首页 > 最新文献

Journal of Korea Multimedia Society最新文献

英文 中文
Examining the Impacts of Task Interval on Subjective Workload and Operational Behavior in a Multi-Conversational Agent Control System 多会话智能体控制系统中任务间隔对主观工作量和操作行为的影响研究
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.982
Kyuhyeong Kim, Sungho Moon, Myungho Lee
This paper explores the effect of task interval within a multi-conversational agent control system on the perceived workload and operational behaviors of administrators. An experimental study was conducted employing three distinctive task intervals, namely 10s, 30s, and 60s, with a sample of 39 participants. The results indicated a direct correlation between shorter task intervals and increased subjective workload of administrators, which correspondingly resulted in expedited response times. On the contrary, longer intervals were associated with enhanced response quality and more meticulous behavior. Eye-tracking data analysis further provided insights into user engagement; shorter intervals heightened focus on chat content, while longer intervals led to an increase in distractions. The findings underscore the significance of task intervals as a pivotal mechanism for optimization of multi-conversational agent control systems and enhancement of conversation quality. For future work, we plan to investigate strategies aimed at mitigating administrators
本文探讨了多会话代理控制系统中任务间隔对管理员感知工作量和操作行为的影响。实验研究采用三种不同的任务间隔,即10分钟、30分钟和60分钟,对39名参与者进行了实验研究。结果表明,较短的任务间隔和增加的管理员主观工作量之间存在直接关联,这相应地导致响应时间加快。相反,间隔时间越长,反应质量越高,行为越细致。眼动追踪数据分析进一步提供了对用户粘性的洞察;较短的时间间隔会让人更专注于聊天内容,而较长的时间间隔则会让人分心。研究结果强调了任务间隔作为优化多会话代理控制系统和提高会话质量的关键机制的重要性。对于未来的工作,我们计划研究旨在减轻管理员负担的策略
{"title":"Examining the Impacts of Task Interval on Subjective Workload and Operational Behavior in a Multi-Conversational Agent Control System","authors":"Kyuhyeong Kim, Sungho Moon, Myungho Lee","doi":"10.9717/kmms.2023.26.8.982","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.982","url":null,"abstract":"This paper explores the effect of task interval within a multi-conversational agent control system on the perceived workload and operational behaviors of administrators. An experimental study was conducted employing three distinctive task intervals, namely 10s, 30s, and 60s, with a sample of 39 participants. The results indicated a direct correlation between shorter task intervals and increased subjective workload of administrators, which correspondingly resulted in expedited response times. On the contrary, longer intervals were associated with enhanced response quality and more meticulous behavior. Eye-tracking data analysis further provided insights into user engagement; shorter intervals heightened focus on chat content, while longer intervals led to an increase in distractions. The findings underscore the significance of task intervals as a pivotal mechanism for optimization of multi-conversational agent control systems and enhancement of conversation quality. For future work, we plan to investigate strategies aimed at mitigating administrators","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Phishing Website Detection Model for User Decision Making Based on XAI 基于XAI的用户决策网络钓鱼网站检测模型
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.1013
Daeyeob Kim
Phishing websites based on social engineering are significant cyber threats in the web environment. Recently, a number of studies have been implemented to detect phishing websites using AI (Artificial Intelligence), and they have demonstrated excellent detection performance. However, most of the proposed AI models are black-box. By the nature of black-box, it is difficult to explain how AI models determine if a website is phishing or not. Moreover, false negative is inevitable in the detection system using AI models. Therefore, it is unreliable to detect phishing websites based on the prediction result of an AI model. Because of these limitations, users need to interpret the output of an AI model and make the final decision. In this paper, we propose an interpretable phishing website detection model based on the XAI (eXplainable Artificial Intelligence) techniques so that users can make a reasonable decision with the interpretation of the outputs from the AI model.
