Hierarchical classification learning, an emerging classification task in machine learning, is an essential topic. In which various feature selection algorithms have been proposed to select informative features for hierarchical classification. How-ever, existing hierarchical feature selection algorithms consider that the feature space of data is completely obtained in advance, and neglect the uncertainty and dynamism, i.e., feature arrives dynamically in an online manner. In this paper, we present an online streaming feature selection framework with hierarchical structure. First, we apply the closeness matrix between internal nodes to the Relief algorithm, which can calculate the weights of the dynamic features. Second, significant features are dynamically selected for each internal node by considering the hierarchical relationships and feature weights between nodes in the tree structure. Moreover, we perform redundant analysis of features by calculating the covariance between features, and then obtain a superior online feature subset for each internal node. Finally, the proposed algorithm is compared with six online streaming feature selection methods on six hierarchical data sets. The experimental results prove that our algorithm can improve the classification accuracy of the classifier by 10% compared to the suboptimal algorithms, which indicates that the algorithm outperforms other comparative algorithms in hierarchical data sets.
{"title":"OFHR: Online Streaming Feature Selection With Hierarchical Structure Based on Relief","authors":"Chenxi Wang, Xiaoqing Zhang, Jinkun Chen, Yu Mao, Shaozi Li, Yaojin Lin","doi":"10.1109/ITME53901.2021.00038","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00038","url":null,"abstract":"Hierarchical classification learning, an emerging classification task in machine learning, is an essential topic. In which various feature selection algorithms have been proposed to select informative features for hierarchical classification. How-ever, existing hierarchical feature selection algorithms consider that the feature space of data is completely obtained in advance, and neglect the uncertainty and dynamism, i.e., feature arrives dynamically in an online manner. In this paper, we present an online streaming feature selection framework with hierarchical structure. First, we apply the closeness matrix between internal nodes to the Relief algorithm, which can calculate the weights of the dynamic features. Second, significant features are dynamically selected for each internal node by considering the hierarchical relationships and feature weights between nodes in the tree structure. Moreover, we perform redundant analysis of features by calculating the covariance between features, and then obtain a superior online feature subset for each internal node. Finally, the proposed algorithm is compared with six online streaming feature selection methods on six hierarchical data sets. The experimental results prove that our algorithm can improve the classification accuracy of the classifier by 10% compared to the suboptimal algorithms, which indicates that the algorithm outperforms other comparative algorithms in hierarchical data sets.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"1 1","pages":"140-145"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82962993","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}
Objectives: This study aimed to investigate the efficacy of stabbing and bleeding combined with auricular pressure in the treatment of chronic urticaria (CU) and the differential metabolites in the serum of patients before and after the treatment. Methods: Six patients with CU who met the requirements were recruited, and the changes in the degree of wind mass and itching at different time points were assessed using the Urticaria Activity Score (UAS), the Visual Analog Scale (VAS) score of pruritus intensity, and the Dermatologic Disease Quality of Life Index (DLQI). The differential metabolites in the serum of patients before and after the treatment were further analyzed using liquid chromatography-mass spectrometry duplex (LC/MS) and non-targeted metabolomics analysis. Results: Compared with baseline scores, UAS, VAS, and DLQI scores decreased significantly in six patients after the treatment, with statistically significant differences (P < 0.05). Results also suggested that stabbing and releasing blood for CU could down-regulate lysophosphatidylcholine (LPC) in patients' serum. Conclusion: The combination of piercing and bloodletting with auricular acupressure can effectively improve the life quality of CU patients through lowering LPC in serum, and thus alleviating the clinical symptoms and improving the cure rate of CU patients.
