Pub Date : 2020-11-01DOI: 10.1109/CIS52066.2020.00012
Caixu Xu, Guo Hui, He Jie
Aiming at problems such as difficulties in determini--ng sub-mode position relations and complexity in image calculations caused by asymmetric segmentation in SNAM image representation, the present study first recovers submodule spatial position relations of SNAM representation with grid arrays and improves the grid arrays satisfying geometric calculation of images. Then, it proposes a geometric calculation algorithm based on SNAM. According to experimental results compared to geometric calculations represented by linear quad-tree and arrays or the like, the proposed algorithm has obvious higher efficiency. It is an eight-neighborhood image geometric calculation algorithm with excellent performance and adaptability to SNAM representation.
{"title":"Binary Image Geometric Calculation Algorithm Based on SNAM Representation","authors":"Caixu Xu, Guo Hui, He Jie","doi":"10.1109/CIS52066.2020.00012","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00012","url":null,"abstract":"Aiming at problems such as difficulties in determini--ng sub-mode position relations and complexity in image calculations caused by asymmetric segmentation in SNAM image representation, the present study first recovers submodule spatial position relations of SNAM representation with grid arrays and improves the grid arrays satisfying geometric calculation of images. Then, it proposes a geometric calculation algorithm based on SNAM. According to experimental results compared to geometric calculations represented by linear quad-tree and arrays or the like, the proposed algorithm has obvious higher efficiency. It is an eight-neighborhood image geometric calculation algorithm with excellent performance and adaptability to SNAM representation.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127267810","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}
With global industrialization, air pollution is becoming a critical issue that threatens human health. The World Health Organization (WHO) estimated that air pollution kills several million people worldwide each year. Researchers from various areas and governments and enterprises have invested many resources in investigating and reducing air pollution. Air Quality Index (AQI) is one of the essential indexes indicating air quality or the level of air pollution. A new dataset, including hourly AQI information recorded by 1,615 observation sites covering China from 2015 to 2019, is constructed. Several methods, including linear model and state-of-art techniques, such as Back Propagation Neural Network (BPNN), Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bi-directional Long Short-Term Memory (BiLSTM), are adopted to forecast hourly AQI. The performance of these techniques is evaluated, and experiments show that the BiLSTM gives the best performance.
{"title":"Prediction of Air Quality in Major Cities of China by Deep Learning","authors":"Choujun Zhan, Songyan Li, Jianbin Li, Yijing Guo, Quansi Wen, WeiSheng Wen","doi":"10.1109/CIS52066.2020.00023","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00023","url":null,"abstract":"With global industrialization, air pollution is becoming a critical issue that threatens human health. The World Health Organization (WHO) estimated that air pollution kills several million people worldwide each year. Researchers from various areas and governments and enterprises have invested many resources in investigating and reducing air pollution. Air Quality Index (AQI) is one of the essential indexes indicating air quality or the level of air pollution. A new dataset, including hourly AQI information recorded by 1,615 observation sites covering China from 2015 to 2019, is constructed. Several methods, including linear model and state-of-art techniques, such as Back Propagation Neural Network (BPNN), Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bi-directional Long Short-Term Memory (BiLSTM), are adopted to forecast hourly AQI. The performance of these techniques is evaluated, and experiments show that the BiLSTM gives the best performance.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124932973","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 : 2020-11-01DOI: 10.1109/cis52066.2020.00003
{"title":"[Copyright notice]","authors":"","doi":"10.1109/cis52066.2020.00003","DOIUrl":"https://doi.org/10.1109/cis52066.2020.00003","url":null,"abstract":"","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114457885","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00078
Yaling Zhang, Jiale Li, Shibo Bai
Due to the differences in features between different languages, Chinese text is more complicated and difficult in natural language processing tasks than English text. This paper proposes a neural network Chinese sentiment classification model based on particle swarm optimization (PSO-Attention-LSTM), the model uses the Long Short Term Memory Network superimposed attention mechanism to extract information from Chinese review data and determine the sentiment polarity of the sentence; aiming at the problem that parameters such as the number of hidden layer neurons in the LSTM unit and the number of batches of the neural network are difficult to determine, the global optimization capability of the particle swarm optimization (PSO) is used to optimize the parameters. The experimental results show that the neural network Chinese sentiment classification model based on particle swarm optimization has improved the accuracy of the hotel data set by nearly 6 percentage points.
