发布求助
文献互助 智能选刊 最新文献

2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)最新文献

筛选
英文 中文
Research of curve fitting method combined with LPR based on attention mechanism 基于注意机制的LPR与曲线拟合方法研究
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9987894
Na Song, Shanhong Zheng, Wanlong Li, Shaocong Yu
{"title":"Research of curve fitting method combined with LPR based on attention mechanism","authors":"Na Song, Shanhong Zheng, Wanlong Li, Shaocong Yu","doi":"10.1109/ICDSCA56264.2022.9987894","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9987894","url":null,"abstract":"With the continuous deepening of interest rate market reform, how to break through the blockage of market interest rate transmission to loan interest rates has become a new challenge for fund transfer pricing. A single combination of loan interest rates and market interest rates tends to ignore their respective problems. At present, LPR interest rates are difficult to form a good interaction with policy interest rates. At the same time, the high volatility of market interest rates cannot adapt to the cost of deposits and loans. Therefore, we eliminates the high volatility peaks of market interest rates, and integrates market interest rates and LPR interest rates through a neural network model to construct an internal fund transfer pricing benchmark curve. Commercial banks can make adjustments based on their own development needs and give full play to the role of FTP in the transmission of interest rates.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128823527","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
Few-shot Medical Image Classification with MAML Based on Dice Loss 基于骰子损失的MAML少镜头医学图像分类
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988390
Ce Zhang, Qingshan Cui, Shaolong Ren
{"title":"Few-shot Medical Image Classification with MAML Based on Dice Loss","authors":"Ce Zhang, Qingshan Cui, Shaolong Ren","doi":"10.1109/ICDSCA56264.2022.9988390","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988390","url":null,"abstract":"In medical image processing based on deep learning, medical image datasets are usually few-shot and unbalanced between classes. This will cause the model to overfit and be biased towards the class with more samples during training and the accuracy of the class with fewer samples will decrease. As a result, the overall accuracy will also decrease. To address these issues, the model-agnostic meta-learning based on dice loss is proposed. The algorithm avoids the need for a large amount of data to be driven and can quickly adapt to new tasks with only a small amount of labeled data. Meanwhile, the objective function can be optimized autonomously in the direction of a small number of classes during training. Finally, good results are achieved on two few-shot datasets of medical images. Our method can provide a solution to achieve good results with less data cost in medical image processing.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131872266","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
Deep Neural Networks for Detecting Hate Speech 用于检测仇恨言论的深度神经网络
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988324
Jianfeng Wang
{"title":"Deep Neural Networks for Detecting Hate Speech","authors":"Jianfeng Wang","doi":"10.1109/ICDSCA56264.2022.9988324","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988324","url":null,"abstract":"With increased social media activity, hate speech on the Internet has become increasingly prevalent. It is a hazardous and damaging form of internet content that targets a group or individual based on their religion, race, or sexual orientation. As a result, it has garnered increasing attention from researchers. This article will examine current research trends, data sources, and methodologies and recommend future study directions. The subject of hate speech was determined at the start of 2020, and it includes attacks on minorities, religion, women, the general election agenda, and politics. Individuals have experimented with various methodologies and models and discovered several characteristics that fulfill the exclusion requirements. However, these methodologies and features do not imply that they will perform well in detecting hatred. The data collection, selected features, number of categories, and mutually exclusive categories all significantly impact the classification performance of hate speech.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"303 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124284417","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
Simulation of Industrial Robot and Automatic Production Conveyor Based on RobotStudio 基于RobotStudio的工业机器人与自动生产输送机仿真
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9987762
Xiaohong Zhang, Bo Luo
