发布求助
文献互助 智能选刊 最新文献

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)最新文献

筛选
英文 中文
Research on Intelligent Video Analysis Technology in Smart Campus Security Scenario 智慧校园安防场景下的智能视频分析技术研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731339
Weitao Wan
{"title":"Research on Intelligent Video Analysis Technology in Smart Campus Security Scenario","authors":"Weitao Wan","doi":"10.1109/acait53529.2021.9731339","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731339","url":null,"abstract":"The core of smart campus is security. In order to explore the application effect of intelligent video analysis technology in different security scenarios, this study has carried out research and experiments on the improved smoke detection algorithm based on optical flow and the personnel detection algorithm based on SVM. The results show that the improved smoke detection algorithm based on optical flow has high recall rate and can achieve efficient smoke detection in different application scenarios; the efficiency of the SVM-based personnel detection algorithm is significantly higher than other feature recognition algorithms, with a detection rate of 94.38%. Therefore, it shows that in the smart campus security scenario, the two algorithms proposed in this study have good application effects and are worth promoting vigorously.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131082907","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
Robust Sparse Transfer Learning for Image Classification 鲁棒稀疏迁移学习用于图像分类
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731184
Yuwu Lu, Wenjing Wang, Zhihui Lai
{"title":"Robust Sparse Transfer Learning for Image Classification","authors":"Yuwu Lu, Wenjing Wang, Zhihui Lai","doi":"10.1109/acait53529.2021.9731184","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731184","url":null,"abstract":"Transfer learning aims to transfer the knowledge learned from the source to the target data. However, noise-corrupted target data may limit the transfer learning capability. Thus, removing the noise in the data is essential to improve transfer learning performance. This paper proposes robust sparse transfer learning (RSTL) to improve the robustness of transfer learning. The RSTL uses noise-removed target domain data for project learning, where the employed nuclear norm ensures that the clean data matrix and the coefficient matrix are low-rank. The L norm is also adopted to ensure the sparsity of the target domain noise. Further, a reconstructive term is used, which aims to learn a reconstruction coefficient matrix. Extensive experimental evaluations on four datasets verify the promising ability of the proposed method compared with the other methods.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125086698","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
An Improved Dragonfly Optimization Algorithm for Solving Numerical and Three-bar Truss Optimization Problems 求解数值及三杆桁架优化问题的改进蜻蜓优化算法
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731344
Feng Min, Huajuan Huang
{"title":"An Improved Dragonfly Optimization Algorithm for Solving Numerical and Three-bar Truss Optimization Problems","authors":"Feng Min, Huajuan Huang","doi":"10.1109/acait53529.2021.9731344","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731344","url":null,"abstract":"The Dragonfly Algorithm(DA) is a burgeoning swarm intelligence algorithm based on the theory of dragonflies avoiding natural enemies and hunting their food. This algorithm has the benefits of a powerful search ability and ease of implementation, but it also has drawbacks like low solution accuracy and sluggish convergence time. Simulated Annealing (SA) is a Monte-Carlo iterative solution strategy-based random optimization technique. It can viably dodge falling into a nearby least and in the long run tend to the global optimum. So as to decrease the visual deficiency of dragonfly algorithm, progress it’s solution exactness and meeting speed, and maintain a strategic distance from dragonfly algorithm from falling into nearby optimal solution. A dragonfly algorithm based on simulated annealing mechanism (SADA) is proposed in this paper. In each iteration, if the new position has better adaptability, it will directly replace the original position. Otherwise, the Metropolis acceptance criteria will be utilized to decide whether to accept the unused solution. Therefore, while improving the solution accuracy and convergence speed, it can successfully dodge the dragonfly algorithm from falling into the nearby optimum. The viability of the calculation is confirmed by 22 benchmark test functions and three-bar truss engineering problems. Test comes about appear that SADA has way better execution in optimizing functions and can discover superior solutions in building applications.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131103834","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
Construction of Industrial Robot Manipulator Sorting System based on Convolution Neural Network 基于卷积神经网络的工业机器人机械手分拣系统构建
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731263
B. Liu
