发布求助
文献互助 智能选刊 最新文献

2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)最新文献

筛选
英文 中文
Lightweight Detection Network of Trunk Contents 中继内容轻量级检测网络
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498239
Ke Zhang, Dong Yin
{"title":"Lightweight Detection Network of Trunk Contents","authors":"Ke Zhang, Dong Yin","doi":"10.1109/ICAICA52286.2021.9498239","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498239","url":null,"abstract":"During the annual vehicle review, real-time identification of oil-to-gas vehicles is one of the most important contents. Aiming at the characteristics of objects in the trunk of such vehicles, a Trunk-YOLO lightweight real-time detection network is proposed. Firstly, by streamlining the number and structure of CSP modules, and cutting the convolutional layer to perform feature extraction, the cost of feature extraction will be reduced while modifying the activation function. Secondly, a faster K-means algorithm is proposed to perform target candidate frames for the features of the trunk object cluster analysis of numbers. Finally, the YOLO-Head module performs classification and regression, and outputs the prediction results. The method proposed in this paper is tested on the self-made dataset TRUNK-Dataset and compared with the classic lightweight target detection network. The test results show that the network proposed in this paper has achieved good results in detection speed and accuracy.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130427369","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
Bayberry maturity estimation algorithm based on multi-feature fusion 基于多特征融合的杨梅成熟度估计算法
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498084
Huang Kai, Lei Huan, Jiao Zeyu, Huang Tianlun, Chen Zaili, Wang Nan
{"title":"Bayberry maturity estimation algorithm based on multi-feature fusion","authors":"Huang Kai, Lei Huan, Jiao Zeyu, Huang Tianlun, Chen Zaili, Wang Nan","doi":"10.1109/ICAICA52286.2021.9498084","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498084","url":null,"abstract":"The rapid development of smart orchards is conducive to scientific planting and management, the estimation of fruit maturity is the key to harvest in orchards. Nowadays, research on the maturity of bayberry is almost nothing, in order to quickly and accurately estimate the maturity of bayberry in orchards, a bayberry maturity estimation algorithm is proposed based on multi-feature fusion by machine vision. Firstly, considering the local and global texture characteristics of bayberry appearance, bayberry image of texture features were extracted based on GLCM and LBP. Simultaneously the algorithm extracted R, G, B, H and S components based on RGB and HSV color space, the color components were transformed by histogram to obtain the color features of bayberry. Then the color and texture features were fused in series to accurately describe the surface features of bayberry with different maturity. Finally, an SVM-based bayberry maturity estimation model was constructed, the linear kernel function was selected to estimate bayberry maturity based on the sample features. Through experimental verification, the algorithm takes into account the accuracy and real-time performance, the average accuracy rate on the test set reaches 91.2%, and the reasoning time is only 5 ms, which has high practical value.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127845776","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
Semantic segmentation with step-by-step upsampling of the fusion context 语义分割与逐步上采样的融合上下文
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497923
Yanzhao Lu, Huiyi Liu
{"title":"Semantic segmentation with step-by-step upsampling of the fusion context","authors":"Yanzhao Lu, Huiyi Liu","doi":"10.1109/ICAICA52286.2021.9497923","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497923","url":null,"abstract":"The existing semantic segmentation network deelabv3+ has the problem of weak segmentation ability to small-scale target objects and rough edge segmentation. The method of parallel connection of multiple resolution subnets in HRNet network is introduced. After deeplabv3+ down sampling, the network layers of different sizes were fused with features, and the decode side was fused with up sampling step by step to improve the edge segmentation accuracy. Attention mechanism is added before feature fusion to improve the recognition ability of small object. At the end, the edge is refined again by using CRF random vector field. The test is carried out on Pascal VOC 2012, the experimental results show that: the segmentation is more detailed from the image edge details, the recognition of small objects is more accurate, the Pixel Accuracy (PA) and Mean Intersection over Union (MIOU) are improved compared with deeplabv3+.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125402698","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 on Electronic Forensics System of Digital Copier 数字复印机电子取证系统的研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498077
Xue Bing, Zhang Youwei, Zhang Xueyan