{"title":"Simulation of Industrial Robot and Automatic Production Conveyor Based on RobotStudio","authors":"Xiaohong Zhang, Bo Luo","doi":"10.1109/ICDSCA56264.2022.9987762","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9987762","url":null,"abstract":"The main content of this paper is to use Robtostudio Software to realize the simulation of a Pallet Assembly Conveyor. It mainly uses the functions of Smart components in Robotstudio software to create multiple sub-components such as: Attacher, Detacher, Source, Sensor and so on, to realize the movement of conveyor and the robot's Attacher and Detacher. In this paper, three robot systems are created to realize the cyclic tasks of Pallet Assembly Conveyor by creating station logic between robot systems.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124427775","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
Exploration of a New Active Noise Cancellation Headset Based on Spectral Contrast Enhancement Technique 基于光谱对比度增强技术的新型有源降噪耳机的探索
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988562
Renjie Qu
{"title":"Exploration of a New Active Noise Cancellation Headset Based on Spectral Contrast Enhancement Technique","authors":"Renjie Qu","doi":"10.1109/ICDSCA56264.2022.9988562","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988562","url":null,"abstract":"The purpose of this project is to provide a new and more cost-effective Active Noise Cancellation headset for hearing impaired patients for improving speech recognition. This project mainly adopts the Active Noise Cancellation technique based on the LMS algorithm and the spectral contrast enhancement technique of sound. After comparing the commercially available Active Noise Cancellation techniques and spectral contrast enhancement techniques, the algorithms in this project were selected according to the needs and limitations of realistic signal processing components. Also, SSCE is used as the base algorithm of the spectral contrast technique, and FxLMS and NLMS are used as the base algorithm of the Active Noise Cancellation technique, respectively, and improvements and optimizations are made on this basis. Finally, this topic is based on the MATLAB SIMULINKF simulation platform to design computer simulation experiments, and the performance of the algorithm is measured empirically. The results show that Active Noise Cancellation can effectively reduce the random noise of non-human voices in the audio, enhance the signal-to-noise ratio of the original audio, and provide a basis for the signal enhancement of spectral contrast enhancement techniques in specific human voice bands when tested offline. However, the Active Noise Cancellation system or spectral enhancement techniques both will cause a certain distortion of the audio signal. The distortion of the signal can only be mitigated to a certain extent by the modeling of the propagation channel and can not be well improved.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116016117","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
Simulation and analysis of GFDM system performance GFDM系统性能仿真与分析
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988036
Xuemei Li, Xiangning Chen, Yang Li
{"title":"Simulation and analysis of GFDM system performance","authors":"Xuemei Li, Xiangning Chen, Yang Li","doi":"10.1109/ICDSCA56264.2022.9988036","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988036","url":null,"abstract":"5G has the outstanding characteristics of high speed, low latency and large connection and has diversified application scenarios. 5G takes spectrum efficiency, non-orthogonal access, coexistence of multiple services and other factors into account. So, it is necessary to reduce out-of-band radiation as much as possible and reduce interference to adjacent frequency bands. In view of the above requirements, GFDM stands out among 5G candidate waveforms with its flexibility. Therefore, this paper will introduce the modulation and demodulation principle of GFDM and analyze the performance of GFDM system through MATLAB simulation, such as out-of-band radiation, PAPR, self-interference and explain in detail the influence of different parameter settings on GFDM related performance as well as the performance comparison with OFDM in these aspects.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116265612","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 Impact of Geometry on the Absorber Using Finite Difference Time Domain and Simulation Analysis 利用时域有限差分和仿真分析研究几何形状对吸波器的影响
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988107
Beining Ding
{"title":"Research on the Impact of Geometry on the Absorber Using Finite Difference Time Domain and Simulation Analysis","authors":"Beining Ding","doi":"10.1109/ICDSCA56264.2022.9988107","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988107","url":null,"abstract":"Absorbers made of traditional materials are mainly aimed at strong absorption. Usually, they have shortcomings such as large structure size, fixed absorption frequency, low absorption rate per unit thickness, and untunable operating frequency. Through artificially engineered microstructures, metamaterials can acquire exotic but very useful dynamic material properties, thereby enhancing the absorption efficiency of absorbers. This paper investigates the effect of material and geometry on the absorption characteristics of the absorber. The overall shape of the absorber is a laminated structure composed of gold as the substrate, silicon dioxide and silicon alternately superimposed, and the upper and lower surfaces of the top silicon are covered with graphene to achieve broadband absorption in the visible light band. Using Finite Difference Time Domain(FDTD) to carry out simulation analysis, the results show that under the same structure, under the dual influence of geometric shape and material properties, adding graphene coating to the square structure can improve the absorption rate of the model, but circular structure is not sensitive to the number of graphene layers, Under the same material, the square structure model has better absorption characteristics than the circular structure model.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123596967","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 security platform based on cloud edge combined with machine vision 基于云边缘与机器视觉相结合的安全平台设计