{"title":"Exploration of the mechanism of action of stabbing and releasing blood combined with auricular acupressure in the treatment of chronic urticaria","authors":"Boyuan Wang, Fangzi Shi, Yu Shi, Xuejun Zhang, Mingxin Sun, Yanjun Wang","doi":"10.1109/ITME53901.2021.00094","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00094","url":null,"abstract":"Objectives: This study aimed to investigate the efficacy of stabbing and bleeding combined with auricular pressure in the treatment of chronic urticaria (CU) and the differential metabolites in the serum of patients before and after the treatment. Methods: Six patients with CU who met the requirements were recruited, and the changes in the degree of wind mass and itching at different time points were assessed using the Urticaria Activity Score (UAS), the Visual Analog Scale (VAS) score of pruritus intensity, and the Dermatologic Disease Quality of Life Index (DLQI). The differential metabolites in the serum of patients before and after the treatment were further analyzed using liquid chromatography-mass spectrometry duplex (LC/MS) and non-targeted metabolomics analysis. Results: Compared with baseline scores, UAS, VAS, and DLQI scores decreased significantly in six patients after the treatment, with statistically significant differences (P < 0.05). Results also suggested that stabbing and releasing blood for CU could down-regulate lysophosphatidylcholine (LPC) in patients' serum. Conclusion: The combination of piercing and bloodletting with auricular acupressure can effectively improve the life quality of CU patients through lowering LPC in serum, and thus alleviating the clinical symptoms and improving the cure rate of CU patients.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"32 1","pages":"439-445"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81186094","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00116
Wang Haipeng, Tang Tiantian, M. Zhongyang, Zheng Yuanjie, Wang Hong, Jia Weikuan, Guo Qiang
With the advent of the era of big data, a new generation of intelligent information processing technology develop rapidly and vigorously, which has greatly promoted the innovative reform in the concept of education and teaching. The aim of this research is to promote learning efficiency and teaching precision through using big data technology and intelligent means. An intelligent personalized learning mode is built, which mainly including four aspects: academic analysis, intelligent push, individual feedback, multiple evaluations. The mode can conduct in-depth mining and analysis of student data, enrich students' off-class learning resources, intelligently push students' individual learning feedback in real time, and conduct multiple evaluations for each student. Consequently the mode completely changing the deficiency of the traditional learning mode, including one-sided cognition of each students, insufficient learning resources, lack of real-time feedback and single learning evaluation. The mode can form an intelligent and efficient personalized learning environment based on making the overall learning process quantifiable, real-time feedback, and evaluable.
{"title":"Analysis of Intelligent Personalized Learning Mode in Big Data Era","authors":"Wang Haipeng, Tang Tiantian, M. Zhongyang, Zheng Yuanjie, Wang Hong, Jia Weikuan, Guo Qiang","doi":"10.1109/ITME53901.2021.00116","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00116","url":null,"abstract":"With the advent of the era of big data, a new generation of intelligent information processing technology develop rapidly and vigorously, which has greatly promoted the innovative reform in the concept of education and teaching. The aim of this research is to promote learning efficiency and teaching precision through using big data technology and intelligent means. An intelligent personalized learning mode is built, which mainly including four aspects: academic analysis, intelligent push, individual feedback, multiple evaluations. The mode can conduct in-depth mining and analysis of student data, enrich students' off-class learning resources, intelligently push students' individual learning feedback in real time, and conduct multiple evaluations for each student. Consequently the mode completely changing the deficiency of the traditional learning mode, including one-sided cognition of each students, insufficient learning resources, lack of real-time feedback and single learning evaluation. The mode can form an intelligent and efficient personalized learning environment based on making the overall learning process quantifiable, real-time feedback, and evaluable.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"21 1","pages":"548-551"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78410240","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00130
Zhong-hua Luo
The external practice teaching bases for college students is an important mode for collaborative education between universities and enterprises. During the process of talent training in applied universities, the external practicing and teaching plays a key role in promoting students to consolidate professional knowledge, improving engineering practical ability and innovation ability, and cultivate new engineering talents urgently needed for enterprises. In view of the problems existing in the construction of external practicing and teaching bases, combined with professional characteristics and enterprise needs, the strategies of practical teaching bases construction and management are discussed in the paper. The practice of bases construction in recent years has shown that students' engineering practical ability, teamwork ability and employment competitiveness have been significantly improved, and the quality of practical teaching has been steadily improved, which provides a valuable reference for innovating practical teaching reform in application-oriented universities.
