Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809891
Pei Qie, Kai Shuang
It is a challenge task to extract the potential pairs of emotion clause and corresponding cause clause from the documents. The existing state-of-the-art ECPE method formulates the task in an end-to-end model, which processes the interactions of emotion-cause pairs based on joint two-dimensional. The model has two shortcomings: 1) the potential semantic particularity of the causal relation between the emotion-cause pair is not fully considered; 2) it falls short of capturing various regional features of contextualized representation. In this work, we propose an end-to-end model named DCN-ECPE. The model generates the representation of emotion-cause pairs with dual-channel, which takes both potential causal features and contextualized interactions of the clause pairs into consideration. One channel extracts potential semantic feature of the causal relation from constructed statements, and the other channel processes the representation of clause pairs with CNN to capture various regional features. Our method outperforms existing state-of-the-art end-to-end ECPE method in all aspects.
{"title":"DCN-ECPE: Dual-Channel Network for Emotion-Cause Pair Extraction","authors":"Pei Qie, Kai Shuang","doi":"10.1109/ICWOC55996.2022.9809891","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809891","url":null,"abstract":"It is a challenge task to extract the potential pairs of emotion clause and corresponding cause clause from the documents. The existing state-of-the-art ECPE method formulates the task in an end-to-end model, which processes the interactions of emotion-cause pairs based on joint two-dimensional. The model has two shortcomings: 1) the potential semantic particularity of the causal relation between the emotion-cause pair is not fully considered; 2) it falls short of capturing various regional features of contextualized representation. In this work, we propose an end-to-end model named DCN-ECPE. The model generates the representation of emotion-cause pairs with dual-channel, which takes both potential causal features and contextualized interactions of the clause pairs into consideration. One channel extracts potential semantic feature of the causal relation from constructed statements, and the other channel processes the representation of clause pairs with CNN to capture various regional features. Our method outperforms existing state-of-the-art end-to-end ECPE method in all aspects.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130761842","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}
Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809870
Qian Yu, Zhiping Huang, Junhao Ba
To compensate for signal damage during transmission and retrieve signal in coherent optical communication, the receiver side must be clock synchronized first. For the classic Gardner timing synchronization algorithm has disadvantages such as extended synchronization establishment time and algorithm failure when neighboring symbols have the same polarity, an improved Gardner feedback timing synchronization loop is proposed in this paper. First, the Lagrangian cubic interpolation filter is chosen for interpolation, and the polarity of the interpolated sequence is determined before it enters the timing error detector. The improved Gardner algorithm is then used selectively based on whether the adjacent symbols have the same polarity. The simulation objects are QPSK signals, and the simulation results demonstrate that the improved algorithm takes less time to reach synchronization, and the fractional interval and timing error converge faster than the classic Gardner approach, improving the loop's performance to some amount.
{"title":"An Improved Gardner Feedback Timing Synchronization Loop","authors":"Qian Yu, Zhiping Huang, Junhao Ba","doi":"10.1109/ICWOC55996.2022.9809870","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809870","url":null,"abstract":"To compensate for signal damage during transmission and retrieve signal in coherent optical communication, the receiver side must be clock synchronized first. For the classic Gardner timing synchronization algorithm has disadvantages such as extended synchronization establishment time and algorithm failure when neighboring symbols have the same polarity, an improved Gardner feedback timing synchronization loop is proposed in this paper. First, the Lagrangian cubic interpolation filter is chosen for interpolation, and the polarity of the interpolated sequence is determined before it enters the timing error detector. The improved Gardner algorithm is then used selectively based on whether the adjacent symbols have the same polarity. The simulation objects are QPSK signals, and the simulation results demonstrate that the improved algorithm takes less time to reach synchronization, and the fractional interval and timing error converge faster than the classic Gardner approach, improving the loop's performance to some amount.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"2010 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132899250","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}
Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809850
Q. Zhang, Jie Zhang, Wencheng Sun, Zhangjian Qin
In order to ensure the stable operation of high voltage transmission network, DeepLab V3+_SDF is proposed based on DeepLab V3+ for rapid and intelligent landslide detection from high resolution remote sensing images. Firstly, the backbone network is replaced by ResNet with squeeze-and-excitation (SE) attention mechanism to enhance the extraction of useful features. Secondly, astrous spatial pyramid pooling (ASPP) is reconstructed based on dense connection to expand the receptive field. More low-level features are then added to the decoder with feature pyramid networks plus (FPNP) to enhance detail recovery. Finally, a mixed loss function is proposed based on the pixel distribution to solve the sample imbalance problem. DeepLabV3+ _SDF is trained with self-made landslide remote sensing dataset. The experimental results show that the mean pixel accuracy(mPA) and mean intersection over union (mIoU) of DeepLab V3+_SDF on the landslide dataset reach 95.38 % and 85.27 %, which are 2.90 % and 7.76 % higher than those of DeepLabV3+. Finally, the trained DeepLab V3+_SDF is applied to Sichuan-Chongqing region in China, and the comparison results with manual interpretation show that the algorithm can be used for rapid identification of landslides in large-scale mountainous areas.
