Pub Date : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35128
You You, Q. Gao, Yixiang Lu, Dong Sun
Object tracking is one of the most important tasks in computer vision, many researchers have proposed a lot of effective methods to solve the all kinds of the recent problems in object tracking. During the movement of the targets, the change of object scale may produce a lot of difficulties in object tracing problems, and it may lead to be failed in tracking. The paper proposed method is designed both correlation filter and particle filter. In order to achieve the purpose of tracking, the process of correlation filter is to learn an array of filters so that the response value obtained by the convolution of the learned filters is the largest. The particle filter guides the sample particles to the distribution mode of the target state. The samples of the particle strategy can effectively deal with the large scale variations of the target during movement. Experiment on the OTB database shows that the paper proposed method makes good performance.
{"title":"Target Tracking Method Based on Correlation Filter and Particle Filter","authors":"You You, Q. Gao, Yixiang Lu, Dong Sun","doi":"10.12783/dtcse/cisnr2020/35128","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35128","url":null,"abstract":"Object tracking is one of the most important tasks in computer vision, many researchers have proposed a lot of effective methods to solve the all kinds of the recent problems in object tracking. During the movement of the targets, the change of object scale may produce a lot of difficulties in object tracing problems, and it may lead to be failed in tracking. The paper proposed method is designed both correlation filter and particle filter. In order to achieve the purpose of tracking, the process of correlation filter is to learn an array of filters so that the response value obtained by the convolution of the learned filters is the largest. The particle filter guides the sample particles to the distribution mode of the target state. The samples of the particle strategy can effectively deal with the large scale variations of the target during movement. Experiment on the OTB database shows that the paper proposed method makes good performance.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"76 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81111160","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35169
Daolin Han, Xiaojian Song, Yong Cui
The usage of chatbot for handling the conversations is gradually increasing. By using this technique, companies can provide a real-time and efficient channel to deliver the information to their users. Chatbot can response significant volume of frequent-asked and typical questions, which is bound to reduce the company human resource consumption. However, sometimes a chatbot cannot satisfy users with the provided answers, in such situation, chatbot should be transferred to an agent in order to handle the rest of the conversation. A concise summary of the user utterances helps the agent to handle the rest of the chat without raising annoying delay. Because the dialog between chatbots and user is fragmented and informal when compared to classic summarization dataset, high complexity models often have difficulty in achieving ideal results. In this paper, we present an extractive chat summarization system to provide a concise summary of the discussed topics in chat. We conclude three groups of critical and universally applicable features dedicated to summarization tasks and use the features to extract keywords for ranking sentences’ importance in the chat. We evaluate supervised and unsupervised methods for keyword extraction and generate the summary by combining selected sentences with specific rules. We compare our obtained results with two state-of-art, deep learning based methods over a new chatlog dataset. Experimental results reveal our method to be more effective and efficient than currently popular, high complexity methods.
{"title":"An Extractive Chat Summary Generation Method for Ecommerce Chatbots","authors":"Daolin Han, Xiaojian Song, Yong Cui","doi":"10.12783/dtcse/cisnr2020/35169","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35169","url":null,"abstract":"The usage of chatbot for handling the conversations is gradually increasing. By using this technique, companies can provide a real-time and efficient channel to deliver the information to their users. Chatbot can response significant volume of frequent-asked and typical questions, which is bound to reduce the company human resource consumption. However, sometimes a chatbot cannot satisfy users with the provided answers, in such situation, chatbot should be transferred to an agent in order to handle the rest of the conversation. A concise summary of the user utterances helps the agent to handle the rest of the chat without raising annoying delay. Because the dialog between chatbots and user is fragmented and informal when compared to classic summarization dataset, high complexity models often have difficulty in achieving ideal results. In this paper, we present an extractive chat summarization system to provide a concise summary of the discussed topics in chat. We conclude three groups of critical and universally applicable features dedicated to summarization tasks and use the features to extract keywords for ranking sentences’ importance in the chat. We evaluate supervised and unsupervised methods for keyword extraction and generate the summary by combining selected sentences with specific rules. We compare our obtained results with two state-of-art, deep learning based methods over a new chatlog dataset. Experimental results reveal our method to be more effective and efficient than currently popular, high complexity methods.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83416932","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35142
Junyan Liu, Xiong-wei Li, Lin-fang Liu, Zhihui Wang, Panfei Du, Kang Li
In view of the increasingly prominent problems exposed by chips in integrated circuits and the destructive problems of traditional chip detection methods, a BPAdaBoost neural network model based on genetic algorithm optimization was proposed and applied to chip detection and classification. By using electromagnetic probes to collect the electromagnetic signals generated by different chips in the same operating state and using the electromagnetic radiation signals as the basis for chip identification and classification, the signals are put into the BP-AdaBoost model optimized by genetic algorithm for learning and training. Experimental results show that this method has good effect in the application of chip recognition and classification.
