Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00017
Yaming Ren, Mei-Chun Liao
Differential evolution algorithm belongs to intelligent algorithm. The initial population of differential evolution algorithm is generated randomly within the constraint range of variable upper and lower limits, and the vector between random individuals in the population is used as the orientation of individuals. Differential evolution algorithm can effectively search for the optimal solution in the global scope, and it does not need the differentiable and convex properties of the objective function. In this paper, we use the differential evolution algorithm to solve the economic scheduling problem of power system, and the simulation results prove the effectiveness and correctness of the differential evolution algorithm.
{"title":"Application of Differential Evolution Algorithm to Power System Economic Dispatch Problem","authors":"Yaming Ren, Mei-Chun Liao","doi":"10.1109/ICAA53760.2021.00017","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00017","url":null,"abstract":"Differential evolution algorithm belongs to intelligent algorithm. The initial population of differential evolution algorithm is generated randomly within the constraint range of variable upper and lower limits, and the vector between random individuals in the population is used as the orientation of individuals. Differential evolution algorithm can effectively search for the optimal solution in the global scope, and it does not need the differentiable and convex properties of the objective function. In this paper, we use the differential evolution algorithm to solve the economic scheduling problem of power system, and the simulation results prove the effectiveness and correctness of the differential evolution algorithm.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130497171","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00071
Beixi Hao, Yi Liu, Jacob Henry Hao
Information extraction from clinical dialogue to build a knowledge graph that can generate electronic medical charts has been an important application of NLP in the medical industry. Although substantial research has been carried out on such information extractor, existing models underperform due to lack of contextual background between dialogue windows. This study proposes a model that can extract relevant medical items from the doctor-patient dialogues by leveraging a multi-layer encoder-decoder framework. The experimental results on a well-studied dataset shows that our model outperform the current baseline models, which prove the model effectiveness.
{"title":"Enhanced Medical Dialogue Diagnosis with Intra-inter Window Attention Encoder","authors":"Beixi Hao, Yi Liu, Jacob Henry Hao","doi":"10.1109/ICAA53760.2021.00071","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00071","url":null,"abstract":"Information extraction from clinical dialogue to build a knowledge graph that can generate electronic medical charts has been an important application of NLP in the medical industry. Although substantial research has been carried out on such information extractor, existing models underperform due to lack of contextual background between dialogue windows. This study proposes a model that can extract relevant medical items from the doctor-patient dialogues by leveraging a multi-layer encoder-decoder framework. The experimental results on a well-studied dataset shows that our model outperform the current baseline models, which prove the model effectiveness.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129029661","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00111
Haoqi Yu, Jiangshen Pan, Jinjian Yang
Blockchain technology has attracted great attention in various fields because of its advantages of distributed network. Its rational application in enterprise's financial activities can optimize financial processes and control operating costs; improve the quality of financial information, reduce information asymmetry; promote the transformation and progress of financial personnel. But there may be difficulties in the practical application of new technology, and this paper will put forward feasible solutions based on these problems.
{"title":"Blockchain Plus Finance: Application, Dilemma and Solution","authors":"Haoqi Yu, Jiangshen Pan, Jinjian Yang","doi":"10.1109/ICAA53760.2021.00111","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00111","url":null,"abstract":"Blockchain technology has attracted great attention in various fields because of its advantages of distributed network. Its rational application in enterprise's financial activities can optimize financial processes and control operating costs; improve the quality of financial information, reduce information asymmetry; promote the transformation and progress of financial personnel. But there may be difficulties in the practical application of new technology, and this paper will put forward feasible solutions based on these problems.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"23 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125891136","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00064
Yi Zhou, Yi Wang, Min Wang, Zhanghua Wu, Z. Du, Wei Xi
Aiming at the efficiency of traditional template attacks in actual attacks, this paper focuses on the ResN et network model with excellent feature extraction capabilities in the field of image recognition, and proposes a template attack method based on the ResN et network model. In order to adapt the neural network to the characteristics of the side channel data, the network model structure was adjusted appropriately. In the experiment, the traditional multivariate Gaussian distribution and the ResNet-based convolutional neural network model were used to establish templates. The final experimental results show that the success rate of template attacks based on the ResNet model is 94.5%, which is 9.4% higher than the traditional template attacks.
{"title":"Encryption Chip Template Attack Based on ResNet Convolutional Neural Network","authors":"Yi Zhou, Yi Wang, Min Wang, Zhanghua Wu, Z. Du, Wei Xi","doi":"10.1109/ICAA53760.2021.00064","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00064","url":null,"abstract":"Aiming at the efficiency of traditional template attacks in actual attacks, this paper focuses on the ResN et network model with excellent feature extraction capabilities in the field of image recognition, and proposes a template attack method based on the ResN et network model. In order to adapt the neural network to the characteristics of the side channel data, the network model structure was adjusted appropriately. In the experiment, the traditional multivariate Gaussian distribution and the ResNet-based convolutional neural network model were used to establish templates. The final experimental results show that the success rate of template attacks based on the ResNet model is 94.5%, which is 9.4% higher than the traditional template attacks.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127295273","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00179
Huiqun Gao, Xu Qin
In this paper, we apply the random forest kernel to nonparametric regression model with spherical and linear variables. Validate the new model with simulated data and actual airfoil noise data. Comparing with the Gaussian kernel and the linear-circular kernel, the experimental results show that the random forest kernel has stable performance and fast computation speed, and the random forest kernel has a better fitting effect in high dimension.
