Multi-label classification (MLC) is the supervised learning problem where an instance is associated with multiple labels, rather than with a single label. The widely known binary relevance method (BR) for multi-label classification considers each label as an independent binary problem and has been sidelined in the literature due to perceived inadequacy of label correlations. In this paper, we outline several BR-based classification methods and present our improved conditional dependency networks for multi-label classification (ICDN). ICDN inherits the framework of double layer based classifier chain (DCC) to exploit the label correlations in training stage and modifiers the conditional dependency networks (CDN) by initializing the input values of the second layer with the prediction values from the first layer during the testing stage. The main contribution of the algorithm is that it reduces randomization of input for the conditional dependency networks and improves convergence rate. Experiments on benchmark datasets demonstrate that ICDN obtains the best predictive performance across several datasets under several evaluation methods specifically designed for multi-label classification.
{"title":"Improved Conditional Dependency Networks for Multi-label Classification","authors":"Guo Tao, Li Guiyang","doi":"10.1109/ICMTMA.2015.142","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.142","url":null,"abstract":"Multi-label classification (MLC) is the supervised learning problem where an instance is associated with multiple labels, rather than with a single label. The widely known binary relevance method (BR) for multi-label classification considers each label as an independent binary problem and has been sidelined in the literature due to perceived inadequacy of label correlations. In this paper, we outline several BR-based classification methods and present our improved conditional dependency networks for multi-label classification (ICDN). ICDN inherits the framework of double layer based classifier chain (DCC) to exploit the label correlations in training stage and modifiers the conditional dependency networks (CDN) by initializing the input values of the second layer with the prediction values from the first layer during the testing stage. The main contribution of the algorithm is that it reduces randomization of input for the conditional dependency networks and improves convergence rate. Experiments on benchmark datasets demonstrate that ICDN obtains the best predictive performance across several datasets under several evaluation methods specifically designed for multi-label classification.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"35 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121000133","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}
Due to the urgent needs for high precision surgical equipments in minimally invasive spine surgeries, a novel robot-assisted system for the accurate placement of pedicle screws in lumbar spinal surgeries is developed. The structure design of the robot is based on a macro-micro mechanism, which includes a serial mechanism and a bi-planar 5R parallel mechanism. The researchable workspace, kinematic model and dynamic model of the planar 5R mechanism are analyzed, based on which the links lengths of 5R mechanisms are optimized. This paper provides a reference for the structure design of new medical robots for minimally invasive spine surgeries.
{"title":"Structure Optimization of a Bi-planar Parallel Mechanism for Spine Surgeries","authors":"Wang Yongfeng, Yu Hongjian, Du Zhijiang, D. Wei","doi":"10.1109/ICMTMA.2015.249","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.249","url":null,"abstract":"Due to the urgent needs for high precision surgical equipments in minimally invasive spine surgeries, a novel robot-assisted system for the accurate placement of pedicle screws in lumbar spinal surgeries is developed. The structure design of the robot is based on a macro-micro mechanism, which includes a serial mechanism and a bi-planar 5R parallel mechanism. The researchable workspace, kinematic model and dynamic model of the planar 5R mechanism are analyzed, based on which the links lengths of 5R mechanisms are optimized. This paper provides a reference for the structure design of new medical robots for minimally invasive spine surgeries.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117287376","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}
Using the supporting theory of Surrounding Rock unstable circle, before supporting design, BA-II unstable circle tester of surrounding rock is used to test the unstable circle of the new excavated 20m soft rock roadway of +588m level main roadway. Analysis of the test result concludes that the unstable circle of soft rock roadway range from 1.06 to 1.70m. According to the test result, the roadway supporting scheme is improved, and provides technical reference for the soft rock roadway supporting design under similar engineering geology conditions.
{"title":"The Supporting Scheme Improvement and Surrounding Rock Unstable Circle Test of the Roadway under the Conditions of Soft Rock in Deep Coal","authors":"Zhang Xiaoyu, Jiang Yuannan, Li Tao, T. Zhigang","doi":"10.1109/ICMTMA.2015.320","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.320","url":null,"abstract":"Using the supporting theory of Surrounding Rock unstable circle, before supporting design, BA-II unstable circle tester of surrounding rock is used to test the unstable circle of the new excavated 20m soft rock roadway of +588m level main roadway. Analysis of the test result concludes that the unstable circle of soft rock roadway range from 1.06 to 1.70m. According to the test result, the roadway supporting scheme is improved, and provides technical reference for the soft rock roadway supporting design under similar engineering geology conditions.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115435213","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}
Along with the information technology's development of hydropower, hydropower industry has accumulated abundant data resources, hydropower big data era has arrived, the data has started from the simple processing object into a sort of basic resources. Starting from the essence of hydropower's large data and its resources, based on introducing the basic concept of big data, explaining the road of hydropower's large data and its resources, giving the technical route of hydropower's data and its resources, finally analyzing the key technology involved in the process of recycling. This study is a beneficial exploration for promoting the process of hydropower's large data and its resources.