{"title":"Counterfeit IC Detection Research Based on BP-AdaBoost Model and Genetic Algorithm","authors":"Junyan Liu, Xiong-wei Li, Lin-fang Liu, Zhihui Wang, Panfei Du, Kang Li","doi":"10.12783/dtcse/cisnr2020/35142","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35142","url":null,"abstract":"In view of the increasingly prominent problems exposed by chips in integrated circuits and the destructive problems of traditional chip detection methods, a BPAdaBoost neural network model based on genetic algorithm optimization was proposed and applied to chip detection and classification. By using electromagnetic probes to collect the electromagnetic signals generated by different chips in the same operating state and using the electromagnetic radiation signals as the basis for chip identification and classification, the signals are put into the BP-AdaBoost model optimized by genetic algorithm for learning and training. Experimental results show that this method has good effect in the application of chip recognition and classification.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"113 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88466175","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35167
Siqing Wang, Yunzhu Liu
Aiming at the requirement for the establishment of intelligent and autonomous targets for air defense weapon simulation training, this paper uses modular and componentized model structure to construct the framework and granular analysis of CGF air target modeling. In this paper, a target maneuvering model, a radar fire control model and an intelligent expert decision-making model are established, and there are two target construction methods: autonomous and controlled. The simulation experiment is conducted with a certain type of air defense weapon target simulator as the background. The results show that this model solves the problem of single target parameter in the CGF simulation training system, training complexity and lack of realism, and meets the requirements of simulation training and strengthens training. The immersion of the personnel has effectively improved the training level. And the component-based development model gives the model good reusability and interactivity.
{"title":"Modeling and Simulation of CGF Aerial Targets for Simulation Training","authors":"Siqing Wang, Yunzhu Liu","doi":"10.12783/dtcse/cisnr2020/35167","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35167","url":null,"abstract":"Aiming at the requirement for the establishment of intelligent and autonomous targets for air defense weapon simulation training, this paper uses modular and componentized model structure to construct the framework and granular analysis of CGF air target modeling. In this paper, a target maneuvering model, a radar fire control model and an intelligent expert decision-making model are established, and there are two target construction methods: autonomous and controlled. The simulation experiment is conducted with a certain type of air defense weapon target simulator as the background. The results show that this model solves the problem of single target parameter in the CGF simulation training system, training complexity and lack of realism, and meets the requirements of simulation training and strengthens training. The immersion of the personnel has effectively improved the training level. And the component-based development model gives the model good reusability and interactivity.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73220268","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35129
Shu Zong, Jun Xiao, Zhi-zhu Liu, Xiuhao Xi
Taking a high speed on-off valve as an example, the effects of air gap, shell thickness, armature length, guide sleeve type and armature radius on the electromagnetic force performance are studied. The results show that the air gap is negatively related to the electromagnetic force, the shell thickness, armature length and armature radius are positively related to the electromagnetic force, and the effect of pure copper guide sleeve and non-guide sleeve on the electromagnetic force is basically the same. The electromagnetic force can be increased by the guide sleeve with magnetic separation ring. The influence order of parameters on electromagnetic force is: air gap > armature radius increment > armature length increment > shell thickness increment.
