Pub Date : 2022-10-22DOI: 10.1109/UV56588.2022.10185530
Ziye Fang, Shu Jiang, Xiaoyu Du, Zechao Li
The ocean is an important part of the ecosystem and is closely related to our lives. Detecting the status of algae in the ocean contributes to the protection of the marine environment. With the continuous development of target detection technology, small target detection tasks are gradually applied to the task of monitoring marine organisms. We use two-stage cascade RCNN with Res2Net, ResNeSt, CBNet, ConvNeXt and DetectoRS backbone. Secondly, data pre-processing was used with blur, motion blur, MixUp, random rotation and other data enhancements. Then the pseudo label training model is used as a pre-training model. And model ensemble is used to improve the inference results. Finally Post-processing is performed using reduced bbox. We conduct extensive experiments on the dataset and achieve the performance of 0.562.
{"title":"Deep Learning Based Algae Detection Method","authors":"Ziye Fang, Shu Jiang, Xiaoyu Du, Zechao Li","doi":"10.1109/UV56588.2022.10185530","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185530","url":null,"abstract":"The ocean is an important part of the ecosystem and is closely related to our lives. Detecting the status of algae in the ocean contributes to the protection of the marine environment. With the continuous development of target detection technology, small target detection tasks are gradually applied to the task of monitoring marine organisms. We use two-stage cascade RCNN with Res2Net, ResNeSt, CBNet, ConvNeXt and DetectoRS backbone. Secondly, data pre-processing was used with blur, motion blur, MixUp, random rotation and other data enhancements. Then the pseudo label training model is used as a pre-training model. And model ensemble is used to improve the inference results. Finally Post-processing is performed using reduced bbox. We conduct extensive experiments on the dataset and achieve the performance of 0.562.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121498246","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}
Nowadays, with the development of industrial production technology, defect detection has become an indispensable part of industrial production. However, due to various types of products and defects, it can be extremely difficult to identify and locate those defects precisely and accurately. The current major trend in defect detection is using convolutional neural networks and semantic segmentation techniques to better minimize the error rate of human eye recognition and highly improve efficiency. Our work is based on semantic segmentation method and combines it with transfer learning technique enabling our model to train on a relatively small dataset without compromising the performance, and use CNN to firstly classify input images in order to further reduce the number of images to improve computational efficiency and accuracy. Then through incorporating state-of-the-art semantic segmentation model U-Net++, our model achieves the best performance compared to UNet under transfer learning scenario. We compare our model with the state-of-the-art U-Net. Then we use mIOU and pixel accuracy to measure the models’ performance under two scenarios. Results illustrated that through transfer learning scenario, our model achieves the highest scores over other methods.
{"title":"Carpet Defect Detection by Transfer Learning Combing Classification and Semantic Segmentation","authors":"Tianqing Ren, Longfei Zhou, Ke Xu, Yifan Wang, Siyu Wu, Yuliang Gai, Jiazheng Chen, Zhichao Gou","doi":"10.1109/UV56588.2022.10185478","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185478","url":null,"abstract":"Nowadays, with the development of industrial production technology, defect detection has become an indispensable part of industrial production. However, due to various types of products and defects, it can be extremely difficult to identify and locate those defects precisely and accurately. The current major trend in defect detection is using convolutional neural networks and semantic segmentation techniques to better minimize the error rate of human eye recognition and highly improve efficiency. Our work is based on semantic segmentation method and combines it with transfer learning technique enabling our model to train on a relatively small dataset without compromising the performance, and use CNN to firstly classify input images in order to further reduce the number of images to improve computational efficiency and accuracy. Then through incorporating state-of-the-art semantic segmentation model U-Net++, our model achieves the best performance compared to UNet under transfer learning scenario. We compare our model with the state-of-the-art U-Net. Then we use mIOU and pixel accuracy to measure the models’ performance under two scenarios. Results illustrated that through transfer learning scenario, our model achieves the highest scores over other methods.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123498369","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185484
Wenjie Lin, Yajun Fang
Primary hyperhidrosis (PH) is a rare inherited disorder characterized by excessive sweating. It can affect any part of the body, but most commonly affects the axilla, palms of the hands, groin, chest, and soles of the feet. This paper comprehensively overviews current and potential diagnosis and management methods of PH from both medical and engineering perspectives. We also investigate how patients and society can live better with PH by non-invasive medical treatments and propose potential engineering and social interventions.
