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 strategies to improve model accuracy based on incomplete time series data 基于不完全时间序列数据的模型精度提高策略研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731336
Wenya Wang, Li Bi
{"title":"Research on strategies to improve model accuracy based on incomplete time series data","authors":"Wenya Wang, Li Bi","doi":"10.1109/acait53529.2021.9731336","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731336","url":null,"abstract":"Aiming at the problem of inaccurate model prediction caused by incomplete time series data, an improved denoising autoencoder was proposed to supplement missing data. Firstly, the convolutional neural network is added into the encoding and decoding of the denoising autoencoder for sequence analysis. The missing values are completed by making full use of the spatial correlation in the time series and used to build models. Secondly, real photovoltaic data are used to train and test the model. In the training process, instances with random missing values are used as the verification set, and the model with the best generalization ability is selected. Then, the performance of the training strategy against instances with missing values of different granularity is tested, which proves the generalization and robustness of the algorithm. Finally, under the unified standard, the model accuracy of this method is improved by 32.64% based on the original model, which verifies that the algorithm improves the model accuracy after data filling, and verifies the feasibility and efficiency of the proposed missing value filling algorithm. The data filling algorithm in this paper greatly improves the problem that the performance of the prediction model deteriorates due to data loss caused by various reasons in photovoltaic power stations.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"2 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":"121106364","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 Recognition and Intelligent English Dialogue System Based on ELM Control Algorithm 基于ELM控制算法的机器识别与智能英语对话系统
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731300
Z. Li, Wenjing Cheng, Jianzhang Luo
{"title":"Machine Recognition and Intelligent English Dialogue System Based on ELM Control Algorithm","authors":"Z. Li, Wenjing Cheng, Jianzhang Luo","doi":"10.1109/acait53529.2021.9731300","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731300","url":null,"abstract":"In this study, a machine recognition and intelligent English dialogue system model based on the control algorithm of Extreme learning machines (ELM) is established. The system can preprocess and analyze the features of speech input signal, separate and recognize the signal through ELM classifier, and synthesize speech. The recognition experiments and performance tests of the system model show that the speech separation recognition of the system is feasible, and the recognition accuracy for English is as high as 88.9%, which is higher than that of the reference SVM classifier and DBN classifier.","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":"125917218","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 Collision Avoidance Technology of Manipulator based on AABB Hierarchical Bounding Box Algorithm 基于AABB层次包围盒算法的机械臂避碰技术研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731121
Dawei Hou, Xiaodong Wang, Jiancheng Liu, Baohua Yang, Gang Hou
{"title":"Research on Collision Avoidance Technology of Manipulator based on AABB Hierarchical Bounding Box Algorithm","authors":"Dawei Hou, Xiaodong Wang, Jiancheng Liu, Baohua Yang, Gang Hou","doi":"10.1109/acait53529.2021.9731121","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731121","url":null,"abstract":"With the acceleration of the intelligent process of domestic industry, the manipulator in the production workshop is increasingly widely used, and the collision problem of the manipulator is becoming more and more prominent. Aiming at this problem, the AABB hierarchical bounding box algorithm is designed based on the AABB bounding box algorithm. The algorithm and the commonly used bounding box algorithm are used to envelope the human 3D point cloud data model. The results show that the operation time of this algorithm is 18.11% and 25.04% shorter than that of OBB and k-DOPs algorithms, but the proportion of human body in the volume of bounding box is only reduced by 6.65% and 11.20%, and the comprehensive effects are the best. Based on the algorithm, a simulation collision avoidance detection model is built on MATLAB. The simulation results show that the algorithm can realize the collision avoidance function of the manipulator effectively. The research provides a certain reference value for optimizing the collision avoidance ability of the manipulator.","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":"114962188","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
Application of SVM-KNN intelligent classification prediction model in IT Vocational Education SVM-KNN智能分类预测模型在IT职业教育中的应用
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731162
Deng Hao, D. Chai
{"title":"Application of SVM-KNN intelligent classification prediction model in IT Vocational Education","authors":"Deng Hao, D. Chai","doi":"10.1109/acait53529.2021.9731162","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731162","url":null,"abstract":"In the process of sustainable development of information technology, it vocational education has received extensive attention. Its education quality and students’ learning state are very important. In order to explore the effectiveness of it vocational education, this subject experiment applies SVM-KNN intelligent classification prediction model to it vocational education, collects students’ IT vocational data for simulation analysis, and predicts their graduation status. The results show that the intelligent classification prediction model based on SVM-KNN algorithm has high prediction accuracy, and its accuracy and recall remain at a high level. This shows that SVM-KNN intelligent classification prediction model has a good application effect in it vocational education and can help improve the learning quality.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"91 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":"122371244","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
Decoding of motor intention from Brain EEG signal via local spatial sparse pattern 利用局部空间稀疏模式对脑电信号进行运动意图解码
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731143
Xiaofeng Xie, Yao Hou, R. Tang, Yizhen Wang, Songyuan Xiao, Junzhe Huang
{"title":"Decoding of motor intention from Brain EEG signal via local spatial sparse pattern","authors":"Xiaofeng Xie, Yao Hou, R. Tang, Yizhen Wang, Songyuan Xiao, Junzhe Huang","doi":"10.1109/acait53529.2021.9731143","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731143","url":null,"abstract":"In the brain-computer interfaces (BCI) systems of motor imagery, the spatial pattern on global EEG channels were commonly used to identify the motor intention from EEG signal. However, some channels are more important than the others in motor imagery tasks. Thus, the spatial pattern from global EEG channels can not reflect the difference of channels. To enhance the classification performance of motor imagery system, we proposed local sparse common spatial pattern (CSP) method for addressing the problem of channel’s difference frequently arising in BCIs. It constructs local channels based on Euclidean distance and performs joint diagonalization on each local channels to obtain multiple local spatial features. Lastly, we used the group sparse model to select discriminative features from different channels. Experimental evaluations on motor imagery dataset show that the proposed algorithm has higher classification performance than the competing methods.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"7 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":"117319500","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 Digital Media Image Data Tampering Forensics Technology Based on Improved CNN Algorithm 基于改进CNN算法的数字媒体图像数据篡改取证技术研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731182
