发布求助
文献互助 智能选刊 最新文献

2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)最新文献

筛选
英文 中文
Application of Smart Service Robot Path Planning Based on Improved A* Algorithm 基于改进A*算法的智能服务机器人路径规划应用
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688814
Xiaoyi Yuan
{"title":"Application of Smart Service Robot Path Planning Based on Improved A* Algorithm","authors":"Xiaoyi Yuan","doi":"10.1109/TOCS53301.2021.9688814","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688814","url":null,"abstract":"Aiming at the problems of long time-consuming path planning and low node search efficiency when the exhibition hall service robots autonomously pick up and deliver items, a global path planning improved A* algorithm is proposed, which adds location information of the service robot on the basis of the traditional evaluation function. Contains the weight function of the cost function and heuristic function; in view of the low efficiency of A* algorithm node search, it is proposed to determine the quadrant where the target is located, and at the same time only perform the depth-first expansion search to the quadrant where the target is located, thereby ignoring other unnecessary quadrants; This paper uses Bezier curve to smooth the planned path, so that the smoothed path is closer to the actual motion path. The experimental results show that the average path length obtained by the improved A* algorithm path planning scheme is 5.34% less than the traditional A* algorithm, and the average time required is reduced by 22.56%. While ensuring the optimal path, it can improve the efficiency of service robot path planning and make the driving trajectory Smoother.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128788148","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 literature cognitive strategy model by big data and statistical analysis 基于大数据和统计分析的文献认知策略模型研究
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688783
Wang Qian, Lin Mingzu
{"title":"Research on literature cognitive strategy model by big data and statistical analysis","authors":"Wang Qian, Lin Mingzu","doi":"10.1109/TOCS53301.2021.9688783","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688783","url":null,"abstract":"In recent years, with the deepening of English teaching reform and the cultivation of English thinking ability, the application of English cross-cultural communication ability has gradually become the most important task and goal in English teaching. The purpose of this paper is to analyze the current situation of English literature by using big data combined with the current social background, and then make a targeted study on the cognitive strategies of English literature. This paper mainly through consulting the relevant literature at home and abroad and using the observation and comparison method to carry out the experiment, so as to achieve our experimental goal – to study the cognitive strategies of English literature based on the background of big data, so as to improve the cognitive strategies of English literature in Colleges and universities. The experimental results show that big data can effectively carry out the research on the thinking teaching mode of English literature reading and follow the research progress at home and abroad at any time.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129041651","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 Learning Named Entity Recognition of Pressure Sensor Patent Text Based on MLM 基于MLM的压力传感器专利文本小样本学习命名实体识别
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688929
Yue Deng, Honghui Li, Xueliang Fu
{"title":"Few-shot Learning Named Entity Recognition of Pressure Sensor Patent Text Based on MLM","authors":"Yue Deng, Honghui Li, Xueliang Fu","doi":"10.1109/TOCS53301.2021.9688929","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688929","url":null,"abstract":"Abstract of patent text, as an important support for intellectual property protection, is an ideal data source for technology mining. Named entity recognition of patent text can reduce the workload of patent analysis, improve work efficiency, and provide effective technical means for patent discovery, patent promotion, patent infringement and other aspects. However, the technical terms of patent texts are difficult to be mined, extracted and labeled. Therefore, this paper proposes a few-shot learning named entity recognition method to solve the problem that the named entity recognition of pressure sensor patent text lacks sufficient annotation data.This method uses MLM (Masked Language Model) pretraining method of BERT Model, selects a small part of token to mask each time, and then repeatedly trains on the same sample, finally obtains the training embedding of bidirectional fusion information on massive continuous corpus. Then the CRF layer is used to decode and finally the prediction tag sequence is obtained. Experiments on 55 patent abstracts and 34 patent abstracts in the field of pressure sensor preparation, the simulation results show that the proposed method can improve the recognition accuracy by about 10% compared with the traditional machine learning model (HMM, CRF) in the case of small samples. Compared with the deep learning model (BI-LSTM and BiLSTM+CRF), the accuracy of the model is improved by about 30%, and the accuracy of the model is 93%.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123308549","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
