This paper introduces a control method of gyro stabilized platform. By introducing the control principle of speed compensation, it points out the defect of dynamic error accumulation in speed compensation control algorithm, and proposes a control method based on dynamic position loop. In this paper, the stability accuracy of the speed compensation algorithm and the dynamic position loop compensation algorithm is tested through the application comparison on the two axis gyro stabilized platform. The test results show that the dynamic position loop control algorithm can greatly improve the stability performance of the gyro stabilized platform. The control algorithm is widely used in satellite communication antenna servo and photoelectric load equipment, and its performance is superior.
{"title":"A Control Method of Gyro Stabilized Platform Based on Dynamic Position Loop","authors":"Yong Zhang, Feiyu Song, Jian Wang","doi":"10.1145/3459104.3459130","DOIUrl":"https://doi.org/10.1145/3459104.3459130","url":null,"abstract":"This paper introduces a control method of gyro stabilized platform. By introducing the control principle of speed compensation, it points out the defect of dynamic error accumulation in speed compensation control algorithm, and proposes a control method based on dynamic position loop. In this paper, the stability accuracy of the speed compensation algorithm and the dynamic position loop compensation algorithm is tested through the application comparison on the two axis gyro stabilized platform. The test results show that the dynamic position loop control algorithm can greatly improve the stability performance of the gyro stabilized platform. The control algorithm is widely used in satellite communication antenna servo and photoelectric load equipment, and its performance is superior.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130903481","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}
The k-means algorithm has been widely used in the last several decades, but the efficiency of Lloyd's k-means algorithm drops sharply in dealing with large-scale data scenarios. To solve this problem, this paper proposes a fast k-means algorithm based on neighbor information. Firstly, we propose a localization strategy in the reassignment step of k-means. Through this strategy, the scale of distance calculation is greatly reduced. Secondly, we propose the neighbor update strategy. In such a way, more accurate neighbors for each cluster could be found in each iteration, thereby ensuring the clustering quality when the k-means algorithm converges. The proposed k-means algorithm was evaluated on multiple real-world datasets and increased the speed up to hundreds of times while only losing about 1.10% of the clustering result quality.
{"title":"Fast k-means Clustering Based on the Neighbor Information","authors":"Daowan Peng, Zizhong Chen, Jingcheng Fu, Shuyin Xia, Qing Wen","doi":"10.1145/3459104.3459194","DOIUrl":"https://doi.org/10.1145/3459104.3459194","url":null,"abstract":"The k-means algorithm has been widely used in the last several decades, but the efficiency of Lloyd's k-means algorithm drops sharply in dealing with large-scale data scenarios. To solve this problem, this paper proposes a fast k-means algorithm based on neighbor information. Firstly, we propose a localization strategy in the reassignment step of k-means. Through this strategy, the scale of distance calculation is greatly reduced. Secondly, we propose the neighbor update strategy. In such a way, more accurate neighbors for each cluster could be found in each iteration, thereby ensuring the clustering quality when the k-means algorithm converges. The proposed k-means algorithm was evaluated on multiple real-world datasets and increased the speed up to hundreds of times while only losing about 1.10% of the clustering result quality.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128282560","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}
Aspect term extraction (ATE) aims to extract aspect terms from reviews as opinion targets for sentiment analysis. Although some of the previous works prove that dependency relationship between aspect terms and context is useful for ATE, they have barely tried to use graph neural networks to capture valuable information in dependency patterns automatically. In this paper, we propose a novel sequence labeling method for ATE, which exploits convolutional neural network (CNN) to capture local information of a sentence, and further aggregate k-order neighbor nodes’ information via graph convolutional network (GCN) over dependency tree. Differently from approaches based on sequential networks like recurrent neural network (RNN), our convolution model can be calculated in parallel, which improves the training and inference speed. Experimental results show that our approach outperforms other baseline methods, which don't rely on pre-trained transformer model.
