For imbalanced datasets, the focus of classification is to identify samples of the minority class. The performance of current data mining algorithms is not good enough for processing imbalanced datasets. The synthetic...For imbalanced datasets, the focus of classification is to identify samples of the minority class. The performance of current data mining algorithms is not good enough for processing imbalanced datasets. The synthetic minority over-sampling technique(SMOTE) is specifically designed for learning from imbalanced datasets, generating synthetic minority class examples by interpolating between minority class examples nearby. However, the SMOTE encounters the overgeneralization problem. The densitybased spatial clustering of applications with noise(DBSCAN) is not rigorous when dealing with the samples near the borderline.We optimize the DBSCAN algorithm for this problem to make clustering more reasonable. This paper integrates the optimized DBSCAN and SMOTE, and proposes a density-based synthetic minority over-sampling technique(DSMOTE). First, the optimized DBSCAN is used to divide the samples of the minority class into three groups, including core samples, borderline samples and noise samples, and then the noise samples of minority class is removed to synthesize more effective samples. In order to make full use of the information of core samples and borderline samples,different strategies are used to over-sample core samples and borderline samples. Experiments show that DSMOTE can achieve better results compared with SMOTE and Borderline-SMOTE in terms of precision, recall and F-value.展开更多
Ionic liquids ( ILs) based ultrasonic-assisted extract has been applied for the extraction of essential oil from Persicaria minor leaves. The effects of temperature,sonication time,and particle size of the plant mater...Ionic liquids ( ILs) based ultrasonic-assisted extract has been applied for the extraction of essential oil from Persicaria minor leaves. The effects of temperature,sonication time,and particle size of the plant material on the yield of essential oil were investigated. Among the different ILs employed,1-ethyl-3-methyli midazolium acetate was the most effective,providing a 9. 55% yield of the essential oil under optimum conditions( 70 ℃,25 min,IL ∶hexane ratio of 7 ∶10 ( v /v) ,particle size 60-80 mesh) . The performance of 1-ethyl-3-methylimidazolium acetate in the extraction was attributed to its lowviscosity and ability to disintegrate the structural matrix of the plant material. The ability of 1-ethyl-3-methylimidazolium acetate was also confirmed using the conductor like-screening model for realistic solvents. This research proves that ILs can be used to extract essential oils from lignocellulosic biomass.展开更多
To reduce the computational complexity of matrix inversion, which is the majority of processing in many practical applications, two numerically efficient recursive algorithms （called algorithms I and II, respectively...To reduce the computational complexity of matrix inversion, which is the majority of processing in many practical applications, two numerically efficient recursive algorithms （called algorithms I and II, respectively） are presented. Algorithm I is used to calculate the inverse of such a matrix, whose leading principal minors are all nonzero. Algorithm II, whereby, the inverse of an arbitrary nonsingular matrix can be evaluated is derived via improving the algorithm I. The implementation, for algorithm II or I, involves matrix-vector multiplications and vector outer products. These operations are computationally fast and highly parallelizable. MATLAB simulations show that both recursive algorithms are valid.展开更多
The general structure of ship-borne helicopter landing forecast system is presented, and a novel ship motion prediction model based on minor component analysis (MCA) is built up to improve the forecast effectiveness. ...The general structure of ship-borne helicopter landing forecast system is presented, and a novel ship motion prediction model based on minor component analysis (MCA) is built up to improve the forecast effectiveness. To validate the feasibility of this landing forecast system, time series for the roll, pitch and heave are generated by simulation and then forecasted based on MCA. Simulation results show that ship-borne helicopters can land safely in higher sea condition while carrying on rescue or replenishment tasks at sea in terms of the landing forecast system.展开更多
Geochemical characteristics of trace and minor elements in some strata of geosynclinal tectonic layer, platform tectonic layer, in granite of Diwa stage, altered rocks and wolframite in the Xiangdong Tungsten Mine are...Geochemical characteristics of trace and minor elements in some strata of geosynclinal tectonic layer, platform tectonic layer, in granite of Diwa stage, altered rocks and wolframite in the Xiangdong Tungsten Mine are systematically studied. Enrichment of W, Sn and Cu in geosynclinal tectonic layer could be one part of mineralization. Different types of alteration might result in variance of distribution of the same trace or minor element. mNb/mTa and mMn/mFe ratios, contents of Nb and Ta in wolframite vary with vein groups′ location.展开更多
