发布求助
文献互助 智能选刊 最新文献

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)最新文献

筛选
英文 中文
Multi-band discriminant speech synthesis analysis based on Natural Language Processing 基于自然语言处理的多波段判别语音合成分析
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778506
Songjia Liu, Yuancheng Yao, Binyu Liu, Rui Zhu, Jing Ren
{"title":"Multi-band discriminant speech synthesis analysis based on Natural Language Processing","authors":"Songjia Liu, Yuancheng Yao, Binyu Liu, Rui Zhu, Jing Ren","doi":"10.1109/ICSP54964.2022.9778506","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778506","url":null,"abstract":"With the rapid development of neural networks and deep learning, speech synthesis technology has been significantly improved. The end-to-end speech synthesis systems based on deep learning have been able to synthesize speech with naturalness close to the original human pronunciation. However, the existing end-to-end speech synthesis system model is complex, and it is impossible to achieve real-time speech synthesis on devices with low computing power. In this paper, a multi-band discriminative autoregressive speech synthesis model is proposed based on natural language processing. The model uses an encoder-decoder architecture with attention mechanism, which is mainly composed of DSC-GRN modules. Stacking multiple convolutions with different expansion coefficients by gating the residual structure can increase the receptive field so that the encoder and decoder can pay attention to the context information with a longer time span, which can improve the performance of the model. The whole model uses full convolution architecture and can be trained in parallel. Compared with the existing autoregressive model, the number of parameters of the model is greatly reduced. The synthesis speed is improved, and the quality of synthesized speech is ensured.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"265 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120985888","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
Boston house price prediction: machine learning 波士顿房价预测:机器学习
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778372
Songyi Bai
{"title":"Boston house price prediction: machine learning","authors":"Songyi Bai","doi":"10.1109/ICSP54964.2022.9778372","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778372","url":null,"abstract":"The Boston housing problem has been studied by many data scientists for over 50 years. The problem is proven to be extremely profitable, and it is considered as one of the most classical machine learning problems. Using machine learning techniques, computer scientists have already reduced the error of their estimation to around 4%. To solve this problem, computer scientists have developed a number of machine learning algorithms in recent years. Some are simple, while others are more complex; some offer a rough estimate of house value, while others offer more precise estimates In this essay we will see how they approach the problem using machine learning regression methods.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126901177","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
Infrared and Visible Missile-borne Image Fusion Based on Structural Information 基于结构信息的弹载红外与可见光图像融合
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778796
Song Xue, Hang Zhang, Chaoyi Chen, Chuandong Yang
{"title":"Infrared and Visible Missile-borne Image Fusion Based on Structural Information","authors":"Song Xue, Hang Zhang, Chaoyi Chen, Chuandong Yang","doi":"10.1109/ICSP54964.2022.9778796","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778796","url":null,"abstract":"This paper proposed a structure based infrared visible light missile borne image fusion method. The method uses the idea of structural patch decomposition to decompose the image block into three components: signal strength, mean intensity and signal structure. The Laplace pyramid is used to decompose the signal structure component into low frequency band and high frequency band. Different methods are used to calculate the recovered signal structure. Finally, the fusion of image structure block decomposition is transformed into the final fusion image based on mean filtering. The fusion experiment is carried out by using the simulated missile-borne infrared and visible images, and the experimental results are evaluated subjectively and objectively. The experimental results show that the proposed method is superior to some classical fusion methods in subjective and objective assessment, and can obtain better fusion effect. The algorithm has high effectiveness and stability, and can be applied to real-time fusion tasks to a certain extent.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126917265","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
Research on the Direction Determination of the Drill Bit Based on the Beamforming Algorithm under the Line Array 线阵下基于波束形成算法的钻头方向确定研究
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778771
Kai Feng, R. Fu, Wanxiang Lou, Jiaxu Chen
