ETRI Journal最新文献_第2页

Distance mean-square loss function for ordinal text classification of emergency service response codes in disaster management 灾害管理中应急服务响应码有序文本分类的距离均方损失函数

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-27 DOI: 10.4218/etrij.2024-0478

Eungyeol Lee, Sungwon Byon, Eui-Suk Jung, Eunjung Kwon, Hyunho Park

{"title":"Distance mean-square loss function for ordinal text classification of emergency service response codes in disaster management","authors":"Eungyeol Lee, Sungwon Byon, Eui-Suk Jung, Eunjung Kwon, Hyunho Park","doi":"10.4218/etrij.2024-0478","DOIUrl":"https://doi.org/10.4218/etrij.2024-0478","url":null,"abstract":"The National Fire Agency (NFA) and National Police Agency (NPA) have defined risk levels based on the severity of disasters. Risk-level data possess the characteristics of ordinal data such as NPA's Emergency Service Response Code (ESRC) data, which are classified based on their magnitudes (from C0 to C4). In this study, we propose a distance mean-square (DiMS) loss function to improve the accuracy of ordinal data classification. The DiMS loss function calculates loss values based on the distances between the predicted and true labels: value distances (commonly used in regression analysis for magnitude data) and probability distances (typically used in classification analysis). Therefore, the DiMS loss function contributes to improved accuracy when classifying ordinal data, such as ESRC. In addition, using the DiMS loss function, we achieved state-of-the-art performance in classifying the SST-5 data, which is a representative ordinal dataset. The DiMS loss function for ordinal classification enabled accurate risk recognition. Thus, accurate risk recognition using the DiMS loss function enhances disaster response.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 3","pages":"472-479"},"PeriodicalIF":1.3,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0478","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Secure task offloading scheme for traffic video surveillance via reinforcement learning 基于强化学习的交通视频监控安全任务分流方案

IF 1.6 4区计算机科学

ETRI Journal Pub Date : 2025-06-25 DOI: 10.4218/etrij.2024-0363

Jianhua Liu, Kexin Wang, Xiaoni Shi, Xiaoguang Tu, Jiajia Liu

{"title":"Secure task offloading scheme for traffic video surveillance via reinforcement learning","authors":"Jianhua Liu, Kexin Wang, Xiaoni Shi, Xiaoguang Tu, Jiajia Liu","doi":"10.4218/etrij.2024-0363","DOIUrl":"https://doi.org/10.4218/etrij.2024-0363","url":null,"abstract":"Edge computing deploys computing resources to the network edge to diminish task processing delays and power consumption. However, in traffic video surveillance systems, vehicular movement can lead to service interruptions. Moreover, the low credibility of the edge systems affects the success rate of edge offloading. To address these issues, we propose a secure task offloading scheme for traffic video surveillance. This scheme comprehensively evaluates trust values by integrating direct and indirect trust values, selecting nodes based on predefined trust thresholds, and achieving secure offloading and migration with short delays and energy consumption. To model the service migration problem, we adopted a Markov decision process-based approach and employed a \u0000<math>\u0000 <mi>Q</mi></math>-learning algorithm to determine the optimal solution, thereby establishing an effective migration path. Simulation results demonstrate that the proposed scheme yields higher comprehensive trust values and improved reliability. Furthermore, while ensuring seamless task migration, the migration success rate exceeded 90%, with the energy consumption reduced by more than 9.8%.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 5","pages":"893-908"},"PeriodicalIF":1.6,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0363","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Marker-based adaptive virtual military training system for enhanced immersion and realism 基于标记的增强沉浸感和真实感的自适应虚拟军事训练系统

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-19 DOI: 10.4218/etrij.2024-0456

Hoseok Tong, Seongjean Kim, Hyunse Yoon, Jungsu Kim, Soyeon Lee, Sangjoon Park, Blagovest Vladimirov, Sanghoon Lee

