检索结果-内蒙古大学图书馆

5th International Conference on Computer Information and Big Data Applications, CIBDA 2024

作者： Wang, Yaohui Zhang, Jian Zhao, Yuxian Sun, Xiaohu Hao, Qiang Lyu, Xueqiang Huaneng Coal Technology Research Co. Ltd. Beijing100070 China Beijing Key Laboratory of Network Culture and Digital Communication Beijing Information Science and Technology University Beijing100101 China

ISBN: (纸本)9798400718106

Intelligent Q&A is an essential part of the intelligent construction of coal mines. However, in practical applications, there is a lack of Q&A related data sets in the field of coal mine production, and it is difficult to obtain annotated data. The existing Q&A system in the field of coal mine production has problems such as inability to solve polysemy issues and accurately understand user needs. To solve these problems, this paper introduces prompt learning into the field of coal mine production for the first time for Q&A intent classification. By introducing multiple prompt templates to fine-tune the BERT pre-trained model, the accuracy of Q&A intent classification is improved in the case of low data volume. Experimental results show that after introducing the prompt template, the accuracy, recall rate, and F1 value of the model are increased by 0.66, 1.21, and 1.29 percentage points, respectively. In addition, we have also conducted experiments in low-sample scenarios, proving that prompt learning methods can quickly adapt to new domain tasks in low-sample scenarios. The proposed method has good application value in Q&A intent classification in the field of coal mine production. © 2024 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A New CP-Based Non-Overlapping FBMC-QAM System for Future Wireless communications

引用

China communications 2025年第5期22卷 108-127页

作者： Ren Defeng Li Jing Sun Chuiqiang Zhang Guohua Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts and TelecommunicationsXi’an 710121China State Key Laboratory of Integrated Services Networks Xidian UniversityXi’an 710071China China Academy of Space Technology(Xi’an) Xi’an 710000China

A new cyclic prefix(CP)-based nonoverlapping FBMC-QAM(CP-NO-FBMC-QAM)system with two prototype filters is proposed in this paper,which satisfies complex orthogonality conditions and good frequency energy confinement at the same *** analyze its inter-carrier interference/inter-symbol interference(ICI/ISI)over multipath *** to the additional CP,the ISI of received symbols over multipath channels is eliminated in the proposed system,and the resulting improvement in the signal-to-interference ratio(SIR)performance is evaluated by theoretical ***,for the ICI caused by multipath propagation in received symbols,we develop a method that eliminates the ICI by frequency-domain channel estimation and equalization before the receiver filtering *** proposed CP-NO-FBMC-QAM system and ICI cancellation method(ICICM)are validated by comparisons of implementation complexity,power spectral density(PSD),bit error rate(BER)and channel estimation performance with conventional CP-based orthogonal frequency division multiplexing(CP-OFDM)and FBMC-QAM systems.

关键词： channel equalization channel estimation cyclic prefix FBMC ICI cancellation

来源：评论

学校读者我要写书评

暂无评论

PONizing Wi-Fi for Fiber-to-The-Room Scenario: A Unified PON and Wi-Fi Access Based on PON MAC Protocol

PONizing Wi-Fi for Fiber-to-The-Room Scenario: A Unified PON...

引用

2023 Opto-Electronics and communications Conference, OECC 2023

作者： Shen, Gangxiang Li, Jun Chen, Yuxuan Cai, Jinhan Chang, Tianhai School of Electronic and Information Engineering Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network Suzhou Key Laboratory of Advanced Optical Communication Network Technology Suzhou China Huawei Technologies Co. Ltd. Shenzhen China

ISBN: (纸本)9781665462136

We propose a unified PON and Wi-Fi access scheme tailored for the fiber-to-the-room scenario, in which WiFi access is PONized based on the PON protocol. The proposed scheme can significantly improve network access rate, resource utilization, and handover time, compared with a benchmark based on non-integrated PON and Wi-Fi access. © 2023 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Named entity recognition method for mine electromechanical equipment field 24

Named entity recognition method for mine electromechanical e...