{"title":"Construction of Industrial Robot Manipulator Sorting System based on Convolution Neural Network","authors":"B. Liu","doi":"10.1109/acait53529.2021.9731263","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731263","url":null,"abstract":"With the development of intelligent manufacturing, the application of intelligent algorithms in manufacturing industry is gradually enriched. This research combines convolutional neural network with industrial manipulator, and uses the image feature extraction advantages of convolutional neural network to build a manipulator sorting system. The results show that the average accuracy of the system for sorting parts is more than 70%, and when compared with other systems, its accuracy value is also greater than that of other systems. It can be seen that the identification and positioning accuracy of this system is stronger and the performance is better.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122122472","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 Ink Color Matching based on Stearns Noechel and BBO Optimization Algorithm 基于Stearns Noechel和BBO优化算法的油墨颜色匹配研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731156
Hua Chen
{"title":"Research on Ink Color Matching based on Stearns Noechel and BBO Optimization Algorithm","authors":"Hua Chen","doi":"10.1109/acait53529.2021.9731156","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731156","url":null,"abstract":"With the advancement of industrial informatization, the intelligent reform of printing industry is imperative. In order to improve the efficiency and quality of printing ink color matching, the basic model of BP neural network is optimized and improved by using Stearns noechel algorithm and BBO algorithm, and an intelligent ink color matching model based on Stearns noechel and BBO is constructed. The simulation results show that the average prediction error rate of the intelligent color matching model based on Stearns noechel and BBO is 3.2%, which is lower than 15.3% of K-M theory and 7.9% of BP neural network. After optimization and improvement, the prediction error of the model is reduced by 4.7% compared with the basic model of BP neural network, and the prediction performance is significantly improved, It provides a new computer intelligent color matching scheme for ink color matching of printing enterprises, improves the performance and accuracy of ink color matching, has practicability and optimization, and has important practical significance for the intelligent development of printing industry.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129622159","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 estimation models of rubber tree leaf nitrogen content based on hyperspectral and GWO-SVR 基于高光谱和GWO-SVR的橡胶树叶片氮含量估算模型研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731158
R. Tang, Xiaowei Li, Chuang Li, Jingjin Wu
{"title":"Research on estimation models of rubber tree leaf nitrogen content based on hyperspectral and GWO-SVR","authors":"R. Tang, Xiaowei Li, Chuang Li, Jingjin Wu","doi":"10.1109/acait53529.2021.9731158","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731158","url":null,"abstract":"Natural rubber is an essential economic crop in tropical parts. The quality and yield of rubber can be improved by proper fertilization. Therefore, it is crucial to develop a rapid and accurate model to detect the nitrogen content of rubber trees to improve quality and yield. This paper proposed a new and exemplary method for predicting nitrogen content by support vector regression (SVR) based on the Grey Wolf Optimizer (GWO). The successive projections algorithm (SPA) and competitive adapted reweighted sampling (CARS) were applied to choose the influential bands among the hyperspectral data, and the model was established using SVR. On the test data, the CARS-GWO-SVR model established by the GWO algorithm to optimize the SVR parameter penalty factor c and the kernel function parameter g has a prediction correlation coefficient R2 p=0.8967, and a prediction root mean square error RMSEP=0.2247. Comparative to the CARS-SVR model, The R2 p increased by 10.88%, and the RMSEP decreased by 9.15%. Therefore, GWO-SVR based on hyperspectral can establish a more accurate prediction model for the nitrogen content of rubber trees, providing technical support for the proper fertilization of rubber trees.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126674369","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
Flame Detection with Pruned and Knowledge Distilled YOLOv5 火焰检测与修剪和知识蒸馏YOLOv5
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731227
You Zhou, Mei Wu, Yong Bai, Chenglin Guo
