2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)最新文献_第2页

A Survey: Complex Knowledge Base Question Answering 一项调查:复杂知识库问答

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828967

Yuxin Luo, Bailong Yang, Donghui Xu, Luogeng Tian

引用次数: 2

An Advanced NMF-Based Approach for Single Cell Data Clustering 一种基于神经网络的单细胞数据聚类方法

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828919

Peng Zhao, Yongpan Sheng, Xiaohui Zhan

引用次数: 0

STDE: A Single-Senior-Teacher Knowledge Distillation Model for High-Dimensional Knowledge Graph Embeddings 面向高维知识图嵌入的单个高级教师知识蒸馏模型

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828905

Xiaobo Guo, Pei Wang, Neng Gao, Xin Wang, Wenying Feng

{"title":"STDE: A Single-Senior-Teacher Knowledge Distillation Model for High-Dimensional Knowledge Graph Embeddings","authors":"Xiaobo Guo, Pei Wang, Neng Gao, Xin Wang, Wenying Feng","doi":"10.1109/icicse55337.2022.9828905","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828905","url":null,"abstract":"An important role of Knowledge Graph Embedding (KGE) is to automatically complete the missing fact in a knowledge base. It is well-known that human society is constantly developing and the knowledge generated by human society will always being increasing. The increasing scale of the knowledge base is a great challenge to the storage and computing resources of downstream applications. At present, the dimensions of most mainstream knowledge graph embedding models are between 200-1000. For a large-scale knowledge base with millions of entities, these embeddings with hundreds of dimensional values are not conducive to rapid and frequent deployment on many kinds of artificial intelligent applications with limited storage and computing resources. To solve this problem, we propose a single-senior-teacher knowledge distillation model for high-dimensional knowledge graph embeddings named STDE, which constructs a low-dimensional student from a trained high-dimensional teacher. In STDE, the senior teacher can help the student learn key knowledge from correct knowledge and indistinguishable wrong knowledge with use of high-quality negative samples of triplets. We apply STDE to four typical KGE models on two famous data sets. Experimental results show that STDE can compress the embedding parameters of high-dimensional KGE models to 1/8 or 1/16 of their original scales. We further verify the effectiveness of \"senior teacher\" through ablation experiments.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124415382","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

A Combined Algorithm for Imbalanced Classification Based on Dual Distribution Representation Learning and Classifier Decoupling Learning 基于对偶分布表示学习和分类器解耦学习的不平衡分类组合算法

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828930

Lin Guo-yuan, Hongyu Liao, Hongxiao Gao, Jianliang Ma

{"title":"A Combined Algorithm for Imbalanced Classification Based on Dual Distribution Representation Learning and Classifier Decoupling Learning","authors":"Lin Guo-yuan, Hongyu Liao, Hongxiao Gao, Jianliang Ma","doi":"10.1109/icicse55337.2022.9828930","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828930","url":null,"abstract":"Existing classification algorithms for imbalanced datasets adopt data resampling, classes reweighting and other class balancing strategies to strengthen representation ability for minority classes and adjust the classification interface. However, these algorithms weaken the network’s representation ability for majority classes. Therefore, a combined algorithm is proposed based on dual distribution representation learning (DDRL) and classifier decoupling learning (CDL). Here, DDRL preserves the original distribution and samples the balanced distribution from it to guide the learning of dual distribution representation, which enhances minority classes' feature representation ability and retains it for majority classes. CDL decouples the classifier from feature representation network, and trains an MLP classifier with a balanced subset, aiming at adjusting the classification deviation caused by weak features of minority classes. Experimental results show that the proposed algorithm can improve the classification accuracy on class imbalanced datasets effectively.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127820663","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