{"title":"Application of the Random Forest Kernel in Nonparametric Regression Model with Spherical Variables","authors":"Huiqun Gao, Xu Qin","doi":"10.1109/ICAA53760.2021.00179","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00179","url":null,"abstract":"In this paper, we apply the random forest kernel to nonparametric regression model with spherical and linear variables. Validate the new model with simulated data and actual airfoil noise data. Comparing with the Gaussian kernel and the linear-circular kernel, the experimental results show that the random forest kernel has stable performance and fast computation speed, and the random forest kernel has a better fitting effect in high dimension.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126497606","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00098
Yi-Fan Song, Zhenyan Liu, Chunxia Zhang
Multi-label classification is an extension of multi-class classification. For multi-label problem, each instance may not be restricted to have only one label. In this paper, the methods to solve multi-label classification are divided into four aspects which are binary relevance method, label combination method, classifier chain and ensemble classifier chain. In order to enhance the performance of the text classifier, text adversarial attack should be used to enrich the training dataset. Thus, the related works with text adversarial attack are also introduced. In the end, we also explore some potential future issues in multi-label text classification and text adversarial attack.
{"title":"Multi-label Text Classification and Text Adversarial Attack","authors":"Yi-Fan Song, Zhenyan Liu, Chunxia Zhang","doi":"10.1109/ICAA53760.2021.00098","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00098","url":null,"abstract":"Multi-label classification is an extension of multi-class classification. For multi-label problem, each instance may not be restricted to have only one label. In this paper, the methods to solve multi-label classification are divided into four aspects which are binary relevance method, label combination method, classifier chain and ensemble classifier chain. In order to enhance the performance of the text classifier, text adversarial attack should be used to enrich the training dataset. Thus, the related works with text adversarial attack are also introduced. In the end, we also explore some potential future issues in multi-label text classification and text adversarial attack.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131468828","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00029
Yunyi Liu, Beixi Hao
Task-oriented question answering dialogue systems have been an important branch of conversational systems for oral language, where they first understand the query requested by users, and the models are demanded to seek for answers within the context considering the query information. Previous work models the semantic and syntactic information without taking the interaction into consideration. In this paper, we propose an intra-and-inter sentence attention framework, equipped with self-attention mechanism, which enables the model to focus more on a small part of the context and enhances the model capability of extracting the interactive information. Our experiments are based on the Stanford Question Answering Dataset (SQuAD) and the experimental result shows that our model achieves 68.5 EM and 77.7 F1 score, which verifies how the proposed model improves on the dataset.
{"title":"Intra-and-inter Sentence Attention Model for Enhanced Question Answering System","authors":"Yunyi Liu, Beixi Hao","doi":"10.1109/ICAA53760.2021.00029","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00029","url":null,"abstract":"Task-oriented question answering dialogue systems have been an important branch of conversational systems for oral language, where they first understand the query requested by users, and the models are demanded to seek for answers within the context considering the query information. Previous work models the semantic and syntactic information without taking the interaction into consideration. In this paper, we propose an intra-and-inter sentence attention framework, equipped with self-attention mechanism, which enables the model to focus more on a small part of the context and enhances the model capability of extracting the interactive information. Our experiments are based on the Stanford Question Answering Dataset (SQuAD) and the experimental result shows that our model achieves 68.5 EM and 77.7 F1 score, which verifies how the proposed model improves on the dataset.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114068480","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00038
Huan Liang, Xinhua Wang, Zhe Hu, Kai Zhang, Hao Wang
Robot path planning is a hot issue in the robotics field. Based on many algorithms, we consider the efficiency and accuracy of path planning. This paper proposes a path planning method that combines improved ant colony algorithm and $mathrm{A}^{ast}$ algorithm. First, by improving the pheromone update method, state transition probability and heuristic function in the ant colony algorithm, an ant colony algorithm with better performance is obtained. Afterwards, aiming at the defect that the same initial pheromone concentration in the ant colony algorithm leads to the purposeless search of the first-generation ant colony, the fusion improved ant colony algorithm and the $mathrm{A}^{ast}$ algorithm are proposed, and simulation experiments are carried out. The experimental results show that the path is planned through the fusion algorithm the search time is shortened, the number of iterations when reaching convergence is reduced, and a better path can be obtained, which shows that the algorithm can achieve good results when dealing with path planning problems.