引用

3rd International Conference on Computer, Artificial Intelligence and Control Engineering, CAICE 2024

作者： Wang, Yi Long Wen, Ying Zi Wang, Yao Hui She, Xin Peng Sun, Xiao Hu Lyu, Xue Qiang Hao, Qiang Huaneng Coal Technology Research Co. Ltd. Beijing100070 China Beijing Key Laboratory of Network Culture and Digital Communication Beijing Information Science and Technology University Beijing100101 China

ISBN: (纸本)9798400716942

Aiming at the lack of annotated corpus in the field of mine electromechanical equipment, the high similarity between different categories of entities and the long names of some entities, this paper proposed an entity extraction method of mine electromechanical equipment based on the fusion of technical words and comparative learning. Firstly, an ontology library was constructed according to the characteristics of mine electromechanical equipment, Word2Vec was used to obtain the vector representation of characters and words, and the term words were obtained by matching in the ontology library. The multi-term multi-head attention mechanism was used to assign larger weights to these term words and then they were fused with the character vector. Then, the Bi-LSTM model was used for feature extraction, and a contrastive learning strategy based on R-drop was used to reduce the recognition bias error caused by the similarity of entity names. We also improved the loss function by using the relative entropy loss calculated by the Bi-LSTM layer as the regularization term of the loss in the CRF layer to form a constraint on the loss function and enhance the robustness of the model to Dropout. Finally, we used the CRF model to decode to obtain the optimal label. Experimental results show that compared with the existing mainstream baseline method Lattice-LSTM, our proposed method achieves better results on the self-constructed mine electromechanical equipment corpus. The precision, recall and F1 value are improved by 4.73, 5.5 and 5.09 percentage points, respectively. © 2024 ACM.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

ReLFA:Resist Link Flooding Attacks via Renyi Entropy and Deep Reinforcement Learning in SDN-IoT

引用

China communications 2022年第7期19卷 157-171页

作者： Jiushuang Wang Ying Liu Weiting Zhang Xincheng Yan Na Zhou Zhihong Jiang School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518055China ZTE Corporation Nanjing 210012China

Link flooding attack(LFA)is a fresh distributed denial of service attack(DDoS).Attackers can cut off the critical links,making the services in the target area *** manipulates legal lowspeed flow to flood critical links,so traditional technologies are difficult to resist such ***,LFA is also one of the most important threats to Internet of things(IoT)*** introduction of software defined network(SDN)effectively solves the security problem of the *** at the LFA in the software defined Internet of things(SDN-IoT),this paper proposes a new LFA mitigation scheme *** entropy is to locate the congested link in the data plane in our scheme,and determines the target links according to the alarm *** LFA is detected on the target links,the control plane uses the method based on deep reinforcement learning(DRL)to carry out traffic *** results show that ReLFA can effectively alleviate the impact of LFA in SDN *** addition,the rerouting time of ReLFA is superior to other latest schemes.

关键词： link flooding attacks renyi entropy deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Trajectory Prediction by Short-Term Target Estimation in Autonomous Driving Scenarios

Pedestrian Trajectory Prediction by Short-Term Target Estima...

引用

2024 IEEE Global communications Conference, GLOBECOM 2024

作者： Yang, Jing Wang, Peng Cui, Yaping He, Peng Wu, Dapeng Wang, Ruyan School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Chongqing China

ISBN: (纸本)9798350351255

As the most vulnerable part of the traffic scenario, it is vital to ensure the safety of pedestrians. Accurately predicting the future trajectory of pedestrians not only ensures the safety of pedestrians but also improves the efficiency of traffic operations. In light of this, this paper presents a novel target-driven method for pedestrian trajectory prediction. The method uses bidirectional long short-term memory (Bi-LSTM) to predict the approximate position of the pedestrian at different time intervals and uses the short-term location as a short-term target for pedestrians. Meanwhile, our method takes into account the influence of surrounding vehicles on the future trajectory of pedestrians. We predict the speed of vehicles around the pedestrian and apply it to the pedestrian trajectory prediction to make the prediction more accurate. We evaluated our method on two public datasets, PIE and JAAD, and demonstrated its superiority over the benchmark methods. The ablation experiments further reveal that the target estimation and speed estimation modules reduced prediction errors by approximately 11% and 30% respectively. © 2024 IEEE.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

Ultra Flexible S-band 1x5 Wavelength Selective Switch Based On Off-the-shelf C-band Optics

Ultra Flexible S-band 1x5 Wavelength Selective Switch Based ...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

作者： Feng, Zhenhua You, Quan Liu, Minghuan Shi, Hu Chen, Weizhang State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen China WDM System Department of ZTE Corp. Wuhan China WDM System Department of ZTE Corp. Beijing China

An S-band 1x5 WSS prototype covering 1470 to 1520 nm is experimentally demonstrated using off-the-shelf C band optical elements. The main optical performances are measured, showing comparable or even superior performa... 详细信息

ISBN: (纸本)9798350379266

关键词： Optical band gaps

来源：评论

学校读者我要写书评

暂无评论

Ranking Aggregation with Interactive Feedback for Collaborative Person Re-identification 33

Ranking Aggregation with Interactive Feedback for Collaborat...

