Reduced Q-matrix （Qr matrix） plays an important role in the rule space model （RSM） and the attribute hierarchy method （AHM）. Based on the attribute hierarchy, a valid/invalid item is defined. The judgment method...Reduced Q-matrix （Qr matrix） plays an important role in the rule space model （RSM） and the attribute hierarchy method （AHM）. Based on the attribute hierarchy, a valid/invalid item is defined. The judgment method of the valid/invalid item is developed on the relation between reachability matrix and valid items. And valid items are explained from the perspective of graph theory. An incremental augment algorithm for constructing Qr matrix is proposed based on the idea of incremental forward regression, and its validity is theoretically considered. Results of empirical tests are given in order to compare the performance of the incremental augment algo-rithm and the Tatsuoka algorithm upon the running time. Empirical evidence shows that the algorithm outper-forms the Tatsuoka algorithm, and the analysis of the two algorithms also show linear growth with respect to the number of valid items. Mathematical models with 10 attributes are built for the two algorithms by the linear regression analysis.展开更多
An improved Hybrid Collaborative Filtering algorithm(H-CF)is proposed,addressing the issues of data sparsity,low recommendation accuracy,and poor scalability present in traditional collaborative filtering algorithms.T...An improved Hybrid Collaborative Filtering algorithm(H-CF)is proposed,addressing the issues of data sparsity,low recommendation accuracy,and poor scalability present in traditional collaborative filtering algorithms.The core of H-CF is a linear weighted hybrid algorithm based on the Latent Factor Model(LFM)and the Improved Item Clustering and Similarity Calculation Collaborative Filtering Algorithm(ITCSCF).To begin with,the items are clustered based on their attribute dimension,which accelerates the computation of the nearest neighbor set.Subsequently,H-CF enhances the formula for scoring similarity by penalizing popular items and optimizing unpopular items.This improvement enhances the rationality of scoring similarity and reduces the impact of data sparseness.Furthermore,a weighting function is employed to combine the various improved algorithms.The balance factor of the weighting function is dynamically adjusted to attain the optimal recommendation list.To address the real-time and scalability concerns,the algorithm leverages the Spark big data distributed cluster computing framework.Experiments were conducted using the public dataset Movie Lens,where the improved algorithm’s performance was compared against the algorithm before enhancement and the algorithm running on a single machine.The experimental results demonstrate that the improved algorithm outperforms in terms of data sparsity,recommendation personalization,accuracy,recall,and efficiency.展开更多
In this article,we propose a novel probabilistic framework to improve the accuracy of a weighted majority voting algorithm.In order to assign higher weights to the classifiers which can correctly classify hard-to-clas...In this article,we propose a novel probabilistic framework to improve the accuracy of a weighted majority voting algorithm.In order to assign higher weights to the classifiers which can correctly classify hard-to-classify instances,we introduce the item response theory(IRT)framework to evaluate the samples′difficulty and classifiers′ability simultaneously.We assigned the weights to classifiers based on their abilities.Three models are created with different assumptions suitable for different cases.When making an inference,we keep a balance between the accuracy and complexity.In our experiment,all the base models are constructed by single trees via bootstrap.To explain the models,we illustrate how the IRT ensemble model constructs the classifying boundary.We also compare their performance with other widely used methods and show that our model performs well on 19 datasets.展开更多
The inbound and outbound tasks for valuable imported ship outfitting items are operated by multiple automated guided vehicles(AGVs)simultaneously in the outfitting warehouse.Given the efficiency mismatch between trans...The inbound and outbound tasks for valuable imported ship outfitting items are operated by multiple automated guided vehicles(AGVs)simultaneously in the outfitting warehouse.Given the efficiency mismatch between transportation equipment and the lack of effective scheduling of AGVs,the objective of the studied scheduling problem is to minimize the total travel time cost of vehicles.A multi-AGV task scheduling model based on time window is established considering the loading constraints of AGVs and cooperation time window constraints of stackers.According to the transportation characteristics in the outfitting warehouse,this study pro-poses a conflict detection method for heavy forklift AGVs,and correspondingly defines a conflict penalty function.Furthermore,to comprehensively optimize travel time cost and conflict penalty,a hybrid genetic neighborhood search algorithm(GA-ANS)is proposed.Five neighborhood structures are designed,and adaptive selection opera-tors are introduced to enhance the ability of global search and local chemotaxis.Numerical experiments show that the proposed GA-ANS algorithm can effectively solve the problem even when the scale of the problem increases and the effectiveness of the vehicle conflict penalty strategy is analyzed.展开更多
In this paper,We study the Apriori and FP-growth algorithm in mining association rules and give a method for computing all the frequent item-sets in a database.Its basic idea is giving a concept based on the boolean v...In this paper,We study the Apriori and FP-growth algorithm in mining association rules and give a method for computing all the frequent item-sets in a database.Its basic idea is giving a concept based on the boolean vector business product,which be computed between all the businesses,then we can get all the two frequent item-sets(minsup=2).We basis their inclusive relation to construct a set-tree of item-sets in database transaction,and then traverse path in it and get all the frequent item-sets.Therefore,we can get minimal frequent item sets between transactions and items in the database without scanning the database and iteratively computing in Apriori algorithm.展开更多
基金Supported by the National Natural Science Foundation of China (30860084,60673014,60263005)the Backbone Young Teachers Foundation of Fujian Normal University(2008100244)the Department of Education Foundation of Fujian Province (ZA09047)~~
文摘Reduced Q-matrix （Qr matrix） plays an important role in the rule space model （RSM） and the attribute hierarchy method （AHM）. Based on the attribute hierarchy, a valid/invalid item is defined. The judgment method of the valid/invalid item is developed on the relation between reachability matrix and valid items. And valid items are explained from the perspective of graph theory. An incremental augment algorithm for constructing Qr matrix is proposed based on the idea of incremental forward regression, and its validity is theoretically considered. Results of empirical tests are given in order to compare the performance of the incremental augment algo-rithm and the Tatsuoka algorithm upon the running time. Empirical evidence shows that the algorithm outper-forms the Tatsuoka algorithm, and the analysis of the two algorithms also show linear growth with respect to the number of valid items. Mathematical models with 10 attributes are built for the two algorithms by the linear regression analysis.