{"title":"Robot Path Planning Based on Fusion Improved Ant Colony Algorithm","authors":"Huan Liang, Xinhua Wang, Zhe Hu, Kai Zhang, Hao Wang","doi":"10.1109/ICAA53760.2021.00038","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00038","url":null,"abstract":"Robot path planning is a hot issue in the robotics field. Based on many algorithms, we consider the efficiency and accuracy of path planning. This paper proposes a path planning method that combines improved ant colony algorithm and $mathrm{A}^{ast}$ algorithm. First, by improving the pheromone update method, state transition probability and heuristic function in the ant colony algorithm, an ant colony algorithm with better performance is obtained. Afterwards, aiming at the defect that the same initial pheromone concentration in the ant colony algorithm leads to the purposeless search of the first-generation ant colony, the fusion improved ant colony algorithm and the $mathrm{A}^{ast}$ algorithm are proposed, and simulation experiments are carried out. The experimental results show that the path is planned through the fusion algorithm the search time is shortened, the number of iterations when reaching convergence is reduced, and a better path can be obtained, which shows that the algorithm can achieve good results when dealing with path planning problems.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114023378","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00015
Mingtian Shao, Kai Lu, Wen-zhe Zhang
With the increase of the user's demand for High Performance Computing (HPC), the hardware resources have been continuously developed and expanded. The interconnections between the various parts of HPC systems are increasingly complex. How to maximize the performance of the system and how to maximize the utilization of resources have become the major problem. The integration of virtualization technology improves the resource utilization of HPC system, but loses some performance. The multi-user usage scenarios and the pursuit of performance in HPC system put forward high requirements for virtualization technology. The highly customized nature of HPC systems also adds to the challenges of virtualization. This paper introduces operating system-level and application-level virtualization in HPC system, and discusses the current problems and the future development direction.
{"title":"Survey on Virtualization of High Performance Computing","authors":"Mingtian Shao, Kai Lu, Wen-zhe Zhang","doi":"10.1109/ICAA53760.2021.00015","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00015","url":null,"abstract":"With the increase of the user's demand for High Performance Computing (HPC), the hardware resources have been continuously developed and expanded. The interconnections between the various parts of HPC systems are increasingly complex. How to maximize the performance of the system and how to maximize the utilization of resources have become the major problem. The integration of virtualization technology improves the resource utilization of HPC system, but loses some performance. The multi-user usage scenarios and the pursuit of performance in HPC system put forward high requirements for virtualization technology. The highly customized nature of HPC systems also adds to the challenges of virtualization. This paper introduces operating system-level and application-level virtualization in HPC system, and discusses the current problems and the future development direction.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123970816","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}
Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00119
Zhuojing Tian, Zhenchun Huang, Yinong Zhang
Inter-cloud environment provides massive computing resources to meet the increasing amount of data and computation for remote sensing applications. However, how to effectively map sub-tasks to different cloud service providers to achieve QoS(Quality of Service) index optimization is still a problem that needs to be studied. Remote sensing applications need to process trillions of bytes of data each time, unreasonable scheduling will lead to a large amount of data transmission across the cloud, which will seriously affect the performance of QoS indicators such as makespan and cost. By using data transformation graph(DTG) to study the data transmission process of global drought detection application, which is a remote sensing application, an optimized scientific workflow scheduling based on genetic algorithm is proposed for inter-cloud environment, which can minimize makespan and cost simultaneously. Experimental results show that this method can significantly optimize QoS index for data-intensive application like remote sense application and can effectively reduce the impact of performance bottlenecks.
云间环境提供了海量的计算资源，以满足遥感应用日益增长的数据量和计算量。然而，如何有效地将子任务映射到不同的云服务提供商，实现QoS(Quality of service)指标优化，仍然是一个需要研究的问题。遥感应用每次需要处理数万亿字节的数据，不合理的调度会导致大量数据跨云传输，严重影响makespan、cost等QoS指标的性能。通过利用数据转换图(DTG)研究全球干旱探测应用的数据传输过程，提出了一种基于遗传算法的云间环境下优化的科学工作流调度方法，使完工时间和成本同时最小化。实验结果表明，该方法可以显著优化遥感等数据密集型应用的QoS指标，有效降低性能瓶颈的影响。
{"title":"Workflow Scheduling for Remote Sense Application Using Data Transformation Graph in Inter-cloud","authors":"Zhuojing Tian, Zhenchun Huang, Yinong Zhang","doi":"10.1109/ICAA53760.2021.00119","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00119","url":null,"abstract":"Inter-cloud environment provides massive computing resources to meet the increasing amount of data and computation for remote sensing applications. However, how to effectively map sub-tasks to different cloud service providers to achieve QoS(Quality of Service) index optimization is still a problem that needs to be studied. Remote sensing applications need to process trillions of bytes of data each time, unreasonable scheduling will lead to a large amount of data transmission across the cloud, which will seriously affect the performance of QoS indicators such as makespan and cost. By using data transformation graph(DTG) to study the data transmission process of global drought detection application, which is a remote sensing application, an optimized scientific workflow scheduling based on genetic algorithm is proposed for inter-cloud environment, which can minimize makespan and cost simultaneously. Experimental results show that this method can significantly optimize QoS index for data-intensive application like remote sense application and can effectively reduce the impact of performance bottlenecks.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127648058","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：