首页 > 最新文献

2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)最新文献

英文 中文
Research on Packet Pilot Multiplexing and Encryption Strategy in 5G Mimo System 5G Mimo系统中分组导频复用与加密策略研究
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048666
Yongliang Jia, Peng Tao, Chao Zhang, Bingyu Zhang, Xinghan Pan
Aiming at the pilot pollution problem in large-scale MIMO system, a grouped pilot multiplexing strategy is proposed, which redistributes the pilot sequence. Users are divided into central user group and edge user group according to the severity of user interference in the cell, and the edge user is assigned a completely orthogonal pilot sequence; To solve the security problem of signal transmission in Massive MIMO systems, an iterative encryption algorithm based on pilot is presented. An iterative encryption module is added to the modulation part before the pilot signal is sent. The simulation results show that the proposed method can effectively suppress pilot pollution, suppress attacker stealing information, and improve system performance and security.
针对大规模MIMO系统中导频污染问题,提出了一种分组导频复用策略,对导频序列进行重新分配。根据小区内用户干扰的严重程度将用户分为中心用户组和边缘用户组,边缘用户分配一个完全正交的导频序列;为了解决大规模MIMO系统中信号传输的安全问题,提出了一种基于导频的迭代加密算法。在发送导频信号之前,在调制部分添加迭代加密模块。仿真结果表明,该方法能有效抑制导频污染,抑制攻击者窃取信息,提高系统性能和安全性。
{"title":"Research on Packet Pilot Multiplexing and Encryption Strategy in 5G Mimo System","authors":"Yongliang Jia, Peng Tao, Chao Zhang, Bingyu Zhang, Xinghan Pan","doi":"10.1109/ICECE56287.2022.10048666","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048666","url":null,"abstract":"Aiming at the pilot pollution problem in large-scale MIMO system, a grouped pilot multiplexing strategy is proposed, which redistributes the pilot sequence. Users are divided into central user group and edge user group according to the severity of user interference in the cell, and the edge user is assigned a completely orthogonal pilot sequence; To solve the security problem of signal transmission in Massive MIMO systems, an iterative encryption algorithm based on pilot is presented. An iterative encryption module is added to the modulation part before the pilot signal is sent. The simulation results show that the proposed method can effectively suppress pilot pollution, suppress attacker stealing information, and improve system performance and security.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114953233","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 High-Linear Rail-to-Rail Class-AB PGA with Transconductance Compensation Based on Common-Mode Detection 基于共模检测的高线性ab类跨导补偿PGA
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048657
Wenbo Yao, Xiaotian Li, Nai-Qi Wu, Tongbei Yang, Hao Wang, Fang Tang
A low total harmonic distortion (THD) programmable gain amplifier (PGA) with dual operational amplifiers (op-amps) for electrocardiogram (ECG) signal acquisition applications is presented. The proposed op-amp comprises the rail-to-rail input stage and class-AB output stage. To solve the transcon-ductance (gm) variation caused by the supply voltage changes in rail-to-rail amplifiers with the traditional DC level-shifting technique, a common-mode-detection-based transconductance linearization scheme is proposed in this paper, associated with a 7-steps resistor-feedback digital gain control from 1 V/V to 12 V/V, which can realize less than 2.7% transconductance variations. The proposed rail-to-rail class-AB PGA is implemented in 0.18-µm CMOS technology with 2.7-V∼5-V power supply voltage. Spice simulation results show that the THD is -110 dB with an input signal of 5 mVpp and the input-referred noise spectrum density is $mu {mathbf{V}}/sqrt {Hz}$ at a 10-Hz frequency point, after adopting an 8-kHz chopping. The total DC current including the bias circuit is 30µA at 5 V.
