According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are comput...According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.展开更多
In order to make effective use a large amount of graduate data in colleges and universities that accumulate by teaching management of work, the paper study the data mining for higher vocational graduates database usin...In order to make effective use a large amount of graduate data in colleges and universities that accumulate by teaching management of work, the paper study the data mining for higher vocational graduates database using the data mining technology. Using a variety of data preprocessing methods for the original data, and the paper put forward to mining algorithm based on commonly association rule Apriori algorithm, then according to the actual needs of the design and implementation of association rule mining system, has been beneficial to the employment guidance of college teaching management decision and graduates of the mining results.展开更多
The nuclei around magic number N=126 are investigated in the deformed relativistic mean field (RMF)model with effective interactions TMA.We focus investigations on the N=126 isotonic chain.The N=126 shellevolution is ...The nuclei around magic number N=126 are investigated in the deformed relativistic mean field (RMF)model with effective interactions TMA.We focus investigations on the N=126 isotonic chain.The N=126 shellevolution is studied by analyzing the variations of two-neutron (proton) separation energies,quadruple deformations,single particle levels etc.The good agreement of two-neutron separation energies between experimental data and calculatedvalues is reached.The RMF theory predicts that the sizes of N=126 shell become smaller and smaller withthe increasing of proton number Z.However,the N=126 shell exists in our calculated region all along.According tothe calculated two-proton separation energies,the RMF theory suggests ^(220)Pu is a two-proton drip-line nucleus in theN=126 isotonic chain.展开更多
Spectrum sensing is one of the key issues in cognitive radio networks. Most of previous work concenates on sensing the spectrum in a single spectrum band. In this paper, we propose a spectrum sensing sequence predicti...Spectrum sensing is one of the key issues in cognitive radio networks. Most of previous work concenates on sensing the spectrum in a single spectrum band. In this paper, we propose a spectrum sensing sequence prediction scheme for cognitive radio networks with multiple spectrum bands to decrease the spectrum sensing time and increase the throughput of secondary users. The scheme is based on recent advances in computational learning theory, which has shown that prediction is synonymous with data compression. A Ziv-Lempel data compression algorithm is used to design our spectrum sensing sequence prediction scheme. The spectrum band usage history is used for the prediction in our proposed scheme. Simulation results show that the proposed scheme can reduce the average sensing time and improve the system throughput significantly.展开更多
The prediction study on coal and gas outbursts is carried out by monitoring some indices which are sensitive to the initiation of coal and gas outbursts. The values and changing roles of the indices are the foundation...The prediction study on coal and gas outbursts is carried out by monitoring some indices which are sensitive to the initiation of coal and gas outbursts. The values and changing roles of the indices are the foundations of coal and gas outbursts prediction. But now, only the data of ere key monitoring station is used in the coal and gas outbursts prediction practice, and the other data are ignored. In order to overcome the human factor and make full use of the monitoring information, the technique of multi-sensor target tracking is proposed to deal with the microseismic informatiion. With the results of microseismic events, the activities of geological structure, fracure-depth of roof and floor, and the location of gas channel are obtained. These studies indicate that it is considerably possible to predict the coal and gas outbursts using microseismic monitoring with its inherent ability to remotely monitor the progressive failure caused by mining.展开更多
