• ETRI Journal
• /
• v.45 no.5
• /
• pp.758-767
• /
• 2023

In this study, we introduce a loosely coupled relative position estimation method that utilizes a decentralized ultrawideband (UWB), Global Navigation Support System and inertial navigation system for flight controllers (FCs). Key obstacles to multidrone collaboration include relative position errors and the absence of communication devices. To address this, we provide an extended Kalman filter-based algorithm and module that correct distance errors by fusing UWB data acquired through random communications. Via simulations, we confirm the feasibility of the algorithm and verify its distance error correction performance according to the amount of communications. Real-world tests confirm the algorithm's effectiveness on FCs and the potential for multidrone collaboration in real environments. This method can be used to correct relative multidrone positions during collaborative transportation and simultaneous localization and mapping applications.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.236-241
• /
• 2024

Due to the recent emphasis on carbon neutrality and environmental regulations, the global electric vehicle (EV) market is experiencing rapid growth. This surge has raised concerns about the recycling and disposal methods for EV batteries. Unlike traditional internal combustion engine vehicles, EVs require unique and safe methods for the recovery and disposal of their batteries. In this process, predicting the lifespan of the battery is essential. Impedance and State of Charge (SOC) analysis are commonly used methods for this purpose. However, predicting the lifespan of batteries with complex chemical characteristics through electrical measurements presents significant challenges. To enhance the accuracy and precision of existing measurement methods, this paper proposes using a Long Short-Term Memory (LSTM) model, a type of deep learning-based recurrent neural network, to diagnose battery performance. The goal is to achieve safe classification through this model. The designed structure was evaluated, yielding results with a Mean Absolute Error (MAE) of 0.8451, a Root Mean Square Error (RMSE) of 1.3448, and an accuracy of 0.984, demonstrating excellent performance.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.973-979
• /
• 2024

In this research, we present the implementation of a mixed-input neural network for daylight prediction in the architectural design process. This approach harnesses the advantages of both image and numerical inputs to construct a robust neural network model. The hybrid model consists of two branches, each handling in-depth information about the building. Consequently, this model can effectively accommodate a wide range of building layouts, incorporating additional information for enhanced predictions. The building data was created utilizing PlanFinder in Rhino Grasshopper, while simulation data were generated using Honeybee and Ladybug. Weather data were collected from three distinct localities in Vietnam: Ha Noi, Da Nang, and Ho Chi Minh City. The neural network demonstrates outstanding performance, achieving an R-squared (R2) value of 0.95 and the overall percentage difference in the testing dataset ranges from 0 to 20.7%.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.421-428
• /
• 2006

In this paper, the way of remote installation and back-up of 3-tier structure is introduced for efficient utilizing the cluster system resources distributed at several places. Recently, cluster system is constructed as the system of over hundreds nodes under complex network system mixed with public networks and private networks. Therefore, the as installation method suitable for the large scale cluster system and the remote recovery of failure nodes are important. However the previous researches which are based on 2-tier architecture may not provide the efficient cluster installation and image back-up method when the network of cluster system is composed of several private networks and public networks. In this paper, RISE (Remote Installation Service and Environment) based on the 3-tier architecture is proposed to solve this problem. In our approach, the managing node's role is divided into the global master node (GRISE) and the local master node (LRISE) to provide the efficient initial system deployment and remote failure recovery of distributed cluster system under the various network systems. Also, LRISE's availability is ensured under the complex network environments by adopting the auto-synchronization mechanism between GRISE and LRISE. In this work, a 64-node cluster system with gigabit network system is utilized for the experiment. From the experimental result, the system image with 1.86GB data can be obtained in 5 minutes and 53 seconds and the image-based installation of 64-node system can be carried out in 17 minutes and 53 seconds.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.1
• /
• pp.32-38
• /
• 2012