基于社会工程的网络钓鱼网站是网络环境中重要的网络威胁。近年来,利用人工智能技术对网络钓鱼网站进行了大量的检测研究,并取得了良好的检测效果。然而,大多数提出的人工智能模型都是黑盒的。由于黑盒的性质,很难解释人工智能模型如何确定一个网站是否存在网络钓鱼。此外,在使用人工智能模型的检测系统中,假阴性是不可避免的。因此,基于AI模型的预测结果来检测钓鱼网站是不可靠的。由于这些限制,用户需要解释AI模型的输出并做出最终决定。在本文中,我们提出了一种基于XAI(可解释人工智能)技术的可解释网络钓鱼网站检测模型,使用户可以根据AI模型输出的解释做出合理的决策。
{"title":"Phishing Website Detection Model for User Decision Making Based on XAI","authors":"Daeyeob Kim","doi":"10.9717/kmms.2023.26.8.1013","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.1013","url":null,"abstract":"Phishing websites based on social engineering are significant cyber threats in the web environment. Recently, a number of studies have been implemented to detect phishing websites using AI (Artificial Intelligence), and they have demonstrated excellent detection performance. However, most of the proposed AI models are black-box. By the nature of black-box, it is difficult to explain how AI models determine if a website is phishing or not. Moreover, false negative is inevitable in the detection system using AI models. Therefore, it is unreliable to detect phishing websites based on the prediction result of an AI model. Because of these limitations, users need to interpret the output of an AI model and make the final decision. In this paper, we propose an interpretable phishing website detection model based on the XAI (eXplainable Artificial Intelligence) techniques so that users can make a reasonable decision with the interpretation of the outputs from the AI model.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhanced CCTV Enclosure Record Management Model through DAG Blockchain 基于DAG区块链的闭路电视监控录像管理模型
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.932
Kwan-Woo Yu, Byung-Mun Lee
Managing enclosures is necessary in order to safely transfer video stream of public CCTV. Smart enclosure monitoring system provides efficient management by providing operating status and environment of enclosures and blockchain based enclosure record management system provides data integrity to this end. However, the blockchain with linear structure has a limit on data rate for storing depending on the block generation cycle and size. If the amount of data over this limit, a bottleneck occurs. The bottleneck reduces availability of the system. Therefore, this paper proposes a directed acyclic graph blockchain based CCTV enclosure record management model to reduce the bottleneck. This model stores the record in blockchain of DAG structure and maintains its integrity. The blockchain increases throughput and reduces the bottleneck of the linear blockchain by storing multiple blocks at the same time. To evaluate the performance of this model, an experiment simulating the confirmation time of linear and DAG blockchain was conducted. As a result the linear blockchain showed a maximum time of 859 seconds and the DAG blockchain showed a maximum time of 12.9 seconds in an environment composed of 1500 nodes, confirming that the bottleneck was reduced.
为了保证公共闭路电视视频流的安全传输,对围场进行管理是必要的。智能机框监控系统通过提供机框的运行状态和环境实现高效管理,基于区块链的机框记录管理系统实现数据完整性。然而,线性结构的区块链根据区块生成周期和大小,对存储的数据速率有限制。如果数据量超过这个限制,就会出现瓶颈。瓶颈降低了系统的可用性。为此,本文提出了一种基于有向无环图区块链的闭路电视箱体记录管理模型,以减少瓶颈。该模型将记录存储在DAG结构的区块链中,并保持其完整性。区块链通过同时存储多个区块,提高了吞吐量,减少了线性区块链的瓶颈。为了评估该模型的性能,进行了模拟线性区块链和DAG区块链确认时间的实验。结果显示,在1500个节点组成的环境中,线性区块链的最长时间为859秒,DAG区块链的最长时间为12.9秒,这证实了瓶颈的减少。
{"title":"Enhanced CCTV Enclosure Record Management Model through DAG Blockchain","authors":"Kwan-Woo Yu, Byung-Mun Lee","doi":"10.9717/kmms.2023.26.8.932","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.932","url":null,"abstract":"Managing enclosures is necessary in order to safely transfer video stream of public CCTV. Smart enclosure monitoring system provides efficient management by providing operating status and environment of enclosures and blockchain based enclosure record management system provides data integrity to this end. However, the blockchain with linear structure has a limit on data rate for storing depending on the block generation cycle and size. If the amount of data over this limit, a bottleneck occurs. The bottleneck reduces availability of the system. Therefore, this paper proposes a directed acyclic graph blockchain based CCTV