基金Supported by the Natural Science Foundation of Jiangxi Province(20212BAB202018)Provincial Virtual Simulation Experiment Education Project of Jiangxi Education Department(2020-2-0048)the Science and Technology Research Project of Jiangxi Province Educational Department(GJJ210333)。
文摘An improved Hybrid Collaborative Filtering algorithm(H-CF)is proposed,addressing the issues of data sparsity,low recommendation accuracy,and poor scalability present in traditional collaborative filtering algorithms.The core of H-CF is a linear weighted hybrid algorithm based on the Latent Factor Model(LFM)and the Improved Item Clustering and Similarity Calculation Collaborative Filtering Algorithm(ITCSCF).To begin with,the items are clustered based on their attribute dimension,which accelerates the computation of the nearest neighbor set.Subsequently,H-CF enhances the formula for scoring similarity by penalizing popular items and optimizing unpopular items.This improvement enhances the rationality of scoring similarity and reduces the impact of data sparseness.Furthermore,a weighting function is employed to combine the various improved algorithms.The balance factor of the weighting function is dynamically adjusted to attain the optimal recommendation list.To address the real-time and scalability concerns,the algorithm leverages the Spark big data distributed cluster computing framework.Experiments were conducted using the public dataset Movie Lens,where the improved algorithm’s performance was compared against the algorithm before enhancement and the algorithm running on a single machine.The experimental results demonstrate that the improved algorithm outperforms in terms of data sparsity,recommendation personalization,accuracy,recall,and efficiency.
文摘In this article,we propose a novel probabilistic framework to improve the accuracy of a weighted majority voting algorithm.In order to assign higher weights to the classifiers which can correctly classify hard-to-classify instances,we introduce the item response theory(IRT)framework to evaluate the samples′difficulty and classifiers′ability simultaneously.We assigned the weights to classifiers based on their abilities.Three models are created with different assumptions suitable for different cases.When making an inference,we keep a balance between the accuracy and complexity.In our experiment,all the base models are constructed by single trees via bootstrap.To explain the models,we illustrate how the IRT ensemble model constructs the classifying boundary.We also compare their performance with other widely used methods and show that our model performs well on 19 datasets.
基金China Ministry of Industry and Information Technology for High-Tech Ship Project。
文摘The inbound and outbound tasks for valuable imported ship outfitting items are operated by multiple automated guided vehicles(AGVs)simultaneously in the outfitting warehouse.Given the efficiency mismatch between transportation equipment and the lack of effective scheduling of AGVs,the objective of the studied scheduling problem is to minimize the total travel time cost of vehicles.A multi-AGV task scheduling model based on time window is established considering the loading constraints of AGVs and cooperation time window constraints of stackers.According to the transportation characteristics in the outfitting warehouse,this study pro-poses a conflict detection method for heavy forklift AGVs,and correspondingly defines a conflict penalty function.Furthermore,to comprehensively optimize travel time cost and conflict penalty,a hybrid genetic neighborhood search algorithm(GA-ANS)is proposed.Five neighborhood structures are designed,and adaptive selection opera-tors are introduced to enhance the ability of global search and local chemotaxis.Numerical experiments show that the proposed GA-ANS algorithm can effectively solve the problem even when the scale of the problem increases and the effectiveness of the vehicle conflict penalty strategy is analyzed.
文摘In this paper,We study the Apriori and FP-growth algorithm in mining association rules and give a method for computing all the frequent item-sets in a database.Its basic idea is giving a concept based on the boolean vector business product,which be computed between all the businesses,then we can get all the two frequent item-sets(minsup=2).We basis their inclusive relation to construct a set-tree of item-sets in database transaction,and then traverse path in it and get all the frequent item-sets.Therefore,we can get minimal frequent item sets between transactions and items in the database without scanning the database and iteratively computing in Apriori algorithm.