{"title":"Marker-based adaptive virtual military training system for enhanced immersion and realism","authors":"Hoseok Tong, Seongjean Kim, Hyunse Yoon, Jungsu Kim, Soyeon Lee, Sangjoon Park, Blagovest Vladimirov, Sanghoon Lee","doi":"10.4218/etrij.2024-0456","DOIUrl":"https://doi.org/10.4218/etrij.2024-0456","url":null,"abstract":"The complexity of modern battlefields demands advanced military training systems that prepare forces for realistic scenarios. Even though traditional training methods are effective, they are costly and time consuming and are associated with safety risks. Virtual training systems offer a safer and more cost-effective alternative; however, current solutions often compromise realism because of the need for multiple sensors and wearable devices that can diminish immersion. To address these limitations, we propose a marker-based, adaptive, virtual military training system (MAVMTS) that enhances realism by using a minimal set of fiducial markers and multiview cameras to estimate the trainee's posture and weapon orientation without cumbersome wearables. The system integrates action recognition to generate responsive virtual adversaries, thereby creating dynamic and immersive training environments. MAVMTS reduces considerably the equipment burden and enhances the realism of virtual military training, thereby offering a more effective solution for preparing personnel for modern warfare.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 3","pages":"393-409"},"PeriodicalIF":1.3,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0456","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Next-generation wireless communication technologies for improved disaster response and management 改进灾害响应和管理的下一代无线通信技术

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0546

Hwankyu Song, Jong-Moon Chung

引用次数: 0

Semantic potential field for mobile robot navigation using grid maps 基于网格地图的移动机器人导航语义势场

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0454

Truong Son Nguyen, Huy Nhat Cao, Minh Trien Pham

{"title":"Semantic potential field for mobile robot navigation using grid maps","authors":"Truong Son Nguyen, Huy Nhat Cao, Minh Trien Pham","doi":"10.4218/etrij.2024-0454","DOIUrl":"https://doi.org/10.4218/etrij.2024-0454","url":null,"abstract":"Traditional navigation methods for mobile robots face significant challenges in dynamic environments, including local minima avoidance and efficient path planning. This paper introduces the semantic potential field (SPF) method, which synergizes geometric and semantic data using a semantic grid map to improve navigation efficiency and adaptability. The key features of the SPF method include (i) a semantic grid map combining light detection and ranging (LiDAR) and camera data to distinguish static and dynamic obstacles and (ii) a dynamically modulated potential field incorporating semantic weights for adaptive path planning and obstacle avoidance. The experimental results demonstrate that the SPF method significantly reduces the travel distance and computation time compared with those of traditional methods, ensuring robust navigation in diverse environments. By addressing the limitations in real-time navigation systems, the SPF represents a significant advancement in mobile robot path planning, with promising applications in disaster response, autonomous logistics, and defense.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 3","pages":"422-432"},"PeriodicalIF":1.3,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0454","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

5G defense network using commercial gNodeB with zero trust architecture 5G防御网络采用商用gndeb零信任架构

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0476

Woocheol Kim, Sunji Oh, Chang-Gyu Lim, Kiwon Kim, Jongkuk Lee, Hea-Sook Park

{"title":"5G defense network using commercial gNodeB with zero trust architecture","authors":"Woocheol Kim, Sunji Oh, Chang-Gyu Lim, Kiwon Kim, Jongkuk Lee, Hea-Sook Park","doi":"10.4218/etrij.2024-0476","DOIUrl":"https://doi.org/10.4218/etrij.2024-0476","url":null,"abstract":"As 5G technology expands globally, the demand for secure and reliable military communication is growing significantly. This study examines 5G military network architectures that integrate commercial 5G elements, ranging from isolated to shared configurations, to balance security, cost, and coverage. We propose a network leveraging commercial next-generation Node B (gNodeB or gNB) with a military Public Land Mobile Network (PLMN) ID, ensuring extensive coverage, robust security, and cost efficiency. To enhance secure access, a zero trust (ZT) architecture using a software-defined perimeter (SDP) is employed. The connection process for user equipment accessing private networks is detailed through 5G authentication and ZT access management. Simulated 5G analysis compares scenarios before and after applying SDP under denial-of-service (DoS) and IP scanning attacks. Results demonstrate that SDP mitigates IP scanning threats, improves throughput during DoS attacks, and maintains performance. Validation on a real-world 5G testbed confirms feasibility, robust security, and stability. These findings underscore the potential of ZT-based 5G military networks for modern defense communication.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 3","pages":"445-458"},"PeriodicalIF":1.3,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0476","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maximization of near-infrared modulation by optimizing the transparent conducting–electrode resistance 通过优化透明导电电极电阻实现近红外调制的最大化