In this research, major and immobile minor and trace elements are used to study the petrology of Yamaghan deposit. Some major elements of least altered samples were used to classify the host rocks and their magma type...In this research, major and immobile minor and trace elements are used to study the petrology of Yamaghan deposit. Some major elements of least altered samples were used to classify the host rocks and their magma type. Considering slight to medium alteration of the host rock, immobile minor and trace elements of more than 110 samples were used to get more confidential results as well. The results show the high accuracy and reliability of the implemented techniques in the study area.展开更多
基金supported by the National Key Research and Development Program of China(2018YFB1003700)the Scientific and Technological Support Project(Society)of Jiangsu Province(BE2016776)+2 种基金the“333” project of Jiangsu Province(BRA2017228 BRA2017401)the Talent Project in Six Fields of Jiangsu Province(2015-JNHB-012)
文摘For imbalanced datasets, the focus of classification is to identify samples of the minority class. The performance of current data mining algorithms is not good enough for processing imbalanced datasets. The synthetic minority over-sampling technique(SMOTE) is specifically designed for learning from imbalanced datasets, generating synthetic minority class examples by interpolating between minority class examples nearby. However, the SMOTE encounters the overgeneralization problem. The densitybased spatial clustering of applications with noise(DBSCAN) is not rigorous when dealing with the samples near the borderline.We optimize the DBSCAN algorithm for this problem to make clustering more reasonable. This paper integrates the optimized DBSCAN and SMOTE, and proposes a density-based synthetic minority over-sampling technique(DSMOTE). First, the optimized DBSCAN is used to divide the samples of the minority class into three groups, including core samples, borderline samples and noise samples, and then the noise samples of minority class is removed to synthesize more effective samples. In order to make full use of the information of core samples and borderline samples,different strategies are used to over-sample core samples and borderline samples. Experiments show that DSMOTE can achieve better results compared with SMOTE and Borderline-SMOTE in terms of precision, recall and F-value.
基金supported by the National Program for Wildlife Conservation and Nature Reserve Construction, Chinaby the Science & Technology Plan of Shenzhen, China (SY200704300157A)
文摘Ionic liquids ( ILs) based ultrasonic-assisted extract has been applied for the extraction of essential oil from Persicaria minor leaves. The effects of temperature,sonication time,and particle size of the plant material on the yield of essential oil were investigated. Among the different ILs employed,1-ethyl-3-methyli midazolium acetate was the most effective,providing a 9. 55% yield of the essential oil under optimum conditions( 70 ℃,25 min,IL ∶hexane ratio of 7 ∶10 ( v /v) ,particle size 60-80 mesh) . The performance of 1-ethyl-3-methylimidazolium acetate in the extraction was attributed to its lowviscosity and ability to disintegrate the structural matrix of the plant material. The ability of 1-ethyl-3-methylimidazolium acetate was also confirmed using the conductor like-screening model for realistic solvents. This research proves that ILs can be used to extract essential oils from lignocellulosic biomass.
文摘To reduce the computational complexity of matrix inversion, which is the majority of processing in many practical applications, two numerically efficient recursive algorithms （called algorithms I and II, respectively） are presented. Algorithm I is used to calculate the inverse of such a matrix, whose leading principal minors are all nonzero. Algorithm II, whereby, the inverse of an arbitrary nonsingular matrix can be evaluated is derived via improving the algorithm I. The implementation, for algorithm II or I, involves matrix-vector multiplications and vector outer products. These operations are computationally fast and highly parallelizable. MATLAB simulations show that both recursive algorithms are valid.
文摘The general structure of ship-borne helicopter landing forecast system is presented, and a novel ship motion prediction model based on minor component analysis (MCA) is built up to improve the forecast effectiveness. To validate the feasibility of this landing forecast system, time series for the roll, pitch and heave are generated by simulation and then forecasted based on MCA. Simulation results show that ship-borne helicopters can land safely in higher sea condition while carrying on rescue or replenishment tasks at sea in terms of the landing forecast system.
文摘Geochemical characteristics of trace and minor elements in some strata of geosynclinal tectonic layer, platform tectonic layer, in granite of Diwa stage, altered rocks and wolframite in the Xiangdong Tungsten Mine are systematically studied. Enrichment of W, Sn and Cu in geosynclinal tectonic layer could be one part of mineralization. Different types of alteration might result in variance of distribution of the same trace or minor element. mNb/mTa and mMn/mFe ratios, contents of Nb and Ta in wolframite vary with vein groups′ location.
文摘In this research, major and immobile minor and trace elements are used to study the petrology of Yamaghan deposit. Some major elements of least altered samples were used to classify the host rocks and their magma type. Considering slight to medium alteration of the host rock, immobile minor and trace elements of more than 110 samples were used to get more confidential results as well. The results show the high accuracy and reliability of the implemented techniques in the study area.