为了保证高压输电网的稳定运行，在DeepLab V3+的基础上，提出了DeepLab V3+_SDF，实现高分辨率遥感影像滑坡快速智能检测。首先，将骨干网替换为ResNet，采用SE关注机制增强有用特征的提取;其次，在密集连接的基础上重构星形空间金字塔池(astrous space pyramid pooling, ASPP)，扩大接收野;然后用特征金字塔网络加(FPNP)将更多的低级特征添加到解码器中，以增强细节恢复。最后，提出了一种基于像素分布的混合损失函数来解决样本不平衡问题。DeepLabV3+ _SDF用自制的滑坡遥感数据集进行训练。实验结果表明，DeepLabV3+ _SDF在滑坡数据集上的平均像元精度(mPA)和平均交联精度(mIoU)分别达到95.38%和85.27%，分别比DeepLabV3+提高2.90%和7.76%。最后，将训练好的DeepLab V3+_SDF应用于中国川渝地区，与人工解译的对比结果表明，该算法可用于大尺度山区滑坡的快速识别。
{"title":"Landslide Recognition in High Resolution Remote Sensing Images Based on Semantic Segmentation","authors":"Q. Zhang, Jie Zhang, Wencheng Sun, Zhangjian Qin","doi":"10.1109/ICWOC55996.2022.9809850","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809850","url":null,"abstract":"In order to ensure the stable operation of high voltage transmission network, DeepLab V3+_SDF is proposed based on DeepLab V3+ for rapid and intelligent landslide detection from high resolution remote sensing images. Firstly, the backbone network is replaced by ResNet with squeeze-and-excitation (SE) attention mechanism to enhance the extraction of useful features. Secondly, astrous spatial pyramid pooling (ASPP) is reconstructed based on dense connection to expand the receptive field. More low-level features are then added to the decoder with feature pyramid networks plus (FPNP) to enhance detail recovery. Finally, a mixed loss function is proposed based on the pixel distribution to solve the sample imbalance problem. DeepLabV3+ _SDF is trained with self-made landslide remote sensing dataset. The experimental results show that the mean pixel accuracy(mPA) and mean intersection over union (mIoU) of DeepLab V3+_SDF on the landslide dataset reach 95.38 % and 85.27 %, which are 2.90 % and 7.76 % higher than those of DeepLabV3+. Finally, the trained DeepLab V3+_SDF is applied to Sichuan-Chongqing region in China, and the comparison results with manual interpretation show that the algorithm can be used for rapid identification of landslides in large-scale mountainous areas.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116708526","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}
Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809887
Dongyao Wang, Xiaobao Sun, Y. Liu, Yuan Chen
Multi-View Video (MVV) is an emerging video technology that allows users to freely change their viewing angle when watching. Compared with traditional video transmission, multi-view video transmission requires large bandwidth and high computing power, which brings great challenges to multi-view video transmission under wireless networks. With the rapid development of Mobile Edge Computing (MEC) technology, this technology has become one of the potential solutions to the problem of multi-view video transmission in wireless networks by using edge caching and computing technology. This paper firstly establishes a communication model for multi-view video transmission, models different transmission paths in the process of multi-view video transmission, and jointly optimizes the design of edge computing and storage resources to maximize the hit rate of edge caching and computing. Further, a deep reinforcement learning algorithm is designed for the resource allocation mechanism of edge computing and storage. Finally, the simulation results verify that the algorithm can significantly improve the hit rate of edge computing and storage.
