-residual net 보다 높은 성능을 보여준다.

• The Journal of the Korea Contents Association
• /
• v.13 no.8
• /
• pp.371-385
• /
• 2013

Library and information service (LIS) of academic libraries plays an important role in the education and research activities of universities. Such importance of LIS facilitated much research that defines the quality factors constituting LIS and identifies the importance of them. The previous literature, however, has some limitations. The limitations arise from the interrelationship among the quality factors and the perception gap between users and providers on LIS quality factors. Despite the understanding of the interrelationship and the perception gap, LIS studies to deal with both dimesions synthetically are sparse. Therefore, this paper defines the interrelationship among LIS quality factors as a network model, then identifies the perception gap on LIS quality factors by exploiting the analytic network process. As an early stage study, this paper contributes to helping the quality improvement of acedemic LIS by considering the interrelationship among LIS quality factors and the perception gap on the LIS quality factors between LIS users and providers.

• Journal of Biomedical Engineering Research
• /
• v.38 no.5
• /
• pp.237-241
• /
• 2017

Early detection of the pulmonary nodule is important for diagnosis and treatment of lung cancer. Recently, CT has been used as a screening tool for lung nodule detection. And, it has been reported that computer aided detection(CAD) systems can improve the accuracy of the radiologist in detection nodules on CT scan. The previous study has been proposed a method using Convolutional Neural Network(CNN) in Lung CAD system. But the proposed model has a limitation in accuracy due to its sparse layer structure. Therefore, we propose a Deep Convolutional Neural Network to overcome this limitation. The model proposed in this work is consist of 14 layers including 8 convolutional layers and 4 fully connected layers. The CNN model is trained and tested with 61,404 regions-of-interest (ROIs) patches of lung image including 39,760 nodules and 21,644 non-nodules extracted from the Lung Image Database Consortium(LIDC) dataset. We could obtain the classification accuracy of 91.79% with the CNN model presented in this work. To prevent overfitting, we trained the model with Augmented Dataset and regularization term in the cost function. With L1, L2 regularization at Training process, we obtained 92.39%, 92.52% of accuracy respectively. And we obtained 93.52% with data augmentation. In conclusion, we could obtain the accuracy of 93.75% with L2 Regularization and Data Augmentation.

• ETRI Journal
• /
• v.28 no.3
• /
• pp.329-336
• /
• 2006

This paper investigates the problem of protecting multicast sessions in mesh wavelength-division multiplexing (WDM) networks against single link failures, for example, a fiber cut in optical networks. First, we study the two characteristics of multicast sessions in mesh WDM networks with sparse light splitter configuration. Traditionally, a multicast tree does not contain any circles, and the first characteristic is that a multicast tree has better performance if it contains some circles. Note that a multicast tree has several branches. If a path is added between the leave nodes on different branches, the segment between them on the multicast tree is protected. Based the two characteristics, the survivable multicast sessions routing problem is formulated into an Integer Linear Programming (ILP). Then, a heuristic algorithm, named the adaptive shared segment protection (ASSP) algorithm, is proposed for multicast sessions. The ASSP algorithm need not previously identify the segments for a multicast tree. The segments are determined during the algorithm process. Comparisons are made between the ASSP and two other reported schemes, link disjoint trees (LDT) and shared disjoint paths (SDP), in terms of blocking probability and resource cost on CERNET and USNET topologies. Simulations show that the ASSP algorithm has better performance than other existing schemes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2338-2356
• /
• 2019

Vehicular ad-hoc network (VANET) is the name of technology, which uses 'mobile internet' to facilitate communication between vehicles. The aim is to ensure road safety and achieve secure communication. Therefore, the reliability of this type of networks is a serious concern. The reliability of VANET is dependent upon proper communication between vehicles within a given amount of time. Therefore a new formula is introduced, the terms of the new formula correspond 1 by 1 to a class special ST route (SRORT). The new formula terms are much lesser than the Inclusion-Exclusion principle. An algorithm for the Source-to-Terminal reliability was presented, the algorithm produced Source-to-Terminal reliability or computed a Source-to-Terminal reliability expression by calculating a class of special networks of the given network. Since the architecture of this class of networks which need to be computed was comparatively trivial, the performance of the new algorithm was superior to the Inclusion-Exclusion principle. Also, we introduce a mobility metric called universal speed factor (USF) which is the extension of the existing speed factor, that suppose same speed of all vehicles at every time. The USF describes an exact relation between the relative speed of consecutive vehicles and the headway distance. The connectivity of vehicles in different mobile situations is analyzed using USF i.e., slow mobility connectivity, static connectivity, and high mobility connectivity. It is observed that $p_c$ probability of connectivity is directly proportional to the mean speed ${\mu}_{\nu}$ till specified threshold ${\mu}_{\tau}$, and decreases after ${\mu}_{\tau}$. Finally, the congested network is connected strongly as compared to the sparse network as shown in the simulation results.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.113-120
• /
• 2024

The population sparseness index(PSI) is being utilized to describe the functioning of internal layers in artificial neural networks from the perspective of neurons, shedding light on the black-box nature of the network's internal operations. There is research indicating a positive correlation between the PSI and performance in each layer of convolutional neural network models for image classification. In this study, we observed the internal operations of a convolutional neural network when adversarial examples were applied. The results of the experiments revealed a similar pattern of positive correlation for adversarial examples, which were modified to maintain 5% accuracy compared to applying benign data. Thus, while there may be differences in each adversarial attack, the observed PSI for adversarial examples demonstrated consistent positive correlations with benign data across layers.