With the advent of 5G era, The Internet of Things (IoT) is obtaining considerable attention in all walks of life nowadays. However, due to the hardware problems of devices, there may exists some security problems in IOT. While existing intrusion detection methods rarely consider the time series feature of the data. In this paper, we propose an anomaly monitoring model for Autoencoder based on Long-Short Term Memory (LSTMs-AE), in which LTSM is exploited to capture time-series features and the intrusion detection is performed by the feature learning ability of Autoencoder. Thorough experiments demonstrate that our model has better intrusion detection performance than ordinary Autoencoder, as in most of the dataset the accuracy rate of proposed scheme exceeds 0.95.
{"title":"Deep Learning for IoT Intrusion Detection based on LSTMs-AE","authors":"Yingfei Xu, Yong Tang, Qiang Yang","doi":"10.1145/3421766.3421891","DOIUrl":"https://doi.org/10.1145/3421766.3421891","url":null,"abstract":"With the advent of 5G era, The Internet of Things (IoT) is obtaining considerable attention in all walks of life nowadays. However, due to the hardware problems of devices, there may exists some security problems in IOT. While existing intrusion detection methods rarely consider the time series feature of the data. In this paper, we propose an anomaly monitoring model for Autoencoder based on Long-Short Term Memory (LSTMs-AE), in which LTSM is exploited to capture time-series features and the intrusion detection is performed by the feature learning ability of Autoencoder. Thorough experiments demonstrate that our model has better intrusion detection performance than ordinary Autoencoder, as in most of the dataset the accuracy rate of proposed scheme exceeds 0.95.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114625596","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 outbreak of novel coronavirus (2019-nCoV), wearing masks has become an effective way to prevent the transmission of the virus. But in public places, people are often reluctant to wear face masks and cause the virus to spread widely. This paper uses an efficient and robust object detection algorithm to automatically detect the faces with masks or without masks, making the epidemic prevention work more intelligent. Specifically, we collected an extensive database of 9886 images of people with and without face masks and manually labeled them, then use multi-scale training and image mixup methods to improve YOLOv3, an object detection algorithm, to automatically detect whether a face is wearing a mask. Our experiment results demonstrate that the mean Average Precision (mAP) of the improved YOLOv3 algorithm model reached 86.3%. This work can effectively and automatically detect whether people are wearing masks, which reduces the pressure of deploying human resources for checking masks in public places and has high practical application value.
{"title":"Robust Deep Learning Method to Detect Face Masks","authors":"Changjin Li, Jian Cao, Xing Zhang","doi":"10.1145/3421766.3421768","DOIUrl":"https://doi.org/10.1145/3421766.3421768","url":null,"abstract":"With the outbreak of novel coronavirus (2019-nCoV), wearing masks has become an effective way to prevent the transmission of the virus. But in public places, people are often reluctant to wear face masks and cause the virus to spread widely. This paper uses an efficient and robust object detection algorithm to automatically detect the faces with masks or without masks, making the epidemic prevention work more intelligent. Specifically, we collected an extensive database of 9886 images of people with and without face masks and manually labeled them, then use multi-scale training and image mixup methods to improve YOLOv3, an object detection algorithm, to automatically detect whether a face is wearing a mask. Our experiment results demonstrate that the mean Average Precision (mAP) of the improved YOLOv3 algorithm model reached 86.3%. This work can effectively and automatically detect whether people are wearing masks, which reduces the pressure of deploying human resources for checking masks in public places and has high practical application value.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133506424","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 author establish the dynamic model of vehicle power transmission, taking three gear to four gear as an example, Simulate the vehicle acceleration, Research the change of clutch control oil pressure and torque transmission. In order to improve the power performance and comfort performance of the whole vehicle in the shifting process, the control parameters of the shifting process are optimized to minimize the acceleration fluctuation of the whole vehicle in the shifting process
{"title":"Research on Analyse for Shifting Process of Automatic Transmission","authors":"Yi Zhang, Tian Wang, Q. Ren","doi":"10.1145/3421766.3421863","DOIUrl":"https://doi.org/10.1145/3421766.3421863","url":null,"abstract":"The author establish the dynamic model of vehicle power transmission, taking three gear to four gear as an example, Simulate the vehicle acceleration, Research the change of clutch control oil pressure and torque transmission. In order to improve the power performance and comfort performance of the whole vehicle in the shifting process, the control parameters of the shifting process are optimized to minimize the acceleration fluctuation of the whole vehicle in the shifting process","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130085259","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-bank mobile divisible, recoverable and transferable electronic cash system adapts on mobile terminals for e-business that can work in multi-banks and cannot confine from the bank which distributes the electronic cash. My thesis discusses on the protocol of the establishing account, the withdrawal protocol, the pay protocol, the deposit protocol, renew agreement of the electronic cash, the transferable agreement is based upon elliptic curve cryptography (ECC). The detachable electronic cash does not need bank by the usage of a electronic cash, so the bank will not turn into the bottleneck of e-business. This system is fitter for mobile micro-payment terminals with localization of storage, operand capacity, power supply and network bandwidth, which can satisfy the daily necessities of business. The new protocol can prevent from double spending, non-frameability, eavesdropping, tampering and "perfect crime" effectively as well. It can secured against mis-identity attacks, secured against two-layer anonymity attacks, secured against linking attacks.
