Pub Date : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170289
Xue Li, Yanlong Song, Weilu Shan
A bi-level joint planning model of distributed generation (DG), electric vehicle charging station (EVCS) and active distribution network (ADN) framework is proposed by considering demand side management (DSM). The upper ADN framework planning model is established by taking the lowest annual comprehensive cost as the upper level objective, which is solved by the improved partheno-genetic algorithm (IPGA). Based on the upper framework scheme, the lower DG and EVCS planning model is established to minimum the annual construction maintenance cost, and is solved by the biogeography-based optimization (BBO) algorithm. Simulation results confirm the effectiveness of the proposed joint planning method of DG, EVCS and ADN framework.
{"title":"Joint Planning of Distributed Generation, Electric Vehicle Charging Station, and Active Distribution Network Framework","authors":"Xue Li, Yanlong Song, Weilu Shan","doi":"10.1109/ISKE47853.2019.9170289","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170289","url":null,"abstract":"A bi-level joint planning model of distributed generation (DG), electric vehicle charging station (EVCS) and active distribution network (ADN) framework is proposed by considering demand side management (DSM). The upper ADN framework planning model is established by taking the lowest annual comprehensive cost as the upper level objective, which is solved by the improved partheno-genetic algorithm (IPGA). Based on the upper framework scheme, the lower DG and EVCS planning model is established to minimum the annual construction maintenance cost, and is solved by the biogeography-based optimization (BBO) algorithm. Simulation results confirm the effectiveness of the proposed joint planning method of DG, EVCS and ADN framework.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"586 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121133532","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170271
Wenhui Li, You-shan Qu, Ying Wang, Jialun Liu
Simulation tools are widely used in intelligent vehicle systems and robot auto-control systems. They considerably contribute in the cost reduction of the validation and testing stages of the new intelligent functionalities. As one of the common parts of these systems, visual sensors need to be simulated physically, in order to enable the implementation of the computer vision-based perception techniques in the virtual environment. Fish-eye cameras are often used in this techniques to provide an omnidirectional field of view, and thus need to be simulated. The existing methods cannot simulate the output image of specific real fish-eye cameras. In this paper, we present a post-processing fisheye camera simulation method. According to the stereographic projection model, a mapping is established between the output image and a cube-map rendered with the graphic engine. In order to simulate the output of a specific camera, the distortion of the real camera is measured and added to the simulated image. Experimental result shows that our simulation method can give output close enough to the image captured by a specific fish-eye camera. The practicality of our method is validated in an actual application.
{"title":"Camera-Specific Simulation Method of Fish-Eye Image","authors":"Wenhui Li, You-shan Qu, Ying Wang, Jialun Liu","doi":"10.1109/ISKE47853.2019.9170271","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170271","url":null,"abstract":"Simulation tools are widely used in intelligent vehicle systems and robot auto-control systems. They considerably contribute in the cost reduction of the validation and testing stages of the new intelligent functionalities. As one of the common parts of these systems, visual sensors need to be simulated physically, in order to enable the implementation of the computer vision-based perception techniques in the virtual environment. Fish-eye cameras are often used in this techniques to provide an omnidirectional field of view, and thus need to be simulated. The existing methods cannot simulate the output image of specific real fish-eye cameras. In this paper, we present a post-processing fisheye camera simulation method. According to the stereographic projection model, a mapping is established between the output image and a cube-map rendered with the graphic engine. In order to simulate the output of a specific camera, the distortion of the real camera is measured and added to the simulated image. Experimental result shows that our simulation method can give output close enough to the image captured by a specific fish-eye camera. The practicality of our method is validated in an actual application.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116295178","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170415
Jie Hu, Tianrui Li, Yan Yang, Peng Xie, Xueli Xiao
Nowadays, multi-view dataset have become ubiquitous along with more and more data are gathered from different measuring technologies or various sources, in which various aspects of dataset are formalized as multiple views. Although a variety of multi-view clustering analysis approaches have been put forward to uncover the cluster structure hidden in the data, most of these existing methods are based on such a hypothesis: the relationship between objects and clusters are definite. However, most of the data in our real life may have no clear cluster boundaries but have indistinct or overlapping boundaries. How to effectively reveal the uncertain cluster structure under multiview data is still a big challenge for multi-view clustering analysis. Inspired by the powerful uncertain information modeling and analysis capabilities of rough and fuzzy sets, this paper proposes a new multi-view clustering method to discover the uncertain cluster information. A rough set concept based cluster centroid updating strategy is designed to efficiently describe the uncertain construction of clusters. A view weight is introduced to capture the different importance of various views. A fuzzy-based iterative optimization objective function is developed to fuse different view information. Finally, an efficient iterative optimization algorithm is devised to solve the proposed rough fuzzy objective function. Experiments on widely used benchmark datasets prove that our proposed method is always superior to several latest clustering approaches.