{"title":"Research on the Direction Determination of the Drill Bit Based on the Beamforming Algorithm under the Line Array","authors":"Kai Feng, R. Fu, Wanxiang Lou, Jiaxu Chen","doi":"10.1109/ICSP54964.2022.9778771","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778771","url":null,"abstract":"The problem of collision prevention and obstacle bypass between wells often occurs with the application of cluster well technology. In order to obtain the drilling direction of the drill bit in real time, it is avoided that the operation safety of offshore cluster wells is affected by the excessive deviation between the drilling direction and the preset direction. Based on the beamforming algorithm, this paper proposes a theoretical model of direction determination of the drill bit by using a line array sensor. The model collects the vibration signal of the drill bit into the formation through a line array formed by multiple acceleration sensors. Obtain the directivity function values at different angles through signal processing algorithms such as beamforming to estimate the direction of the drill bit. This paper designs and carries out a simulation verification test The results show that the bit direction determination model can effectively predict the bit direction and improve the safety of offshore cluster well operations.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"498 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127223682","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
Power Spectral Density Features for Classifying Action Intention Understanding EEG Signals 动作意图分类与脑电信号理解的功率谱密度特征
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778810
Xingliang Xiong, S. Ge, Haixian Wang, Xue-song Lu
{"title":"Power Spectral Density Features for Classifying Action Intention Understanding EEG Signals","authors":"Xingliang Xiong, S. Ge, Haixian Wang, Xue-song Lu","doi":"10.1109/ICSP54964.2022.9778810","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778810","url":null,"abstract":"Background: Classification of action intention understanding is extremely important for social interaction and brain-computer interface (BCI). However, it is very difficult to obtain a satisfactory experimental result. Method: This study first extracts power spectral density (PSD) features based on preprocessed EEG signals, and then selects the effective features by statistical thresholds. Results: Under different combining conditions from three pairwise action intention stimuli and five frequency bands, some electrodes show manifest statistical differences, as well as most of subjects obtain high average classification accuracies. Conclusions: The PSD features selected with statistical thresholds are exceedingly useful for the classification task of action intention understanding EEG signals.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"os-46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127788008","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: 2
Comparison of different machine learning algorithms on Cell Classification with scRNA-seq after Principal Component Analysis 主成分分析后不同机器学习算法与scRNA-seq细胞分类的比较
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778439
Jingkai Guo, Jing Gao
{"title":"Comparison of different machine learning algorithms on Cell Classification with scRNA-seq after Principal Component Analysis","authors":"Jingkai Guo, Jing Gao","doi":"10.1109/ICSP54964.2022.9778439","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778439","url":null,"abstract":"This project did the process of the Single-cell RNA sequencing data (scRNA-seq) to predict the cell type. Researchers iterated the currently commonly used machine learning algorithm to form predict training models from an extensive dataset. To begin with, researchers executed the principal component analysis (PCA) to reduce the dataset sample dimension. Furthermore, four other different algorithms were constructed in this classification process in each iteration: logistic regression (LR), k nearest neighbor (kNN), supporting vector machine (SVM). In addition, this work applied boosting methods to the decision tree algorithm. Finally, the best approach for listing testing models above is the PCA for dimensional reduction and logistic regression as the classifier. The accuracy is 54.4% for testing data.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128754237","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
Image segmentation of persimmon leaf diseases based on UNet 基于UNet的柿叶病害图像分割
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778390
Zhida Jia, Aiju Shi, Guangkuo Xie, Shaomin Mu
{"title":"Image segmentation of persimmon leaf diseases based on UNet","authors":"Zhida Jia, Aiju Shi, Guangkuo Xie, Shaomin Mu","doi":"10.1109/ICSP54964.2022.9778390","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778390","url":null,"abstract":"The size and shape of lesion area of persimmon diseases will vary with the occurrence period and degree. CNN has fixed receptive field when extracting persimmon disease features, which can not adapt to the geometric changes of disease spots, resulting in incomplete disease feature extraction and reducing the segmentation accuracy of persimmon disease images. Deformable convolution can dynamically adjust the size of the receptive field according to the input features, and automatically adapt to the geometric deformation of the lesion. This paper proposes a UNet based on self-attention mechanism and deformable convolution for image segmentation of persimmon leaf disease. With UNet as the basic network, the standard convolution in the down-sampling stage of UNet is replaced by deformable convolution to extract more abundant features, and the self-attention mechanism is used to learn the relationship between the various features to obtain more spatial information and context information. The experimental results show that the mPA and the mIoU of the proposed algorithm are 89.18 % and 83.58 %, its segmentation effect is better than UNet.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127424780","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