{"title":"Primary Hyperhidrosis: A Systematic Review of Current Status and Potential Interventions","authors":"Wenjie Lin, Yajun Fang","doi":"10.1109/UV56588.2022.10185484","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185484","url":null,"abstract":"Primary hyperhidrosis (PH) is a rare inherited disorder characterized by excessive sweating. It can affect any part of the body, but most commonly affects the axilla, palms of the hands, groin, chest, and soles of the feet. This paper comprehensively overviews current and potential diagnosis and management methods of PH from both medical and engineering perspectives. We also investigate how patients and society can live better with PH by non-invasive medical treatments and propose potential engineering and social interventions.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124172432","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185495
Mohammad Shokrolah Shirazi, Hung-Fu Chang, Shiqi Zhang
The turning movement count (TMC) is a salient data source used for design and planning of intersections including sign, and signal installation, timing setup, as well as traffic and capacity analysis. This work presents a typical framework for utilizing the TMC data with simulation of Urban MObility (SUMO) software to mimic realistic traffic scenarios for intersection evaluation and analysis. Due to safety and mobility concerns regarding school campus zones, three intersections around the San Jose State university are selected and their corresponding turning movement data are ported into SUMO for intersection evaluation during peak hours occurred between 8:00 - 9:00 a.m. The traffic parameters extracted from each intersection simulation with realistic scenario are vehicles waiting time, speed and network flow links which imply the effectiveness of utilizing proposed approach for decision making and targeting intersections for signal optimization.
{"title":"Intersection Evaluation Using Turning Movement Count Data and SUMO","authors":"Mohammad Shokrolah Shirazi, Hung-Fu Chang, Shiqi Zhang","doi":"10.1109/UV56588.2022.10185495","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185495","url":null,"abstract":"The turning movement count (TMC) is a salient data source used for design and planning of intersections including sign, and signal installation, timing setup, as well as traffic and capacity analysis. This work presents a typical framework for utilizing the TMC data with simulation of Urban MObility (SUMO) software to mimic realistic traffic scenarios for intersection evaluation and analysis. Due to safety and mobility concerns regarding school campus zones, three intersections around the San Jose State university are selected and their corresponding turning movement data are ported into SUMO for intersection evaluation during peak hours occurred between 8:00 - 9:00 a.m. The traffic parameters extracted from each intersection simulation with realistic scenario are vehicles waiting time, speed and network flow links which imply the effectiveness of utilizing proposed approach for decision making and targeting intersections for signal optimization.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128546083","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185476
Yalin Wen, Wei Ke, Hao Sheng
With the aging of population and the advance of technology, handwritten numeral recognition system is sophisticated and widely used. However, due to the presence of different writing surfaces, postures and other factors, the performance of handwritten numeral recognition is limited. In this paper, we propose a new supervised recurrent neural network, which combines time and space for target location prediction on handwritten datasets. Our method is based on the YOLO framework, and combines a long and short term memory (LSTM) mechanism. Moreover, our method not only locates handwritten images, but also improves the classification accuracy. Extensive comparison with the state-of-the-art methods demonstrates that our method achieves both accuracy and robustness on handwritten datasets. Meanwhile, our method is effective with low computational cost.
{"title":"Improved Handwritten Numeral Recognition on MNIST Dataset with YOLO and LSTM","authors":"Yalin Wen, Wei Ke, Hao Sheng","doi":"10.1109/UV56588.2022.10185476","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185476","url":null,"abstract":"With the aging of population and the advance of technology, handwritten numeral recognition system is sophisticated and widely used. However, due to the presence of different writing surfaces, postures and other factors, the performance of handwritten numeral recognition is limited. In this paper, we propose a new supervised recurrent neural network, which combines time and space for target location prediction on handwritten datasets. Our method is based on the YOLO framework, and combines a long and short term memory (LSTM) mechanism. Moreover, our method not only locates handwritten images, but also improves the classification accuracy. Extensive comparison with the state-of-the-art methods demonstrates that our method achieves both accuracy and robustness on handwritten datasets. Meanwhile, our method is effective with low computational cost.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"15 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132738181","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185524
Jaechul Roh, Minhao Cheng, Yajun Fang
Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models from various websites empowered the public users as well as some major institutions to give a momentum to their real-life application. However, it was recently proven that models become extremely vulnerable when they are backdoor attacked with trigger-inserted poisoned datasets by malicious users. The attackers then redistribute the victim models to the public to attract other users to use them, where the models tend to misclassify when certain triggers are detected within the training sample. In this paper, we will introduce a novel improved textual backdoor defense method, named MSDT, that outperforms the current existing defensive algorithms in specific datasets. The experimental results illustrate that our method can be effective and constructive in terms of defending against backdoor attack in text domain.