{"title":"Chinese Sentiment Classification Model of Neural Network Based on Particle Swarm Optimization","authors":"Yaling Zhang, Jiale Li, Shibo Bai","doi":"10.1109/CIS52066.2020.00078","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00078","url":null,"abstract":"Due to the differences in features between different languages, Chinese text is more complicated and difficult in natural language processing tasks than English text. This paper proposes a neural network Chinese sentiment classification model based on particle swarm optimization (PSO-Attention-LSTM), the model uses the Long Short Term Memory Network superimposed attention mechanism to extract information from Chinese review data and determine the sentiment polarity of the sentence; aiming at the problem that parameters such as the number of hidden layer neurons in the LSTM unit and the number of batches of the neural network are difficult to determine, the global optimization capability of the particle swarm optimization (PSO) is used to optimize the parameters. The experimental results show that the neural network Chinese sentiment classification model based on particle swarm optimization has improved the accuracy of the hotel data set by nearly 6 percentage points.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129055061","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00022
Peng Zhou, Ye Lu, Dong Cheng, Chuanqi Li
With the explosive growth of data and the continuous expansion of the network scale, the spectrum resource problem in the network is becoming more and more serious, which hinders the development of the Internet. Aiming at the problem that the spectrum utilization of the optical code division multiple access (OCDMA) system, we give a possible strategy for communication scheme, analyze them, and derive expressions for coding and decoding states. We design an experimental system with the data-rate of 5Gbit/s, the distance of 620km. The results indicate the high recovery accuracy of the user data. Furthermore, we compare coherent and incoherent systems in terms of transmission distance and bit error rate (BER). The simulation results show that the scheme we proposed can transmit longer distances and the BER is lower than incoherent systems.
{"title":"Electro-optic Combination Coherent Communication System Based On OCDMA Theory","authors":"Peng Zhou, Ye Lu, Dong Cheng, Chuanqi Li","doi":"10.1109/CIS52066.2020.00022","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00022","url":null,"abstract":"With the explosive growth of data and the continuous expansion of the network scale, the spectrum resource problem in the network is becoming more and more serious, which hinders the development of the Internet. Aiming at the problem that the spectrum utilization of the optical code division multiple access (OCDMA) system, we give a possible strategy for communication scheme, analyze them, and derive expressions for coding and decoding states. We design an experimental system with the data-rate of 5Gbit/s, the distance of 620km. The results indicate the high recovery accuracy of the user data. Furthermore, we compare coherent and incoherent systems in terms of transmission distance and bit error rate (BER). The simulation results show that the scheme we proposed can transmit longer distances and the BER is lower than incoherent systems.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124515614","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00065
Hui Wang, Xiaobo Song, Zhihao Tong, Xiaoli Wang
Periodic multi-installment scheduling (PMIS) has been the most effective model for large-scale divisible-load scheduling on distributed systems. In practice, the decreasing order of communication speeds, denoted as IZ, has always been used as the scheduling sequence of servers because it has been proven that IZ is the optimal sequence to achieve minimum makespan for single-installment scheduling and studies available have shown that IZ is the near-optimal sequence for multi-installment scheduling. In this paper, however, we illustrate by an example that IZ unfortunately causes time conflicts for servers between the last installment but one and the last installment, thus it is definitely not a feasible sequence for PMIS, not to mention an optimal or near-optimal sequence. Further, to obtain a feasible order of servers, we provide rigorous proof in this paper that there is no time conflict when servers follow the increasing order of communication speeds.