A Noisy Image Segmentation Method Based on Improved Active Contour Model 一种基于改进活动轮廓模型的噪声图像分割方法
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688905
Yinlong Wang, Zhongchun Wang, Z. Xie
{"title":"A Noisy Image Segmentation Method Based on Improved Active Contour Model","authors":"Yinlong Wang, Zhongchun Wang, Z. Xie","doi":"10.1109/TOCS53301.2021.9688905","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688905","url":null,"abstract":"Using active contour model to segment image is a classical image segmentation method. But the effect of this method is not good. The current active contour model is sensitive to noise, and it is difficult to achieve accurate segmentation of weak boundary image. This paper proposes an image segmentation algorithm based on gradient vector flow active contour model. Firstly, the wavelet transform is used to process the segmented image to solve the interference of noise on image segmentation. Then, the gradient vector flow active contour model is used to segment the denoised image to fit the contour curve evolution process of different regions in the image, so as to realize the segmentation of different regions. Compared with other current image segmentation algorithms, the simulation results show that the gradient vector flow active contour model can segment the image with high accuracy, and the segmentation time is greatly reduced, and the anti-noise ability is improved. The overall performance of the algorithm is obviously better than other image segmentation algorithms.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121149102","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 and Application of Business English Sand Table Simulation Training Course in Secondary Vocational School Based on Machine Learning 基于机器学习的中职商务英语沙盘模拟实训课程设计与应用
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688789
Jie Song
{"title":"Design and Application of Business English Sand Table Simulation Training Course in Secondary Vocational School Based on Machine Learning","authors":"Jie Song","doi":"10.1109/TOCS53301.2021.9688789","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688789","url":null,"abstract":"Sand table training teaching for English majors truly embodies the characteristics of combining theory with practice, and also enables students to truly apply what they have learned and improve their practical ability and practical skills. At present, all secondary vocational schools aim at cultivating high-quality compound applied talents to meet the needs of the society, and pay special attention to the cultivation of students’ professional skills and professional abilities. Based on machine learning, this paper designs the sand table simulation training course of business English in secondary vocational schools, and establishes an English vocabulary self-adaptive learning model that realizes machine learning algorithm. The solution process of the model refers to the self-adaptive test process based on item response theory. This model can continuously iterate the fitness until it is stable, and finally push out the learning content that suits him. Sand table training teaching has the characteristics of short-term intensive training and strong practical operation, which can help students transform the business knowledge in textbooks into flexible business operations.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114324219","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
A Study of Intelligent Rehabilitation Robot Imitation of Human Behavior Based on Kinect 基于Kinect的智能康复机器人仿人行为研究
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688921
Xing Pan, Quan Liu, Fengkai Luan, Kun Chen, Qingsong Ai
{"title":"A Study of Intelligent Rehabilitation Robot Imitation of Human Behavior Based on Kinect","authors":"Xing Pan, Quan Liu, Fengkai Luan, Kun Chen, Qingsong Ai","doi":"10.1109/TOCS53301.2021.9688921","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688921","url":null,"abstract":"In recent years, the number of stroke patients has gradually increased, and the serious imbalance between the number of rehabilitation physicians and patients has led to a large number of patients unable to perform the necessary rehabilitation training, which affects the rehabilitation effect of patients. The emergence of medical rehabilitation robots on the basis of existing robots. The integration of the teaching strategy can effectively reduce the workload of rehabilitation physicians, while the existing teaching rehabilitation robots use less visual fusion, and the manipulation method is complicated and cumbersome. In response to the above situation, this paper proposes a Kinect camera-based rehabilitation robot schematic behavior recognition method to realize the task of using machine vision to perceive the trajectory of the rehabilitation physician’s schematic teaching task to the patient and map it onto the rehabilitation robot.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116240120","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 smart synthetic speech answer-sheet system based on deep neural network and CR-DNN 基于深度神经网络和CR-DNN的智能合成语音答题系统设计