{"title":"STC: Stacked Two-stage Convolution for Aspect Term Extraction","authors":"Ruiqi Wang, Shuai Liu, Binhui Wang, Shusong Xing","doi":"10.1145/3459104.3459181","DOIUrl":"https://doi.org/10.1145/3459104.3459181","url":null,"abstract":"Aspect term extraction (ATE) aims to extract aspect terms from reviews as opinion targets for sentiment analysis. Although some of the previous works prove that dependency relationship between aspect terms and context is useful for ATE, they have barely tried to use graph neural networks to capture valuable information in dependency patterns automatically. In this paper, we propose a novel sequence labeling method for ATE, which exploits convolutional neural network (CNN) to capture local information of a sentence, and further aggregate k-order neighbor nodes’ information via graph convolutional network (GCN) over dependency tree. Differently from approaches based on sequential networks like recurrent neural network (RNN), our convolution model can be calculated in parallel, which improves the training and inference speed. Experimental results show that our approach outperforms other baseline methods, which don't rely on pre-trained transformer model.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122982629","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}
Shicheng Zu, Kai Yang, Xiulai Wang, Zhongzheng Yu, Yawen Hu, Jia Long
We have witnessed drastic progress in object detection in recent years due to the development of neural networks. Most mainstream object detectors are inclined to detect objects of regular scale because their detection depends on deep convolutional feature maps. Our study focused on UAVs-based small object detection at a high altitude, i.e., 100 meters. We constructed a pipeline by integrating the foreground segmentation algorithm, the image classification algorithm, the boosted cascaded classifier, and the tracker together that can detect and track the small object progressively in a cascaded manner. We performed the qualitative and quantitative evaluation of our pipeline's performance under various complex conditions. The comparison study confirmed its superiority in small object detection and strong robustness against various influential nuisances. Based on our constructed pipeline, we developed a real-time UAVs-based small object detection and tracking system. The system architecture and the general steps taken by the UAVs to realize small object detection were also presented. Finally, we qualitatively and quantitatively evaluated 8 popular trackers based on relevant image attributes. The most suitable tracker can be determined in response to a given condition. Our study testified that by taking advantage of each algorithm germane to a given task, the implementation performance can be improved. We also performed a quantitative evaluation of the 8 trackers on each pertinent image attribute. The results are shown in table 2. For each attribute, we highlighted the most suitable tracker in bold. In term of IV, the trackers utilizing feature assembly, i.e., the CSR-DCF and AdaBoost or the trackers using the texture features, i.e., LBP and HoG, usually perform better because the texture features are not sensitive to the IV [21]. The MIL tracker with the Haar-like features, however, is sensitive to the IV because the Haar-like features reflect the pixel intensity variations by subtracting pixel intensities between adjacent rectangular regions [21]. As far as OCC is concerned, the AdaBoost has superior performance because it allows online switching of multiple features for every frame [19]. The KCF shows diminished performance because the FFT requires the filter and the search region size to be equal limiting the detection range [17]. The reduced performance is also observed in the GOTURN since it estimates the object's location with one forward pass [20]. For MB, the MOSSE has improved performance because the correlation between the filter and the image becomes an element-wise multiplication in Fourier domain [16]. The MEDIANFLOW tracker does not perform well in MB because the rapid unpredictable motion causes a large discrepancy between the forward and backward tracking trajectories [22]. The OV resembles the occlusion in some respects. The MOSSE has improved performance in OV because it can detect occlusion via Peak-To-Sidelobe Ratio (PSR) and rei
{"title":"UAVs-based Small Object Detection and Tracking in Various Complex Scenarios","authors":"Shicheng Zu, Kai Yang, Xiulai Wang, Zhongzheng Yu, Yawen Hu, Jia Long","doi":"10.1145/3459104.3459141","DOIUrl":"https://doi.org/10.1145/3459104.3459141","url":null,"abstract":"We have witnessed drastic progress in object detection in recent years due to the development of neural networks. Most mainstream object detectors are inclined to detect objects of regular scale because their detection depends on deep convolutional feature maps. Our study focused on UAVs-based small object detection at a high altitude, i.e., 100 meters. We constructed a pipeline by integrating the foreground segmentation algorithm, the image classification algorithm, the boosted cascaded classifier, and the tracker together that can detect and track the small object progressively in a cascaded manner. We performed the qualitative and quantitative evaluation of our pipeline's performance under various complex conditions. The comparison study confirmed its superiority in small object detection and strong robustness against various influential