enclosure record management model to reduce the bottleneck. This model stores the record in blockchain of DAG structure and maintains its integrity. The blockchain increases throughput and reduces the bottleneck of the linear blockchain by storing multiple blocks at the same time. To evaluate the performance of this model, an experiment simulating the confirmation time of linear and DAG blockchain was conducted. As a result the linear blockchain showed a maximum time of 859 seconds and the DAG blockchain showed a maximum time of 12.9 seconds in an environment composed of 1500 nodes, confirming that the bottleneck was reduced.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
3D Scene Graph Generation Using Prior Knowledge from Large Language Model (LLM) 基于LLM先验知识的三维场景图生成
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.859
Ho-Jun Baek, Incheol Kim
In this paper, we propose a novel 3D scene graph generation model, L3DSG, which can make use of rich prior knowledge obtained from large language model (LLM) by prompt engineering. The proposed model is built upon our previous 3D scene graph generation model, C3DSG, that adopts Point Transformer as 3D geometric feature extractor and uses the NE-GAT graph neural network as context reasoner. The new proposed model addresses the inability of C3DSG to utilize prior knowledge on indoor physical environments. It focuses on issues of how to obtain prior knowledge from LLM and how to make use of it for predicting objects and their relations effectively. The proposed model is extended from C3DSG by adding several elaborate modules to prompt, encode, and fuse prior knowledge from LLM. Through various experiments using the benchmark dataset 3DSSG, we show the superiority of the proposed model.
本文提出了一种新的三维场景图生成模型L3DSG,该模型可以利用大语言模型(large language model, LLM)中丰富的先验知识。该模型是在我们之前的三维场景图生成模型C3DSG的基础上建立的,C3DSG采用Point Transformer作为三维几何特征提取器,并使用NE-GAT图神经网络作为上下文推理器。新提出的模型解决了C3DSG无法利用室内物理环境的先验知识的问题。重点研究了如何从LLM中获取先验知识,以及如何利用先验知识有效地预测对象及其关系。该模型是在C3DSG的基础上扩展而来的,通过添加一些精细的模块来提示、编码和融合来自LLM的先验知识。通过使用基准数据集3DSSG的各种实验,我们证明了所提出模型的优越性。
{"title":"3D Scene Graph Generation Using Prior Knowledge from Large Language Model (LLM)","authors":"Ho-Jun Baek, Incheol Kim","doi":"10.9717/kmms.2023.26.8.859","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.859","url":null,"abstract":"In this paper, we propose a novel 3D scene graph generation model, L3DSG, which can make use of rich prior knowledge obtained from large language model (LLM) by prompt engineering. The proposed model is built upon our previous 3D scene graph generation model, C3DSG, that adopts Point Transformer as 3D geometric feature extractor and uses the NE-GAT graph neural network as context reasoner. The new proposed model addresses the inability of C3DSG to utilize prior knowledge on indoor physical environments. It focuses on issues of how to obtain prior knowledge from LLM and how to make use of it for predicting objects and their relations effectively. The proposed model is extended from C3DSG by adding several elaborate modules to prompt, encode, and fuse prior knowledge from LLM. Through various experiments using the benchmark dataset 3DSSG, we show the superiority of the proposed model.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Study on the Influence of Audience Satisfaction on Multinational Adapted Films -Adapted Movie 〈Heosamgwan〉 Focusing on 〈Chronicle of a Blood Merchant〉 - 观众满意度对跨国改编电影的影响研究——以《血商实录》为中心的改编电影《活三官b>
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.1055
Yuan-Yuan Liu, Yeon-Woo Lee, Chee-Yong Kim
The Korean film 〈Heosamgwan〉 adapted from Yu Hua"s novel 〈Chronicle of a Blood Merchant〉 is well received. Chinese and Korean scholars have made a lot of in-depth research on the adaptation of 〈Heosamgwan〉, from the narrative text to the adaptation strategy, but few of them have focused on the audience. In this study, a survey on satisfaction was conducted after watching the movie 〈Heosamgwan〉 for Chinese international students in Korea, and a SEM model was built based on the satisfaction theory. The relationship between storytelling, audiovisual effects, and emotional experience was analyzed through the model.