{"title":"Research on the Key Technology of Hydropower's Large Data and Its Resources","authors":"W. Xing, Wan Tian","doi":"10.1109/ICMTMA.2015.229","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.229","url":null,"abstract":"Along with the information technology's development of hydropower, hydropower industry has accumulated abundant data resources, hydropower big data era has arrived, the data has started from the simple processing object into a sort of basic resources. Starting from the essence of hydropower's large data and its resources, based on introducing the basic concept of big data, explaining the road of hydropower's large data and its resources, giving the technical route of hydropower's data and its resources, finally analyzing the key technology involved in the process of recycling. This study is a beneficial exploration for promoting the process of hydropower's large data and its resources.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115474844","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 the wireless sensor network monitoring activities, the sensor node location information is very important. To achieve node location information localization algorithm is adopted to estimate the better method. This article will mainly study the wireless sensor network localization algorithm based on multidimensional scaling, is proposed based on the Hop - Euclidean MDS - MAP (D) localization algorithm. It is not only improve the location accuracy, and it is conducive to the expansion of the network.
{"title":"Wireless Sensor Network Locating Algorithm Based on Multi-dimensional Scaling Study","authors":"Guo Li, L. Lai","doi":"10.1109/ICMTMA.2015.342","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.342","url":null,"abstract":"In the wireless sensor network monitoring activities, the sensor node location information is very important. To achieve node location information localization algorithm is adopted to estimate the better method. This article will mainly study the wireless sensor network localization algorithm based on multidimensional scaling, is proposed based on the Hop - Euclidean MDS - MAP (D) localization algorithm. It is not only improve the location accuracy, and it is conducive to the expansion of the network.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116561576","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}
As the core link and an important content, credit risk assessment plays vital special role for moderate operation of commercial banks. It is important to work out credit risk assessment model of commercial banks. A system of credit risk assessment which contains five aspects including 25 indicators is proposed. Based on establishment of credit risk assessment model, empirical analysis is carried out. The result shows this model has high accuracy of predication, better reliability and strong assessment ability.
{"title":"Commercial Bank Credit Risk Evaluation Method Based on Decision Tree Algorithm","authors":"Guo Wei, S. Yingjie, Yan Xi Mu","doi":"10.1109/ICMTMA.2015.75","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.75","url":null,"abstract":"As the core link and an important content, credit risk assessment plays vital special role for moderate operation of commercial banks. It is important to work out credit risk assessment model of commercial banks. A system of credit risk assessment which contains five aspects including 25 indicators is proposed. Based on establishment of credit risk assessment model, empirical analysis is carried out. The result shows this model has high accuracy of predication, better reliability and strong assessment ability.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115313468","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}
Server load balancing based on SDN compared with the traditional load balancing method, can effectively improve the performance of the server load balancing, and reduce the complexity of implementation. Open flow is south interface protocol of SDN switch. The core of server load balancing based on SDN is dynamic building Open flow flow tables. This paper puts forward a dynamic flow table design algorithm which based on "single flow table" and "group flow table" combination, "Single flow table" can accurately monitor traffic of each client, "Group flow table" can effectively category client hosts. This algorithm does not only effectively avoid excessive number of flow tables, and better solve the defect that flow table matching range is too wide, experiments show that the algorithm has good feasibility and higher traffic scheduling performance of network.
{"title":"A Load Balancing Method Based on SDN","authors":"Mao Qilin, Shen Weikang","doi":"10.1109/ICMTMA.2015.13","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.13","url":null,"abstract":"Server load balancing based on SDN compared with the traditional load balancing method, can effectively improve the performance of the server load balancing, and reduce the complexity of implementation. Open flow is south interface protocol of SDN switch. The core of server load balancing based on SDN is dynamic building Open flow flow tables. This paper puts forward a dynamic flow table design algorithm which based on \"single flow table\" and \"group flow table\" combination, \"Single flow table\" can accurately monitor traffic of each client, \"Group flow table\" can effectively category client hosts. This algorithm does not only effectively avoid excessive number of flow tables, and better solve the defect that flow table matching range is too wide, experiments show that the algorithm has good feasibility and higher traffic scheduling performance of network.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123233538","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 aim of this study was to predict groundwater inflow of Bangladesh Barapukuria coal mine using grey theory. The mine water inflow is affected by geological and hydro geological conditions, precipitation, degree of exploration and mining conditions, as well as many incomplete and synthesis of uncertain or unknown factors, belonging to the grey system. In this paper, present mine water inflow data were analyzed in detail and a GM model was built. In addition, a program based on Mat lab was used to calculate the model. The prediction was compared with in-situ measured data to assess the reliability of the GM (1, 1) model. The results showed that grey theory model is reliable enough to conduct groundwater inflow prediction. The results calculated can be used to design coal mine drainage system and develop mine water prevention and control measures.