{"title":"Research on Electromagnetic Force Performance of High Speed on-off Valve","authors":"Shu Zong, Jun Xiao, Zhi-zhu Liu, Xiuhao Xi","doi":"10.12783/dtcse/cisnr2020/35129","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35129","url":null,"abstract":"Taking a high speed on-off valve as an example, the effects of air gap, shell thickness, armature length, guide sleeve type and armature radius on the electromagnetic force performance are studied. The results show that the air gap is negatively related to the electromagnetic force, the shell thickness, armature length and armature radius are positively related to the electromagnetic force, and the effect of pure copper guide sleeve and non-guide sleeve on the electromagnetic force is basically the same. The electromagnetic force can be increased by the guide sleeve with magnetic separation ring. The influence order of parameters on electromagnetic force is: air gap > armature radius increment > armature length increment > shell thickness increment.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81506923","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35130
Ping Deng, Lian Song, Mi Zhang
In order to effectively predict the lockage freight volume of the Three Gorges Dam area, an improved grey prediction model for the lockage freight volume is proposed under the action of the optimized variable weight weakening buffer operator. By exploring the trend of the original data of freight volume, it is found that the original data sequence has the oscillation properties of "small sample" and "shock wave interference". The classical GM(1,1) model is difficult to simulate well for non-homogeneous exponential sequences and trend mutation sequences. So the method of constructing optimized variable weight weakening buffer operator is proposed by introducing accumulative transformation and translation transformation. On this basis, a new grey prediction model adapted to the lockage freight volume of the Three Gorges Dam area is established, and a case forecast is performed. By comparing and analyzing the prediction accuracy of the improved gray model and the traditional prediction model, it can be clearly seen that the improved gray model prediction accuracy of the optimized variable weight weakening buffer operator is significantly improved.
{"title":"Forecasting Method for Lockage Freight Volume of Three Gorges Dam Area Based on Optimized Grey Buffer Operator","authors":"Ping Deng, Lian Song, Mi Zhang","doi":"10.12783/dtcse/cisnr2020/35130","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35130","url":null,"abstract":"In order to effectively predict the lockage freight volume of the Three Gorges Dam area, an improved grey prediction model for the lockage freight volume is proposed under the action of the optimized variable weight weakening buffer operator. By exploring the trend of the original data of freight volume, it is found that the original data sequence has the oscillation properties of \"small sample\" and \"shock wave interference\". The classical GM(1,1) model is difficult to simulate well for non-homogeneous exponential sequences and trend mutation sequences. So the method of constructing optimized variable weight weakening buffer operator is proposed by introducing accumulative transformation and translation transformation. On this basis, a new grey prediction model adapted to the lockage freight volume of the Three Gorges Dam area is established, and a case forecast is performed. By comparing and analyzing the prediction accuracy of the improved gray model and the traditional prediction model, it can be clearly seen that the improved gray model prediction accuracy of the optimized variable weight weakening buffer operator is significantly improved.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91199829","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35134
Xiangxiang Chen, Shu-Wen Wang, Jin Rong, Mengmeng Zhang, Wangchun Wu
As an important part of image processing, digital image inpainting is more and more widely used in daily life. Its main repair method is to automatically recover lost information based on the existing information of the damaged image. The article first explains the concept and application of image inpainting; secondly, it outlines the current main image inpainting techniques and main evaluation methods; and finally, the prospect of image inpainting techniques.