Font Design Method Based on Multi-scale CycleGAN 基于多尺度CycleGAN的字体设计方法

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828945

Yan Pan, Gang Liu, Xinyun Wu, Changlin Chen, Zhenghao Zhou, Xin Liu

{"title":"Font Design Method Based on Multi-scale CycleGAN","authors":"Yan Pan, Gang Liu, Xinyun Wu, Changlin Chen, Zhenghao Zhou, Xin Liu","doi":"10.1109/icicse55337.2022.9828945","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828945","url":null,"abstract":"Font design is an important research direction in art design and has high commercial value. It requires professionals to design fonts, which is not only time-consuming and costly, but also inefficient. Font-to-font translation is a commonly used font design method. Font-to-font translation is essentially the problem of image synthesis. Currently, generative adversarial networks (GANs) have been used for image synthesis and achieved some results. However, for the task of font-to-font translation the existing methods based on GANs generally have low-quality visual effects, such as incomplete fonts and distortion of font details. In order to solve the above problems, we propose a more effective multi-scale CycleGAN for font-to-font translation and the proposed method can obtain the font images with better visual quality. The proposed method is called MSM-CycleGAN. In MSM-CycleGAN, a U-net with multiple outputs (UM) is used as the generator. UM outputs the generated images of multiple scales. And then the outputs of UM are fed into the multi-scale discriminator. Our model uses the unsupervised learning method. This multi-scale discrimination method effectively improves the detailed information of the generated image. Experimental results show that our method performs better than other state-of-the-art image synthesis methods, and can obtain the font images with higher visual quality.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128445773","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

ECG Signal Detection Method Based on Millimeter Wave Radar 基于毫米波雷达的心电信号检测方法

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828872

Tian Li, Guangyang Wan, Linsheng Liu, Tong Zhu, Peng-Chu Wang

{"title":"ECG Signal Detection Method Based on Millimeter Wave Radar","authors":"Tian Li, Guangyang Wan, Linsheng Liu, Tong Zhu, Peng-Chu Wang","doi":"10.1109/icicse55337.2022.9828872","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828872","url":null,"abstract":"In the medical field, the detection of breathing and heartbeat signals is very important. This paper analyzes and verifies a method for detecting and estimating characteristic parameters of heartbeat signals based on millimeter wave radar, and analyzes the effect of decomposing respiratory and heartbeat signals based on wavelet changes and empirical mode decomposition. Perform range FFT on the radar echo signal to obtain the range-time image of the target, and then estimate the center of the constellation based on the method.The least squares approximation algorithm based on iterative weighting is used to eliminate the static clutter of the actual FMCW radar signal. Then the target is detected in the azimuth by the capon algorithm, and the CFAR detection is performed to extract the echo signal on the unit of distance where the target is located. The target signal is phase demodulated to obtain the phase information of micro-motions such as breathing and heartbeat. The wavelet transform is used to decompose the breathing and heartbeat signals from the phase information, and the short-term average amplitude difference function frequency estimation method is used to estimate the frequency of breathing and heartbeat.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117254629","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

Uncertain Environmental Economic Dispatch of Power Grid with Solar PV Based on a Multi-objective Cross Entropy Algorithm 基于多目标交叉熵算法的太阳能光伏电网不确定环境经济调度

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828899

Qun Niu, Litao Yu, Ming-Sian You

{"title":"Uncertain Environmental Economic Dispatch of Power Grid with Solar PV Based on a Multi-objective Cross Entropy Algorithm","authors":"Qun Niu, Litao Yu, Ming-Sian You","doi":"10.1109/icicse55337.2022.9828899","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828899","url":null,"abstract":"The penetration of renewable energies into power systems is a trend in this field. However, the randomness and uncertainty of these intermittent energy sources is also a thorny problem. Robust optimization method is introduced to solve this kind of problems in this paper. Firstly, the dynamic environmental economic load dispatch model (DEED) with solar photovoltaic is established, and then the adjustable robust optimization method is introduced to transform the initial DEED model into a robust optimization model with uncertain parameters. In order to balance the robustness of the system and the economy of the scheme, a robust cost method with improved uncertain boundary is used for decision-making. Then, a multi-objective cross entropy algorithm, namely MMOCE is used to solve the DEED problem defined by the final model. MMOCE algorithm adopts a congestion calculation technology and an external archive mechanism, and the introduction of adaptive parameter operator and cross operator further improves the performance of the algorithm. Based on the robust decision method, the MMOCE is used to solve the model, and a reasonable and reliable multi-objective solution considering the robustness and economy of the system is obtained.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116606136","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