{"title":"Electronic Cash System based on Multi-Bank Mobile Divisible, Recoverable and Transferable","authors":"Ting Huang","doi":"10.1145/3421766.3421788","DOIUrl":"https://doi.org/10.1145/3421766.3421788","url":null,"abstract":"Multi-bank mobile divisible, recoverable and transferable electronic cash system adapts on mobile terminals for e-business that can work in multi-banks and cannot confine from the bank which distributes the electronic cash. My thesis discusses on the protocol of the establishing account, the withdrawal protocol, the pay protocol, the deposit protocol, renew agreement of the electronic cash, the transferable agreement is based upon elliptic curve cryptography (ECC). The detachable electronic cash does not need bank by the usage of a electronic cash, so the bank will not turn into the bottleneck of e-business. This system is fitter for mobile micro-payment terminals with localization of storage, operand capacity, power supply and network bandwidth, which can satisfy the daily necessities of business. The new protocol can prevent from double spending, non-frameability, eavesdropping, tampering and \"perfect crime\" effectively as well. It can secured against mis-identity attacks, secured against two-layer anonymity attacks, secured against linking attacks.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116594642","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}
F. Meng, Dashun Zhang, Jing Wang, Liqin Miao, Penghui Li, Huizhong Hu, Xueguang Li
Virtual assembly simulation system plays a vital role in the intelligent manufacturing, especially in the field of complex machine or product manufacturing. The designing defects or product drawbacks could be identified in the designing period using the virtual assembly system. In this paper, the virtual simulation model of three-axis CNC machine was developed using virtual simulation software, interactive virtual assembly function was realized based on menu button, people can make assembly for the machine in the system, through the menu button, the interactive assembly could come true. Then using coarse-to-fine collision detection method and the face-level precision inspection to obtain assembly constraints, using a bounding box method for rough detection. The specific detection process was discussed in detail. The interactive virtual assembly simulation system was established and verified at last, it has great meaning for complex product machining.
{"title":"Design of Interactive Virtual Assembly Simulation System for CNC Machine Tool","authors":"F. Meng, Dashun Zhang, Jing Wang, Liqin Miao, Penghui Li, Huizhong Hu, Xueguang Li","doi":"10.1145/3421766.3421889","DOIUrl":"https://doi.org/10.1145/3421766.3421889","url":null,"abstract":"Virtual assembly simulation system plays a vital role in the intelligent manufacturing, especially in the field of complex machine or product manufacturing. The designing defects or product drawbacks could be identified in the designing period using the virtual assembly system. In this paper, the virtual simulation model of three-axis CNC machine was developed using virtual simulation software, interactive virtual assembly function was realized based on menu button, people can make assembly for the machine in the system, through the menu button, the interactive assembly could come true. Then using coarse-to-fine collision detection method and the face-level precision inspection to obtain assembly constraints, using a bounding box method for rough detection. The specific detection process was discussed in detail. The interactive virtual assembly simulation system was established and verified at last, it has great meaning for complex product machining.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116629835","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}
Four-wheel alignment parameters are important indexes to promise handling stability when automobile drives in straight line. Aiming at the problems of traditional four-wheel alignment measurement - kingpin inclination angle and kingpin caster angle are calculated indirectly and approximately by geometrical relationship, which cannot be measured directly or have large measurement error, etc. This paper proposes a new technique to obtain the four-wheel alignment parameters by means of installing an intelligent triple-axis acceleration sensor unit on the wheel to make inertia measurement on wheel alignment angle so as to establish a brand new four-wheel alignment attitude parameter calculation model to acquire four-wheel alignment parameters. The new technique proposed here can establish a four-wheel alignment parameters calculation model to acquire the parameters through installing an intelligent triple-axis acceleration sensor unit on the wheel. The experiment results indicate that under experimental conditions, the indication error of wheel alignment parameter (γwi, αwi, γki, θki) is (-0.01°, 0.00°, -0.65°, -0.31°), and the indication variance is (0.45°, 0.63°, 1.00°, 0.49°). This new technique is able to test the four-wheel alignment parameters quickly, dynamically and accurately, achieve a better measurement accuracy on performance index, and realize expected effect.