{"title":"Construction Path Exploration on the External Practice Teaching Bases under the Background of New Engineering","authors":"Zhong-hua Luo","doi":"10.1109/ITME53901.2021.00130","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00130","url":null,"abstract":"The external practice teaching bases for college students is an important mode for collaborative education between universities and enterprises. During the process of talent training in applied universities, the external practicing and teaching plays a key role in promoting students to consolidate professional knowledge, improving engineering practical ability and innovation ability, and cultivate new engineering talents urgently needed for enterprises. In view of the problems existing in the construction of external practicing and teaching bases, combined with professional characteristics and enterprise needs, the strategies of practical teaching bases construction and management are discussed in the paper. The practice of bases construction in recent years has shown that students' engineering practical ability, teamwork ability and employment competitiveness have been significantly improved, and the quality of practical teaching has been steadily improved, which provides a valuable reference for innovating practical teaching reform in application-oriented universities.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"34 1","pages":"614-617"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79288827","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00109
Zhiqi Xu, Xuewen Shen, Shengyou Lin, Fan Zhang
More and more colleges have offered introductory programming courses for students from different majors, aiming to cultivate students' computational thinking skills. However, teaching introductory programming courses, especially to freshmen, remains a challenging endeavor despite a lot of research and experiments. In this paper we presented our innovative teaching strategy and its implementation both with the utilization of visualization in an introductory Python programming course. The results from our comparative teaching experiments show that visualization could benefit students a lot in learning Python programming and improving their computational thinking abilities.
{"title":"Using Visualization to Teach an Introductory Programming Course with Python","authors":"Zhiqi Xu, Xuewen Shen, Shengyou Lin, Fan Zhang","doi":"10.1109/ITME53901.2021.00109","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00109","url":null,"abstract":"More and more colleges have offered introductory programming courses for students from different majors, aiming to cultivate students' computational thinking skills. However, teaching introductory programming courses, especially to freshmen, remains a challenging endeavor despite a lot of research and experiments. In this paper we presented our innovative teaching strategy and its implementation both with the utilization of visualization in an introductory Python programming course. The results from our comparative teaching experiments show that visualization could benefit students a lot in learning Python programming and improving their computational thinking abilities.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"315 1","pages":"514-518"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91083402","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00022
Cui Zeyu, Huaiqing Zhang, Nianfu Zhu, Tingdong Yang, Liu Yang, Yuanqing Zuo, Zhang Jing, Hua-Lin Zhang, Lin-lin Wang
For the difficulty of tree polymorphism 3D modeling in the stand, the paper explored a 3D forest-tree-modeling approach based on loading trunk model and branch models. The approach is combined with the characteristics of tree branch structure that calculate the branch matching points of the intersection between the branch model and the crown curve to construct the tree branch structure. In addition, branch models are adjusted to eliminate the overlapping of branch models when the adjacent trees had overlapping crowns. The 3D model of forest-tree was constructed in accordance with the growth law and morphological characteristics of forest-tree. The results showed that this approach can use a small amount of measurement data to simulate forest-tree crown of sample plot or stand.