{"title":"Order of Servers for Periodic Multi-Installment Scheduling","authors":"Hui Wang, Xiaobo Song, Zhihao Tong, Xiaoli Wang","doi":"10.1109/CIS52066.2020.00065","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00065","url":null,"abstract":"Periodic multi-installment scheduling (PMIS) has been the most effective model for large-scale divisible-load scheduling on distributed systems. In practice, the decreasing order of communication speeds, denoted as IZ, has always been used as the scheduling sequence of servers because it has been proven that IZ is the optimal sequence to achieve minimum makespan for single-installment scheduling and studies available have shown that IZ is the near-optimal sequence for multi-installment scheduling. In this paper, however, we illustrate by an example that IZ unfortunately causes time conflicts for servers between the last installment but one and the last installment, thus it is definitely not a feasible sequence for PMIS, not to mention an optimal or near-optimal sequence. Further, to obtain a feasible order of servers, we provide rigorous proof in this paper that there is no time conflict when servers follow the increasing order of communication speeds.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126436267","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00042
Ya-juan Yang, Liang Zhang, Yi Niu, Ouan-Ju Zhang
The two most famous models, one is called mean-variance optimization model (in short MVO) which was proposed by Markowiz who won the Nobel prize in 1990 due to his pioneering research in the theory of modern financial economics, and another is named after B-L model proposed by Black-Litterman. This paper introduces the evolution of these two models in asset allocating: MVO model and B-L model. First, the advantages and disadvantages of the two models are described in case of treating a practical investment strategy by the two models being employed. Second, we illustrate that, with a comparison of the mean-variance optimization model, the key ingredients are accurate judgment on the performance and correlation of each asset for Black-Litterman model. Finally, we point out that the Black-Litterman model is not always superior to mean-variance optimization in case of the experiences of an investor are insufficient.
{"title":"A Brief Review of Two Classical Models for Asset Allocating","authors":"Ya-juan Yang, Liang Zhang, Yi Niu, Ouan-Ju Zhang","doi":"10.1109/CIS52066.2020.00042","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00042","url":null,"abstract":"The two most famous models, one is called mean-variance optimization model (in short MVO) which was proposed by Markowiz who won the Nobel prize in 1990 due to his pioneering research in the theory of modern financial economics, and another is named after B-L model proposed by Black-Litterman. This paper introduces the evolution of these two models in asset allocating: MVO model and B-L model. First, the advantages and disadvantages of the two models are described in case of treating a practical investment strategy by the two models being employed. Second, we illustrate that, with a comparison of the mean-variance optimization model, the key ingredients are accurate judgment on the performance and correlation of each asset for Black-Litterman model. Finally, we point out that the Black-Litterman model is not always superior to mean-variance optimization in case of the experiences of an investor are insufficient.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126512493","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00058
Liping Jia, Zhonghua Li
As an enormous epidemic for the global, COVID-19, has become a major threat to the mankind thus influence economy, living activities, especial eduction. The public sentiment has been produced in the internet. In this paper, public emotional sentiment about returning to the university is crawled from the weibo and studied. By analyzing the reviews, the students' emotional analysis is studied by snowNLP-based method and TF-IDF-based method. Numerical experiments and visualization results indicate that the students have positive emotion for returning to the university.
{"title":"Emotional Analysis on the Public Sentiment of Students Returning to University under COVID-19","authors":"Liping Jia, Zhonghua Li","doi":"10.1109/CIS52066.2020.00058","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00058","url":null,"abstract":"As an enormous epidemic for the global, COVID-19, has become a major threat to the mankind thus influence economy, living activities, especial eduction. The public sentiment has been produced in the internet. In this paper, public emotional sentiment about returning to the university is crawled from the weibo and studied. By analyzing the reviews, the students' emotional analysis is studied by snowNLP-based method and TF-IDF-based method. Numerical experiments and visualization results indicate that the students have positive emotion for returning to the university.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133612621","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00040
Yang Li
Hadoop bundles the two computing resources of memory and CPU in the management resources, and then divides it into two resource models: MapSlot and ReduceSlot according to task types. MapReduce applications will have a large number of sorting operations in operation. Most of these sorts are executed iteratively, which consumes a lot of performance. Chapter 5 of this article takes this as an entry point and reorganizes the execution process of the Shuffle stage. Researched to replace quick sort with more efficient counting sorting. At the same time, the Shuffle execution is branched according to the definition of Combiner. One branch deletes the quick sort in the partition in the spill phase and the merge sort in the combine phase to reduce performance consumption. The other branch executes Combiner in advance to improve data processing efficiency. The two branches processed 21GB of log data on a 7-node PC cluster, and both achieved an efficiency improvement of about half an hour.