提出了一种低总谐波失真(THD)可编程增益放大器(PGA),具有双运算放大器(运放),用于心电图(ECG)信号采集。所提出的运放包括轨对轨输入级和ab类输出级。为了解决传统直流移电平技术中轨对轨放大器电源电压变化引起的跨导(gm)变化,本文提出了一种基于共模检测的跨导线性化方案,并结合1 V/V ~ 12 V/V的7步电阻反馈数字增益控制,可实现小于2.7% transconductance variations. The proposed rail-to-rail class-AB PGA is implemented in 0.18-µm CMOS technology with 2.7-V∼5-V power supply voltage. Spice simulation results show that the THD is -110 dB with an input signal of 5 mVpp and the input-referred noise spectrum density is $mu {mathbf{V}}/sqrt {Hz}$ at a 10-Hz frequency point, after adopting an 8-kHz chopping. The total DC current including the bias circuit is 30µA at 5 V.
{"title":"A High-Linear Rail-to-Rail Class-AB PGA with Transconductance Compensation Based on Common-Mode Detection","authors":"Wenbo Yao, Xiaotian Li, Nai-Qi Wu, Tongbei Yang, Hao Wang, Fang Tang","doi":"10.1109/ICECE56287.2022.10048657","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048657","url":null,"abstract":"A low total harmonic distortion (THD) programmable gain amplifier (PGA) with dual operational amplifiers (op-amps) for electrocardiogram (ECG) signal acquisition applications is presented. The proposed op-amp comprises the rail-to-rail input stage and class-AB output stage. To solve the transcon-ductance (gm) variation caused by the supply voltage changes in rail-to-rail amplifiers with the traditional DC level-shifting technique, a common-mode-detection-based transconductance linearization scheme is proposed in this paper, associated with a 7-steps resistor-feedback digital gain control from 1 V/V to 12 V/V, which can realize less than 2.7% transconductance variations. The proposed rail-to-rail class-AB PGA is implemented in 0.18-µm CMOS technology with 2.7-V∼5-V power supply voltage. Spice simulation results show that the THD is -110 dB with an input signal of 5 mVpp and the input-referred noise spectrum density is $mu {mathbf{V}}/sqrt {Hz}$ at a 10-Hz frequency point, after adopting an 8-kHz chopping. The total DC current including the bias circuit is 30µA at 5 V.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116557512","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
Design of Ka-Band Tree-Shaped Fractal Millimeter Wave Antenna ka波段树形分形毫米波天线设计
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048646
Youqing Lu, Jinbing Jia, W. He
With the continuous increase of people’s demand for communication, modern wireless communication systems have higher and higher requirements for antennas. The goal of antenna design is broadband, low profile, and miniaturized antennas. Such antennas are used in personal communication systems, small satellite communication terminals, drones, etc. In this paper, a tree-shaped fractal millimeter wave UWB antenna is designed. The antenna is composed of a microstrip feeder, a tree-shaped fractal, a dielectric substrate and a limited ground. The finite ground is a rectangular structure. The antenna is optimized by electromagnetic simulation software, so that the antenna can obtain good impedance matching. The operating frequency band of the antenna is 28.25-39.90GHz (relative bandwidth is 37.6%), and the antenna gain is 5.09dBi. It can be applied to Ka-band and is suitable for future 5G communication. (Abstract)
随着人们对通信需求的不断提高,现代无线通信系统对天线的要求也越来越高。天线设计的目标是宽带、低轮廓和小型化天线。这种天线用于个人通信系统、小型卫星通信终端、无人机等。本文设计了一种树形分形毫米波超宽带天线。该天线由微带馈线、树形分形、介电衬底和有限地组成。有限地面为矩形结构。通过电磁仿真软件对天线进行优化,使天线获得良好的阻抗匹配。天线的工作频段为28.25 ~ 39.90 ghz(相对带宽为37.6%),天线增益为5.09dBi。可应用于ka波段,适用于未来5G通信。(抽象)
{"title":"Design of Ka-Band Tree-Shaped Fractal Millimeter Wave Antenna","authors":"Youqing Lu, Jinbing Jia, W. He","doi":"10.1109/ICECE56287.2022.10048646","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048646","url":null,"abstract":"With the continuous increase of people’s demand for communication, modern wireless communication systems have higher and higher requirements for antennas. The goal of antenna design is broadband, low profile, and miniaturized antennas. Such antennas are used in personal communication systems, small satellite communication terminals, drones, etc. In this paper, a tree-shaped fractal millimeter wave UWB antenna is designed. The antenna is composed of a microstrip feeder, a tree-shaped fractal, a dielectric substrate and a limited ground. The finite ground is a rectangular structure. The antenna is optimized by electromagnetic simulation software, so that the antenna can obtain good impedance matching. The operating frequency band of the antenna is 28.25-39.90GHz (relative bandwidth is 37.6%), and the antenna gain is 5.09dBi. It can be applied to Ka-band and is suitable for future 5G communication. (Abstract)","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114264573","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
Virtual Network Embedding Reconfiguration Problem of Time-Varying Traffic Problem in EONs EONs时变流量问题的虚拟网络嵌入重构问题
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048624
D. Din
In this paper, the virtual network embedding reconfiguration (VNER) problem on elastic optical networks (EONs) with time-varying traffic was studied. Two reconfiguration methods: Most extra Resource First (MRF) and Less Extra Resource First (LERF) and three link expansion methods Same Path (SP), Different Path (DP) and Redeploy method (Rm) were proposed to solve the VNE reconfiguration. We show the effectiveness of the proposed methods through extensive simulations. The results show that the blocking rate of the MRF_Rm method is 2% to 7% lower than the other reconfiguration algorithms. The LRF scheme is better than the MRF scheme.