In this paper, it described the architecture of a tool called DiagData. This tool aims to use a large amount of data and information in the field of plant disease diagnostic to generate a disease predictive system. In...In this paper, it described the architecture of a tool called DiagData. This tool aims to use a large amount of data and information in the field of plant disease diagnostic to generate a disease predictive system. In this approach, techniques of data mining are used to extract knowledge from existing data. The data is extracted in the form of rules that are used in the development of a predictive intelligent system. Currently, the specification of these rules is built by an expert or data mining. When data mining on a large database is used, the number of generated rules is very complex too. The main goal of this work is minimize the rule generation time. The proposed tool, called DiagData, extracts knowledge automatically or semi-automatically from a database and uses it to build an intelligent system for disease prediction. In this work, the decision tree learning algorithm was used to generate the rules. A toolbox called Fuzzygen was used to generate a prediction system from rules generated by decision tree algorithm. The language used to implement this software was Java. The DiagData has been used in diseases prediction and diagnosis systems and in the validation of economic and environmental indicators in agricultural production systems. The validation process involved measurements and comparisons of the time spent to enter the rules by an expert with the time used to insert the same rules with the proposed tool. Thus, the tool was successfully validated, providing a reduction of time.展开更多
The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of...The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.展开更多
Bispyribac is a widely used herbicide that targets the acetohydroxyacid synthase （AHAS） enzyme. Mutations in AHAS have caused serious herbicide resistance that threatened the continued use of the herbicide. So far, ...Bispyribac is a widely used herbicide that targets the acetohydroxyacid synthase （AHAS） enzyme. Mutations in AHAS have caused serious herbicide resistance that threatened the continued use of the herbicide. So far, a unified model to decipher herb- icide resistance in molecular level with good prediction is still lacking. In this paper, we have established a new QSAR method to construct a prediction model for AHAS mutation resistance to herbicide Bispyribac. A series of AHAS mutants concerned with the herbicide resistance were constructed, and the inhibitory properties of Bispyribac against these mutants were meas- ured. The 3D-QSAR method has been transformed to process the AHAS mutants and proposed as mutation-dependent biom- acromolecular QSAR （MB-QSAR）. The excellent correlation between experimental and computational data gave the MB-QSAR/CoMFA model （q2 = 0.615, P = 0.921, F2pred = 0.598） and the MB-QSAR/CoMSIA model （q2 = 0.446, r2 = 0.929, r2pred = 0.612）, which showed good prediction for the inhibition properties of Bispyribac against AHAS mutants. Such MB-QSAR models, containing the three-dimensional molecular interaction diagram, not only disclose to us for the first time the detailed three-dimensional information about the structure-resistance relationships, but may also provide further guidance to resistance mutation evolution. Also, the molecular interaction diagram derived from MB-QSAR models may aid the resistance-evading herbicide design.展开更多
基金Project(70671039) supported by the National Natural Science Foundation of China
文摘According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.
文摘In order to make effective use a large amount of graduate data in colleges and universities that accumulate by teaching management of work, the paper study the data mining for higher vocational graduates database using the data mining technology. Using a variety of data preprocessing methods for the original data, and the paper put forward to mining algorithm based on commonly association rule Apriori algorithm, then according to the actual needs of the design and implementation of association rule mining system, has been beneficial to the employment guidance of college teaching management decision and graduates of the mining results.
基金Supported by National Natural Science Foundation of China under Grant Nos.10535010 and 10775068973 National Major State Basic Research and Development of China (2007CB815004)+2 种基金CAS Knowledge Innovation Project (KJCX2-SW-N02)Research Fund of Education Ministry under contract RFDP (20070284016)Green-blue Project of Jiangsu Province
文摘The nuclei around magic number N=126 are investigated in the deformed relativistic mean field (RMF)model with effective interactions TMA.We focus investigations on the N=126 isotonic chain.The N=126 shellevolution is studied by analyzing the variations of two-neutron (proton) separation energies,quadruple deformations,single particle levels etc.The good agreement of two-neutron separation energies between experimental data and calculatedvalues is reached.The RMF theory predicts that the sizes of N=126 shell become smaller and smaller withthe increasing of proton number Z.However,the N=126 shell exists in our calculated region all along.According tothe calculated two-proton separation energies,the RMF theory suggests ^(220)Pu is a two-proton drip-line nucleus in theN=126 isotonic chain.