{"title":"Performance Analysis of Scheduling Algorithms in Apache Hadoop","authors":"Yang Li","doi":"10.1109/CIS52066.2020.00040","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00040","url":null,"abstract":"Hadoop bundles the two computing resources of memory and CPU in the management resources, and then divides it into two resource models: MapSlot and ReduceSlot according to task types. MapReduce applications will have a large number of sorting operations in operation. Most of these sorts are executed iteratively, which consumes a lot of performance. Chapter 5 of this article takes this as an entry point and reorganizes the execution process of the Shuffle stage. Researched to replace quick sort with more efficient counting sorting. At the same time, the Shuffle execution is branched according to the definition of Combiner. One branch deletes the quick sort in the partition in the spill phase and the merge sort in the combine phase to reduce performance consumption. The other branch executes Combiner in advance to improve data processing efficiency. The two branches processed 21GB of log data on a 7-node PC cluster, and both achieved an efficiency improvement of about half an hour.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132173907","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 : 2020-11-01DOI: 10.1109/CIS52066.2020.00036
Jie Song, Qifeng Luo, J. Nie
In the existing dialogue system, there are numerous sentences in non-standardized verbal expression form, which usually is brief and vague. It is a challenging task to identify the intentions through the analysis of these sentences. Considering that the supervised learning approach is the mainstream on multi-intention recognition, an amount of public labeled multi-intention dialogue data is necessary. However, labeling work is costly and time-consuming. In this paper, we put forward a multi-label classification method based on existing mainstream classification algorithms and used for dialogue-level multi-intention recognition to reduce the cost of labeling work. We publish the Chinese Multi-Intention Dialogue (CMID-Transportation) dataset of transportation customer service, which is collected by us in an actual production project. We conduct a series of experiments on the CMID-Transportation corpus by using the mainstream classification algorithms and then produce the basic benchmark performance. We find that BERT achieves the best results. We hope that the CMID-Transportation dataset can promote the research and development of intent recognition tasks in multiple rounds of dialogue.
{"title":"Research and Application of Multi-Round Dialogue Intent Recognition Method","authors":"Jie Song, Qifeng Luo, J. Nie","doi":"10.1109/CIS52066.2020.00036","DOIUrl":"https://doi.org/10.1109/CIS52066.2020.00036","url":null,"abstract":"In the existing dialogue system, there are numerous sentences in non-standardized verbal expression form, which usually is brief and vague. It is a challenging task to identify the intentions through the analysis of these sentences. Considering that the supervised learning approach is the mainstream on multi-intention recognition, an amount of public labeled multi-intention dialogue data is necessary. However, labeling work is costly and time-consuming. In this paper, we put forward a multi-label classification method based on existing mainstream classification algorithms and used for dialogue-level multi-intention recognition to reduce the cost of labeling work. We publish the Chinese Multi-Intention Dialogue (CMID-Transportation) dataset of transportation customer service, which is collected by us in an actual production project. We conduct a series of experiments on the CMID-Transportation corpus by using the mainstream classification algorithms and then produce the basic benchmark performance. We find that BERT achieves the best results. We hope that the CMID-Transportation dataset can promote the research and development of intent recognition tasks in multiple rounds of dialogue.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124435429","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}