{"title":"Flame Detection with Pruned and Knowledge Distilled YOLOv5","authors":"You Zhou, Mei Wu, Yong Bai, Chenglin Guo","doi":"10.1109/acait53529.2021.9731227","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731227","url":null,"abstract":"Fire is the main disaster that causes economic losses and threats to life safety. The target detector can detect the flame and send an alarm in the early stage of the fire, preventing the deterioration of the fire and causing more losses. Most current target detection models are too large to be deployed on flame detection equipment. In this work, we improved the efficiency of YOLOv5 for real-time flame detection. We pruned the YOLOv5s model at the BatchNormalization (BN) layer, and further distilled the pruned model to fine-tune the accuracy. The compressed YOLOv5s model can reach 76.9% mAP at 44 FPS on our expanded dataset. The accuracy of the compressed model does not decrease compared with the original YOLOv5 model. The Flops is reduced by 54.5%, the parameter amount is reduced by 37.8%, the weight storage file size is reduced by 37.5%, and the inference rate has an increase of four frames per second.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128945430","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 Simulation of Intelligent Robot System for Substation Inspection 智能变电站巡检机器人系统仿真研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731266
Ming Yi
{"title":"Research on Simulation of Intelligent Robot System for Substation Inspection","authors":"Ming Yi","doi":"10.1109/acait53529.2021.9731266","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731266","url":null,"abstract":"In this paper, the substation inspection intelligent robot is modularized, that is, it is analyzed one by one from the three systems of walking, navigation and inspection, and finally the design of substation inspection intelligent robot is completed. Specifically, combining the three major system requirements of substation inspection intelligent robots, the paper carries out the hardware design of the walking system of the inspection intelligent robot, the navigation system, and the inspection system. Through comprehensive prototype tests and simulation experiments, the feasibility verification of the functional modules and control strategies of the intelligent robot for substation inspection is carried out. The test results are in line with expectations.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130611294","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 Landscape Plant Configuration Based on ANN Technology 基于人工神经网络技术的景观植物配置设计
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9730890
Shen Qu, Y. Yao
{"title":"Design of Landscape Plant Configuration Based on ANN Technology","authors":"Shen Qu, Y. Yao","doi":"10.1109/acait53529.2021.9730890","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9730890","url":null,"abstract":"With the support of GIS, the BP network model of landscape plant morphological fractal dimension and diversity index based on the composition structure of landscape elements was constructed by using artificial neural network (ANN). By comparing the model performance of training samples, the results show that the diversity index and fractal dimension fitting accuracy of the training model are high, which shows that the training model constructed in this study is in line with the theoretical and practical values. At the same time, through the multi-dimensional and diversity index test of the test samples, the results show that the test accuracy of BP model meets the requirements, indicating that the convergence performance of garden plant configuration design network based on ANN technology is ideal, and can better simulate the impact of ecological environment on landscape plant configuration pattern.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131729798","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
Learning Multi-Scale Attention Model for Spine Multi-Category Segmentation 学习脊柱多品类分割的多尺度注意模型
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731136
Rui Ma, Mei Ma, Zebin Hu, Zhendong Li, Weichang Xu, Zhiyi Ding
{"title":"Learning Multi-Scale Attention Model for Spine Multi-Category Segmentation","authors":"Rui Ma, Mei Ma, Zebin Hu, Zhendong Li, Weichang Xu, Zhiyi Ding","doi":"10.1109/acait53529.2021.9731136","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731136","url":null,"abstract":"In the second CSIG spine multi-category segmentation challenge, the official spine structure data of 172 cases were provided, which contains up to 20 categories. If the multiscale method of encoder-decoder structure is used in multi-category segmentation at this dataset level, similar low-level features will be extracted multiple times, resulting in redundant use of information and the scale of the dataset limits the learning effect of the model. In order to avoid the aforementioned limitations, this work leverages a method based on a multiscale attention mechanism to solve the problem of multi-category segmentation. First, perform both operations of standardization and data augmentation on the given competition data, aiming to reinforce the data quality and the scalability. Secondly, the features at different scales are exploited through the Resnet network architecture, in parallel, the attention module consisting of the channel attention mechanism and the position attention mechanism extracts the features at different scales to obtain the corresponding attention maps. Finally, the features at different scales and the corresponding attention maps are fused in a weighted average to obtain the final prediction results. In the data set provided by the CSIG, Our multi-category segmentation method performance is 0.8438, which ranks 10-th place in the competition.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131872642","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