{"title":"3D Forest-tree Modeling Approach Based on Loading Segment Models","authors":"Cui Zeyu, Huaiqing Zhang, Nianfu Zhu, Tingdong Yang, Liu Yang, Yuanqing Zuo, Zhang Jing, Hua-Lin Zhang, Lin-lin Wang","doi":"10.1109/ITME53901.2021.00022","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00022","url":null,"abstract":"For the difficulty of tree polymorphism 3D modeling in the stand, the paper explored a 3D forest-tree-modeling approach based on loading trunk model and branch models. The approach is combined with the characteristics of tree branch structure that calculate the branch matching points of the intersection between the branch model and the crown curve to construct the tree branch structure. In addition, branch models are adjusted to eliminate the overlapping of branch models when the adjacent trees had overlapping crowns. The 3D model of forest-tree was constructed in accordance with the growth law and morphological characteristics of forest-tree. The results showed that this approach can use a small amount of measurement data to simulate forest-tree crown of sample plot or stand.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"53 1","pages":"55-59"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91331318","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00048
Huiyong Li, Qing Lei, Hongbo Zhang, Jixiang Du
Action quality assessment(AQA) aims at achieving automatic evaluation the performance of human actions in video. Compared with action recognition problem, AQA focuses more on subtle differences both in spatial and temporal dimensions during the whole executing process of actions. However, most existing AQA methods tried to extract features directly from RGB videos through a 3D ConvNets, which makes the features mixed with useless scene information. To overcome this problem, We propose a deep pose feature learning AQA method that captured detailed and meaningful representations for skeleton information to discover the subtle motion difference of AQA problem. We first apply pose estimation method to obtain human skeleton data from RGB videos. Then a spatio-temporal graph convolutional network (ST-GCN) is employed to extract the dynamic changes of skeleton data and obtain the representative pose features. Finally, a regressor composed of three fully connected layers is developed to reduce the dimension of the obtained pose features and predict the final score. Experiments on MIT figure skating dataset have been extensively conducted, and the results demonstrate that the proposed method has achieved improvements that outperformed current state-of-the-art methods.
{"title":"Skeleton Based Action Quality Assessment of Figure Skating Videos","authors":"Huiyong Li, Qing Lei, Hongbo Zhang, Jixiang Du","doi":"10.1109/ITME53901.2021.00048","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00048","url":null,"abstract":"Action quality assessment(AQA) aims at achieving automatic evaluation the performance of human actions in video. Compared with action recognition problem, AQA focuses more on subtle differences both in spatial and temporal dimensions during the whole executing process of actions. However, most existing AQA methods tried to extract features directly from RGB videos through a 3D ConvNets, which makes the features mixed with useless scene information. To overcome this problem, We propose a deep pose feature learning AQA method that captured detailed and meaningful representations for skeleton information to discover the subtle motion difference of AQA problem. We first apply pose estimation method to obtain human skeleton data from RGB videos. Then a spatio-temporal graph convolutional network (ST-GCN) is employed to extract the dynamic changes of skeleton data and obtain the representative pose features. Finally, a regressor composed of three fully connected layers is developed to reduce the dimension of the obtained pose features and predict the final score. Experiments on MIT figure skating dataset have been extensively conducted, and the results demonstrate that the proposed method has achieved improvements that outperformed current state-of-the-art methods.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"64 1","pages":"196-200"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90428058","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00076
XU Xinghao, Hu Rong, Du Guodong, Xiang Yan, Ma Lei
For the existing data of medical and health questions, the majority of them are so inarticulate short texts with few terms that the text features are sparse, posing a daunting challenge to relevant classification effort. Against this background, to enlarge the terms and datasets of short tests, this paper proposes a keyword-based data augmentation algorithm, which can be used in two ways: (1) With regard to short texts featuring few terms, for the purpose of keyword expansion, keywords are extracted by topic model and trained through domain knowledge-assisted word vector model to obtain synonyms of expanded keywords, so as to expand the original keywords; (2) with regard to incomplete health questions, the synonyms are used to replace original keywords. Then the augmented samples obtained by the above two methods are sent to the classifier. As a result, the algorithm in this paper significantly improves recall, precision and macro value compared to those without data augmentation.