{"title":"MSDT: Masked Language Model Scoring Defense in Text Domain","authors":"Jaechul Roh, Minhao Cheng, Yajun Fang","doi":"10.1109/UV56588.2022.10185524","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185524","url":null,"abstract":"Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models from various websites empowered the public users as well as some major institutions to give a momentum to their real-life application. However, it was recently proven that models become extremely vulnerable when they are backdoor attacked with trigger-inserted poisoned datasets by malicious users. The attackers then redistribute the victim models to the public to attract other users to use them, where the models tend to misclassify when certain triggers are detected within the training sample. In this paper, we will introduce a novel improved textual backdoor defense method, named MSDT, that outperforms the current existing defensive algorithms in specific datasets. The experimental results illustrate that our method can be effective and constructive in terms of defending against backdoor attack in text domain.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"633 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116207004","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185527
Yupeng Niu, Jiaqi Xu, Jingxuan Tan
In this paper, a comprehensive prediction model of daily vaccination in China was established by using Informer long sequence prediction model. For the first time, we established a comprehensive prediction model considering the number of nearby residents, transportation convenience, number of medical personnel, vaccine storage and transportation costs.
{"title":"Vaccine Prediction and Distribution Model under the New Situation in China Based on Informer","authors":"Yupeng Niu, Jiaqi Xu, Jingxuan Tan","doi":"10.1109/UV56588.2022.10185527","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185527","url":null,"abstract":"In this paper, a comprehensive prediction model of daily vaccination in China was established by using Informer long sequence prediction model. For the first time, we established a comprehensive prediction model considering the number of nearby residents, transportation convenience, number of medical personnel, vaccine storage and transportation costs.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122901664","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185487
Yunchen Zhang, Wei Zeng, Fan Yang
This technical report introduces our solution for microalgae object detection in IEEE UV 2022 Vision Meets Alage Object Detection Challenge. The purpose of this challenge is to employ computer vision to more effectively analyze population change in ocean microalgae species. Therefore, we performed a comprehensive analysis of the distribution of the microalgae dataset and designed a customized training strategy for the task. In order to better identify the categories and coordinates of microalgae in microscopic images, we propose CBSwin-Cascade RCNN++ as a strong baseline for microalgae detection. Our final submission the results, which achieves 56.13 in mAP 0.5:0.95 on a single model, and obtains 57.09 in mAP 0.5:0.95 with the ensembled models.
{"title":"Towards Effective Microalgae Object Detection Solutions to IEEE UV 2022 “Vision Meets Alage” Object Detection Challenge","authors":"Yunchen Zhang, Wei Zeng, Fan Yang","doi":"10.1109/UV56588.2022.10185487","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185487","url":null,"abstract":"This technical report introduces our solution for microalgae object detection in IEEE UV 2022 Vision Meets Alage Object Detection Challenge. The purpose of this challenge is to employ computer vision to more effectively analyze population change in ocean microalgae species. Therefore, we performed a comprehensive analysis of the distribution of the microalgae dataset and designed a customized training strategy for the task. In order to better identify the categories and coordinates of microalgae in microscopic images, we propose CBSwin-Cascade RCNN++ as a strong baseline for microalgae detection. Our final submission the results, which achieves 56.13 in mAP 0.5:0.95 on a single model, and obtains 57.09 in mAP 0.5:0.95 with the ensembled models.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125164053","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185472
Fan He, Longfei Zhou, Siyu Wu, Haoliang Liu, Zehang Li, Ke Xu, Yuliang Gai, Fei Teng, Pengfei Liu
Vehicular traffic congestion is a severe global problem, leading to a range of issues such as increased travel times, increased fuel consumption, and increased pollutant emissions. The signal timing of traffic lights is one of the major factors that we can change to reduce traffic congestion at signalized intersections. Most traffic lights used in real life are hard-coded which means the fixed timing is applied for traffic control. In these hard-coded signalized intersection models, we do not have much to do to deal with real-time congestion, especially for large traffic volumes. In this study, we propose an adaptive signal timing control approach to reduce traffic congestion according to real-time traffic flow situations. In this novel approach, the signal timing can be changed over time based on real-time information about traffic flows. The Eclipse SUMO is used to simulate traffic conditions at real-world intersections to optimize road traffic light control and reduce real-time traffic delays for signalized intersections. Simulation results show that the proposed method obtains better performance than typical traffic light timing control strategies.