研究了时变流量弹性光网络中的虚拟网络嵌入重构问题。提出了两种重构方法:Most extra Resource First (MRF)和Less extra Resource First (LERF),以及三种链路扩展方法Same Path (SP)、Different Path (DP)和redeployment method (Rm)来解决VNE重构问题。我们通过大量的仿真证明了所提出方法的有效性。结果表明,MRF_Rm方法的阻塞率比其他重构算法低2% ~ 7%。LRF方案优于MRF方案。
{"title":"Virtual Network Embedding Reconfiguration Problem of Time-Varying Traffic Problem in EONs","authors":"D. Din","doi":"10.1109/ICECE56287.2022.10048624","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048624","url":null,"abstract":"In this paper, the virtual network embedding reconfiguration (VNER) problem on elastic optical networks (EONs) with time-varying traffic was studied. Two reconfiguration methods: Most extra Resource First (MRF) and Less Extra Resource First (LERF) and three link expansion methods Same Path (SP), Different Path (DP) and Redeploy method (Rm) were proposed to solve the VNE reconfiguration. We show the effectiveness of the proposed methods through extensive simulations. The results show that the blocking rate of the MRF_Rm method is 2% to 7% lower than the other reconfiguration algorithms. The LRF scheme is better than the MRF scheme.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124637053","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: 1
Studies Documenting the Components Associated with Instagram Influence: A Review of the Scientific Literature 记录与Instagram影响相关成分的研究:科学文献综述
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048648
Katherine Valeria Salazar-Vegas, Adriana Margarita Turriate-Guzmán
Currently, social networks worldwide play an important role in the life of every individual, so it is common to see people interacting and creating content with the tools provided by digital platforms. Therefore, in the following article, the studies that document the influence of the social network Instagram are addressed. This study aimed to carry out a systematic review using the PRISMA methodology. To this end, the Science Direct, Scielo, and Scopus databases were reviewed, and the papers were selected using inclusion and exclusion criteria. In this way, more information based on the analyzed articles was obtained, and it was verified which audiovisual tools help to generate influence in the social network Instagram.