{"title":"Application of GM Model in Coal Mine Water Inflow Prediction","authors":"Hao Wang, Ankun Luo, Rui Chai, Qisheng Liu","doi":"10.1109/ICMTMA.2015.54","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.54","url":null,"abstract":"The aim of this study was to predict groundwater inflow of Bangladesh Barapukuria coal mine using grey theory. The mine water inflow is affected by geological and hydro geological conditions, precipitation, degree of exploration and mining conditions, as well as many incomplete and synthesis of uncertain or unknown factors, belonging to the grey system. In this paper, present mine water inflow data were analyzed in detail and a GM model was built. In addition, a program based on Mat lab was used to calculate the model. The prediction was compared with in-situ measured data to assess the reliability of the GM (1, 1) model. The results showed that grey theory model is reliable enough to conduct groundwater inflow prediction. The results calculated can be used to design coal mine drainage system and develop mine water prevention and control measures.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123568913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper concentrates on the problem of Input/Output efficiency between science-technology and finance, and this problem is of great importance for modern society development. Firstly, we illustrate the analytic hierarchy process, which can adopt the relative evaluations computed by a decision maker. Considering the standard analytic hierarchy process model needs to exact judgments, it is impossible to obtain precise judgments by AHP. Therefore, we introduce fuzzy theory to the standard analytic hierarchy process. Secondly, an index system for the input/output efficiency evaluation problem is proposed, which covers two goals: 1) Financial investment, and 2) Science and technology output. Particularly, thirteen indexes are included in this index system. Finally, in the experiment, we collect experimental data from Chinese statistical yearbook, and experimental results demonstrate the effectiveness of our method.
{"title":"Evaluating the Input/Output Efficiency between Science-Technology and Finance via Analytic Hierarchy Process","authors":"Li Xi-mei","doi":"10.1109/ICMTMA.2015.117","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.117","url":null,"abstract":"This paper concentrates on the problem of Input/Output efficiency between science-technology and finance, and this problem is of great importance for modern society development. Firstly, we illustrate the analytic hierarchy process, which can adopt the relative evaluations computed by a decision maker. Considering the standard analytic hierarchy process model needs to exact judgments, it is impossible to obtain precise judgments by AHP. Therefore, we introduce fuzzy theory to the standard analytic hierarchy process. Secondly, an index system for the input/output efficiency evaluation problem is proposed, which covers two goals: 1) Financial investment, and 2) Science and technology output. Particularly, thirteen indexes are included in this index system. Finally, in the experiment, we collect experimental data from Chinese statistical yearbook, and experimental results demonstrate the effectiveness of our method.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123353257","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 condition of urban tourism development, including the urban tourism resources, accessibility, visitor perceptions, cognitions, market segmentation, market demand and market competitors are analyzed. Then based on the current status of the development of urban tourism, the urban tourism product development and makes systematic study of each category is classified so as to arrive at the general idea of urban tourism product development. Qingdao urban tourism product development is selected as an example to analyze the condition of Qingdao urban tourism product development, and based on the current status and questions of Qingdao urban tourism product development, the enhancement suggestions of its development is proposed to improve the research system.
{"title":"Urban Tourism Product Development Based on Multi-objective Optimization","authors":"Suo Hong, Teng Da","doi":"10.1109/ICMTMA.2015.337","DOIUrl":"https://doi.org/10.1109/ICMTMA.2015.337","url":null,"abstract":"The condition of urban tourism development, including the urban tourism resources, accessibility, visitor perceptions, cognitions, market segmentation, market demand and market competitors are analyzed. Then based on the current status of the development of urban tourism, the urban tourism product development and makes systematic study of each category is classified so as to arrive at the general idea of urban tourism product development. Qingdao urban tourism product development is selected as an example to analyze the condition of Qingdao urban tourism product development, and based on the current status and questions of Qingdao urban tourism product development, the enhancement suggestions of its development is proposed to improve the research system.","PeriodicalId":196962,"journal":{"name":"2015 Seventh International Conference on Measuring Technology and Mechatronics Automation","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124722993","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：