nuisances. Based on our constructed pipeline, we developed a real-time UAVs-based small object detection and tracking system. The system architecture and the general steps taken by the UAVs to realize small object detection were also presented. Finally, we qualitatively and quantitatively evaluated 8 popular trackers based on relevant image attributes. The most suitable tracker can be determined in response to a given condition. Our study testified that by taking advantage of each algorithm germane to a given task, the implementation performance can be improved. We also performed a quantitative evaluation of the 8 trackers on each pertinent image attribute. The results are shown in table 2. For each attribute, we highlighted the most suitable tracker in bold. In term of IV, the trackers utilizing feature assembly, i.e., the CSR-DCF and AdaBoost or the trackers using the texture features, i.e., LBP and HoG, usually perform better because the texture features are not sensitive to the IV [21]. The MIL tracker with the Haar-like features, however, is sensitive to the IV because the Haar-like features reflect the pixel intensity variations by subtracting pixel intensities between adjacent rectangular regions [21]. As far as OCC is concerned, the AdaBoost has superior performance because it allows online switching of multiple features for every frame [19]. The KCF shows diminished performance because the FFT requires the filter and the search region size to be equal limiting the detection range [17]. The reduced performance is also observed in the GOTURN since it estimates the object's location with one forward pass [20]. For MB, the MOSSE has improved performance because the correlation between the filter and the image becomes an element-wise multiplication in Fourier domain [16]. The MEDIANFLOW tracker does not perform well in MB because the rapid unpredictable motion causes a large discrepancy between the forward and backward tracking trajectories [22]. The OV resembles the occlusion in some respects. The MOSSE has improved performance in OV because it can detect occlusion via Peak-To-Sidelobe Ratio (PSR) and rei","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115945180","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}
Aspect-level sentiment classification aims to identify the sentiment polarity of a given aspect. However, most of the past methods do not analyze the role of words well, and the connection between context and a given aspects is not well realized, which greatly limits the effectiveness of the model. In this paper, we have designed a model based on the attention mechanism. First, the word embedding and aspect embedding are represented by pre-trained BERT coding. Next, we use the recurrent neural network to obtain the hidden state. Then, the context and aspect are related through the attention mechanism. Finally, the experiments were conducted on 3 data sets widely used in the field of sentiment analysis. The BATAE-GRU model was compared with several current advanced models. The results showed that the experimental results of the BATAE-GRU model were better than other models; Compared with the ATAE-LSTM model, the accuracy of the model in two comparative experiments has been improved by 6.9% and 9.9% respectively.
{"title":"BATAE-GRU: Attention-based Aspect Sentiment Analysis Model","authors":"Yuan Wang, Qian Wang","doi":"10.1145/3459104.3459110","DOIUrl":"https://doi.org/10.1145/3459104.3459110","url":null,"abstract":"Aspect-level sentiment classification aims to identify the sentiment polarity of a given aspect. However, most of the past methods do not analyze the role of words well, and the connection between context and a given aspects is not well realized, which greatly limits the effectiveness of the model. In this paper, we have designed a model based on the attention mechanism. First, the word embedding and aspect embedding are represented by pre-trained BERT coding. Next, we use the recurrent neural network to obtain the hidden state. Then, the context and aspect are related through the attention mechanism. Finally, the experiments were conducted on 3 data sets widely used in the field of sentiment analysis. The BATAE-GRU model was compared with several current advanced models. The results showed that the experimental results of the BATAE-GRU model were better than other models; Compared with the ATAE-LSTM model, the accuracy of the model in two comparative experiments has been improved by 6.9% and 9.9% respectively.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"5 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120862451","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}
This paper focuses on stabilization issues for the nonlinear singular systems with internal perturbations. A novel robust fuzzy control technique is investigated based on the state-derivative feedback approach. In this paper, the nonlinear perturbed singular systems are expressed by the uncertain Takagi-Sugeno fuzzy models. The so-called parallel distributed compensation method is applied to design the state-derivative feedback fuzzy controller. Considering the Takagi-Sugeno fuzzy perturbed singular systems, the Lyapunov stability theory is employed to derive sufficient stability conditions with decay rate. Then transform these stability conditions into a linear matrix inequality problem. In the end, a numerical example is provided to verify the applicability of the proposed robust fuzzy controller design method.