Each sensor node can know its location in several ways, if the node process the information based on its geographical position in sensor networks. In the localization scheme using GPS, there could be nodes that don't know their locations because the scheme requires line of sight to radio wave. Moreover, this scheme is high costly and consumes a lot of power. The localization scheme without GPS uses a sophisticated mathematical algorithm estimating location of sensor nodes that may be inaccurate. AHLoS(Ad Hoc Localization System) is a hybrid scheme using both GPS and location estimation algorithm. In AHLoS, the GPS node, which can receive its location from GPS, broadcasts its location to adjacent normal nodes which are not GPS devices. Normal nodes can estimate their location by using iterative triangulation algorithms if they receive at least three beacons which contain the position informations of neighbor nodes. But, there are some cases that a normal node receives less than two beacons by geographical conditions, network density, movements of nodes in sensor networks. We propose an indirect localization scheme for low-density sensor nodes which are difficult to receive directly at least three beacons from GPS nodes in wireless network.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.29-37
• /
• 1999

In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.447-454
• /
• 2016

The research on multipath routing has been studied to solve the problem of frequent path breakages due to node and link failures and to enhance data delivery reliability in wireless sensor networks. In the multipath routing, mobile sinks such as soldiers in battle fields and rescuers in disaster areas bring about new challenge for handling their mobility. The sink mobility requests new multipath construction from sources to mobile sinks according to their movement path. Since mobile sinks have continuous mobility, the existing multipath can be exploited to efficiently reconstruct to new positions of mobile sinks. However, the previous protocols do not address this issue. Thus, we proposed an efficient multipath reconstruction protocol called LGMR for mobile sinks in wireless sensor networks. The LGMR address three multipath reconstruction methods based on movement types of mobile sinks: a single hop movement-based local multipath reconstruction, a multiple hop movement-based local multipath reconstruction, and a multiple hop movement-based global multipath reconstruction. Simulation results showed that the LGMR has better performance than the previous protocol in terms of energy consumption and data delivery delay.

• Journal of the Economic Geographical Society of Korea
• /
• v.27 no.3
• /
• pp.174-191
• /
• 2024

This study analyzed the spatiotemporal evolution of Korean multinational corporations' (MNCs') foreign direct investment (FDI) networks from 1978 to 2023, focusing on Samsung Electronics and LG Electronics. Using data on the consolidated overseas subsidiaries of these two companies, a two-mode network was constructed to examine the status of host countries through the betweenness centrality index and to identify types of countries with similar value chain arrangements by investigating their linkage structures. The main findings are as follows. First, during the early phase of Korean electronics MNCs' overseas expansion in the 1980s, they primarily established sales bases in developed consumer markets. However, over time, they gradually expanded into other business areas, including manufacturing, producer services, and R&D, increasing complexity in their FDI networks as cross-border mergers and acquisitions (M&As) became more frequent. Second, the United States has remained central to these MNCs' FDI networks since the 1980s, but more recently, China has emerged as a significant hub, challenging the U.S. in global value chains. Third, emerging Asian economies, including India, Vietnam, and Indonesia, have strengthened their positions due to the diversification of MNCs' investment objectives from manufacturing bases to a broader range of business areas. Finally, since the 2010s, the convergence of the electronics industry with the automotive electronics sector and new industries has led to a diversification of the value chain arrangements of Korean electronics MNCs.

• Journal of the Korea Society for Simulation
• /
• v.16 no.4
• /
• pp.57-65
• /
• 2007

In many sensor network applications, sensor nodes are deployed in open environments, and hence are vulnerable to physical attacks, potentially compromising the node's cryptographic keys. False sensing report can be injected through compromised nodes, which can lead to not only false alarms but also the depletion of limited energy resource in battery powered networks. Fan Ye et al. proposed that statistical en-route filtering scheme(SEF) can do verify the false report during the forwarding process. In this scheme, the choice of a partition value represents a trade off between resilience and energy where the partition value is the total number of partitions which global key pool is divided. If every partition are compromised by an adversary, SEF disables the filtering capability. Also, when an adversary has compromised a very small portion of keys in every partition, the remaining uncompromised keys which take a large portion of the total cannot be used to filter false reports. We propose a fuzzy-based adaptive partitioning method in which a global key pool is adaptively divided into multiple partitions by a fuzzy rule-based system. The fuzzy logic determines a partition value by considering the number of compromised partitions, the energy and density of all nodes. The fuzzy based partition value can conserve energy, while it provides sufficient resilience.