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988609
Yao Li, Congshi Han, Hongkui Xu, Bo Zhou, Fangcun Li, S. Zhou, Minghao Zheng, Zhiwen Kang
{"title":"Design of security platform based on cloud edge combined with machine vision","authors":"Yao Li, Congshi Han, Hongkui Xu, Bo Zhou, Fangcun Li, S. Zhou, Minghao Zheng, Zhiwen Kang","doi":"10.1109/ICDSCA56264.2022.9988609","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988609","url":null,"abstract":"Aiming at the problems of high delay, high bandwidth and low scalability of traditional security system based on deep learning, an extensible security platform design with edge side real-time reasoning is proposed to save bandwidth and computing resources. The design is based on smart chip technology and lightweight deep learning framework, design the fast inference and edge cloud training, intelligence analysis, management, system architecture, using the image optimization technology and large data distributed storage technology, to realize mass storage, video and image data effectively and efficiently design based on micro service business architecture, Service requirements such as monitoring scale expansion and personalized analysis are met. Experimental results show that the platform can significantly reduce intelligent reasoning delay, bandwidth and resource cost, and has scalability and practicability suitable for promotiont.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"56 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121889130","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
Machine vision-based information collection system for collector coin grading boxes 基于机器视觉的钱币分级箱信息采集系统
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9988681
Jingxian Hou, Congpeng Zhang
{"title":"Machine vision-based information collection system for collector coin grading boxes","authors":"Jingxian Hou, Congpeng Zhang","doi":"10.1109/ICDSCA56264.2022.9988681","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9988681","url":null,"abstract":"With the goal of automating the information system acquisition of collector coin grading boxes, this paper designs a vision-based grading box target acquisition robot platform. For the problem of information extraction of grading box images, a character recognition algorithm based on watershed area segmentation is proposed to improve the recognition accuracy of sticky characters, and an information acquisition robot application software is developed. The experimental and application results show that the image acquisition of the collector coin grading box information acquisition system is clear and the character information recognition rate reaches 1000%, which realizes the efficient and fully automated information acquisition of the collector coin grading box information acquisition system.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116802839","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
Cluster-Then-Label Strategy for Sleep Detection U sing Electroencephalogram (EEG) 基于脑电图的聚类-标记睡眠检测策略
2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) Pub Date : 2022-10-28 DOI: 10.1109/ICDSCA56264.2022.9987802
Yifan Guo, Helen X. Mao, Jijun Yin, Z.-H. Mao
{"title":"Cluster-Then-Label Strategy for Sleep Detection U sing Electroencephalogram (EEG)","authors":"Yifan Guo, Helen X. Mao, Jijun Yin, Z.-H. Mao","doi":"10.1109/ICDSCA56264.2022.9987802","DOIUrl":"https://doi.org/10.1109/ICDSCA56264.2022.9987802","url":null,"abstract":"Data deficiency has long been a major obstacle for many areas of machine learning. Manually labeling data could be utterly time-consuming and expensive, especially in medical fields including the sleep research. To address this challenge, we propose a cluster-then-label strategy, which inserts clustering algorithms into traditional supervised learning pipelines. In this paper, we demonstrate the cluster-then-label strategy for sleep detection using electroencephalogram (EEG) data and show that our proposed strategy can boost the classifier's performance on previously unseen subjects. We also developed a method based on nonlinear transformations that can reshape the feature distributions to resemble normal distributions with which the cluster-then-label algorithm becomes more efficient and robust.","PeriodicalId":416983,"journal":{"name":"2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123999686","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
首页 上一页 下一页 尾页
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