{"title":"Keyword-based Data Augmentation Guided Chinese Medical Questions Classification","authors":"XU Xinghao, Hu Rong, Du Guodong, Xiang Yan, Ma Lei","doi":"10.1109/ITME53901.2021.00076","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00076","url":null,"abstract":"For the existing data of medical and health questions, the majority of them are so inarticulate short texts with few terms that the text features are sparse, posing a daunting challenge to relevant classification effort. Against this background, to enlarge the terms and datasets of short tests, this paper proposes a keyword-based data augmentation algorithm, which can be used in two ways: (1) With regard to short texts featuring few terms, for the purpose of keyword expansion, keywords are extracted by topic model and trained through domain knowledge-assisted word vector model to obtain synonyms of expanded keywords, so as to expand the original keywords; (2) with regard to incomplete health questions, the synonyms are used to replace original keywords. Then the augmented samples obtained by the above two methods are sent to the classifier. As a result, the algorithm in this paper significantly improves recall, precision and macro value compared to those without data augmentation.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"46 1","pages":"341-346"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72748084","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00057
Yu Xiehua, Li Shaozi
The reasonable design of worm propagation model can provide a basis for accurately predicting and analyzing the propagation law and mechanism of worm malicious code in the Internet, and help to further carry out the research on worm protection, detection and suppression technology. This paper introduces the transmission model of infectious diseases in the field of biopathology to analyze the transmission mechanism of network worms, and a class of network worm virus transmission model based on differential equations is established by using LaSalle invariant set principle and orbital stability theory of differential equations. The results show that the basic regeneration number is the threshold value of eliminating worm virus and keeping worm virus in a certain range. When the basic regeneration number is less than or equal to 1, worm virus is eliminated effectively. When the basic regeneration number is greater than 1, the worm virus will persist or stabilize in a certain state.
{"title":"Analysis of a Worm Virus Propagation Model Based on Differential Equation","authors":"Yu Xiehua, Li Shaozi","doi":"10.1109/ITME53901.2021.00057","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00057","url":null,"abstract":"The reasonable design of worm propagation model can provide a basis for accurately predicting and analyzing the propagation law and mechanism of worm malicious code in the Internet, and help to further carry out the research on worm protection, detection and suppression technology. This paper introduces the transmission model of infectious diseases in the field of biopathology to analyze the transmission mechanism of network worms, and a class of network worm virus transmission model based on differential equations is established by using LaSalle invariant set principle and orbital stability theory of differential equations. The results show that the basic regeneration number is the threshold value of eliminating worm virus and keeping worm virus in a certain range. When the basic regeneration number is less than or equal to 1, worm virus is eliminated effectively. When the basic regeneration number is greater than 1, the worm virus will persist or stabilize in a certain state.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"21 1","pages":"242-245"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73801056","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00058
Ying Li, Zhaohong Huang, Yang Sun
Plant leaf detection is one of the essential aspects of the scientific plant breeding and precision agriculture process. Manual detection requires professional knowledge of the operators, high labor costs, and long time-consuming cycles. To this end, this paper proposes a multi-scale CNN feature fusion (MCFF) to detect the Rosette plant, Arabidopsis, and Tobacco. The experimental results indicate that the mean average precision of the proposed method is higher than the traditional methods such as RetinaNet, CenterNet, and Faster R-CNN.
{"title":"MCFF: Plant leaf detection based on multi-scale CNN feature fusion","authors":"Ying Li, Zhaohong Huang, Yang Sun","doi":"10.1109/ITME53901.2021.00058","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00058","url":null,"abstract":"Plant leaf detection is one of the essential aspects of the scientific plant breeding and precision agriculture process. Manual detection requires professional knowledge of the operators, high labor costs, and long time-consuming cycles. To this end, this paper proposes a multi-scale CNN feature fusion (MCFF) to detect the Rosette plant, Arabidopsis, and Tobacco. The experimental results indicate that the mean average precision of the proposed method is higher than the traditional methods such as RetinaNet, CenterNet, and Faster R-CNN.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"25 1","pages":"246-250"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76202343","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：