基金Supported by the National Natural Science Foundation of China（No.60832009）, the Natural Science Foundation of Beijing （No.4102044） and the National Nature Science Foundation for Young Scholars of China （No.61001115）
文摘Spectrum sensing is one of the key issues in cognitive radio networks. Most of previous work concenates on sensing the spectrum in a single spectrum band. In this paper, we propose a spectrum sensing sequence prediction scheme for cognitive radio networks with multiple spectrum bands to decrease the spectrum sensing time and increase the throughput of secondary users. The scheme is based on recent advances in computational learning theory, which has shown that prediction is synonymous with data compression. A Ziv-Lempel data compression algorithm is used to design our spectrum sensing sequence prediction scheme. The spectrum band usage history is used for the prediction in our proposed scheme. Simulation results show that the proposed scheme can reduce the average sensing time and improve the system throughput significantly.
基金supported by National Basic Research Programof China(973Program,2010CB226805)Shandong Province Natural Science Fund(Z2008F01)Key Laboratory of Mine Disaster Prevention and Control of Education Ministry(MDPC0809,MDPC0811)
文摘The prediction study on coal and gas outbursts is carried out by monitoring some indices which are sensitive to the initiation of coal and gas outbursts. The values and changing roles of the indices are the foundations of coal and gas outbursts prediction. But now, only the data of ere key monitoring station is used in the coal and gas outbursts prediction practice, and the other data are ignored. In order to overcome the human factor and make full use of the monitoring information, the technique of multi-sensor target tracking is proposed to deal with the microseismic informatiion. With the results of microseismic events, the activities of geological structure, fracure-depth of roof and floor, and the location of gas channel are obtained. These studies indicate that it is considerably possible to predict the coal and gas outbursts using microseismic monitoring with its inherent ability to remotely monitor the progressive failure caused by mining.
文摘In this paper, it described the architecture of a tool called DiagData. This tool aims to use a large amount of data and information in the field of plant disease diagnostic to generate a disease predictive system. In this approach, techniques of data mining are used to extract knowledge from existing data. The data is extracted in the form of rules that are used in the development of a predictive intelligent system. Currently, the specification of these rules is built by an expert or data mining. When data mining on a large database is used, the number of generated rules is very complex too. The main goal of this work is minimize the rule generation time. The proposed tool, called DiagData, extracts knowledge automatically or semi-automatically from a database and uses it to build an intelligent system for disease prediction. In this work, the decision tree learning algorithm was used to generate the rules. A toolbox called Fuzzygen was used to generate a prediction system from rules generated by decision tree algorithm. The language used to implement this software was Java. The DiagData has been used in diseases prediction and diagnosis systems and in the validation of economic and environmental indicators in agricultural production systems. The validation process involved measurements and comparisons of the time spent to enter the rules by an expert with the time used to insert the same rules with the proposed tool. Thus, the tool was successfully validated, providing a reduction of time.
基金supported by the National Natural Science Foundation of China (Grant No. 60974101)Program for New Century Talents of Education Ministry of China (Grant No. NCET-06-0828)
文摘The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.
文摘Bispyribac is a widely used herbicide that targets the acetohydroxyacid synthase （AHAS） enzyme. Mutations in AHAS have caused serious herbicide resistance that threatened the continued use of the herbicide. So far, a unified model to decipher herb- icide resistance in molecular level with good prediction is still lacking. In this paper, we have established a new QSAR method to construct a prediction model for AHAS mutation resistance to herbicide Bispyribac. A series of AHAS mutants concerned with the herbicide resistance were constructed, and the inhibitory properties of Bispyribac against these mutants were meas- ured. The 3D-QSAR method has been transformed to process the AHAS mutants and proposed as mutation-dependent biom- acromolecular QSAR （MB-QSAR）. The excellent correlation between experimental and computational data gave the MB-QSAR/CoMFA model （q2 = 0.615, P = 0.921, F2pred = 0.598） and the MB-QSAR/CoMSIA model （q2 = 0.446, r2 = 0.929, r2pred = 0.612）, which showed good prediction for the inhibition properties of Bispyribac against AHAS mutants. Such MB-QSAR models, containing the three-dimensional molecular interaction diagram, not only disclose to us for the first time the detailed three-dimensional information about the structure-resistance relationships, but may also provide further guidance to resistance mutation evolution. Also, the molecular interaction diagram derived from MB-QSAR models may aid the resistance-evading herbicide design.