{"title":"A Technical Research on Parameters Acquisition of Automotive Four-wheel Alignment","authors":"Mengyao Pan, Shaowei Chen, Feng Wang, Ruitie Huan, Xiaoyong Lv, Yuqing Liu","doi":"10.1145/3421766.3421857","DOIUrl":"https://doi.org/10.1145/3421766.3421857","url":null,"abstract":"Four-wheel alignment parameters are important indexes to promise handling stability when automobile drives in straight line. Aiming at the problems of traditional four-wheel alignment measurement - kingpin inclination angle and kingpin caster angle are calculated indirectly and approximately by geometrical relationship, which cannot be measured directly or have large measurement error, etc. This paper proposes a new technique to obtain the four-wheel alignment parameters by means of installing an intelligent triple-axis acceleration sensor unit on the wheel to make inertia measurement on wheel alignment angle so as to establish a brand new four-wheel alignment attitude parameter calculation model to acquire four-wheel alignment parameters. The new technique proposed here can establish a four-wheel alignment parameters calculation model to acquire the parameters through installing an intelligent triple-axis acceleration sensor unit on the wheel. The experiment results indicate that under experimental conditions, the indication error of wheel alignment parameter (γwi, αwi, γki, θki) is (-0.01°, 0.00°, -0.65°, -0.31°), and the indication variance is (0.45°, 0.63°, 1.00°, 0.49°). This new technique is able to test the four-wheel alignment parameters quickly, dynamically and accurately, achieve a better measurement accuracy on performance index, and realize expected effect.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030553","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}
Wenkang Huang, Mengting Fan, Suhang Yang, Junqing Yuan, Xiongxiong He
Density Peak Clustering (DPC) algorithm can get better clustering results of data sets with lower dimensions. However, for the high-dimensional data sets, there are many nodes in the clustering center area; their densities are relatively high and close to each other, so that it is hard to identify the centering node accurately. It is found that the accuracy of the traditional DPC algorithm decreases terribly with the increasing of data set dimensions. In order to deal with the indistinguishable density problem, we propose a new clustering method, called Clustering by Finding Average Density (CFAD), which can enhance the clustering effect of high-dimensional data sets. Experiments show that the proposed algorithm outperforms DPC for both the artificial and the real data sets.
{"title":"Clustering by Finding Average Density","authors":"Wenkang Huang, Mengting Fan, Suhang Yang, Junqing Yuan, Xiongxiong He","doi":"10.1145/3421766.3421767","DOIUrl":"https://doi.org/10.1145/3421766.3421767","url":null,"abstract":"Density Peak Clustering (DPC) algorithm can get better clustering results of data sets with lower dimensions. However, for the high-dimensional data sets, there are many nodes in the clustering center area; their densities are relatively high and close to each other, so that it is hard to identify the centering node accurately. It is found that the accuracy of the traditional DPC algorithm decreases terribly with the increasing of data set dimensions. In order to deal with the indistinguishable density problem, we propose a new clustering method, called Clustering by Finding Average Density (CFAD), which can enhance the clustering effect of high-dimensional data sets. Experiments show that the proposed algorithm outperforms DPC for both the artificial and the real data sets.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126119786","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 this paper, through the multi-objective optimization design theory, a mathematical model with the maximum structural strength and minimum mass as the objective function is established, and the multi-objective optimization mathematical model can be solved, which the thickness of the square tube in the side frame components and support components is reduced from 3mm to 1.5mm can get the non-inferior optimal solution. Through ANSYS, the static analysis of the structure under full load and stacking conditions is carried out. Under the conditions of satisfying the structural rigidity, strength and deformation, the optimized structure is proposed, and the optimized structure is simulated and verified. The simulation results show that the optimized auxiliary carrying structure can reduce the weight by 17 percent on the basis of satisfying the requirements of use, which can better achieve the design goal and achieve the purpose of lightweight design of the carrying auxiliary fixture structure. This has engineering application value for the improved design of the carrying auxiliary fixture structure, and also provides a design idea for the same type of mechanical structure problems.