{"title":"Derivative-based Fuzzy Control Synthesis for Singular Takagi-Sugeno Fuzzy Systems with Perturbations","authors":"Wen‐Jer Chang, Che-Lun Su, Ming-Hsuan Tsai","doi":"10.1145/3459104.3459128","DOIUrl":"https://doi.org/10.1145/3459104.3459128","url":null,"abstract":"This paper focuses on stabilization issues for the nonlinear singular systems with internal perturbations. A novel robust fuzzy control technique is investigated based on the state-derivative feedback approach. In this paper, the nonlinear perturbed singular systems are expressed by the uncertain Takagi-Sugeno fuzzy models. The so-called parallel distributed compensation method is applied to design the state-derivative feedback fuzzy controller. Considering the Takagi-Sugeno fuzzy perturbed singular systems, the Lyapunov stability theory is employed to derive sufficient stability conditions with decay rate. Then transform these stability conditions into a linear matrix inequality problem. In the end, a numerical example is provided to verify the applicability of the proposed robust fuzzy controller design method.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121944976","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}
In order to take into full account the influence of operational scheduling, signal control and bus stations location, and solve the problem of inconsistency between dedicated bus priority coordination control sub-area and conventional coordination control sub-area, a novel sub-area division method was proposed in consideration of the dedicated bus dwell time, travel time and non-stop pass rate of intersections. Total travel time was calculated based on dedicated bus dwell time prediction, dedicated bus status before-stop and post-stop. Combined with the signal control strategy of downstream intersection, a non-stop pass rate calculation model was established to measure dedicated bus traffic efficiency. The pseudo F-statistic algorithm and clustering algorithm were used to determine initial division for dedicated bus priority. Moreover, intersection adjacent principle and period similarity principle were adapted to refine the division results. The results show that the dedicated bus non-stop pass probability can be greatly increased with a slight increase in the delay of social vehicles. Compared with the conventional coordination control sub-area, the method in this paper could the decrease average number of stops by 28.32% and decrease the per capita delay of arterial line by 12.79%. It proves that the dedicated bus coordination control sub-area division method is efficient and practical.
{"title":"Dedicated Bus Coordination Control Sub-area Division Method","authors":"Xiaoming Liu, Chunlin Shang, Shaohu Tang, G. Zhu","doi":"10.1145/3459104.3459959","DOIUrl":"https://doi.org/10.1145/3459104.3459959","url":null,"abstract":"In order to take into full account the influence of operational scheduling, signal control and bus stations location, and solve the problem of inconsistency between dedicated bus priority coordination control sub-area and conventional coordination control sub-area, a novel sub-area division method was proposed in consideration of the dedicated bus dwell time, travel time and non-stop pass rate of intersections. Total travel time was calculated based on dedicated bus dwell time prediction, dedicated bus status before-stop and post-stop. Combined with the signal control strategy of downstream intersection, a non-stop pass rate calculation model was established to measure dedicated bus traffic efficiency. The pseudo F-statistic algorithm and clustering algorithm were used to determine initial division for dedicated bus priority. Moreover, intersection adjacent principle and period similarity principle were adapted to refine the division results. The results show that the dedicated bus non-stop pass probability can be greatly increased with a slight increase in the delay of social vehicles. Compared with the conventional coordination control sub-area, the method in this paper could the decrease average number of stops by 28.32% and decrease the per capita delay of arterial line by 12.79%. It proves that the dedicated bus coordination control sub-area division method is efficient and practical.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117259890","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}
Pre-trained language representation models are very efficient in learning language representation independent from natural language processing tasks to be performed. The language representation models such as BERT and DistilBERT have achieved amazing results in many language understanding tasks. Studies on text classification problems in the literature are generally carried out for the English language. This study aims to classify the news in the Turkish language using pre-trained language representation models. In this study, we utilize BERT and DistilBERT by tuning both models for the text classification task to learn the categories of Turkish news with different tokenization methods. We provide a quantitative analysis of the performance of BERT and DistilBERT on the Turkish news dataset by comparing the models in terms of their representation capability in the text classification task. The highest performance is obtained with DistilBERT with an accuracy of 97.4%.