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688761
Qingzhu Wu, Shaowei Xiong, Zhengyu Zhu
{"title":"Design of smart synthetic speech answer-sheet system based on deep neural network and CR-DNN","authors":"Qingzhu Wu, Shaowei Xiong, Zhengyu Zhu","doi":"10.1109/TOCS53301.2021.9688761","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688761","url":null,"abstract":"Inspired by the success of utterance-based neural networks in deep feature extraction, in this study we propose the idea of classification- and regression-based deep neural network (CR-DNN) for detection of synthetic speech answer-sheet on intelligent oral English language learning app. In which, CR-DNN is composed of several classification-based and regression-based DNNs and every DNN can be seen as a block. Furthermore, the deep feature is extracted by CR-DNN firstly and then used for the input of detection system. The experimental results show that the deep feature extracted from CR-DNN can give good performance.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"76 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116290149","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 Intelligent Logistics Car Based on MCU 基于单片机的智能物流车设计
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688821
Y. Gong, P. Zhang
{"title":"Design of Intelligent Logistics Car Based on MCU","authors":"Y. Gong, P. Zhang","doi":"10.1109/TOCS53301.2021.9688821","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688821","url":null,"abstract":"With the development of the express delivery and logistics industry, people have put forward higher requirements for logistics. At the same time, science and technology are also constantly developing and progressing. Human beings are in an era of intelligence. Therefore, science and technology are applied to logistics vehicles. In the research, this article researched and designed an intelligent logistics car based on a single chip microcomputer. The specific hardware design includes the minimum system of the single chip microcomputer (the minimum system includes the single chip microcomputer chip, power module, crystal oscillator module, reset circuit module, etc.) System operation module), black tracking module, liquid crystal display module, motor drive module. Finally, through the actual debugging of the intelligent logistics trolley system, the function of the intelligent logistics trolley from tracking and identifying the target task to grasping logistics and transporting to the designated location is realized. It reflects the development trend of the logistics industry from automation to intelligence.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114837446","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 and Experiment on Key Technologies of Endoscopic Sweep Frequency OCT System 内镜扫描频率OCT系统关键技术研究与实验
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688680
Jing Lyu, Lin Ren, Qi Liu, Yan Wang, Yuguo Tang, Min Li
{"title":"Research and Experiment on Key Technologies of Endoscopic Sweep Frequency OCT System","authors":"Jing Lyu, Lin Ren, Qi Liu, Yan Wang, Yuguo Tang, Min Li","doi":"10.1109/TOCS53301.2021.9688680","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688680","url":null,"abstract":"In this paper, a high-speed swept frequency laser light source is used, combined with FPGA and GPU acceleration technology to design a high-speed endoscopic Swept-source optical coherence tomography (SS-OCT) system. Several key parameters that affect the performance of the system are tested. The results show that the system’s imaging depth is 4. 5mm, imaging resolution is $7.3mu mathrm{m}$, and system sensitivity is 110dB in air. The image of finger tissue is stable and the structure is clear. When the rotation speed reaches 9000RPM, the real-time frame rate of the system can reach 141 frames per second.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123996994","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
Data Analysis and Soybean Price Intelligent Prediction Model Based on LSTM Neural Network 基于LSTM神经网络的大豆价格智能预测模型及数据分析
2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) Pub Date : 2021-12-10 DOI: 10.1109/TOCS53301.2021.9688705
Zhang Yu
{"title":"Data Analysis and Soybean Price Intelligent Prediction Model Based on LSTM Neural Network","authors":"Zhang Yu","doi":"10.1109/TOCS53301.2021.9688705","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688705","url":null,"abstract":"To improve the application of the machine learning algorithm in the agricultural product price prediction, the LSTM model predicts the daily closing price of the soybean products futures. By the values of MAPE and the R2, LSTM Neural Network model has good prediction accuracy and high prediction effect on the futures price of soybean products. Therefore, the LSTM neural network has excellent generalization capabilities in futures prediction.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126511213","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 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