▷根据余华的小说《血商实录》改编的韩国电影《活活馆》受到了好评。中韩学者对《活三观》的改编进行了大量深入的研究,从叙事文本到改编策略,但很少关注观众。本研究对在韩中国留学生观影后的满意度进行调查,并基于满意度理论建立SEM模型。通过模型分析了叙事、视听效果和情感体验三者之间的关系。
{"title":"A Study on the Influence of Audience Satisfaction on Multinational Adapted Films -Adapted Movie 〈Heosamgwan〉 Focusing on 〈Chronicle of a Blood Merchant〉 -","authors":"Yuan-Yuan Liu, Yeon-Woo Lee, Chee-Yong Kim","doi":"10.9717/kmms.2023.26.8.1055","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.1055","url":null,"abstract":"The Korean film 〈Heosamgwan〉 adapted from Yu Hua\"s novel 〈Chronicle of a Blood Merchant〉 is well received. Chinese and Korean scholars have made a lot of in-depth research on the adaptation of 〈Heosamgwan〉, from the narrative text to the adaptation strategy, but few of them have focused on the audience. In this study, a survey on satisfaction was conducted after watching the movie 〈Heosamgwan〉 for Chinese international students in Korea, and a SEM model was built based on the satisfaction theory. The relationship between storytelling, audiovisual effects, and emotional experience was analyzed through the model.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Study on the Main Activities and Core Elements of Design Thinking 设计思维的主要活动与核心要素研究
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.1086
An-Young Ryou, Won-Jun Son
This study is a qualitative study to analyze the key elements of design thinking activity and actual application. In order to select survey participants, a deliberate sampling method was used, and 11 design experts with more than 6 years of design experience were interviewed to analyze the specific thinking process. Open coding, axial coding, and selective coding were conducted based on the grounded theory methodology using the recorded data as the original data. As a result of open coding, 93 concepts, 7 categories and 17 properties were derived. Axial coding was performed to present a paradigm model. Through the selective coding, intuitive thinking and analytical thinking were adopted as core categories of designer thinking method. In the important parts of the design work process, analysis of the subject, ideation and decisions for project direction and visualization of concepts, and finding a balance between creativity and applicability, concrete utilization methods were identified.
本研究是一项定性研究,旨在分析设计思维活动的关键要素及其实际应用。为了选择调查对象,采用故意抽样的方法,采访了11位具有6年以上设计经验的设计专家,分析了具体的思维过程。以记录的数据为原始数据,根据扎根理论方法进行开放编码、轴向编码和选择性编码。通过开放编码,得到了93个概念、7个类别和17个属性。轴向编码是一种范式模型。通过选择性编码,将直觉思维和分析思维作为设计师思维方法的核心范畴。在设计工作过程的重要环节,对主题的分析,对项目方向的构思和决策,对概念的可视化,在创造性和适用性之间找到平衡,确定了具体的利用方法。
{"title":"A Study on the Main Activities and Core Elements of Design Thinking","authors":"An-Young Ryou, Won-Jun Son","doi":"10.9717/kmms.2023.26.8.1086","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.1086","url":null,"abstract":"This study is a qualitative study to analyze the key elements of design thinking activity and actual application. In order to select survey participants, a deliberate sampling method was used, and 11 design experts with more than 6 years of design experience were interviewed to analyze the specific thinking process. Open coding, axial coding, and selective coding were conducted based on the grounded theory methodology using the recorded data as the original data. As a result of open coding, 93 concepts, 7 categories and 17 properties were derived. Axial coding was performed to present a paradigm model. Through the selective coding, intuitive thinking and analytical thinking were adopted as core categories of designer thinking method. In the important parts of the design work process, analysis of the subject, ideation and decisions for project direction and visualization of concepts, and finding a balance between creativity and applicability, concrete utilization methods were identified.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Learning based Wall Structure Object Extraction for 3D Building Modeling Automation 基于深度学习的三维建筑建模自动化墙体结构对象提取
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.965
Hyeongjun Yoo, Gyeong-ro Rhee, Je-Ho Ryu, Seungjoo Lee, Jong-Hun Lee
To create a digital twin, 3D modeling data that imitated represents the real-world is essential. However, people manually create modeling data by looking at photos or 3D scanning data. To address 3D modeling by hand, it is necessary to automatically extract information required for 3D modeling from 3D scanning data. In this paper, we propose a method based on deep learning-based 3D semantic segmentation and stochastic-based extraction of wall structure object from point clouds. We validate the performance of the proposed method by comparing the extracted wall structure object information from the initial point cloud with the actual 3D modeling.