{"title":"Research on Electronic Forensics System of Digital Copier","authors":"Xue Bing, Zhang Youwei, Zhang Xueyan","doi":"10.1109/ICAICA52286.2021.9498077","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498077","url":null,"abstract":"The leakage cases of digital photocopiers caused by improper use and supervision bring huge challenge to our country information security. In order to solve the technical problem in the process of copier data forensics, a digital copier electronic forensics system is proposed based on the theory and application of data recovery and electronic data forensics technology. We study the key technologies of data format analysis and information recovery in the data storage of photocopier. The development of electronic forensics system of digital duplicator is realized by using data management technology and .NET development platform, the function of electronic data recovery and forensics of digital copier is realized. Through the experimental analysis of the digital photocopier electronic forensics system, the function feasibility of the system is verified. The digital copier electronic forensics system is applied to the actual inspection and forensics, which has achieved good results in various aspects such as operation convenience and recovery ability.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121106682","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
Performance comparison among the various underwater acousitic positioning algorithms 各种水声定位算法的性能比较
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498138
Bo Guo, Jianye Ma, Juhua Guan
{"title":"Performance comparison among the various underwater acousitic positioning algorithms","authors":"Bo Guo, Jianye Ma, Juhua Guan","doi":"10.1109/ICAICA52286.2021.9498138","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498138","url":null,"abstract":"The selection of the underwater location algorithm is important to various underwater operations. To compare the performance of various underwater acoustic positioning algorithms refined by Extended Kalman filter (EKF) and avoid the blindness and subjectivity in the process of the underwater positioning, seven different underwater acoustic algorithms are a simulated, they are Time of Arrival (TOA), Time Difference of Arrival (TDOA), Angle of Arrival (AOA), and their fusion algorithms. And then, The differences in accuracy, stability and robustness are systematically compared. The results showed that TOA and TDOA fusion positioning algorithm refined by EKF has the best comprehensive performance. The results of this paper help avoid the blindness and subjectivity in selecting positioning algorithms in the underwater positioning.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116217924","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
Cross-Domain Few-Shot Classification through Diversified Feature Transformation Layers 基于多特征变换层的跨域少镜头分类
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498059
Li Yalan, Wu Jijie
{"title":"Cross-Domain Few-Shot Classification through Diversified Feature Transformation Layers","authors":"Li Yalan, Wu Jijie","doi":"10.1109/ICAICA52286.2021.9498059","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498059","url":null,"abstract":"The purpose of the few-shot classification is to classify new categories, and each category contains few labeled samples. The currently popular cross-domain few-shot classification uses a feature transformation layer to transform features to achieve the feature enhancement, so as to simulate various feature distributions in different domains during the training process. However, due to the large differences in the distribution of cross-domain features, a single feature transformation layer cannot perform multiple feature transformations. To obtain the change of the feature distribution in different domains, a diversified feature transformation is proposed based on the original feature transformation layer to solve the metric-based cross-domain few-shot classification problem Simulation results are obtained based on these five datasets commonly used in few-shot classification: mini-ImageNet, CUB, Cars, Places and Plantae. The simulation results show that the proposed diversified feature transformation layer can achieve good results in the metric-based model.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121464831","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
Net Profit Forecast Based on Improved Support Vector Machine 基于改进支持向量机的净利润预测
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497965
Pingwen Xue, Yuan Lei
{"title":"Net Profit Forecast Based on Improved Support Vector Machine","authors":"Pingwen Xue, Yuan Lei","doi":"10.1109/ICAICA52286.2021.9497965","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497965","url":null,"abstract":"Net profit is an essential economic indicator. For the investors, the net profit is the basic factor to get the return on investment. For the managers, the net profit is the basis for making business management decisions. Since this kind of data usually has data noise and more data dimensions, the traditional forecasting methods often produce errors. For such problems this paper uses several models such as support vector machine, combined with the changes of current net profit factors and the historical data of related enterprise net profit, to predict the enterprise net profit. And we use five indicators, mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), to make a relatively comprehensive and objective evaluation of the forecasting ability of the model.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122536991","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 Quality Disturbance Recognition Based on Wavelet Transform and Convolutional Neural Network 基于小波变换和卷积神经网络的电能质量扰动识别