Yuan Wang, Ying-Chun Li
{"title":"Research on Digital Media Image Data Tampering Forensics Technology Based on Improved CNN Algorithm","authors":"Yuan Wang, Ying-Chun Li","doi":"10.1109/acait53529.2021.9731182","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731182","url":null,"abstract":"At present, digital media has widely appeared in the modern Internet network, which has an extremely far-reaching impact on people's life. Due to the data characteristics of digital media images, it is easy to tamper with different purposes in the process of digital media communication. This research is based on CNN algorithm technology to study the methods of digital media image data tampering forensics, constructs the corresponding image tampering operation chain information theory model, and further uses the limited convolution CNN networks algorithm to identify the tampering behavior of pictures of different sizes. Through the comparative simulation analysis of CNN algorithm and SVM algorithm on digital media image data tampering forensics, it can be seen that CNN algorithm has higher recognition accuracy and recognition efficiency.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"5 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":"124792622","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 Path Planning of Airport VIP Service Robot Based on A* Algorithm and Artificial Potential Field Method 基于A*算法和人工势场法的机场VIP服务机器人路径规划研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731342
Yongguang Jin
{"title":"Research on Path Planning of Airport VIP Service Robot Based on A* Algorithm and Artificial Potential Field Method","authors":"Yongguang Jin","doi":"10.1109/acait53529.2021.9731342","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731342","url":null,"abstract":"Aiming at the path planning problem of service robot movement in complex environment, this paper proposes a path planning method combining global planning with local planning algorithm. And then, a new algorithm is carried out by optimizing A*algorithm and artificial potential field algorithm. The results show that the new algorithm has reduced inflection points and break points, made the route smoother and decreased the collision probability of the service robot in the different environments of path planning. Compared with the traditional algorithms, it is found that the new algorithm has better results of path planning through shortening the running time by 59.13% and reducing the length of the optimal path by 52.3%. The algorithm has certain advantages for the service robot to adapt to the path planning in various environments.","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":"130324437","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 Mobile Intelligent Detection Robot for Power Tunnel 电力隧道移动智能探测机器人的设计
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731166
S. Xiong
{"title":"Design of Mobile Intelligent Detection Robot for Power Tunnel","authors":"S. Xiong","doi":"10.1109/acait53529.2021.9731166","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731166","url":null,"abstract":"As an important way of power energy transmission, the safety of power tunnel is related to the stable operation of power system. According to the needs of daily inspection of power tunnel, a mobile intelligent inspection robot scheme for power tunnel is designed. The test results show that the average error value of the motion positioning of the robot is small, and can complete accurate movement control. The infrared temperature measurement accuracy of the robot is high, the hardcover degree of damage detection and positioning is high, and it can accurately identify foreign objects and give alarm and positioning in time. All functions of the robot meet the detection requirements, which provide a new research idea for intelligent automatic patrol inspection of power tunnel.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"411 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":"126688343","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 Novel Whale Optimization Algorithm with Sparrow algorithm and Golden Sine Leading Strategy 基于麻雀算法和金正弦领先策略的鲸类优化算法
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731302
Shixian Huang, Huajuan Huang
{"title":"A Novel Whale Optimization Algorithm with Sparrow algorithm and Golden Sine Leading Strategy","authors":"Shixian Huang, Huajuan Huang","doi":"10.1109/acait53529.2021.9731302","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731302","url":null,"abstract":"Whale optimization algorithm (WOA) is a recently proposed optimization algorithm. In view of the slow convergence velocity, low precision and hard to get away from local optimum of WOA algorithm, this paper puts forward a whale optimization algorithm with sparrow algorithm and golden sine leading strategy (SGSWOA). First, the location update rule of the producer in the sparrow algorithm is integrated into the Encircling prey stage of WOA to increase the search space of the algorithm and escape from the local optimum. Then combined with the golden sine leading strategy, it can balance exploration and development capabilities and enhance the performance of WOA algorithm. Finally, by optimizing 16 benchmark functions and applying the SGSWOA algorithm to practical engineering optimization problems, the experimental results display the SGSWOA algorithm has better convergence accuracy, convergence speed, and robustness.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"25 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":"123641994","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 Improvement of PSO and CNN in Intelligent Classification Technology of Coal Mine Safety Risk 改进的粒子群算法和CNN在煤矿安全风险智能分类技术中的研究
2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731328
Jianjun Wang
{"title":"Research on Improvement of PSO and CNN in Intelligent Classification Technology of Coal Mine Safety Risk","authors":"Jianjun Wang","doi":"10.1109/acait53529.2021.9731328","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731328","url":null,"abstract":"This paper mainly studies the coal mine safety risk, including the classification, management strategy of coal mine safety risk and the development of risk management information technology. For the management of coal mine safety risks, it is very effective to formulate a safety risk classification management system, which can find and manage various safety hazards and risks as soon as possible, and promote efficient and safe operation. Nowadays, people increasingly take safety issues seriously in the coal industry, so the development of safety risk classification and control system has become an important safety management tool. To solve the slow convergence rate of CNN algorithm, this paper uses PSO to improve the error back propagation of CNN by using the training parameters and error functions of CNN as PSO particles and fitness functions respectively. The experimental simulation of AR face database in gender identification verifies that the improved algorithm has fast convergence rate and high recognition accuracy.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"196 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":"116210421","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
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