• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.99-106
• /
• 2023

Recently, many studies on crop yield prediction using deep learning technology have been conducted. These algorithms have difficulty constructing a linear map between input data sets and crop prediction results. Furthermore, implementation of these algorithms positively depends on the rate of acquired attributes. Deep reinforcement learning can overcome these limitations. This paper analyzes the performance of DQN, Double DQN and Dueling DQN to improve crop yield prediction. The DQN algorithm retains the overestimation problem. Whereas, Double DQN declines the over-estimations and leads to getting better results. The proposed models achieves these by reducing the falsehood and increasing the prediction exactness.

• International Journal of Computer Science & Network Security
• /
• v.23 no.2
• /
• pp.101-110
• /
• 2023

Vehicular Ad Hoc Network (VANET) is considered to be a subclass of Mobile Ad Hoc Networks (MANET). It has some challenges and issues of privacy which require to be solved before practical implementation of the system i.e., location preservation privacy. Many schemes have been proposed. The most prominent is pseudonym change based location preservation scheme. Safety message can be compromised when it sends via a wireless medium, consequently, an adversary can eavesdrop the communication to analyze and track targeted vehicle. The issue can be counter by use of pseudo identity instead of real and their change while communication proves to be a sufficient solution for such problems. In this context, a large amount of literature on pseudonym change strategies has been proposed to solve such problems in VANET. In this paper, we have given details on strategies proposed last two decades on pseudonym change based location preservation along with issues that they focus to resolve and try to give full understanding to readers.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.91-97
• /
• 2023

Recent research shows that latent directions can be used to image process towards certain attributes. However, controlling the generation process of generative model is very difficult. Though the latent directions are used to image process for certain attributes, many restrictions are required to enhance the attributes received the latent vectors according to certain text and prompts and other attributes largely unaffected. This study presents a generative model having certain restriction to the latent vectors for image generation and manipulation. The suggested method requires only few minutes per manipulation, and the simulation results through Tensorflow Variational Auto-encoder show the effectiveness of the suggested approach with extensive results.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.667-670
• /
• 2008

센서노드는 무선 센서네트워크를 통해서 감지한 정보를 싱크에게 전송한다. 최근 휴대 무선장비의 이용률 증가로 센서네트워크에서 데이터를 수집하는 싱크를 휴대 무선장비로 대체하여 이동성을 보장하는 연구가 활발히 진행된다. 즉, 싱크가 이동성을 가짐으로써 센서노드가 감지한 정보를 전달하는 방법이 중요한 문제로 부각되고 있다. 따라서 모바일 싱크의 위치를 효율적으로 알리고, 다중 소스노드에서 다중 싱크로 정보를 전달하는 것이 필요하다. 특히, 고정된 싱크에서 사용하던 데이터 전송경로는 모바일 싱크 환경에서 더 이상 효율적이지 못하다. 본 논문에서는 소스노드의 위치정보를 제공하기 위한 서버로서 8방향 앵커시스템(Eight-Direction Anchor system: EDA)을 제안한다. EDA는 센서네트워크의 가장자리에 위치한 센서노드의 편중된 에너지 소모를 막고, 전체 센서노드를 균형적으로 사용함으로써 균등한 에너지 소모를 보장한다. 또한, 모바일 싱크가 소스노드로부터 데이터를 연속적으로 받기위해서 위치기반 최단거리 전송(Location-based Shortest Relay: LSR) 프로토콜을 제안한다. LSR은 소스노드에서 싱크로의 우회하는 경로를 막고, 최소 지연경로를 통하여 연속적인 데이터 전송을 보장한다. 실험결과를 통해서 제안 프로토콜은 효율적인 위치서비스의 제공뿐만 아니라, 다중 소스와 다중 모바일 싱크 환경에서 평균 데이터 전송 비용절감 효과를 얻을 수 있음을 보인다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.43-49
• /
• 2024

In early 2020, as the COVID-19 pandemic hit the world, widespread changes occurred throughout society. COVID-19 also brought changes in consumers' consumption behaviors and preferences. This study aims to find out how the current status of the tourism industry and the coffee industry has changed since the end of COVID-19 by conducting big data analysis focusing on the search frequency of Naver, Google, and the following, which are representative social networks in Korea. Designating "Coffee Industry + Tourism Industry" as the representative keyword, January 1, 2020 to December 31, 2020, the time of each COVID-19 outbreak, was set before the COVID-19 type, and January 1, 2023 to December 31, 2023 was set after the end of COVID-19. Based on the analyzed search binder big data analysis within the period, we would like to find out how the current status of the tourism industry and the coffee industry has changed since the end of COVID-19. Finaly, the coffee and tourism industries are on the path of recovery and growth. In particular, the rise in coffee consumption, the recovery of the number of tourists, the emphasis on local tourism, and the strengthening of links with global markets are prominent.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.221-227
• /
• 2024