{"title":"Optimal Design of Carrying Auxiliary Fixtures in an Automobile Production Line Based on Static Analysis Method","authors":"Haibo Zhang, Yingqiu Li","doi":"10.1145/3421766.3421779","DOIUrl":"https://doi.org/10.1145/3421766.3421779","url":null,"abstract":"In this paper, through the multi-objective optimization design theory, a mathematical model with the maximum structural strength and minimum mass as the objective function is established, and the multi-objective optimization mathematical model can be solved, which the thickness of the square tube in the side frame components and support components is reduced from 3mm to 1.5mm can get the non-inferior optimal solution. Through ANSYS, the static analysis of the structure under full load and stacking conditions is carried out. Under the conditions of satisfying the structural rigidity, strength and deformation, the optimized structure is proposed, and the optimized structure is simulated and verified. The simulation results show that the optimized auxiliary carrying structure can reduce the weight by 17 percent on the basis of satisfying the requirements of use, which can better achieve the design goal and achieve the purpose of lightweight design of the carrying auxiliary fixture structure. This has engineering application value for the improved design of the carrying auxiliary fixture structure, and also provides a design idea for the same type of mechanical structure problems.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"46 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878837","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}
Flexible job shop problem (FJSP), which is inspired by the actual production process, is the most popular research direction in the field of intelligence production. In recent years, a more complex model with sequence-independent setup times (SDST) is proposed to make the solution of the problem in the specific production situation. In this paper, we investigate an FJSB model with SDST which is generated based on replacement of molds and the objective of this model is to minimize the makespan. We also design a selection hyper-heuristic algorithm for the problem. In order to evaluate the algorithm, we solve two problems, classical FJSP and the FJSP with SDST, and compare the results with other methods in other existing literature respectively. The experimental results prove that the approach proposed in this paper overmatch other algorithms in optimization ability and stability.
{"title":"Solving Flexible Job-shop Problem with Sequence-dependent Setup Times by Using Selection Hyper-heuristics","authors":"M. Luo, Jian Lin, Li Xu","doi":"10.1145/3421766.3421780","DOIUrl":"https://doi.org/10.1145/3421766.3421780","url":null,"abstract":"Flexible job shop problem (FJSP), which is inspired by the actual production process, is the most popular research direction in the field of intelligence production. In recent years, a more complex model with sequence-independent setup times (SDST) is proposed to make the solution of the problem in the specific production situation. In this paper, we investigate an FJSB model with SDST which is generated based on replacement of molds and the objective of this model is to minimize the makespan. We also design a selection hyper-heuristic algorithm for the problem. In order to evaluate the algorithm, we solve two problems, classical FJSP and the FJSP with SDST, and compare the results with other methods in other existing literature respectively. The experimental results prove that the approach proposed in this paper overmatch other algorithms in optimization ability and stability.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128849279","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 this design, the foot stamping machine is taken as the research object, and the traditional stamping tools are analyzed with the knowledge of ergonomics, mechanical design principle, simulation and design. Aiming at the problems of large workload, low work efficiency, high repetition rate and high labor cost of the existing stamping machine, a design scheme of foot batch stamping machine is proposed. By combining the knowledge of industrial engineering, such as ergonomics, mechanical design principle, simulation and design, the traditional stamping tools are analyzed, and a model is established to simulate and optimize the stamping machine and simulate batch operation. By using Flexsim simulation software to simulate and optimize the foot stamp machine, it is concluded that the working efficiency of the stamp machine is increased from 80.82% to 83.02%, and the total improvement rate of processing the stamp documents is 27.25%, which replaces many repetitive and tedious links such as manual stamp, delivery, sorting, and many other problems such as the high price and large size of the automatic stamp machine.
{"title":"Design of Simple Pedal Batch Seal Machine Based on Industrial Engineering Method","authors":"Guixiong Ou, Ziyuan Shen, Wei Chen","doi":"10.1145/3421766.3421791","DOIUrl":"https://doi.org/10.1145/3421766.3421791","url":null,"abstract":"In this design, the foot stamping machine is taken as the research object, and the traditional stamping tools are analyzed with the knowledge of ergonomics, mechanical design principle, simulation and design. Aiming at the problems of large workload, low work efficiency, high repetition rate and high labor cost of the existing stamping machine, a design scheme of foot batch stamping machine is proposed. By combining the knowledge of industrial engineering, such as ergonomics, mechanical design principle, simulation and design, the traditional stamping tools are analyzed, and a model is established to simulate and optimize the stamping machine and simulate batch operation. By using Flexsim simulation software to simulate and optimize the foot stamp machine, it is concluded that the working efficiency of the stamp machine is increased from 80.82% to 83.02%, and the total improvement rate of processing the stamp documents is 27.25%, which replaces many repetitive and tedious links such as manual stamp, delivery, sorting, and many other problems such as the high price and large size of the automatic stamp machine.","PeriodicalId":360184,"journal":{"name":"Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127665790","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：