目前,世界范围内的社交网络在每个人的生活中都扮演着重要的角色,所以人们使用数字平台提供的工具进行互动和创建内容是很常见的。因此,在接下来的文章中,我们将对社交网络Instagram的影响进行研究。本研究旨在使用PRISMA方法进行系统评价。为此,我们对Science Direct、Scielo和Scopus数据库进行了审查,并根据纳入和排除标准对论文进行了筛选。这样,在分析文章的基础上获得了更多的信息,并验证了哪些视听工具有助于在社交网络Instagram上产生影响力。
{"title":"Studies Documenting the Components Associated with Instagram Influence: A Review of the Scientific Literature","authors":"Katherine Valeria Salazar-Vegas, Adriana Margarita Turriate-Guzmán","doi":"10.1109/ICECE56287.2022.10048648","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048648","url":null,"abstract":"Currently, social networks worldwide play an important role in the life of every individual, so it is common to see people interacting and creating content with the tools provided by digital platforms. Therefore, in the following article, the studies that document the influence of the social network Instagram are addressed. This study aimed to carry out a systematic review using the PRISMA methodology. To this end, the Science Direct, Scielo, and Scopus databases were reviewed, and the papers were selected using inclusion and exclusion criteria. In this way, more information based on the analyzed articles was obtained, and it was verified which audiovisual tools help to generate influence in the social network Instagram.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123657357","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
Computation Rate Optimization for RIS-Assisted Multi-server MEC System ris辅助多服务器MEC系统运算率优化
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048627
Chen Liu, Wensheng Zhang, Yongwei Wang
Reconfigurable intelligent surface (RIS) is an emerging technology that enables intelligent control of wireless communication environment. In this paper, an RIS-assisted multi-server mobile edge computing (MEC) system is studied. By jointly optimizing the offloading power, offloading time, central processing unit (CPU) frequency, RIS phase shift, and MEC server allocation of each device, the maximum sum computation rate of the system is achieved. A greedy-based algorithm is used to tackle the server allocation problem. The simulation results demonstrate that the computation rate is improved by applying RIS into the MEC system, and it can be further improved by deploying more MEC servers with proper server allocation strategy.
可重构智能表面(RIS)是一种新兴的无线通信环境智能控制技术。本文研究了一种ris辅助的多服务器移动边缘计算系统。通过对各设备的卸载功率、卸载时间、CPU频率、RIS相移、MEC服务器分配等进行联合优化,使系统的总和计算率达到最大。采用一种基于贪婪的算法来解决服务器分配问题。仿真结果表明,将RIS应用到MEC系统中可以提高计算速度,通过合理的服务器分配策略部署更多的MEC服务器可以进一步提高计算速度。
{"title":"Computation Rate Optimization for RIS-Assisted Multi-server MEC System","authors":"Chen Liu, Wensheng Zhang, Yongwei Wang","doi":"10.1109/ICECE56287.2022.10048627","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048627","url":null,"abstract":"Reconfigurable intelligent surface (RIS) is an emerging technology that enables intelligent control of wireless communication environment. In this paper, an RIS-assisted multi-server mobile edge computing (MEC) system is studied. By jointly optimizing the offloading power, offloading time, central processing unit (CPU) frequency, RIS phase shift, and MEC server allocation of each device, the maximum sum computation rate of the system is achieved. A greedy-based algorithm is used to tackle the server allocation problem. The simulation results demonstrate that the computation rate is improved by applying RIS into the MEC system, and it can be further improved by deploying more MEC servers with proper server allocation strategy.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131094641","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 Golden Section Software Synchronization Algorithm Based on Linear Optical Sampling System 基于线性光学采样系统的黄金分割软件同步算法
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048658
Rirong Su, Qinghua Tian, Xiangjun Xin, Xiaoli Yin, Fu Wang, Zhipei Li, Yongjun Wang
In the paper, the linear optical sampling system is studied, and a golden section software synchronization (GSSS) algorithm is proposed to monitor the performance of the signal under test (SUT) and obtain a clear eye diagram. Experiments show that this method produces better results in recovering temporal information. Compared with the chirp-z-transform (CZT) algorithm, the GSSS algorithm reduces the complexity by half, which has a smaller delay and improves the efficiency of real-time monitoring the performance of SUT.