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0474

Jisu Han, Sang Kyu Lee, Juhyun Park, Jugyeong Lee, Chil Seong Ah, Tae-Youb Kim

引用次数: 0

Multi-modem-based FHSS-drone takeover with precision spoofing 基于多调制解调器的fhss无人机接管与精确欺骗

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0369

Jae Gu Kang, Byeong Cheol Choi

引用次数: 0

Design of specific situation estimation function using multi-robot system in military operations 军事作战中多机器人系统的具体态势估计函数设计

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2025-06-09 DOI: 10.4218/etrij.2024-0477

Donggyu Choi, Jaeuk Baek, Chang-eun Lee

{"title":"Design of specific situation estimation function using multi-robot system in military operations","authors":"Donggyu Choi, Jaeuk Baek, Chang-eun Lee","doi":"10.4218/etrij.2024-0477","DOIUrl":"https://doi.org/10.4218/etrij.2024-0477","url":null,"abstract":"Modern warfare, involving both conventional combat and terrorism, often occurs in urban environments. As opposed to traditional outdoor operations, urban operations rely on indoor concealment, creating many hazardous situations. Operations inside buildings result in numerous hiding spots and challenges, such as stairs and varying ceiling heights, which can endanger friendly forces. Effectively responding to enemy concealment and anticipating threats in such environments are critical. The development and research of small equipment for situational awareness have increased rapidly in recent years. This study proposes a framework that uses edge devices, which are widely used in current robotics, in clusters to support effective indoor military operations. The framework enables real-time object location estimation and risk zone identification, even in environments in which the resources required for robot movement are limited. The proposed framework provides auxiliary and intuitive information for situational assessment during indoor military operations, such as building clearing.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 3","pages":"459-471"},"PeriodicalIF":1.3,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0477","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transformer network for time series prediction via wavelet packet decomposition 基于小波包分解的变压器网络时间序列预测

IF 1.6 4区计算机科学

ETRI Journal Pub Date : 2025-05-23 DOI: 10.4218/etrij.2024-0013

Zhichao Wu, Aiye Shi, Yan Ping Tao

{"title":"Transformer network for time series prediction via wavelet packet decomposition","authors":"Zhichao Wu, Aiye Shi, Yan Ping Tao","doi":"10.4218/etrij.2024-0013","DOIUrl":"https://doi.org/10.4218/etrij.2024-0013","url":null,"abstract":"Time series predictions are commonly used in the fields of energy, meteorology, and finance, among others. The accurate prediction of time series data is critical for making decisions and planning. In the real world, non-stationary time series data with statistical properties shift over time, making prediction more challenging. Although, conventional time series processing methods—such as multi-scale feature extraction or Transformer-based algorithms—produce superior prediction results, when dealing with data that contain more noise and outliers, the prediction ability of such methods can suffer. To address this problem, we proposed the WPFormer model, which incorporated time-frequency analysis into the Transformer architecture to increase the long-term series prediction accuracy. The model employed wavelet packet decomposition to identify and eliminate noise efficiently, increasing its immunity to interference. We evaluated WPFormer on four publicly available datasets and compared its performance against the Informer, LogTrans, Reformer, LSTMa, LSTNet, and DeepAR models using MSE and MAE metrics. On average, the WPFormer model surpassed the benchmark models by 16%.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 4","pages":"672-684"},"PeriodicalIF":1.6,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0013","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144843650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0