为了创建数字双胞胎,模拟代表现实世界的3D建模数据是必不可少的。然而,人们通过查看照片或3D扫描数据手动创建建模数据。为了解决手工三维建模问题,需要从三维扫描数据中自动提取三维建模所需的信息。本文提出了一种基于深度学习的三维语义分割和基于随机的点云中墙体结构对象的提取方法。通过将从初始点云中提取的墙体结构目标信息与实际三维建模结果进行对比,验证了所提方法的性能。
{"title":"Deep Learning based Wall Structure Object Extraction for 3D Building Modeling Automation","authors":"Hyeongjun Yoo, Gyeong-ro Rhee, Je-Ho Ryu, Seungjoo Lee, Jong-Hun Lee","doi":"10.9717/kmms.2023.26.8.965","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.965","url":null,"abstract":"To create a digital twin, 3D modeling data that imitated represents the real-world is essential. However, people manually create modeling data by looking at photos or 3D scanning data. To address 3D modeling by hand, it is necessary to automatically extract information required for 3D modeling from 3D scanning data. In this paper, we propose a method based on deep learning-based 3D semantic segmentation and stochastic-based extraction of wall structure object from point clouds. We validate the performance of the proposed method by comparing the extracted wall structure object information from the initial point cloud with the actual 3D modeling.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ensemble-based Solar Power Prediction System Using Missing Value Interpolation Algorithm 基于缺失值插值算法的集成太阳能发电预测系统
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.944
Su-Bin Park, Jin-Seong Kim, Se-Hoon Jung, Chun-Bo Sim
Environmental problems such as global warming due to excessive use of fossil fuels are becoming serious. In order to solve this problem, the supply of new and renewable energy is being activated, and the new and renewable energy market is also expanding. In particular, the share of solar and wind energy among new and renewable energies is rapidly increasing. However, uncertainty and volatility are inherent in renewable energy due to the characteristics of power generation that depend on natural conditions. This leads to a problem in which errors occur in the prediction of the amount of reserve energy required to secure the amount and cost of renewable energy generation. In this paper, we propose an ensemble-based solar power generation prediction system applying missing value interpolation algorithm. It predicts the amount of solar power generation by using weather forecast data from the Korea Meteorological Administration, and provides visualization and scheduling functions for the amount of power generation and predicted amount through a web page.