In autonomous navigation systems, the need for fast and accurate image processing using deep learning and advanced sensor technologies is paramount. These systems rely heavily on the ability to process and interpret visual data swiftly and precisely to ensure safe and efficient navigation. Despite the critical importance of such capabilities, there has been a noticeable lack of research specifically focused on ship image classification for maritime applications. This gap highlights the necessity for more in-depth studies in this domain. In this paper, we aim to address this gap by presenting a comprehensive comparative study of ship image classification using two distinct neural network models: the Feedforward Neural Network (FNN) and the Convolutional Neural Network (CNN). Our study involves the application of both models to the task of classifying ship images, utilizing a dataset specifically prepared for this purpose. Through our analysis, we found that the Convolutional Neural Network demonstrates significantly more effective performance in accurately classifying ship images compared to the Feedforward Neural Network. The findings from this research are significant as they can contribute to the advancement of core source technologies for maritime autonomous navigation systems. By leveraging the superior image classification capabilities of convolutional neural networks, we can enhance the accuracy and reliability of these systems. This improvement is crucial for the development of more efficient and safer autonomous maritime operations, ultimately contributing to the broader field of autonomous transportation technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2281-2297
• /
• 2024

Employing multiple drones as a swarm to complete missions can sharply improve the working efficiency and expand the scope of investigation. Remote UAV swarms utilize satellites as relays to forward investigation information. The increasing amount of data demands higher transmission rate and complex field network coding (CFNC) is deemed as an effective solution for data return. CFNC applied to UAV swarms enhances transmission efficiency by occupying only two time slots, which is less than other network coding schemes. However, conventional CFNC applied to UAVs is combined with constant coding and modulation scheme and results in a waste of spectrum resource when the channel conditions are better. In order to avoid the waste of power resources of the relay satellite and further improve spectral efficiency, a CFNC transmission scheme with MPSK modulation is proposed in this paper. For the proposed scheme, the satellite relay no longer directly forwards information, but transmits information after processing according to the current channel state. The proposed transmission scheme not only maintains throughput advantage of CFNC, but also enhances spectral efficiency, which obtains higher throughput performance. The symbol error probability (SEP) and throughput results corroborated by Monte Carlo simulation show that the proposed transmission scheme improves spectral efficiency in multiples compared to the conventional CFNC schemes. In addition, the proposed transmission scheme enhances the throughput performance for different topology structures while keeping SEP below a certain value.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.148-158
• /
• 2024

We investigate Autism Spectrum Disorder (ASD), which is typified by deficits in social interaction, repetitive behaviors, limited vocabulary, and cognitive delays. Traditional diagnostic methodologies, reliant on expert evaluations, frequently result in deferred detection and intervention, particularly in South Korea, where there is a dearth of qualified professionals and limited public awareness. In this study, we employ advanced deep learning algorithms to enhance early ASD screening through automated video analysis. Utilizing architectures such as Convolutional Long Short-Term Memory (ConvLSTM), Long-term Recurrent Convolutional Network (LRCN), and Convolutional Neural Networks with Gated Recurrent Units (CNN+GRU), we analyze video data from platforms like YouTube and TikTok to identify stereotypic behaviors (arm flapping, head banging, spinning). Our results indicate that the LRCN model exhibited superior performance with 79.61% accuracy on the augmented platform video dataset and 79.37% on the original SSBD dataset. The ConvLSTM and CNN+GRU models also achieved higher accuracy than the original SSBD dataset. Through this research, we underscore AI's potential in early ASD detection by automating the identification of stereotypic behaviors, thereby enabling timely intervention. We also emphasize the significance of utilizing expanded datasets from social media platform videos in augmenting model accuracy and robustness, thus paving the way for more accessible diagnostic methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.861-866
• /
• 2024

The operation mechanism of the superconducting coupled DC circuit breaker system and the simulation analysis of the transient state in DC power networks showed that, when only a conventional DC circuit breaker was applied, the fault current increased and the interruption operation was not fully achieved. In contrast, when coupled with superconductors, the fault current was limited, and the interruption operation was completed quickly. The superconducting coupled DC circuit breaker system proposed in this paper is stable and has the potential to respond to increases in the capacity of power systems. Additionally, it has been confirmed that this system can reduce the burden on circuit breakers, thereby enhancing their lifespan and stability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.18-25
• /
• 2020

With the development of water internet technology, data communication between objects is expanding. Research related to data communication technology between vehicles that incorporates related technologies into vehicles has been actively conducted. For data communication between mobile terminals, data stability, reliability, and real-time performance must be guaranteed. The 5 GHz Wi-Fi band, which is advantageous in bandwidth, communications speed, and wireless saturation of the wireless network, was selected as the data communications network between vehicles. This study analyzes how to design and implement a 5 GHz Wi-Fi network in a vehicle network. Considering the characteristics of the mobile communication terminal device, a continuous variable communications structure is proposed to enable high-speed data switching. We simplify the access point access procedure to reduce the latency between wireless terminals. By limiting the Transmission Control Protocol Internet Protocol (TCP/IP)-based Dynamic Host Configuration Protocol (DHCP) server function and implementing it in a broadcast transmission protocol method, communication delay between terminal devices is improved. Compared to the general commercial Wi-Fi communication method, the connection operation and response speed have been improved by five seconds or more. Utilizing this method can be applied to various types of event data communication between vehicles. It can also be extended to wireless data-based intelligent road networks and systems for autonomous driving.