{"title":"Tuning Language Representation Models for Classification of Turkish News","authors":"Meltem Tokgoz, F. Turhan, Necva Bölücü, Burcu Can","doi":"10.1145/3459104.3459170","DOIUrl":"https://doi.org/10.1145/3459104.3459170","url":null,"abstract":"Pre-trained language representation models are very efficient in learning language representation independent from natural language processing tasks to be performed. The language representation models such as BERT and DistilBERT have achieved amazing results in many language understanding tasks. Studies on text classification problems in the literature are generally carried out for the English language. This study aims to classify the news in the Turkish language using pre-trained language representation models. In this study, we utilize BERT and DistilBERT by tuning both models for the text classification task to learn the categories of Turkish news with different tokenization methods. We provide a quantitative analysis of the performance of BERT and DistilBERT on the Turkish news dataset by comparing the models in terms of their representation capability in the text classification task. The highest performance is obtained with DistilBERT with an accuracy of 97.4%.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115131573","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 the rapid development of various hardware equipment and saving technology, multiple data with different types are uploaded to saving space. There are some private data can not be ignored. For provider, in order to use and deliver these private data to the third party, data anonymization, such as K-anonymity [1] should be applied to cover the explicit information. For receiver, there are still some way to transform these “fake” data to a new data set which obtain the same statistical properties with the original one while not exactly the same in detailed records. Under this condition, we want to show our work —— data perturbation and data reconstruction to deal with this problem. We use RGADP (Retrievable General Addictive Data Perturbation) [2] to produce data perturbation and EM algorithm to reconstruct data. And the results are Perturbated data can be produced by original data, and it can be delivered, reversed or further reconstructed easily. The reconstructed data still keeps the statistical properties as the original one. Compared with conditional way, this method can be more flexible to adjust the privacy protection degree according to the length of bias interval. We integrated these two process and report on the findings of our experimental evaluation.
随着各种硬件设备和存储技术的快速发展，不同类型的多个数据被上传，以节省空间。有一些私人数据是不容忽视的。对于提供者来说，为了将这些私有数据使用和传递给第三方，应该采用数据匿名化，如k -匿名[1]来覆盖显性信息。对于接收方来说，仍然有一些方法将这些“假”数据转换成一个新的数据集，该数据集具有与原始数据相同的统计属性，但在详细记录上并不完全相同。在这种情况下，我们要展示我们的工作——数据摄动和数据重建来处理这个问题。我们使用RGADP (Retrievable General addiction Data摄动)[2]产生数据摄动，并使用EM算法重建数据。结果表明:原始数据可以产生摄动数据，并且可以很容易地传递、反转或进一步重构。重建后的数据仍保持原始数据的统计特性。与有条件的方法相比，该方法可以更灵活地根据偏置间隔的长度来调整隐私保护程度。我们整合了这两个过程，并报告了我们的实验评估结果。
{"title":"A Design for Private Data Protection Combining with Data Perturbation and Data Reconstruction","authors":"Juting Wang, Wai Kin Victor Chan","doi":"10.1145/3459104.3459193","DOIUrl":"https://doi.org/10.1145/3459104.3459193","url":null,"abstract":"With the rapid development of various hardware equipment and saving technology, multiple data with different types are uploaded to saving space. There are some private data can not be ignored. For provider, in order to use and deliver these private data to the third party, data anonymization, such as K-anonymity [1] should be applied to cover the explicit information. For receiver, there are still some way to transform these “fake” data to a new data set which obtain the same statistical properties with the original one while not exactly the same in detailed records. Under this condition, we want to show our work —— data perturbation and data reconstruction to deal with this problem. We use RGADP (Retrievable General Addictive Data Perturbation) [2] to produce data perturbation and EM algorithm to reconstruct data. And the results are Perturbated data can be produced by original data, and it can be delivered, reversed or further reconstructed easily. The reconstructed data still keeps the statistical properties as the original one. Compared with conditional way, this method can be more flexible to adjust the privacy protection degree according to the length of bias interval. We integrated these two process and report on the findings of our experimental evaluation.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126620115","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}
The flight test of transport aircraft is an important segment in the process of aircraft development. In the effectiveness evaluation architecture of the test aircraft mission system, the availability of the test aircraft mission system is not only an important basis for measuring the system in an executable mission state but also an important evaluation parameter for the effectiveness of the aircraft and its system in completing the mission. Based on WSEIAC system effectiveness evaluation model, this paper analyzes the availability of test aircraft and its system in mission, and proposes a feasible availability analysis model based on the mission characteristics of flight tests.
{"title":"Research on Availability Model of Test Aircraft Mission System Based on Mission","authors":"Hao Song, Mingming Sun, Qingling Liu, M. Yi","doi":"10.1145/3459104.3459108","DOIUrl":"https://doi.org/10.1145/3459104.3459108","url":null,"abstract":"The flight test of transport aircraft is an important segment in the process of aircraft development. In the effectiveness evaluation architecture of the test aircraft mission system, the availability of the test aircraft mission system is not only an important basis for measuring the system in an executable mission state but also an important evaluation parameter for the effectiveness of the aircraft and its system in completing the mission. Based on WSEIAC system effectiveness evaluation model, this paper analyzes the availability of test aircraft and its system in mission, and proposes a feasible availability analysis model based on the mission characteristics of flight tests.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125979300","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：