{"title":"RFMC: A Rough Fuzzy Multi-view Clustering Approach","authors":"Jie Hu, Tianrui Li, Yan Yang, Peng Xie, Xueli Xiao","doi":"10.1109/ISKE47853.2019.9170415","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170415","url":null,"abstract":"Nowadays, multi-view dataset have become ubiquitous along with more and more data are gathered from different measuring technologies or various sources, in which various aspects of dataset are formalized as multiple views. Although a variety of multi-view clustering analysis approaches have been put forward to uncover the cluster structure hidden in the data, most of these existing methods are based on such a hypothesis: the relationship between objects and clusters are definite. However, most of the data in our real life may have no clear cluster boundaries but have indistinct or overlapping boundaries. How to effectively reveal the uncertain cluster structure under multiview data is still a big challenge for multi-view clustering analysis. Inspired by the powerful uncertain information modeling and analysis capabilities of rough and fuzzy sets, this paper proposes a new multi-view clustering method to discover the uncertain cluster information. A rough set concept based cluster centroid updating strategy is designed to efficiently describe the uncertain construction of clusters. A view weight is introduced to capture the different importance of various views. A fuzzy-based iterative optimization objective function is developed to fuse different view information. Finally, an efficient iterative optimization algorithm is devised to solve the proposed rough fuzzy objective function. Experiments on widely used benchmark datasets prove that our proposed method is always superior to several latest clustering approaches.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"322 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121616012","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170325
Chunmei Chang, Hongmei Lin, Qiuting Wang, Xuehui Hou, Yefei Zhang, L. Zou
With the rapid development of artificial intelligence, it is of significance in practical application to reasoning in uncertain environment and to make judgment and reasonable decision on this basis. In order to deal with the multiple class data in uncertain environment, we standardize it and convert it into linguistic ordered pair 3-tuple which can describe the linguistic values from both positive and negative aspects, so as to obtain more reasonable reasoning results. Based on the linguistic 2-tuple, this paper constructs a standardized transformation model between the interval-valued fuzzy set and linguistic ordered pair 3-tuple by defining the transformation operator, which solves the problem of data standardization of this type. Furthermore, aiming at the problem of reasoning in uncertain linguistic environment, four operators of linguistic ordered pair 3-tuple are proposed and their properties are discussed. At the same time, in order to increase the credibility of linguistic ordered pair 3-tuple reasoning, we present a reasoning model of linguistic ordered pair 3-tuple combined with the similarity between the rules of linguistic ordered pair 3-tuple. Finally, an example which concerned the intelligent case system is given to illustrate the effectiveness and rationality of the proposed method.