过度使用化石燃料导致的全球变暖等环境问题日益严重。为了解决这一问题,新能源和可再生能源的供应正在被激活,新能源和可再生能源市场也在不断扩大。特别是,太阳能和风能在新能源和可再生能源中所占的份额正在迅速增加。然而,由于发电依赖于自然条件的特点,可再生能源具有固有的不确定性和波动性。这就导致了一个问题,即在预测确保可再生能源发电的数量和成本所需的储备能量时,会出现错误。本文提出了一种应用缺失值插值算法的基于集成的太阳能发电预测系统。利用气象厅的天气预报资料预测太阳能发电量,并通过网页提供发电量和预测值的可视化和调度功能。
{"title":"Ensemble-based Solar Power Prediction System Using Missing Value Interpolation Algorithm","authors":"Su-Bin Park, Jin-Seong Kim, Se-Hoon Jung, Chun-Bo Sim","doi":"10.9717/kmms.2023.26.8.944","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.944","url":null,"abstract":"Environmental problems such as global warming due to excessive use of fossil fuels are becoming serious. In order to solve this problem, the supply of new and renewable energy is being activated, and the new and renewable energy market is also expanding. In particular, the share of solar and wind energy among new and renewable energies is rapidly increasing. However, uncertainty and volatility are inherent in renewable energy due to the characteristics of power generation that depend on natural conditions. This leads to a problem in which errors occur in the prediction of the amount of reserve energy required to secure the amount and cost of renewable energy generation. In this paper, we propose an ensemble-based solar power generation prediction system applying missing value interpolation algorithm. It predicts the amount of solar power generation by using weather forecast data from the Korea Meteorological Administration, and provides visualization and scheduling functions for the amount of power generation and predicted amount through a web page.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Early Fire Detection System by Synthetic Dataset Automatic Generation Model Based on Digital Twin 基于数字孪生的合成数据集自动生成模型的早期火灾探测系统
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.887
HyeonCheol Kim, Suk-Hwan Lee, Soo-Yol Ok
The nature of fire is amorphous and its characteristics vary based on the space, environment, and materials involved. Particularly, early fire detection is a crucial task in preventing large-scale accidents. However, there is a significant lack of learnable early fire datasets for machine learning approaches. This study presents an early fire detection system tailored to specific spaces, achieved through a digital twin-based automatic fire learning data generation model. The proposed method starts by automatically generating realistic particle simulations to create synthetic fire data in RGB-D images. These images are matched to the view angle of monitoring cameras to replicate the digital twin environment closely resembling the actual space. In essence, our approach produces synthetic fire data that captures diverse fire scenarios unique to each specific location. Subsequently, these datasets are employed for transfer learning, enhancing the capabilities of state-of-the-art detection models. The improved models are then deployed on AIoT devices within the real space. This spatially optimized synthetic fire data generation process enhances the accuracy and reduces false detection rates in comparison to existing fire detection models that lack adaptability to specific spaces.
火的性质是无定形的,它的特性根据所涉及的空间、环境和材料而变化。特别是火灾的早期探测是防止大型事故发生的关键。然而,机器学习方法缺乏可学习的早期数据集。本研究提出了一种针对特定空间量身定制的早期火灾探测系统,通过基于数字孪生的自动火灾学习数据生成模型实现。该方法首先自动生成真实的粒子模拟,在RGB-D图像中生成合成火灾数据。这些图像与监控摄像机的视角相匹配,以复制与实际空间非常相似的数字孪生环境。从本质上讲,我们的方法生成了合成的火灾数据,这些数据捕获了每个特定地点独特的各种火灾场景。随后,这些数据集被用于迁移学习,增强了最先进的检测模型的能力。然后将改进的模型部署在真实空间内的AIoT设备上。与缺乏对特定空间适应性的现有火灾探测模型相比,这种空间优化的合成火灾数据生成过程提高了准确性,降低了误检率。
{"title":"Early Fire Detection System by Synthetic Dataset Automatic Generation Model Based on Digital Twin","authors":"HyeonCheol Kim, Suk-Hwan Lee, Soo-Yol Ok","doi":"10.9717/kmms.2023.26.8.887","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.887","url":null,"abstract":"The nature of fire is amorphous and its characteristics vary based on the space, environment, and materials involved. Particularly, early fire detection is a crucial task in preventing large-scale accidents. However, there is a significant lack of learnable early fire datasets for machine learning approaches. This study presents an early fire detection system tailored to specific spaces, achieved through a digital twin-based automatic fire learning data generation model. The proposed