{"title":"Research on Edge Computing and Caching Resource Allocation Mechanism for Multi-view Video","authors":"Dongyao Wang, Xiaobao Sun, Y. Liu, Yuan Chen","doi":"10.1109/ICWOC55996.2022.9809887","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809887","url":null,"abstract":"Multi-View Video (MVV) is an emerging video technology that allows users to freely change their viewing angle when watching. Compared with traditional video transmission, multi-view video transmission requires large bandwidth and high computing power, which brings great challenges to multi-view video transmission under wireless networks. With the rapid development of Mobile Edge Computing (MEC) technology, this technology has become one of the potential solutions to the problem of multi-view video transmission in wireless networks by using edge caching and computing technology. This paper firstly establishes a communication model for multi-view video transmission, models different transmission paths in the process of multi-view video transmission, and jointly optimizes the design of edge computing and storage resources to maximize the hit rate of edge caching and computing. Further, a deep reinforcement learning algorithm is designed for the resource allocation mechanism of edge computing and storage. Finally, the simulation results verify that the algorithm can significantly improve the hit rate of edge computing and storage.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132029658","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}
Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809862
Yuefan Xie, Ying Wang, Jiahang Wei, Jiarui Wang
This paper proposes an improved artificial potential field method on route planing for UAV swarm to evade radar detection during flight and finally reach the target point. We solve the problem of excessive gravitational force is solved by modifying the gravitational function to a segmental function compared to the shortcomings of the traditional artificial potential field method. And solve the problem of target unreachability by concentrating on the relative distance between the UAV swarm and the target. Finally, we solve the problem of local minima by adjusting the step size and direction. The feasibility of our improved artificial potential field method in obstacle avoidance is verified by Matlab simulation in experiment.
{"title":"Research on Radar Wave Avoidance for UAV Swarm Based on Improved Artificial Potential Field","authors":"Yuefan Xie, Ying Wang, Jiahang Wei, Jiarui Wang","doi":"10.1109/ICWOC55996.2022.9809862","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809862","url":null,"abstract":"This paper proposes an improved artificial potential field method on route planing for UAV swarm to evade radar detection during flight and finally reach the target point. We solve the problem of excessive gravitational force is solved by modifying the gravitational function to a segmental function compared to the shortcomings of the traditional artificial potential field method. And solve the problem of target unreachability by concentrating on the relative distance between the UAV swarm and the target. Finally, we solve the problem of local minima by adjusting the step size and direction. The feasibility of our improved artificial potential field method in obstacle avoidance is verified by Matlab simulation in experiment.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133753605","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}
Item-related recommendation is widely used in e-commerce, news, video, and other business scenarios, but there are problems such as sparse data, a large amount of implicit feedback data, limited sample annotation, cold start of items, poor serendipity, insufficient real-time performance, and the recommendation effect needs to be continuously improved. An unsupervised recommendation method is proposed. The method included four recall strategies. The first was to use the search engine and BM25 for real-time text matching recommendation about multi fields, and the second was to combine pre-trained language model BERT and ANN algorithm for real-time semantic matching recommendation about multi fields, and the third was to calculate the similarity by reducing the influence of popular items and active users to optimize the item-based collaborative filtering recommendation algorithm, and the fourth was to introduce the heat index based on Wilson Confidence Intervals to assist the recommendation ranking. Finally, the four recall results were merged and sorted to generate the final recommendation result. Through multiple sets of comparative experiments by the AlB test in the online recommendation system, it is shown that the proposed unsupervised recommendation method is superior to the baseline method in multiple indicators and can effectively improve the recommendation effect and user satisfaction.