{"title":"An Approach of Fuzzy Reasoning Based on Linguistic Ordered Pair 3-tuple","authors":"Chunmei Chang, Hongmei Lin, Qiuting Wang, Xuehui Hou, Yefei Zhang, L. Zou","doi":"10.1109/ISKE47853.2019.9170325","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170325","url":null,"abstract":"With the rapid development of artificial intelligence, it is of significance in practical application to reasoning in uncertain environment and to make judgment and reasonable decision on this basis. In order to deal with the multiple class data in uncertain environment, we standardize it and convert it into linguistic ordered pair 3-tuple which can describe the linguistic values from both positive and negative aspects, so as to obtain more reasonable reasoning results. Based on the linguistic 2-tuple, this paper constructs a standardized transformation model between the interval-valued fuzzy set and linguistic ordered pair 3-tuple by defining the transformation operator, which solves the problem of data standardization of this type. Furthermore, aiming at the problem of reasoning in uncertain linguistic environment, four operators of linguistic ordered pair 3-tuple are proposed and their properties are discussed. At the same time, in order to increase the credibility of linguistic ordered pair 3-tuple reasoning, we present a reasoning model of linguistic ordered pair 3-tuple combined with the similarity between the rules of linguistic ordered pair 3-tuple. Finally, an example which concerned the intelligent case system is given to illustrate the effectiveness and rationality of the proposed method.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124140400","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}
Multi-scale representation ability is one of key criteria for measuring convolutional neural networks (CNNs) effectiveness. Recent studies have shown that multi-scale features can represent different semantic information of original images, and a combination of them would have positive influence on vision tasks. Many researchers are investigated in extract the multi-scale features in a layerwise manner and equipped with relatively inflexible receptive field. In this paper, we propose a multi-scale attention (MSA) module for CNNs, namely MSANet, where the residual block comprises hierarchical attention connections and skip connections. The MSANet improves the multi-scale representation power of the network by adaptively enriching the receptive fields of each convolutional branch. We insert the proposed MSANet block into several backbone CNN models and achieve consistent improvement over backbone models on CIFAR-100 dataset. To better verify the effectiveness of MSANet, the experimental results on major network details, i.e., scale, depth, further demonstrate the superiority of the MSANet over the Res2Net methods.
{"title":"MSANet: A Multi-Scale Attention Module","authors":"Yucheng Huang, Wei Liu, Chao Li, Yongsheng Liang, Huoxiang Yang, Fanyang Meng","doi":"10.1109/iske47853.2019.9170354","DOIUrl":"https://doi.org/10.1109/iske47853.2019.9170354","url":null,"abstract":"Multi-scale representation ability is one of key criteria for measuring convolutional neural networks (CNNs) effectiveness. Recent studies have shown that multi-scale features can represent different semantic information of original images, and a combination of them would have positive influence on vision tasks. Many researchers are investigated in extract the multi-scale features in a layerwise manner and equipped with relatively inflexible receptive field. In this paper, we propose a multi-scale attention (MSA) module for CNNs, namely MSANet, where the residual block comprises hierarchical attention connections and skip connections. The MSANet improves the multi-scale representation power of the network by adaptively enriching the receptive fields of each convolutional branch. We insert the proposed MSANet block into several backbone CNN models and achieve consistent improvement over backbone models on CIFAR-100 dataset. To better verify the effectiveness of MSANet, the experimental results on major network details, i.e., scale, depth, further demonstrate the superiority of the MSANet over the Res2Net methods.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126445400","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170454
En Shi, Xun Gong, Jun Luo, Zhemin Zhang
Ultrasound (US) is one of a primary imageological examination and preoperative assessment for brleast nodules. However, in the field of ultrasound diagnosis, it relies heavily on the experience of physicians due to the overlapping image expression of benign and malignant breast nodules. The diagnostic accuracy of physicians with different qualifications differs by up to 30%. Therefore, it is easy to lead to misdiagnosis and increase the needless rate of puncture biopsy. On the other hand, the current computer-assisted breast ultrasound diagnosis requires lots of human interactions while the accuracy is not reliable enough. In this paper, an end-to-end model is proposed for automatically nodule classification. We presents a heterogeneous three-branch network (HTBN) for benign and malignant classification of the breast ultrasound images. In HTBN, the image information including ultrasound images, contrastenhanced ultrasound (CEUS) images and non-image information including patient’s age and other six pathological features are used simultaneously. In order to validate our method, a breast ultrasound data set with 1303 cases is collected. On this data set, the average diagnosis accuracy of physicians with five-year qualifications is 85.3%. However, the classification accuracy of our method is 92.41%. Through experiments, we confirmed our point of view that by incorporating medical knowledge into the optimization process, adding contrast-enhanced ultrasound images and non-image information to the network, the accuracy and robustness of breast diagnosis are greatly improved.