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Huang, Ji Liang, Chao Zhang, Yue Wang, Zhongyuan Zhang, Chunjie National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong University Beijing100044 China

Person re-identification (re-ID) aims to retrieve the same person from a group of networking cameras. Ranking aggregation (RA), a method to aggregates multiple ranking results, can further improve the retrieval accuracy in re-ID tasks. Existing RA work can be generally divided into unsupervised methods and fully-supervised methods. Unsupervised methods lack external supervision, can hardly achieve the optimal results. In contrast, fully-supervised methods need massive labeling data for training, which is prohibitively expensive in the practical application. This paper studies interactive RA (IRA) to address the above challenges in existing RA research. The core idea is to utilize a small amount of supervisory information, obtained from users' relevance feedback, to supervise RA method to produce better re-ranking results. Compared with unsupervised methods, IRA introduces supervisory information and thus has better aggregation accuracy. Compared with fully-supervision methods, the supervisory information of IRA is more readily available, and can be targeted to specific queries. Particularly, we propose two IRA implementations, based on ranking positions and scores respectively, to adapt to diverse application scenarios, where rankers only give rankings, or rankers give similarity scores. Experiments on three public re-ID datasets have shown that IRA significantly outperforms the-state-of-art unsupervised baselines, and achieves similar accuracy with less labeling cost than the fully-supervised RA method. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Raman amplifier placement in C+L-band elastic optical networks

Raman amplifier placement in C+L-band elastic optical networ...

引用

2023 Advanced Fiber Laser Conference, AFL 2023

作者： Wang, Yong Li, Yongcheng Guo, Ningning Wang, Xiaoling Mo, Siming Zhou, Li Zhang, Guodong Shen, Gangxiang School of Electronic and Information Engineering Soochow University Suzhou China Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network Soochow University Suzhou China Suzhou Key Laboratory of Advanced Optical Communication Network Technology Soochow University Suzhou China Jiangsu Etern Co. Ltd China

ISBN: (纸本)9781510677661

To extend a fiber-optic transmission system from traditional C band to C+L band, it is necessary to place Raman amplifiers to improve the optical signal-to-noise ratios (OSNR) of lightpaths. We develop a heuristic algorithm for optimal Raman amplifier placement. Simulations show that the proposed algorithm is efficient to require up to 50% fewer Raman amplifiers compared with benchmark schemes. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Classification of Zhuang Dialect combined with Bert and SimAM

Classification of Zhuang Dialect combined with Bert and SimA...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Min Huang Xuejun Zhang Wenkang Chen School of Computer Electronics and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China School of Electrical Engineering Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Language recognition refers to the automatic recognition of the language type of the given speech segments. Zhuang is an important language in Southeast Asia, with more than 16 million native speakers. Due to the scarcity of data resources, there is relatively little research about Zhuang in the field of natural language processing, especially in the area of speech-level exploration. Because of the existence of a variety of dialects in Zhuang, this paper is the first to create a speech dataset for the study of the Zhuang language. In the experiment, it was observed that the output of different encoder layers of the BERT has an impact on classification, so this paper innovatively proposes to integrate the SimAM attention mechanism with the BERT model. The model uses a phone recognizer to extract phone sequences from speech segments. Then the Bert model combined with the integrated SimAM attention mechanism performs deep feature representation learning on the semantic information and word order of the sequence. Finally, the classifier realizes the efficient classification of the Zhuang language. Compared with Baseline Systems, the accuracy of the dialect recognition model proposed in this paper is 91.37%, which fully proves the effectiveness of the model.

关键词： Representation learning Attention mechanisms Semantics Speech recognition Bidirectional control Signal processing Feature extraction Encoding Natural language processing Speech processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：