本文对线性光学采样系统进行了研究,提出了一种黄金分割软件同步(GSSS)算法来监测被测信号(SUT)的性能并获得清晰的眼图。实验表明,该方法能较好地恢复时间信息。与chirp-z-transform (CZT)算法相比,GSSS算法的复杂度降低了一半,具有更小的延迟,提高了实时监控SUT性能的效率。
{"title":"A Golden Section Software Synchronization Algorithm Based on Linear Optical Sampling System","authors":"Rirong Su, Qinghua Tian, Xiangjun Xin, Xiaoli Yin, Fu Wang, Zhipei Li, Yongjun Wang","doi":"10.1109/ICECE56287.2022.10048658","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048658","url":null,"abstract":"In the paper, the linear optical sampling system is studied, and a golden section software synchronization (GSSS) algorithm is proposed to monitor the performance of the signal under test (SUT) and obtain a clear eye diagram. Experiments show that this method produces better results in recovering temporal information. Compared with the chirp-z-transform (CZT) algorithm, the GSSS algorithm reduces the complexity by half, which has a smaller delay and improves the efficiency of real-time monitoring the performance of SUT.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134508311","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
Hard Contrastive Learning for Video Captioning 视频字幕的硬对比学习
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048594
Lilei Wu, Jie Liu
Maximum likelihood estimation has been widely adopted along with the encoder-decoder framework for video captioning. However, it ignores the structure of sentences and restrains the diversity and distinction of generated captions. To address this issue, we propose a hard contrastive learning (HCL) method for video captioning. Specifically, built on the encoder-decoder framework, we introduce mismatched pairs to learn a reference distribution of video descriptions. The target model on the matched pairs is learned on top the reference model, which improves the distinctiveness of generated captions. In addition, we further boost the distinctiveness of the captions by developing a hard mining technique to select the hardest mismatched pairs within the contrastive learning framework. Finally, the relationships among multiple relevant captions for each video is consider to encourage the diversity of generated captions. The proposed method generates high quality captions which effectively capture the specialties in individual videos. Extensive experiments on two benchmark datasets, i.e., MSVD and MSR-VTT, show that our approach outperforms state-of-the-art methods.
极大似然估计与编解码器框架一起被广泛应用于视频字幕。然而,它忽略了句子的结构,限制了生成字幕的多样性和差异性。为了解决这个问题,我们提出了一种用于视频字幕的硬对比学习(HCL)方法。具体来说,在编码器-解码器框架的基础上,我们引入了不匹配对来学习视频描述的参考分布。在参考模型的基础上学习匹配对上的目标模型,提高了生成字幕的显著性。此外,我们通过开发一种硬挖掘技术,在对比学习框架内选择最难不匹配的对,进一步提高了字幕的独特性。最后,考虑每个视频的多个相关字幕之间的关系,以鼓励生成字幕的多样性。该方法能够生成高质量的字幕,有效地捕捉单个视频的特征。在两个基准数据集(即MSVD和MSR-VTT)上进行的大量实验表明,我们的方法优于最先进的方法。
{"title":"Hard Contrastive Learning for Video Captioning","authors":"Lilei Wu, Jie Liu","doi":"10.1109/ICECE56287.2022.10048594","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048594","url":null,"abstract":"Maximum likelihood estimation has been widely adopted along with the encoder-decoder framework for video captioning. However, it ignores the structure of sentences and restrains the diversity and distinction of generated captions. To address this issue, we propose a hard contrastive learning (HCL) method for video captioning. Specifically, built on the encoder-decoder framework, we introduce mismatched pairs to learn a reference distribution of video descriptions. The target model on the matched pairs is learned on top the reference model, which improves the distinctiveness of generated captions. In addition, we further boost the distinctiveness of the captions by developing a hard mining technique to select the hardest mismatched pairs within the contrastive learning framework. Finally, the relationships among multiple relevant captions for each video is consider to encourage the diversity of generated captions. The proposed method generates high quality captions which effectively capture the specialties in individual videos. Extensive experiments on two benchmark datasets, i.e., MSVD and MSR-VTT, show that our approach outperforms state-of-the-art methods.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127415543","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
Mobile Networks Classification Based on Time-Series Clustering 基于时间序列聚类的移动网络分类
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048650
S. Lu, Bing-yi Qian, Long Zhao, Qiong Sun
With the increasing complexity of network architecture, the classification of mobile network cells become more important in network operation and maintenance. However, the previous classification method based on manual annotation of scene labeling is inefficient and biased. In this paper, we focus on proposing a data-driven classification method to eliminate the drawbacks of manual annotation. The proposed method extracts the patterns of mobile network on temporal shape and statistical features, and then calculates the fused distance matrix from these two feature sets, K-medoids is leveraged to get the classification labels. We design a series of experiments and analyses to demonstrate the validity of the proposed method, which is based on hourly real data sampled from 9454 mobile cells. The experiments demonstrate that the proposed method achieves good performance on the cell classification of two O&M (Operations and Maintenance) scenarios, and significantly improves the work efficiency.