GCQW: A Quantum Walk Model for Predicting Missing Links of Complex Networks GCQW:预测复杂网络缺失链路的量子行走模型

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828952

Wenbing Liang, Fei Yan, Abdullah M. Iliyasu, Ahmed S. Salama

引用次数: 0

Implementation of Vision Based UAV Positioning System 基于视觉的无人机定位系统实现

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828975

Zhi-Hua Lin, Bingliang Lu, Jianping Cao, Xindong Zhang

{"title":"Implementation of Vision Based UAV Positioning System","authors":"Zhi-Hua Lin, Bingliang Lu, Jianping Cao, Xindong Zhang","doi":"10.1109/icicse55337.2022.9828975","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828975","url":null,"abstract":"Since the emergence of Unmanned Aerial Vehicle (UAV), UAV has played an irreplaceable role in various fields with its unique advantages, such as flexibility, easy manipulation and low cost. Due to the low navigation accuracy and reliability of traditional inertial navigation, it has gradually been unable to meet the needs of people to perform high-precision flight missions. Moreover, the complex unfamiliar environment and electronic interference pose new challenges to the traditional GPS positioning system. This makes the UAV need to perceive the surrounding environment and make independent decisions with its own sensors in the face of complex and changeable environment, so as to realize accurate positioning and autonomous landing without traditional GPS signals. This paper proposes a solution based on the improved optical flow algorithm. The improved feature point matching algorithm can effectively improve the interference ability of the traditional optical flow algorithm in the face of illumination change noise, and the image segmentation algorithm is used to eliminate the interference of foreground motion noise, To a certain extent, it improves the accurate positioning ability of UAV in the face of complex and changeable environment and no GPS signal, and better improves the real-time performance of the algorithm.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132848737","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

Representation Learning of Knowledge Graph Integrating Entity Description and Language Morphological Structure Information 整合实体描述和语言形态结构信息的知识图表示学习

2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE) Pub Date : 2022-03-18 DOI: 10.1109/icicse55337.2022.9828957

Xiaojuan Du, Yizheng Tao, Gongliang Li

{"title":"Representation Learning of Knowledge Graph Integrating Entity Description and Language Morphological Structure Information","authors":"Xiaojuan Du, Yizheng Tao, Gongliang Li","doi":"10.1109/icicse55337.2022.9828957","DOIUrl":"https://doi.org/10.1109/icicse55337.2022.9828957","url":null,"abstract":"Knowledge graph embedding, which projects the symbolic relations and entities onto low-dimension continuous spaces, is the key to knowledge graph completion. The representation learning methods based on translation, such as TransE, TransH and TransR, only consider the triple information of knowledge graph, and fail to make effective use of other information of entity. To solve these problems, in this paper, we propose a knowledge graph representation learning method which integrates entity description and language morphological structure information to deal with complex relations (i.e. 1-N, N-1 and N-N relations). Firstly, the fastText model which considers affix of words is used to get the embedding of all entity description information. Then, the triple embedding, entity description embedding are spliced to obtain the representation of the final entity embedding. In addition, we propose a new score function-distcos–man, which considers the similarity of entity vector not only from the value of each dimension, but also from the direction of vectors. Experiments show that our method achieves substantial improvements against state-of-the-art baselines, especially the Hit@10s of head entity prediction for N-1 relations and tail entity prediction for 1-N relations improved by about 11.6% and 17.9% on FB15K database respectively.","PeriodicalId":177985,"journal":{"name":"2022 IEEE 2nd International Conference on Information Communication and Software Engineering (ICICSE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133627818","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