{"title":"A Novel Adaptive Signal Timing Control Approach for Signalized Intersections","authors":"Fan He, Longfei Zhou, Siyu Wu, Haoliang Liu, Zehang Li, Ke Xu, Yuliang Gai, Fei Teng, Pengfei Liu","doi":"10.1109/UV56588.2022.10185472","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185472","url":null,"abstract":"Vehicular traffic congestion is a severe global problem, leading to a range of issues such as increased travel times, increased fuel consumption, and increased pollutant emissions. The signal timing of traffic lights is one of the major factors that we can change to reduce traffic congestion at signalized intersections. Most traffic lights used in real life are hard-coded which means the fixed timing is applied for traffic control. In these hard-coded signalized intersection models, we do not have much to do to deal with real-time congestion, especially for large traffic volumes. In this study, we propose an adaptive signal timing control approach to reduce traffic congestion according to real-time traffic flow situations. In this novel approach, the signal timing can be changed over time based on real-time information about traffic flows. The Eclipse SUMO is used to simulate traffic conditions at real-world intersections to optimize road traffic light control and reduce real-time traffic delays for signalized intersections. Simulation results show that the proposed method obtains better performance than typical traffic light timing control strategies.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128831401","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 : 2022-10-22DOI: 10.1109/UV56588.2022.10185477
Ling Chen, Yaman Wang, Yuchen Long, Zengfeng Duan, Yanyan Li
Complex precision parts of electronic products are essential to defense information technology equipment and the manufacturing industry. The workshop testing process for electronic products is crucial to ensuring their quality is qualified. Due to its multi-breed, multi-batch, and complex structure, its experimental process design is challenged by more and more indicators and complex processes. Currently, the process of detecting complex electronic products still adopts manual process document design, which is inefficient and inconsistent, and it is difficult to guarantee accuracy by manual experience. Therefore, a new intelligent test process method is designed to complete the process design. The method first automatically extracts test indicators and related parameters from the imported unstructured technical files or sop files, then automatically matches the test indicators with the test table, then automatically fills the test parameters under each index, then clusters and outputs XML test procedures for each indicator. Moreover, the key technology of each process is studied, the intelligent test process system for complex electronic products is developed, and the application of one model of microwave component products in a military industry enterprise is used as an example. The test program generated by the system can be directly used for subsequent workshop machine execution.
{"title":"Research and Development of Intelligent Tests and a Process Design System for Complex and Precision Parts of Electronic Products","authors":"Ling Chen, Yaman Wang, Yuchen Long, Zengfeng Duan, Yanyan Li","doi":"10.1109/UV56588.2022.10185477","DOIUrl":"https://doi.org/10.1109/UV56588.2022.10185477","url":null,"abstract":"Complex precision parts of electronic products are essential to defense information technology equipment and the manufacturing industry. The workshop testing process for electronic products is crucial to ensuring their quality is qualified. Due to its multi-breed, multi-batch, and complex structure, its experimental process design is challenged by more and more indicators and complex processes. Currently, the process of detecting complex electronic products still adopts manual process document design, which is inefficient and inconsistent, and it is difficult to guarantee accuracy by manual experience. Therefore, a new intelligent test process method is designed to complete the process design. The method first automatically extracts test indicators and related parameters from the imported unstructured technical files or sop files, then automatically matches the test indicators with the test table, then automatically fills the test parameters under each index, then clusters and outputs XML test procedures for each indicator. Moreover, the key technology of each process is studied, the intelligent test process system for complex electronic products is developed, and the application of one model of microwave component products in a military industry enterprise is used as an example. The test program generated by the system can be directly used for subsequent workshop machine execution.","PeriodicalId":211011,"journal":{"name":"2022 6th International Conference on Universal Village (UV)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131303271","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：