{"title":"Overview of Digital Image Inpainting Technology","authors":"Xiangxiang Chen, Shu-Wen Wang, Jin Rong, Mengmeng Zhang, Wangchun Wu","doi":"10.12783/dtcse/cisnr2020/35134","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35134","url":null,"abstract":"As an important part of image processing, digital image inpainting is more and more widely used in daily life. Its main repair method is to automatically recover lost information based on the existing information of the damaged image. The article first explains the concept and application of image inpainting; secondly, it outlines the current main image inpainting techniques and main evaluation methods; and finally, the prospect of image inpainting techniques.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"74 274 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83317048","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35133
Bin Qin
{"title":"Elliptical Microlens Fabrication by Spatially Shaped Femtosecond Laser-assisted Chemical Etching","authors":"Bin Qin","doi":"10.12783/dtcse/cisnr2020/35133","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35133","url":null,"abstract":"","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85142081","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35172
Hongliang Yu, Hao Xu, Fuxiang Cong
This paper studies life cycle consulting of engineering construction risk. Firstly build a risk evaluation hierarchy for the life cycle consulting of engineering construction risk, and then transform expert evaluation information into intuitionistic fuzzy sets to form an evaluation matrix, use intuitionistic fuzzy entropy to describe the degree of fuzziness of expert information and determine the criterion weight; then use Euclidean distance to determine the similarity of expert information The expert weight is determined by combining the degree of hesitation with the degree of hesitation, and the score function is used to determine the comprehensive score value of each risk factor, and the risk factor is predicted accordingly.
{"title":"Life Cycle Consulting of Engineering Construction Risk Evaluation Based Intuitionistic Fuzzy Sets and Euclidean Similarity","authors":"Hongliang Yu, Hao Xu, Fuxiang Cong","doi":"10.12783/dtcse/cisnr2020/35172","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35172","url":null,"abstract":"This paper studies life cycle consulting of engineering construction risk. Firstly build a risk evaluation hierarchy for the life cycle consulting of engineering construction risk, and then transform expert evaluation information into intuitionistic fuzzy sets to form an evaluation matrix, use intuitionistic fuzzy entropy to describe the degree of fuzziness of expert information and determine the criterion weight; then use Euclidean distance to determine the similarity of expert information The expert weight is determined by combining the degree of hesitation with the degree of hesitation, and the score function is used to determine the comprehensive score value of each risk factor, and the risk factor is predicted accordingly.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85254132","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 : 2020-12-30DOI: 10.12783/dtcse/cisnr2020/35135
Gang Li, Wei Qiu, Shuwei Li
The power factor correction (PFC) can be realized by the input-output linearization method for boost converter, The advantage is that the duty cycle of MOS transistor can be calculated directly without control parameter setting, but when the converter is connected to constant power load (CPL), because the duty cycle formula includes the ratio of output voltage to current, the load of Buck CPL has no current flow during the toff period, so the normal calculation results cannot be given. In order to solve the problem that the output duty cycle cannot be calculated, this paper starts from the relationship of equal input and output power, and merges resistance into the output terminal. At the same time, in order to reduce the power loss, the capacitor is connected to the original circuit to provide continuous current to correct the current discontinuity, and then the output voltage is precisely adjusted to realize the fast constant voltage control of Boost PFC converter under CPL.
{"title":"Boost PFC Constant Voltage Control with Constant Power Load","authors":"Gang Li, Wei Qiu, Shuwei Li","doi":"10.12783/dtcse/cisnr2020/35135","DOIUrl":"https://doi.org/10.12783/dtcse/cisnr2020/35135","url":null,"abstract":"The power factor correction (PFC) can be realized by the input-output linearization method for boost converter, The advantage is that the duty cycle of MOS transistor can be calculated directly without control parameter setting, but when the converter is connected to constant power load (CPL), because the duty cycle formula includes the ratio of output voltage to current, the load of Buck CPL has no current flow during the toff period, so the normal calculation results cannot be given. In order to solve the problem that the output duty cycle cannot be calculated, this paper starts from the relationship of equal input and output power, and merges resistance into the output terminal. At the same time, in order to reduce the power loss, the capacitor is connected to the original circuit to provide continuous current to correct the current discontinuity, and then the output voltage is precisely adjusted to realize the fast constant voltage control of Boost PFC converter under CPL.","PeriodicalId":11066,"journal":{"name":"DEStech Transactions on Computer Science and Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76492008","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：