{"title":"Unsupervised Item-Related Recommendation Method Combining BERT and Collaborative Filtering","authors":"Jing Yu, Jingjing Shi, Mingxing Zhou, Wenhai Liu, Yunwen Chen, Fan Xiong","doi":"10.1109/ICWOC55996.2022.9809848","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809848","url":null,"abstract":"Item-related recommendation is widely used in e-commerce, news, video, and other business scenarios, but there are problems such as sparse data, a large amount of implicit feedback data, limited sample annotation, cold start of items, poor serendipity, insufficient real-time performance, and the recommendation effect needs to be continuously improved. An unsupervised recommendation method is proposed. The method included four recall strategies. The first was to use the search engine and BM25 for real-time text matching recommendation about multi fields, and the second was to combine pre-trained language model BERT and ANN algorithm for real-time semantic matching recommendation about multi fields, and the third was to calculate the similarity by reducing the influence of popular items and active users to optimize the item-based collaborative filtering recommendation algorithm, and the fourth was to introduce the heat index based on Wilson Confidence Intervals to assist the recommendation ranking. Finally, the four recall results were merged and sorted to generate the final recommendation result. Through multiple sets of comparative experiments by the AlB test in the online recommendation system, it is shown that the proposed unsupervised recommendation method is superior to the baseline method in multiple indicators and can effectively improve the recommendation effect and user satisfaction.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133277943","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}
Pub Date : 2022-06-10DOI: 10.1109/ICWOC55996.2022.9809897
Li Wang, Hui Li
Internet of things (IOT) networks aim for providing significantly higher data rates. Typical IOT applications like power IOT involves increasing volume of data, which requires high performance data transmission. Orthogonal Frequency Division Multiplexing (OFDM) is currently promising for IOT. Estimation of maximum doppler shift (MDS) is inevitable for the channel response estimation in OFDM systems. To improve the accuracy and efficiency of channel estimation, we propose machine learning (ML) based MDS estimation method in this paper. Our method is based on the fact that the distribution of the instantaneous frequency offset (IFO) is related to the MDS. The ML algorithm is used to learn the functional relationship between the statistic of the IFO and the MDS. To make our method feasible in the realtime communication process, we further propose MDS estimation architecture. The functional relationship is obtained through the offline training and can be directly used in the communication process, thus greatly decreasing the implementation complexity. Simulation results indicate that our method is effective in a wide range of MDS and signal to noise ratio (SNR), and greatly improves the communication performance.
{"title":"Machine Learning Based Channel Estimation Optimization for OFDM Communication Systems","authors":"Li Wang, Hui Li","doi":"10.1109/ICWOC55996.2022.9809897","DOIUrl":"https://doi.org/10.1109/ICWOC55996.2022.9809897","url":null,"abstract":"Internet of things (IOT) networks aim for providing significantly higher data rates. Typical IOT applications like power IOT involves increasing volume of data, which requires high performance data transmission. Orthogonal Frequency Division Multiplexing (OFDM) is currently promising for IOT. Estimation of maximum doppler shift (MDS) is inevitable for the channel response estimation in OFDM systems. To improve the accuracy and efficiency of channel estimation, we propose machine learning (ML) based MDS estimation method in this paper. Our method is based on the fact that the distribution of the instantaneous frequency offset (IFO) is related to the MDS. The ML algorithm is used to learn the functional relationship between the statistic of the IFO and the MDS. To make our method feasible in the realtime communication process, we further propose MDS estimation architecture. The functional relationship is obtained through the offline training and can be directly used in the communication process, thus greatly decreasing the implementation complexity. Simulation results indicate that our method is effective in a wide range of MDS and signal to noise ratio (SNR), and greatly improves the communication performance.","PeriodicalId":402416,"journal":{"name":"2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115852485","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：