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498060
Wenhui Hong, Ziwen Liu, Xuyan Wu
{"title":"Power Quality Disturbance Recognition Based on Wavelet Transform and Convolutional Neural Network","authors":"Wenhui Hong, Ziwen Liu, Xuyan Wu","doi":"10.1109/ICAICA52286.2021.9498060","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498060","url":null,"abstract":"Power quality (PQ) interference has caused many adverse effects on industry and life. In order to improve the accuracy of power quality disturbance identification, a hybrid detection method based on wavelet transform and convolutional neural network is proposed in this paper, which is for the recognition of power quality disturbance. Wavelet transform can extract the time-frequency domain features of perturbation signals, and convolutional neural network can recognize and classify these features. In order to test the performance of the proposed method, several experiments have been conducted. Firstly, mathematical modelling for seven kinds of power quality disturbances is carried out by this paper. Secondly, identification experiments is processed. Finally, some common methods are used as comparison to experiments. The obtained experimental results reveal that the proposed method has high accuracy and stable performance.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122905609","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
Research on Active Control Strategy of Electric Vehicle Dynamic Charging System Based on Fuzzy PID 基于模糊PID的电动汽车动态充电系统主动控制策略研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498145
Jie Pang, Changhong Zhang, Hao Wang, Haoran Hu, Haoyuan Wang
{"title":"Research on Active Control Strategy of Electric Vehicle Dynamic Charging System Based on Fuzzy PID","authors":"Jie Pang, Changhong Zhang, Hao Wang, Haoran Hu, Haoyuan Wang","doi":"10.1109/ICAICA52286.2021.9498145","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498145","url":null,"abstract":"In this paper, based on the existing problems of electric vehicles, such as short range and long charging time, an electric vehicle dynamic charging system is proposed. In order to ensure the current stability of the system, an active pressure control strategy of carbon skateboard based on fuzzy PID is proposed. Firstly, the mechanism characteristics and working principle of the system are introduced, and the influence of pressure on the performance of the system under electric current is described. Then, according to the working principle, the basic idea of active pressure control of the carbon skateboard is proposed, and the system model of active pressure control is built by using the fuzzy PID active control algorithm using Simulink simulation software. Finally, the stress conditions of carbon skateboard under fuzzy PID, PID and no active control are compared and analyzed, and it is proved that the active control strategy based on fuzzy PID can effectively improve the stability of carbon skateboard under pressure.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131528536","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 Real-time Interactive Multi-Model (RT-IMM) Target Tracking Method 一种实时交互多模型目标跟踪方法
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498215
Luan Zhuzheng, Gu Bing, W. Jinfeng
{"title":"A Real-time Interactive Multi-Model (RT-IMM) Target Tracking Method","authors":"Luan Zhuzheng, Gu Bing, W. Jinfeng","doi":"10.1109/ICAICA52286.2021.9498215","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498215","url":null,"abstract":"The IMM target tracking theory employs the invariant Markov transfer probability matrix and the residual model in the model probability update, which lacks real-time adaptability. In this paper, Bayesian estimation theory is utilized to update the target state distribution by integration with multi-model tracking results, and the model probability of next moment is updated according to the model likelihood function. The likelihood function theory is applied to model probability interactive update, and the current filtering model target state distribution is employed to update the Markov transfer probability matrix among models. The proposed method is compared with conventional IMM method through Monte Carlo simulation. The simulation results show that the accuracy of the proposed method is better than conventional IMM, and it can track the maneuvering targets and fluctuating targets effectively.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133582878","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