Application of Support Vector Machine Based on Particle Swarm Optimization in Classification and Prediction of Heart Disease 基于粒子群优化的支持向量机在心脏病分类与预测中的应用
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778616
Tian Xue, Zhao Jieru
{"title":"Application of Support Vector Machine Based on Particle Swarm Optimization in Classification and Prediction of Heart Disease","authors":"Tian Xue, Zhao Jieru","doi":"10.1109/ICSP54964.2022.9778616","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778616","url":null,"abstract":"This heart disease is the number one killer of Chinese residents' health. Early detection of heart disease and timely treatment are of great significance to every heart disease patient. In this article, by mining the physical index data of patients with heart disease, aiming at the problem that the optimal parameters in the traditional support vector machine model are difficult to find, particle swarm optimization is used to optimize, and a classification prediction model of heart disease based on particle swarm optimization support vector machine is established. The experimental results show that compared with the traditional support vector machine model, the optimized model improves the prediction accuracy by 1.33%, and also shortens the model training time, which helps to improve the diagnosis efficiency of heart disease.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132676395","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
Research progress and trend analysis of object tracking technology based on CiteSpace 基于CiteSpace的目标跟踪技术研究进展及趋势分析
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778337
Liang Yu
{"title":"Research progress and trend analysis of object tracking technology based on CiteSpace","authors":"Liang Yu","doi":"10.1109/ICSP54964.2022.9778337","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778337","url":null,"abstract":"Object tracking technology is an important research direction in the field of computer vision, and nowadays, it has played an increasingly indispensable role in the fields of intelligent surveillance, modern military, human-computer interaction, intelligent transportation, etc. While making breakthroughs, it has also brought great convenience to people’s lives. In this paper, CiteSpace information visualization software is used to visualize the object tracking research literature based on nearly 10,000 papers in the field of object tracking from 2001 to 2021. From the bibliometric perspective, the visual knowledge graphs of information on three aspects of object tracking technology: scientific cooperation, research fields, and recent progress are analyzed, in which the analysis of scientific cooperation includes the distribution of countries and institutions, the analysis of research fields includes the distribution of categories and keywords, and the analysis of recent progress and frontiers includes the distribution of references and the analysis of keyword timeline graph. Then, we present the three main problems and challenges facing this technology: changes of illumination and color, changes of scene and posture, and the distinction between foreground and background. And three targeted suggestions are proposed for feature fusion, 3D reconstruction, and deeper development based on Siamese Network in deep learning algorithms. Finally, the future development of object tracking technology has been prospected.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114889631","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
Multi-head Mutual Self-attention Generative Adversarial Network for Texture Synthesis 纹理合成的多头相互自关注生成对抗网络
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778480
Shasha Xie, Wenhua Qian
{"title":"Multi-head Mutual Self-attention Generative Adversarial Network for Texture Synthesis","authors":"Shasha Xie, Wenhua Qian","doi":"10.1109/ICSP54964.2022.9778480","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778480","url":null,"abstract":"Example-based texture synthesis requires synthesizing textures that are as similar as possible to the exemplar. However, for complex texture patterns, the existing methods lead to wrong synthesis results due to insufficient feature extraction capabilities. To address this problem, this paper proposed an optimized generative adversarial network model to address the quality issues such as low resolution and insufficient detail in texture synthesis. To this end, we propose a new multi-head mutual self-attention (MHMSA) mechanism. Different from the self-attention, MHMSA is to model the mutual relationship of each position in the feature space, and clues from all feature positions can be used to generate details. Therefore, embedding the MHMSA into the generator can help to improve its ability to extract detailed features and global features. Experimental results show that the proposed model significantly improves the visual quality of texture synthesis images, and demonstrates that MHMSA outperforms self-attention in the image generation task.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133517692","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
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信