method starts by automatically generating realistic particle simulations to create synthetic fire data in RGB-D images. These images are matched to the view angle of monitoring cameras to replicate the digital twin environment closely resembling the actual space. In essence, our approach produces synthetic fire data that captures diverse fire scenarios unique to each specific location. Subsequently, these datasets are employed for transfer learning, enhancing the capabilities of state-of-the-art detection models. The improved models are then deployed on AIoT devices within the real space. This spatially optimized synthetic fire data generation process enhances the accuracy and reduces false detection rates in comparison to existing fire detection models that lack adaptability to specific spaces.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficient Low-Rank Matrix Completion Updating Algorithm for Recommender System 推荐系统的高效低秩矩阵补全更新算法
Pub Date : 2023-08-31 DOI: 10.9717/kmms.2023.26.8.974
Geunseop Lee
Recommender systems aim to provide personalized item recommendations to users based on users ratings. However, not all ratings are provided by users, so the rating matrix, which summarizes the user-item interaction data, has many missing values. To fill out these missing values, matrix completion problem is considered. One of the most popular approaches to matrix completion problem is based on low-rank approximation of the rating matrix. To do this, singular value decomposition is required in every iteration, however it is prohibitively expensive when large-scale rating matrices are used. Additionally, recommender systems are frequently updated when a new user or item is added, or existing information is updated. In this paper, we propose a new matrix completion algorithm by recycling the existing information to speed up the computation when a small part of the rating matrix is updated instead of computing the matrix completion from scratch. Experimental results demonstrate that our algorithm is very attractive when the rating matrix is updated frequently by showing that our algorithm has significantly faster execution speed while producing very similar or even better accuracy than the other algorithms.
推荐系统的目标是根据用户的评分向用户提供个性化的商品推荐。然而,并不是所有的评分都是由用户提供的,因此总结了用户-物品交互数据的评分矩阵有许多缺失值。为了填补这些缺失值,考虑了矩阵补全问题。求解矩阵补全问题最常用的方法之一是基于评级矩阵的低秩逼近。要做到这一点,在每次迭代中都需要奇异值分解,然而,当使用大规模评级矩阵时,它的成本非常高。此外,当添加新用户或新项目或更新现有信息时,推荐系统会频繁更新。在本文中,我们提出了一种新的矩阵补全算法,通过回收已有的信息来加快计算速度,当评级矩阵的一小部分更新时,而不是从头计算矩阵补全。实验结果表明,当评级矩阵频繁更新时,我们的算法非常有吸引力,表明我们的算法在产生非常相似甚至更好的精度的同时具有显着更快的执行速度。
{"title":"Efficient Low-Rank Matrix Completion Updating Algorithm for Recommender System","authors":"Geunseop Lee","doi":"10.9717/kmms.2023.26.8.974","DOIUrl":"https://doi.org/10.9717/kmms.2023.26.8.974","url":null,"abstract":"Recommender systems aim to provide personalized item recommendations to users based on users ratings. However, not all ratings are provided by users, so the rating matrix, which summarizes the user-item interaction data, has many missing values. To fill out these missing values, matrix completion problem is considered. One of the most popular approaches to matrix completion problem is based on low-rank approximation of the rating matrix. To do this, singular value decomposition is required in every iteration, however it is prohibitively expensive when large-scale rating matrices are used. Additionally, recommender systems are frequently updated when a new user or item is added, or existing information is updated. In this paper, we propose a new matrix completion algorithm by recycling the existing information to speed up the computation when a small part of the rating matrix is updated instead of computing the matrix completion from scratch. Experimental results demonstrate that our algorithm is very attractive when the rating matrix is updated frequently by showing that our algorithm has significantly faster execution speed while producing very similar or even better accuracy than the other algorithms.","PeriodicalId":16316,"journal":{"name":"Journal of Korea Multimedia Society","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135991519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Journal of Korea Multimedia Society
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1