{"title":"HTBN: A Heterogeneous Network for Breast Ultrasound Image Classification","authors":"En Shi, Xun Gong, Jun Luo, Zhemin Zhang","doi":"10.1109/ISKE47853.2019.9170454","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170454","url":null,"abstract":"Ultrasound (US) is one of a primary imageological examination and preoperative assessment for brleast nodules. However, in the field of ultrasound diagnosis, it relies heavily on the experience of physicians due to the overlapping image expression of benign and malignant breast nodules. The diagnostic accuracy of physicians with different qualifications differs by up to 30%. Therefore, it is easy to lead to misdiagnosis and increase the needless rate of puncture biopsy. On the other hand, the current computer-assisted breast ultrasound diagnosis requires lots of human interactions while the accuracy is not reliable enough. In this paper, an end-to-end model is proposed for automatically nodule classification. We presents a heterogeneous three-branch network (HTBN) for benign and malignant classification of the breast ultrasound images. In HTBN, the image information including ultrasound images, contrastenhanced ultrasound (CEUS) images and non-image information including patient’s age and other six pathological features are used simultaneously. In order to validate our method, a breast ultrasound data set with 1303 cases is collected. On this data set, the average diagnosis accuracy of physicians with five-year qualifications is 85.3%. However, the classification accuracy of our method is 92.41%. Through experiments, we confirmed our point of view that by incorporating medical knowledge into the optimization process, adding contrast-enhanced ultrasound images and non-image information to the network, the accuracy and robustness of breast diagnosis are greatly improved.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125731219","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170293
Xi Yang, Xudong Luo, Ying Liu
The application of artificial intelligence in the legal field can save a lot of the time for legal professionals. In particular, in this paper we propose a method for predicting what kind of conviction a suspect has according to the facts of the crime of the suspect. Specifically, we first pre-process the data and then use multiple classification methods to classify the crime facts, and finally combine the results of each model to gain a more accurate of conviction classification.
{"title":"Criminal Conviction Classification Based on Multiple Learning Methods","authors":"Xi Yang, Xudong Luo, Ying Liu","doi":"10.1109/ISKE47853.2019.9170293","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170293","url":null,"abstract":"The application of artificial intelligence in the legal field can save a lot of the time for legal professionals. In particular, in this paper we propose a method for predicting what kind of conviction a suspect has according to the facts of the crime of the suspect. Specifically, we first pre-process the data and then use multiple classification methods to classify the crime facts, and finally combine the results of each model to gain a more accurate of conviction classification.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115957226","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170321
Ning Hu, Fachao Li, Chenxia Jin
Regression analysis is a prediction method to determine the dependence between controllable variables and expected values of predictors. It is worth noting that the reality often cannot get the complete data in the study, this makes the regression analysis result is affected, although the study of classical regression model is more, but most are based on sample data integrity, data completely reliable as the basic premise, and does not take into account the sample data reliability problems caused by incomplete samples reliable degree affect the nature of the result of the regression model. This paper is based on statistical theory. The effect of sample size on prediction results is analyzed, the measurement strategy of sample credibility based on sample size is given, a sample aggregation method based on mean value is proposed, a weighted regression model based on sample size is established. Then, the comparative analysis is carried out by combining the concrete case with the common regression method. The results show that this method has good interpretability and maneuverability, and enriches the existing regression methods to some extent.