随着网络结构的日益复杂,移动网络单元的分类在网络运维中变得越来越重要。然而,以往基于手动标注场景标签的分类方法效率低下且存在一定的偏差。本文重点提出了一种数据驱动的分类方法,以消除手工标注的缺点。该方法提取移动网络在时间形状和统计特征上的模式,然后计算这两个特征集的融合距离矩阵,利用K-medoids得到分类标签。我们设计了一系列的实验和分析来证明该方法的有效性,该方法基于从9454个移动基站采样的每小时真实数据。实验表明,该方法在两种运维场景的单元分类上取得了良好的性能,显著提高了工作效率。
{"title":"Mobile Networks Classification Based on Time-Series Clustering","authors":"S. Lu, Bing-yi Qian, Long Zhao, Qiong Sun","doi":"10.1109/ICECE56287.2022.10048650","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048650","url":null,"abstract":"With the increasing complexity of network architecture, the classification of mobile network cells become more important in network operation and maintenance. However, the previous classification method based on manual annotation of scene labeling is inefficient and biased. In this paper, we focus on proposing a data-driven classification method to eliminate the drawbacks of manual annotation. The proposed method extracts the patterns of mobile network on temporal shape and statistical features, and then calculates the fused distance matrix from these two feature sets, K-medoids is leveraged to get the classification labels. We design a series of experiments and analyses to demonstrate the validity of the proposed method, which is based on hourly real data sampled from 9454 mobile cells. The experiments demonstrate that the proposed method achieves good performance on the cell classification of two O&M (Operations and Maintenance) scenarios, and significantly improves the work efficiency.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114666499","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 WebGIS Solution for Effective Investment Promotion for Investors: A Case Study in Gia Lai Province, Vietnam 有效促进投资者投资的WebGIS解决方案:以越南嘉莱省为例
Pub Date : 2022-12-16 DOI: 10.1109/ICECE56287.2022.10048638
Nguyen Ngoc Phien, T. T. Duong
Gia Lai is the second largest province in Vietnam. It is a mountainous province in the north of the Central Highlands in central Vietnam. Gia Lai province is also the largest in the Central Highlands, and it has the second most people. This paper shows how to build a web-based GIS to store, manage, analyze, and display data for effective investment promotion for investors. The new thing is mostly about automating the server-side workflow for making and publishing time series maps. On the web browser interface, users can see the results of the analysis. This lets people get to useful information without having to install GIS software.
嘉莱省是越南第二大省。它是越南中部中部高地北部的一个多山省份。嘉莱省也是中部高地最大的省份,人口第二多。本文介绍了如何建立一个基于网络的地理信息系统来存储、管理、分析和显示数据,为投资者提供有效的投资促进。新事物主要是自动化服务器端工作流,用于制作和发布时间序列地图。在web浏览器界面上,用户可以看到分析结果。这使得人们不必安装GIS软件就可以获得有用的信息。
{"title":"A WebGIS Solution for Effective Investment Promotion for Investors: A Case Study in Gia Lai Province, Vietnam","authors":"Nguyen Ngoc Phien, T. T. Duong","doi":"10.1109/ICECE56287.2022.10048638","DOIUrl":"https://doi.org/10.1109/ICECE56287.2022.10048638","url":null,"abstract":"Gia Lai is the second largest province in Vietnam. It is a mountainous province in the north of the Central Highlands in central Vietnam. Gia Lai province is also the largest in the Central Highlands, and it has the second most people. This paper shows how to build a web-based GIS to store, manage, analyze, and display data for effective investment promotion for investors. The new thing is mostly about automating the server-side workflow for making and publishing time series maps. On the web browser interface, users can see the results of the analysis. This lets people get to useful information without having to install GIS software.","PeriodicalId":358486,"journal":{"name":"2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129319178","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
2022 IEEE 5th International Conference on Electronics and Communication Engineering (ICECE)
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