{"title":"Research on the Prediction Method of Weighted Regression Based on Sample Size","authors":"Ning Hu, Fachao Li, Chenxia Jin","doi":"10.1109/ISKE47853.2019.9170321","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170321","url":null,"abstract":"Regression analysis is a prediction method to determine the dependence between controllable variables and expected values of predictors. It is worth noting that the reality often cannot get the complete data in the study, this makes the regression analysis result is affected, although the study of classical regression model is more, but most are based on sample data integrity, data completely reliable as the basic premise, and does not take into account the sample data reliability problems caused by incomplete samples reliable degree affect the nature of the result of the regression model. This paper is based on statistical theory. The effect of sample size on prediction results is analyzed, the measurement strategy of sample credibility based on sample size is given, a sample aggregation method based on mean value is proposed, a weighted regression model based on sample size is established. Then, the comparative analysis is carried out by combining the concrete case with the common regression method. The results show that this method has good interpretability and maneuverability, and enriches the existing regression methods to some extent.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130050719","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170437
Ting Dong, Hui Shi, Yajie Zhu, Kai Li, Fengping Chai, Yan Wang
In order to guarantee the quality of embedded software, based on the software life cycle, a BP neural network is proposed to predict the software reliability. First analyze the various factors that affect the reliability of the software, and then select the metrics that affect the reliability of the software based on relevant standards and engineering practices. The software reliability measurement data in the actual project was collected, and the established software reliability prediction model is used to predict the software module defects, and the prediction results are compared with the real results. The comparison results show that the model can effectively predict the number of software module defects and effectively indicate the test key module for the software unit test work.
{"title":"Embedded Software Reliability Prediction Based on Software Life Cycle","authors":"Ting Dong, Hui Shi, Yajie Zhu, Kai Li, Fengping Chai, Yan Wang","doi":"10.1109/ISKE47853.2019.9170437","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170437","url":null,"abstract":"In order to guarantee the quality of embedded software, based on the software life cycle, a BP neural network is proposed to predict the software reliability. First analyze the various factors that affect the reliability of the software, and then select the metrics that affect the reliability of the software based on relevant standards and engineering practices. The software reliability measurement data in the actual project was collected, and the established software reliability prediction model is used to predict the software module defects, and the prediction results are compared with the real results. The comparison results show that the model can effectively predict the number of software module defects and effectively indicate the test key module for the software unit test work.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131575471","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}
Recently, software-defined satellite has become a research hotspot in the aerospace. Based on an advanced computing platform with open system architecture, researchers can upload software for specific tasks even the satellite has been launched into space. This paper we have designed an on-orbit application for China’s first software-defined satellite TianZhi-1, which use Android smartphone as a system platform. Two main tasks are focused on our work, one is to reduce data redundancy and the other is to compress the size of the software. First, a light-weight and extensible framework is designed to support different image processing algorithms. Following this, we propose a three-step approach for on-orbit valuable image extraction, include image denoising, stitching, and salient object extraction. Experiments on the real satellite achieve outstanding results.
{"title":"Design and Implementation of On-orbit Valuable Image Extraction for the TianZhi-1 Satellite","authors":"Yijun Lin, Junxing Hu, Ling X. Li, Fengge Wu, Junsuo Zhao","doi":"10.1109/ISKE47853.2019.9170453","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170453","url":null,"abstract":"Recently, software-defined satellite has become a research hotspot in the aerospace. Based on an advanced computing platform with open system architecture, researchers can upload software for specific tasks even the satellite has been launched into space. This paper we have designed an on-orbit application for China’s first software-defined satellite TianZhi-1, which use Android smartphone as a system platform. Two main tasks are focused on our work, one is to reduce data redundancy and the other is to compress the size of the software. First, a light-weight and extensible framework is designed to support different image processing algorithms. Following this, we propose a three-step approach for on-orbit valuable image extraction, include image denoising, stitching, and salient object extraction. Experiments on the real satellite achieve outstanding results.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131079320","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：